.RAISE
Paper
NOVEMBER 2024
Stripe Embedding: Efficient Maps with Exact Numeric Computation
Authors
Marco Livesu (CNR IMATI)
Abstract
Abstract:
We consider the fundamental problem of injectively mapping a surface mesh with disk topology onto a boundary constrained convex domain.
We start from the basic observation that mapping a strip of triangles onto a rectangular shape always yields a valid embedding, if the vertices that bound the strip are sorted coherently along the sides of the rectangle.
Based on this intuition, we propose a straightforward algorithm, called Stripe Embedding, that operates by decomposing the input mesh into a set of triangle strips and then embeds each strip into the target domain by means of linear interpolation between two previously embedded vertices.
Thanks to its simplicity, Stripe Embedding is extremely efficient and permits to switch to an exact implementation without almost increasing its running times.
Stripe Embedding is up to three orders of magnitude faster than the Tutte embedding for same numerical model and, even when implemented with costly rational numbers, it is faster than any floating point implementation of prior methods at any scale.
Published:
19 November 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
ACM Transactions on Graphics
Publication type:
Contribution in journal
DOI:
10.1145
SEPTEMBER 2024
Statistical Jump Model for Mixed-Type Data with Missing Data Imputation
Authors
Federico P. Cortese (Institute for Applied Mathematics and Information Technologies “E. Magenes”, Milan) - Antonio Pievatolo (Institute for Applied Mathematics and Information Technologies “E. Magenes”, Milan)
Abstract
Abstract:
In this paper, we address the challenge of clustering mixed-type data with temporal evolution by introducing the statistical jump model for mixed-type data.
This novel framework incorporates regime persistence, enhancing interpretability and reducing the frequency of state switches, and efficiently handles missing data.
The model is easily interpretable through its state-conditional means and modes, making it accessible to practitioners and policymakers.
We validate our approach through extensive simulation studies and an empirical application to air quality data, demonstrating its superiority in inferring persistent air quality regimes compared to the traditional air quality index.
Our contributions include a robust method for mixed-type temporal clustering, effective missing data management, and practical insights for environmental monitoring.
Published:
17 September 2024
RAISE Affiliate:
Spoke 1
Name of the Journal:
arXiv
Publication type:
Report and working paper
DOI:
10.48550
SEPTEMBER 2024
Neuromotor Changes After a Cervical Spinal Cord Injury: Bilateral Assessment of Unilateral Tasks
Authors
Amy Bellitto (Robotics and Systems Engineering (DIBRIS), University of Genova) - Alice de Luca (Robotics and Systems Engineering (DIBRIS), University of Genova) - Simona Gamba (Spinal Cord Unit, Santa Corona Hospital, ASL 2 Savonese) - Luca Losio (Spinal Cord Unit, Santa Corona Hospital, ASL 2 Savonese) - Antonino Massone (S.C. Unità Spinale Unipolare, Santa Corona Hospital, ASL2 Savonese) - Maura Casadio (DIBRIS, University of Genova)
Abstract
Abstract:
Cervical spinal cord injuries (cSCI) severely affect upper limb function, yet research on post-injury neuromotor abilities is limited.
In response, we developed an assessment integrating clinical, kinematic and muscle activity measures.
Twelve cSCI (C5-C7) and six unimpaired participants underwent a clinical (Range Of Motion and Manual Muscle tests) and an instrumented assessment.
During the latter, bilateral upper body kinematics and muscle activity were recorded as participants performed a set of unilateral movements, i.e. reaching movements toward different heights-directions and an object transfer along an arch-shaped structure (arc task).
Kinematics and neuromuscular indicators were analyzed following a two-tiered approach: comparing unimpaired and cSCI and differentiating more and less impaired arms within the cSCI cohort based on their ability to complete the arc task.
Clinical tests revealed shoulder mobility and strength limitations in cSCI participants, with a significant weakness in elbow extension noted in more impaired arms.
The instrumented assessment revealed reduced movement speed, smoothness and accuracy in the cSCI cohort, primarily due to weaknesses in the pectoralis muscle affecting contralateral movements and deltoids affecting ipsilateral movements.
Muscle activations were detected in the non-moving arm of cSCI participants, particularly noticeable during movements toward greater heights or in a contralateral direction.
The pronounced weakness in the pectoralis muscle of the more impaired cSCI arms explained the related ability to complete only 28% of the arc task.
Our findings provide a thorough insight into changes in upper limb neuromotor function following cSCI, underscoring motor deficits and related alterations in bilateral muscle activity.
Published:
11 September 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Applied Sciences
Publication type:
Contribution in journal
DOI:
10.1109
SEPTEMBER 2024
Two Nitsche-based mixed finite element discretizations for the seepage problem in Richards’ equation
Authors
Federico Gatti (Consiglio Nazionale delle Ricerche – Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes” CNR-IMATI) - Andrea Bressan (Consiglio Nazionale delle Ricerche – Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes” CNR-IMATI) - Alessio Fumagalli (MOX, Department of Mathematics, Politecnico di Milano) - Domenico Gallipoli (Department of Civil, Chemical and Environmental Engineering, University of Genoa) - Leonardo Maria Lalicata (Department of Civil, Chemical and Environmental Engineering, University of Genoa) - Simone Pittaluga (Consiglio Nazionale delle Ricerche – Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes” CNR-IMATI) - Lorenzo Tamellini (Consiglio Nazionale delle Ricerche – Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes” CNR-IMATI)
Abstract
Abstract:
This paper proposes two algorithms to impose seepage boundary conditions in the context of Richards’ equation for groundwater flows in unsaturated media.
Seepage conditions are non-linear boundary conditions, that can be formulated as a set of unilateral constraints on both the pressure head and the water flux at the ground surface, together with a complementarity condition: these conditions in practice require switching between Neumann and Dirichlet boundary conditions on unknown portions on the boundary.
Upon realizing the similarities of these conditions with unilateral contact problems in mechanics, we take inspiration from that literature to propose two approaches: the first method relies on a strongly consistent penalization term, whereas the second one is obtained by an hybridization approach, in which the value of the pressure on the surface is treated as a separate set of unknowns.
The flow problem is discretized in mixed form with div-conforming elements so that the water mass is preserved.
Numerical experiments show the validity of the proposed strategy in handling the seepage boundary conditions on geometries with increasing complexity.
Published:
10 September 2024
RAISE Affiliate:
Spoke 3
Name of the Journal:
Computer Methods in Applied Mechanics and Engineering
Publication type:
Contribution in journal
DOI:
10.1016
SEPTEMBER 2024
Advances in the Fabrication, Properties, and Applications of Electrospun PEDOT-Based Conductive Nanofibers
Authors
Emanuele Alberto Slejko (IMEM-CNR, Institute of Materials for Electronics and Magnetism of the National Research Council of Italy) - Giovanni Carraro (IMEM-CNR, Institute of Materials for Electronics and Magnetism of the National Research Council of Italy) - Xiongchuan Huang (School of Information Science and Technology, Fudan University, Handan Rd. 220) - Marco Smerieri (IMEM-CNR, Institute of Materials for Electronics and Magnetism of the National Research Council of Italy)
Abstract
Abstract:
The production of nanofibers has become a significant area of research due to their unique properties and diverse applications in various fields, such as biomedicine, textiles, energy, and environmental science.
Electrospinning, a versatile and scalable technique, has gained considerable attention for its ability to fabricate nanofibers with tailored properties.
Among the wide array of conductive polymers, poly (3,4-ethylenedioxythiophene) (PEDOT) has emerged as a promising material due to its exceptional conductivity, environmental stability, and ease of synthesis.
The electrospinning of PEDOT-based nanofibers offers tunable electrical and optical properties, making them suitable for applications in organic electronics, energy storage, biomedicine, and wearable technology.
This review, with its comprehensive exploration of the fabrication, properties, and applications of PEDOT nanofibers produced via electrospinning, provides a wealth of knowledge and insights into leveraging the full potential of PEDOT nanofibers in next-generation electronic and functional devices by examining recent advancements in the synthesis, functionalization, and post-treatment methods of PEDOT nanofibers.
Furthermore, the review identifies current challenges, future directions, and potential strategies to address scalability, reproducibility, stability, and integration into practical devices, offering a comprehensive resource on conductive nanofibers.
Published:
4 September 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Polymers
Publication type:
Contribution in journal
DOI:
10.3390
SEPTEMBER 2024
A taxonomy of cognitive phenotypes in Multiple Sclerosis: a 1‑year longitudinal study
Authors
Jessica Podda (Italian Multiple Sclerosis Foundation) - Federica Di Antonio (Scientific Research Area, Italian Multiple Sclerosis Foundation) - Andrea Tacchino (Scientific Research Area, Italian Multiple Sclerosis Foundation) - Ludovico Pedullà (Italian Multiple Sclerosis Foundation) - Erica Grange (Scientific Research Area, Italian Multiple Sclerosis Foundation) - Mario Alberto Battaglia (Department of Physiopathology, Experimental Medicine and Public Health, University of Siena) - Giampaolo Brichetto (Scientific Research Area, Italian Multiple Sclerosis Foundation) - Michela Ponzio (Scientific Research Area, Italian Multiple Sclerosis Foundation)
Abstract
Abstract:
As meaningful measure of cognitive impairment (CI), cognitive phenotypes provide an avenue for symptom management and individualized rehabilitation.
Since CI is highly variable in severity and progression, monitoring cognitive phenotypes over time may be useful to identify trajectory of cognitive decline in Multiple Sclerosis (MS).
Based on cognitive and mood information from patient-reported outcomes (PROs) and clinician-assessed outcomes (CAOs), four cognitive subgroups of people with MS (PwMS) were identified: phenotype 1 (44.5%) showed a preserved cognitive profile; phenotype 2 (22.8%) had a mild-cognitive impairment profile with attention difficulties; phenotype 3 (24.3%) included people with marked difficulties in visuo-executive, attention, language, memory and information processing speed; lastly, phenotype 4 (8.4%) grouped individuals with a multi-domain impairment profile (visuo-executive, attention, language, memory, orientation, information processing speed and mood disorders).
Although some fluctuations occurred considering the rate of impairment, cognitive phenotypes did not substantially vary at follow up in terms of type and number of impairments, suggesting that 1 year is a relatively brief temporal window to observe considerable changes.
Our results corroborate that investigating cognitive phenotypes and their stability over time would provide valuable information regarding CI and, in addition, increase clinical importance of PROs and CAOs and their uptake in decision-making and individualized treatment planning for PwMS.
Published:
2 September 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Scientific Reports
Publication type:
Contribution in journal
DOI:
10.1038
AUGUST 2024
Neighborhood Component Feature Selection for Multiple Instance Learning Paradigm
Authors
Giacomo Turri (Computational Statistics and Machine Learning (CSML), Istituto Italiano di Tecnologia) - Luca Romeo (Computational Statistics and Machine Learning (CSML), Istituto Italiano di Tecnologia)
Abstract
Abstract:
In a multiple instance learning (MIL) scenario, the outcome annotation is usually only reported at the bag level.
Considering simplicity and convergence criteria, the lazy learning approach, i.e., k-nearest neighbors (kNN), plays a crucial role in predicting bag labels in the MIL domain.
Notably, two variations of the kNN algorithm tailored to the MIL framework have been introduced, namely Bayesian-kNN (BkNN) and Citation-kNN (CkNN).
These adaptations leverage the Hausdorff metric along with Bayesian or citation approaches.
However, neither BkNN nor CkNN explicitly integrates feature selection methodologies, and when irrelevant and redundant features are present, the model’s generalization decreases.
In the single-instance learning scenario, to overcome this limitation of kNN, a feature weighting algorithm named Neighborhood Component Feature Selection (NCFS) is often applied to find the optimal degree of influence of each feature.
To address the significant gap existing in the literature, we introduce the NCFS method for the MIL framework.
The proposed methodologies, i.e. NCFS-BkNN, NCFS-CkNN, and NCFS-Bayesian Citation-kNN (NCFS-BCkNN), learn the optimal features weighting vector by minimizing the regularized leave-one-out error of the training bags.
Hence, the prediction of unseen bags is computed by combining the Bayesian and citation approaches based on the minimum optimally weighted Hausdorff distance.
Through experiments with various benchmark MIL datasets in the biomedical informatics and affective computing fields, we provide statistical evidence that the proposed methods outperform state-of-the-art MIL algorithms that do not employ any a priori feature weighting strategy.
Published:
22 August 2024
RAISE Affiliate:
Spoke 1
Conference name:
Joint European Conference on Machine Learning and Knowledge Discovery in Databases
Publication type:
Contribution in conference proceedings
DOI:
10.1007
AUGUST 2024
From aerial LiDAR point clouds to multiscale urban representation levels by a parametric resampling
Authors
Chiara Romanengo (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche) - Bianca Falcidieno (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche) - Silvia Biasotti (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche)
Abstract
Abstract:
Urban simulations that involve disaster prevention, urban design, and assisted navigation heavily rely on urban geometric models.
While large urban areas need a lot of time to be acquired terrestrially, government organizations have already conducted massive aerial LiDAR surveys, some even at the national level.
This work aims to provide a pipeline for extracting multi-scale point clouds from 2D building footprints and airborne LiDAR data, which depends on whether the points represent buildings, vegetation, or ground.
We denoise the roof slopes, match the vegetation, and roughly recreate the building façades frequently hidden to aerial acquisition using a parametric representation of geometric primitives.
We then carry out multiple-scale samplings of the urban geometry until a 3D urban representation can be achieved because we annotate the new version of the original point cloud with the parametric equations representing each part.
We mainly tested our methodology in a real-world setting – the city of Genoa – which includes historical buildings and is heavily characterized by irregular ground slopes.
Moreover, we present the results of urban reconstruction on part of two other cities, Matera, which has a complex morphology like Genoa, and Rotterdam.
Published:
9 August 2024
RAISE Affiliate:
Spoke 1
Name of the Journal:
Computers & Graphics
Publication type:
Contribution in journal
DOI:
10.1016
AUGUST 2024
Personality and Memory-Based Software Framework for Human-Robot Interaction
Authors
Alice Nardelli (Department of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa) - Antonio Sgorbissa (Department of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa) - Carmine Recchiuto (Department of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa)
Abstract
Abstract:
The synergic orchestration of the cognitive and psychological dimensions characterizes human intelligence.
Accordingly, carefully designing this mechanism in artificial intelligence can be a successful strategy to increase human likeness in a robot, enhancing mutual understanding and building a more natural and intuitive interaction.
For this purpose, the main contribution of this work is a psychological and cognitive architecture tailored for HRI based on the interplay between robotic personality and memory-based cognitive processes.
Indeed, the artificial personality manifests itself not only in various aspects of the behavior but also within the action selection process, which is closely intertwined with personality-dependent hedonic experiences linked to memories.
Within this paper, we propose a task- and platform-independent framework, evaluated in a multiparty collaborative scenario.
Obtained results show that a robot connected to our proposed framework is perceived as a cognitive agent capable of manifesting perceivable and distinguishable personality traits.
Published:
8 August 2024
RAISE Affiliate:
Spoke 1
Conference name:
IEEE International Conference on Robotics and Automation (ICRA)
Publication type:
Contribution in conference proceedings
DOI:
10.1109
AUGUST 2024
SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes
Authors
Mohammad Zohaib (Pattern Analysis & Computer Vision, Italian Institute of Technology) - Luca Cosmo (Ca’ Foscari University of Venice) - Alessio Del Bue (Pattern Analysis & Computer Vision, Italian Institute of Technology)
Abstract
Abstract:
Unsupervised 3D keypoints estimation from Point Cloud Data (PCD) is a complex task, even more challenging when an object shape is deforming.
As keypoints should be semantically and geometrically consistent across all the 3D frames - each keypoint should be anchored to a specific part of the deforming shape irrespective of intrinsic and extrinsic motion.
This paper presents, "SelfGeo", a self-supervised method that computes persistent 3D keypoints of non-rigid objects from arbitrary PCDs without the need of human annotations.
The gist of SelfGeo is to estimate keypoints between frames that respect invariant properties of deforming bodies.
Our main contribution is to enforce that keypoints deform along with the shape while keeping constant geodesic distances among them.
This principle is then propagated to the design of a set of losses which minimization let emerge repeatable keypoints in specific semantic locations of the non-rigid shape.
We show experimentally that the use of geodesic has a clear advantage in challenging dynamic scenes and with different classes of deforming shapes (humans and animals).
Published:
5 August 2024
RAISE Affiliate:
Spoke 4
Conference name:
European Conference of Computer Vision (ECCV)
Publication type:
Contribution in conference proceedings
DOI:
10.48550
JULY 2024
Extending the Hough transform to recognize and approximate space curves in 3D models
Authors
Chiara Romanengo (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche) - Bianca Falcidieno (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche) - Silvia Biasotti (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, Consiglio Nazionale delle Ricerche)
Abstract
Abstract:
Feature curves are space curves identified by color or curvature variations in a shape, which are crucial for human perception (Biederman, 1995).
Detecting these characteristic lines in 3D digital models becomes important for recognition and representation processes.
For recognizing plane curves in images, the Hough transform (HT) provided a very good solution to the problem.
It selects the best-fitting curve in a dictionary of families of curves through a voting procedure that makes it robust to noise and missing parts.
Since 3D digital models are often obtained by scanning real objects and may have many defects, the HT has been extended to recognize and approximate space curves in 3D models that correspond to relevant features.
This work overviews three HT-based different approaches for identifying and approximating spatial profiles of points extracted from point clouds or meshes.
A first attempt at this extension involved projecting the spatial points onto the regression plane, thus reducing the problem to planar recognition and using families of plane curves. A second approach has been proposed to recognize spatial profiles that cannot be projected onto the regression plane, using two types of space curve families.
Unfortunately, the main drawback of methods based on traditional HT is that it requires prior knowledge of which family of curves to look for.
To overcome this limitation, a third method has been developed that provides a piecewise space curve approximation using specific parametric polynomial curves.
Additionally, free-form curves that a parametric or implicit form cannot express can be represented using this technique.
In the paper, we also analyze the pros and cons of the various approaches and how they managed and reduced the HT's computational cost, given the large number of parameters introduced when families of space curves are considered.
Published:
23 July 2024
RAISE Affiliate:
Spoke 1
Name of the Journal:
Computer Aided Geometric Design
Publication type:
Contribution in journal
DOI:
10.1016
JULY 2024
Recent Advances in Self-Powered Electrochemical Biosensors for Early Diagnosis of Diseases
Authors
Vardan Galstyan (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Ilenia D'Onofrio (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Aris Liboà (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Giuseppe De Giorgio (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Davide Vurro (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Luigi Rovati (Department of Engineering "Enzo Ferrari”, University of Modena and Reggio Emilia) - Giuseppe Tarabella (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR) - Pasquale D'Angelo (Institute of Materials for Electronics and Magnetism, National Research Council IMEM-CNR)
Abstract
Abstract:
Modern sensing technologies are highly required for health monitoring.
In this respect, the development of small-size, high-performance, and self-powered biosensors for detecting and quantifying disease markers in biofluids can bring crucial changes and improvements to the concept of health monitoring systems.
Clinical trials identify a wide range of biomarkers in biofluids that provide significant health information.
Research into novel functional materials with outstanding properties opens up new perspectives for fabricating new-generation biosensors.
Furthermore, energy conversion and storage units are investigated to integrate them into biosensors and develop self-powered systems.
Electrochemical methods are very attractive for applications in biosensor technology, both in terms of biomarker detection and energy generation.
Here the recent achievements in research into self-powered electrochemical biosensors to detect sweat and saliva biomarkers are presented.
Potential biomarkers for efficient analysis of these fluids are discussed in light of their importance in identifying various diseases.
The influence of electrode materials on the performance of sensors is discussed.
Progress in developing operating strategies for self-powered electrochemical monitoring systems is also discussed.
A summary and outlook are presented, mentioning major achievements and current issues to be explored.
Published:
23 July 2024
RAISE Affiliate:
Spoke 3
Name of the Journal:
Advanced Materials Technologies
Publication type:
Contribution in journal
DOI:
10.1002
JULY 2024
US & MR/CT Image Fusion with Markerless Skin Registration: A Proof of Concept
Authors
Martina Paccini (CNR-IMATI ‘E. Magenes’) - Giacomo Paschina (Esaote S.p.a.) - Stefano De Beni (Esaote S.p.a.) - Andrei Stefanov (MedCom GmbH, Dolivostr., 11, Darmstadt, 64293, Germany) - Velizar Kolev (MedCom GmbH, Dolivostr., 11, Darmstadt, 64293, Germany) - Giuseppe Patanè (CNR-IMATI ‘E. Magenes’)
Abstract
Abstract:
This paper presents an innovative automatic fusion imaging system that combines 3D CT/MR images with real-time ultrasound acquisition.
The system eliminates the need for external physical markers and complex training, making image fusion feasible for physicians with different experience levels.
The integrated system involves a portable 3D camera for patient-specific surface acquisition, an electromagnetic tracking system, and US components.
The fusion algorithm comprises two main parts: skin segmentation and rigid co-registration, both integrated into the US machine.
The co-registration aligns the surface extracted from CT/MR images with the 3D surface acquired by the camera, facilitating rapid and effective fusion.
Experimental tests in different settings, validate the system’s accuracy, computational efficiency, noise robustness, and operator independence.
Published:
17 July 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Journal of Imaging Informatics in Medicine
Publication type:
Contribution in journal
DOI:
10.1007
JULY 2024
Resistive switching suppression in metal/Nb:SrTiO3 Schottky contacts prepared by room-temperature pulsed laser deposition
Authors
Renato Buzio (CNR-SPIN Institute for Superconductivity, Innovative Materials and Devices) - Andrea Gerbi (RAISE Ecosystem, Genova)
Abstract
Abstract:
Deepening the understanding of interface-type Resistive Switching (RS) in metal/oxide heterojunctions is a key step for the development of high-performance memristors and Schottky rectifiers.
In this study, we address the role of metallization technique by fabricating prototypical metal/Nb-doped SrTiO3 (M/NSTO) Schottky contacts via Pulsed Laser Deposition (PLD).
Ultrathin Pt and Au electrodes are deposited by PLD onto single-crystal (001)-terminated NSTO substrates and interfacial transport is characterized by conventional macroscale methods and nanoscale Ballistic Electron Emission Microscopy.
We show that PLD metallization gives Schottky contacts with highly reversible current-voltage characteristics under cyclic polarization.
Room-temperature transport is governed by thermionic emission with Schottky barrier height ϕB(Pt/NSTO)=0.71-0.75eV, ϕB(Au/NSTO)=0.70-0.83eV and ideality factors as small as n(Pt/NSTO)=1.1 and n(Au/NSTO)=1.6.
RS remains almost completely suppressed upon imposing broad variations of the Nb doping and of the external stimuli (polarization bias, working temperature, ambient air exposure).
At the nanoscale, we find that both systems display high spatial homogeneity of ϕB(<50meV), which is only partially affected by the NSTO mixed termination (|ϕB (M/SrO) - ϕB (M/TiO2)|<35meV).
Experimental evidences and theoretical arguments indicate that the PLD metallization mitigates interfacial layer effects responsible for RS.
This occurs thanks either to a reduction of the interfacial layer thickness and to the creation of an effective barrier against the permeation of ambient gas species affecting charge trapping and redox reactions.
This description allows to rationalize interfacial aging effects, observed upon several-months-exposure to ambient air, in terms of interfacial re-oxidation.
Published:
5 July 2024
RAISE Affiliate:
Spoke 3
Name of the Journal:
Journal of Physics D: Applied Physics
Publication type:
Contribution in journal
DOI:
10.1088
JUNE 2024
A Bidirectional Research Method to Design a Smart City Evaluation System
Authors
Renata Dameri (University of Genoa) - Monica Bruzzone (Department of Economics and Business, University of Genoa)
Abstract
Abstract:
This paper develops a two-way research method - both top-down and bottom-up - to define a “standard but tailored” assessment framework for smart cities, based on shared smart city concepts, but designed to respond to different needs of each city.
The method aims not to design a measurement standard, but to define a process able to create the best smart city measurement system.
It is based on a standard framework but tailored on each city – with its own features, problems, values, and ideas about the quality of life.
This method overcomes the limitations of using standard framework, as it links smart city assessment tools to local policies but giving to the tool the authoritativeness deriving from the scientific literature and the robustness acquired from international nest practices.
An empirical implementation supports the theoretical background and allows to validate the method, as it has been successfully implemented in Genoa, a medium-sized city in Italy looking for its own performance measurement system that allows comparison with other smart cities at the same time.
The bidirectional method is designed by the authors of this paper, and it is a novelty in the international literature about research methodology for business and management studies.
Published:
26 June 2024
RAISE Affiliate:
Spoke 1
Conference name:
23rd European Conference on Research Methodology for Business and Management Studies
Publication type:
Contribution in conference proceedings
DOI:
10.34190
JUNE 2024
Inflammatory biomarker detection in saliva samples by printed graphene immunosensors
Authors
D. Vurro (Institute of Materials for Electronics and Magnetism, IMEM-CNR) - L. Pasquardini (Indivenire srl, Institute of Materials for Electronics and Magnetism, IMEM-CNR, Trento site c/o Fondazione Bruno Kessler, Department of Engineering, University of Campania “Luigi Vanvitelli”) - M. Borriello (Department of Precision Medicine, University of Campania “Luigi Vanvitelli”) - R. Foresti (Institute of Materials for Electronics and Magnetism, IMEM-CNR, Department of Medicine and Surgery) - M. Barra (CNR-SPIN c/o Department of Physics “Ettore Pancini”) - M. Sidoli (Department of Mathematical, Physical and Computer Sciences) - D. Pontiroli (Department of Mathematical, Physical and Computer Sciences) - L. Fornasini (Department of Mathematical, Physical and Computer Sciences) - L. Aversa (Institute of Materials for Electronics and Magnetism, IMEM-CNR) - R. Verucchi (Institute of Materials for Electronics and Magnetism, IMEM-CNR) - P. D'Angelo (Institute of Materials for Electronics and Magnetism, IMEM-CNRInstitute of Materials for Electronics and Magnetism, IMEM-CNR) - G. Tarabella (Institute of Materials for Electronics and Magnetism, IMEM-CNR)
Abstract
Abstract:
Herein, we present the design and fabrication of a portable biochemical sensor based on the Screen Printed Electrode (SPE) concept and applied for detecting interleukin-6 (IL-6), a key player in the complex process of inflammation, in real human saliva.
The sensing mechanism relies on the antigen-antibody binding between the IL-6 molecule and its antibody immobilized over a surface of a Thermally Exfoliated Graphene Oxide (TEGO) layer.
TEGO, deposited by Aerosol Jet Printing (AJP), provides advantages in terms of a time/cost consumingfast, easy and efficient biofunctionalization.
The biosensor shows a dynamic range comprising IL-6 concentrations falling within the normal IL-6 levels in saliva.
An extensive analysis of device performance, focused on the assessment of the sensor Limit of Detection (LoD) by two modes (i.e. from the lin-log calibration curve and from blank measurements), provides a best value of about 1 × 10−2 pg/ml of IL-6 in saliva.
Our work aims at providing a contribution toward applications in real environment, going beyond a proof of concept or prototyping at lab scale.
Hence, the characterization of the sensor was finalized to find a reliable device-to-device reproducibility and calibration through the introduction of a measurement protocol based on comparative measurements between saliva samples without (blank) and with IL-6 spiked in it, in place of the standard addition method used in daily laboratory practice.
Device-to-device reproducibility has been accordingly tested by acquiring multiple experimental points along the calibration curve using different individual devices for each point.
Published:
21 June 2024
RAISE Affiliate:
Spoke 1
Name of the Journal:
Sensors and Actuators Reports
Publication type:
Contribution in journal
DOI:
10.1016
JUNE 2024
BioemuS: A new tool for neurological disorders studies through real-time emulation and hybridization using biomimetic Spiking Neural Network
Authors
Romain Beaubois (IMS, CNRS UMR5218, Bordeaux INP, University of Bordeaux, Talence, France, Institute of Industrial Science, The University of Tokyo, Tokyo, Japan) - Jérémy Cheslet (IMS, CNRS UMR5218, Bordeaux INP, University of Bordeaux, Institute of Industrial Science, The University of Tokyo, LIMMS, CNRS-Institute of Industrial Science, UMI 2820, The University of Tokyo) - Tomoya Duenki (Institute of Industrial Science, The University of Tokyo, LIMMS, CNRS-Institute of Industrial Science, UMI 2820, The University of Tokyo, Department of Chemistry and Biotechnology, Graduate School of Engineering, The University of Tokyo, Institute for AI and Beyond, The University of Tokyo) - Giuseppe De Venuto (DIBRIS, University of Genova) - Marta Carè (DIBRIS, University of Genova, IRCCS Ospedale Policlinico San Martino, Rehab Technologies, Istituto Italiano di Tecnologia, Genova, Italy)
Abstract
Abstract:
Characterization and modeling of biological neural networks has emerged as a field driving significant advancements in our understanding of brain function and related pathologies.
As of today, pharmacological treatments for neurological disorders remain limited, pushing the exploration of promising alternative approaches such as electroceutics.
Recent research in bioelectronics and neuromorphic engineering have fostered the development of the new generation of neuroprostheses for brain repair.
However, achieving their full potential necessitates a deeper understanding of biohybrid interaction.
In this study, we present a novel real-time, biomimetic, cost-effective and user-friendly neural network capable of real-time emulation for biohybrid experiments.
Our system facilitates the investigation and replication of biophysically detailed neural network dynamics while prioritizing cost-efficiency, flexibility and ease of use.
We showcase the feasibility of conducting biohybrid experiments using standard biophysical interfaces and a variety of biological cells as well as real-time emulation of diverse network configurations.
We envision our system as a crucial step towards the development of neuromorphic-based neuroprostheses for bioelectrical therapeutics, enabling seamless communication with biological networks on a comparable timescale. Its embedded real-time functionality enhances practicality and accessibility, amplifying its potential for real-world applications in biohybrid experiments.
Published:
20 June 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Nature Communications
Publication type:
Contribution in journal
DOI:
10.1038
JUNE 2024
A Strong Core for a Strong Recovery: A Scoping Review of Methods to Improve Trunk Control and Core Stability of People with Different Neurological Conditions
Authors
Giorgia Marchesi (Clinical & Product Division, Movendo Technology srl) - Greta Arena (Clinical & Product Division, Movendo Technology srl) - Alice Parey (IMT Atlantique Bretagne-Pays de la Loire, Campus de Brest, Technopôle Brest-Iroise CS 83818) - Alice De Luca (Unit for Visually Impaired People and Bioinspired Soft Robotics, Italian Institute of Technology) - Maura Casadio (Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genoa) - Camilla Pierella (Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genoa) - Valentina Squeri (Rehab Technologies INAIL IIT Lab, Italian Institute of Technology)
Abstract
Abstract:
Objective: The purpose of this scoping review is to provide valuable insights for clinicians and researchers for designing rehabilitative interventions targeting the trunk and core for individuals who have experienced traumatic events, such as stroke or spinal cord injury, or are grappling with neurological diseases such as multiple sclerosis and Parkinson’s disease.
We investigated training methods used to enhance balance, trunk control, and core stability.
Methods: We conducted an extensive literature search across several electronic databases, including Web of Science, PubMed, SCOPUS, Google Scholar, and IEEE Xplore.
Results: A total of 109 articles met the inclusion criteria and were included in this review.
The results shed light on the diversity of rehabilitation methods that target the trunk and core.
These methods have demonstrated effectiveness in improving various outcomes, including balance, trunk control, gait, the management of trunk muscles, overall independence, and individuals’ quality of life.
Conclusions: Our scoping review provides an overview on the methods and technologies employed in trunk rehabilitation and core strengthening, offering insights into the added value of core training and specific robotic training, focusing on the importance of different types of feedback to enhance training effectiveness.
Published:
5 June 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Applied Sciences
Publication type:
Contribution in journal
DOI:
10.3390
MAY 2024
Testing dynamic balance in people with Multiple Sclerosis: a correlational study between standard posturography and robotic-assistive device
Authors
Jessica Podda (Italian Multiple Sclerosis Foundation) - Giorgia Marchesi (Movendo Technology S.R.L) - Alice Bellosta (Department of Experimental Medicine, University of Genoa) - Valentina Squeri (Movendo Technology S.R.L) - Alice De Luca (Movendo Technology S.R.L) - Ludovico Pedullà (Italian Multiple Sclerosis Foundation) - Andrea Tacchino (Italian Multiple Sclerosis Foundation) - Giampaolo Brichetto (Italian Multiple Sclerosis Foundation, AISM Rehabilitation Service)
Abstract
Abstract:
Background: Robotic devices are known to provide pivotal parameters to assess motor functions in Multiple Sclerosis (MS) as dynamic balance. However, there is still a lack of validation studies comparing innovative technologies with standard solutions.
Thus, this study’s aim was to compare the postural assessment of fifty people with MS (PwMS) during dynamic tasks performed with the gold standard EquiTest® and the robotic platform hunova®, using Center of Pressure (COP)-related parameters and global balance indexes.
Methods: Pearson’s ρ correlations were run for each COP-related measure and the global balance index was computed from EquiTest® and hunova® in both open (EO) and closed-eyes (EC) conditions.
Results: Considering COP-related parameters, all correlations were significant in both EO (0.337 ≤ ρ ≤ 0.653) and EC (0.344 ≤ ρ ≤ 0.668). Furthermore, Pearson’s analysis of global balance indexes revealed relatively strong for visual and vestibular, and strong for somatosensory system associations (ρ = 0.573; ρ = 0.494; ρ = 0.710, respectively).
Conclusions: Findings confirm the use of hunova® as a valid device for dynamic balance assessment in MS, suggesting that such a robotic platform could allow for a more sensitive assessment of balance over time, and thus a better evaluation of the effectiveness of personalized treatment, thereby improving evidence-based clinical practice.
Published:
23 May 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Sensors
Publication type:
Contribution in journal
DOI:
10.3390
MAY 2024
Testing Dynamic Balance in People with Multiple Sclerosis: A Correlational Study between Standard Posturography and Robotic-Assistive Device
Authors
Jessica Podda (Italian Multiple Sclerosis Foundation) - Giorgia Marchesi (Movendo Technology S.R.L) - Alice Bellosta (Department of Experimental Medicine, University of Genoa) - Valentina Squeri (Movendo Technology S.R.L) - Alice De Luca (Movendo Technology S.R.L) - Ludovico Pedullà (Italian Multiple Sclerosis Foundation) - Andrea Tacchino (Italian Multiple Sclerosis Foundation) - Giampaolo Brichetto (Italian Multiple Sclerosis Foundation, AISM Rehabilitation Service)
Abstract
Abstract:
Robotic devices are known to provide pivotal parameters to assess motor functions in Multiple Sclerosis (MS) as dynamic balance.
However, there is still a lack of validation studies comparing innovative technologies with standard solutions.
Thus, this study’s aim was to compare the postural assessment of fifty people with MS (PwMS) during dynamic tasks performed with the gold standard EquiTest® and the robotic platform hunova®, using Center of Pressure (COP)-related parameters and global balance indexes.
Methods: pearson’s ρ correlations were run for each COP-related measure and the global balance index was computed from EquiTest® and hunova® in both open (EO) and closed-eyes (EC) conditions.
Results: considering COP-related parameters, all correlations were significant in both EO (0.337 ≤ ρ ≤ 0.653) and EC (0.344 ≤ ρ ≤ 0.668). Furthermore, Pearson’s analysis of global balance indexes revealed relatively strong for visual and vestibular, and strong for somatosensory system associations (ρ = 0.573; ρ = 0.494; ρ = 0.710, respectively).
Conclusions: findings confirm the use of hunova® as a valid device for dynamic balance assessment in MS, suggesting that such a robotic platform could allow for a more sensitive assessment of balance over time, and thus a better evaluation of the effectiveness of personalized treatment, thereby improving evidence-based clinical practice.
Published:
23 May 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Sensors
Publication type:
Contribution in journal
DOI:
10.3390
APRIL 2024
VERO: A vacuum cleaner equipped quadruped robot for efficient litter removal
Authors
Lorenzo Amatucci (Dynamic Legged Systems Laboratory, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) UniGe) - Giulio Turrisi (Dynamic Legged Systems Laboratory, Istituto Italiano di Tecnologia) - Angelo Bratta (Dynamic Legged Systems Laboratory, Istituto Italiano di Tecnologia) - Victor Barasuol (Dynamic Legged Systems Laboratory, Istituto Italiano di Tecnologia) - Claudio Semini (Dynamic Legged Systems Laboratory, Istituto Italiano di Tecnologia)
Abstract
Abstract:
Litter nowadays presents a significant threat to the equilibrium of many ecosystems. An example is the sea, where litter coming from coasts and cities via gutters, streets, and waterways, releases toxic chemicals and microplastics during its decomposition.
Litter removal is often carried out manually by humans, which inherently lowers the amount of waste that can be effectively collected from the environment.
In this paper, we present a novel quadruped robot prototype that, thanks to its natural mobility, is able to collect cigarette butts (CBs) autonomously, the second most common undisposed waste worldwide, in terrains that are hard to reach for wheeled and tracked robots.
The core of our approach is a convolutional neural network for litter detection, followed by a time-optimal planner for reducing the time needed to collect all the target objects. Precise litter removal is then performed by a visual-servoing procedure which drives the nozzle of a vacuum cleaner that is attached to one of the robot legs on top of the detected CB.
As a result of this particular position of the nozzle, we are able to perform the collection task without even stopping the robot's motion, thus greatly increasing the time-efficiency of the entire procedure. Extensive tests were conducted in six different outdoor scenarios to show the performance of our prototype and method.
To the best knowledge of the authors, this is the first time that such a design and method was presented and successfully tested on a legged robot.
Published:
29 April 2024
RAISE Affiliate:
Spoke 3
Name of the Journal:
Journal of Field Robotics
Publication type:
Contribution in journal
DOI:
10.1002
APRIL 2024
A Biohybrid Self-Dispersing Miniature Machine Using Wild Oat Fruit Awns for Reforestation and Precision Agriculture
Authors
Isabella Fiorello - Marilena Ronzan - Thomas Speck - Edoardo Sinibaldi - Barbara Mazzolai
Abstract
Abstract:
Advances in bioinspired and biohybrid robotics are enabling the creation of multifunctional systems able to explore complex unstructured environments.
Inspired by Avena fruits, a biohybrid miniaturized autonomous machine (HybriBot) composed of a biomimetic biodegradable capsule as cargo delivery system and natural humidity-driven sister awns as biological motors is reported.
Microcomputed tomography, molding via two-photon polymerization and casting of natural awns into biodegradable materials is employed to fabricate multiple HybriBots capable of exploring various soil and navigating soil irregularities, such as holes and cracks.
These machines replicate the dispersal movements and biomechanical performances of natural fruits, achieving comparable capsule drag forces up to ≈0.38 N and awns torque up to ≈100 mN mm−1.
They are functionalized with fertilizer and are successfully utilized to germinate selected diaspores.
HybriBots function as self-dispersed systems with applications in reforestation and precision agriculture.
Published:
7 April 2024
RAISE Affiliate:
Spoke 3
Name of the Journal:
Advanced Materials
Publication type:
Contribution in journal
DOI:
10.1002
MARCH 2024
CurveML: a benchmark for evaluating and training learning-based methods of classification, recognition, and fitting of plane curves
Authors
Andrea Raffo (Department of Biosciences, University of Oslo) - Andrea Ranieri (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Chiara Romanengo (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Bianca Falcidieno (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Silvia Biasotti (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
We propose CurveML, a benchmark for evaluating and comparing methods for the classification and identification of plane curves represented as point sets.
The dataset is composed of 520k curves, of which 280k are generated from specific families characterised by distinctive shapes, and 240k are obtained from Bézier or composite Bézier curves.
The dataset was generated starting from the parametric equations of the selected curves making it easily extensible. It is split into training, validation, and test sets to make it usable by learning-based methods, and it contains curves perturbed with different kinds of point set artefacts.
To evaluate the detection of curves in point sets, our benchmark includes various metrics with particular care on what concerns the classification and approximation accuracy.
Finally, we provide a comprehensive set of accompanying demonstrations, showcasing curve classification, and parameter regression tasks using both ResNet-based and PointNet-based networks.
These demonstrations encompass 14 experiments, with each network type comprising 7 runs: 1 for classification and 6 for regression of the 6 defining parameters of plane curves.
The corresponding Jupyter notebooks with training procedures, evaluations, and pre-trained models are also included for a thorough understanding of the methodologies employed.
Published:
12 March 2024
RAISE Affiliate:
Spoke 1
Name of the Journal:
The Visual Computer
Publication type:
Contribution in journal
DOI:
10.1007
FEBRUARY 2024
Robotic systems for upper-limb rehabilitation in multiple sclerosis: a SWOT analysis and the synergies with virtual and augmented environments
Authors
Giulia A. Albanese (ReWing s.r.l.) - Anna Bucchieri (Rehab Technologies Lab, Istituto Italiano di Tecnologia, Department of Electronics, Information and Bioengineering, Politecnico di Milano) - Jessica Podda (Scientific Research Area, Italian Multiple Sclerosis Foundation, FISM) - Andrea Tacchino (Scientific Research Area, Italian Multiple Sclerosis Foundation, FISM) - Stefano Buccelli (Rehab Technologies Lab, Istituto Italiano di Tecnologia) - Elena De Momi (Department of Electronics, Information and Bioengineering, Politecnico di Milano) - Matteo Laffranchi (Rehab Technologies Lab, Istituto Italiano di Tecnologia) - Kailynn Mannella (Department of Kinesiology, Brock University, St. Catharines, ON, Canada) - Michael W. R. Holmes (Department of Kinesiology, Brock University, St. Catharines, ON, Canada) - Jacopo Zenzeri (ReWing s.r.l.) - Lorenzo De Michieli (Rehab Technologies Lab, Istituto Italiano di Tecnologia) - Giampaolo Brichetto (Scientific Research Area, Italian Multiple Sclerosis Foundation, FISM) - Giacinto Barresi (Rehab Technologies Lab, Istituto Italiano di Tecnologia)
Abstract
Abstract:
The robotics discipline is exploring precise and versatile solutions for upper-limb rehabilitation in Multiple Sclerosis (MS).
People with MS can greatly benefit from robotic systems to help combat the complexities of this disease, which can impair the ability to perform activities of daily living (ADLs).
In order to present the potential and the limitations of smart mechatronic devices in the mentioned clinical domain, this review is structured to propose a concise SWOT (Strengths, Weaknesses, Opportunities, and Threats) Analysis of robotic rehabilitation in MS.
Through the SWOT Analysis, a method mostly adopted in business management, this paper addresses both internal and external factors that can promote or hinder the adoption of upper-limb rehabilitation robots in MS.
Subsequently, it discusses how the synergy with another category of interaction technologies - the systems underlying virtual and augmented environments - may empower Strengths, overcome Weaknesses, expand Opportunities, and handle Threats in rehabilitation robotics for MS.
The impactful adaptability of these digital settings (extensively used in rehabilitation for MS, even to approach ADL-like tasks in safe simulated contexts) is the main reason for presenting this approach to face the critical issues of the aforementioned SWOT Analysis.
This methodological proposal aims at paving the way for devising further synergistic strategies based on the integration of medical robotic devices with other promising technologies to help upper-limb functional recovery in MS.
Published:
27 February 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Frontiers in Robotics and AI
Publication type:
Contribution in journal
DOI:
10.3389
FEBRUARY 2024
Silk Fibroin Materials: Biomedical Applications and Perspectives
Authors
Giuseppe De Giorgio (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council) - Biagio Matera (Center of Dental Medicine, Department of Medicine and Surgery, University of Parma) - Davide Vurro (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council) - Edoardo Manfredi (Center of Dental Medicine, Department of Medicine and Surgery, University of Parma) - Vardan Galstyan (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council, Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia) - Giuseppe Tarabella (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council) - Benedetta Ghezzi (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council, Center of Dental Medicine, Department of Medicine and Surgery, University of Parma) - Pasquale D’Angelo (IMEM-CNR, Institute of Materials for Electronics and Magnetism-National Research Council)
Abstract
Abstract:
The golden rule in tissue engineering is the creation of a synthetic device that simulates the native tissue, thus leading to the proper restoration of its anatomical and functional integrity, avoiding the limitations related to approaches based on autografts and allografts.
The emergence of synthetic biocompatible materials has led to the production of innovative scaffolds that, if combined with cells and/or bioactive molecules, can improve tissue regeneration.
In the last decade, silk fibroin (SF) has gained attention as a promising biomaterial in regenerative medicine due to its enhanced bio/cytocompatibility, chemical stability, and mechanical properties.
Moreover, the possibility to produce advanced medical tools such as films, fibers, hydrogels, 3D porous scaffolds, non-woven scaffolds, particles or composite materials from a raw aqueous solution emphasizes the versatility of SF.
Such devices are capable of meeting the most diverse tissue needs; hence, they represent an innovative clinical solution for the treatment of bone/cartilage, the cardiovascular system, neural, skin, and pancreatic tissue regeneration, as well as for many other biomedical applications.
The present narrative review encompasses topics such as (i) the most interesting features of SF-based biomaterials, bare SF’s biological nature and structural features, and comprehending the related chemo-physical properties and techniques used to produce the desired formulations of SF; (ii) the different applications of SF-based biomaterials and their related composite structures, discussing their biocompatibility and effectiveness in the medical field.
Particularly, applications in regenerative medicine are also analyzed herein to highlight the different therapeutic strategies applied to various body sectors.
Published:
9 February 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Bioengineering
Publication type:
Contribution in journal
DOI:
10.3390
JANUARY 2024
Adaptive Membership Functions and F-transform
Authors
Simone Cammarasana (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Giuseppe Patané (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
The definition of the fuzzy-transform (F-transform) has been limited mainly to 1-D signals and 2-D data due to the difficulty of defining membership functions, their centres, and support on a domain with arbitrary dimensionality and topology.
We propose a novel method for the adaptive selection of the optimal centres and supports of a class of radial membership functions based on minimizing the reconstruction error of the input signal as the F-transform and its inverse, or as a weighted linear combination of the membership functions.
Replacing uniformly sampled centres of the membership functions with adaptive centres and fixed supports with adaptive supports allows us to preserve the input signal's local and global features and achieve a good approximation accuracy with fewer membership functions.
We compare our method with uniform sampling and previous work.
As a result, we improve the image reconstruction with respect to compared methods and we reduce the underlying computational cost and storage overhead.
Finally, our approach applies to any class of continuous membership functions.
Published:
31 January 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
IEE Transactions on Fuzzy Systems
Publication type:
Contribution in journal
DOI:
10.1109
JANUARY 2024
Monitoring Cardiovascular Physiology Using Bio-Compatible AlN Piezoelectric Skin Sensors
Authors
Angela Tafadzwa Shumba (Department of Engineering for Innovation, Università del Salento) - Suleyman Mahircan Demir (Centre for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia) - Vincenzo Mariano Mastronardi (Department of Innovation Engineering Università of Salento) - Francesco Rizzi (Centre for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia) Gaia De Marzo (Centre for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia - Luca Fachechi (Centre for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia)
Abstract
Abstract:
Arterial pulse waves contain a wealth of parameters indicative of cardiovascular disease.
As such, monitoring them continuously and unobtrusively can provide health professionals with a steady stream of cardiovascular health indices, allowing for the development of efficient, individualized treatments and early cardiovascular disease diagnosis solutions.
Blood pulsations in superficial arteries cause skin surface deformations, typically undetectable to the human eye; therefore, Microelectromechanical systems (MEMS) can be used to measure these deformations and thus create unobtrusive pulse wave monitoring devices.
Miniaturized ultrathin and flexible Aluminium Nitride (AlN) piezoelectric MEMS are highly sensitive to minute mechanical deformations, making them suitable for detecting the skin deformations caused by cardiac events and consequently providing multiple biomarkers useful for monitoring cardiovascular health and assessing cardiovascular disease risk.
Conventional wearable continuous pulse wave monitoring solutions are typically large and based on technologies limiting their versatility.
Therefore, we propose the adoption of $29.5 ~\mu \text{m}$ -thick biocompatible, skin-conforming devices on piezoelectric AlN to create versatile, multipurpose arterial pulse wave monitoring devices. In our initial trials, the devices are placed over arteries along the wrist (radial artery), neck (carotid artery), and suprasternal notch (on the chest wall and close to the ascending aorta).
We also leverage the mechano-acoustic properties of the device to detect heart muscle vibrations corresponding to heart sounds S1 and S2 from the suprasternal notch measurement site.
Finally, we characterize the piezoelectric device outputs observed with the cardiac cycle events using synchronized electrocardiogram (ECG) reference signals and provide information on heart rate, breathing rate, and heart sounds.
The extracted parameters strongly agree with reference values as illustrated by minimum Pearson correlation coefficients (r) of 0.81 for pulse rate and 0.95 for breathing rate.
Published:
26 January 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
IEEE Access
Publication type:
Contribution in journal
DOI:
10.1109
JANUARY 2024
Action Observation and Motor Imagery as a Treatment in Patients with Parkinson's Disease
Authors
Susanna Mezzarobba (Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, UniGe, and "RAISE Ecosystem", IRCCS Ospedale Policlinico San Martino) - Gaia Bonassi (Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, University of Genoa, and "RAISE Ecosystem") - Laura Avanzino (IRCCS Ospedale Policlinico San Martino, Department of Experimental Medicine, Section of Human Physiology, UniGe) - Elisa Pelosin (Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health, UniGe, and "RAISE Ecosystem", IRCCS Ospedale Policlinico San Martino)
Abstract
Abstract:
Action observation (AO) and motor imagery (MI) has emerged as promising tool for physiotherapy intervention in Parkinson's disease (PD).
This narrative review summarizes why, how, and when applying AO and MI training in individual with PD.
We report the neural underpinning of AO and MI and their effects on motor learning.
We examine the characteristics and the current evidence regarding the effectiveness of physiotherapy interventions and we provide suggestions about their implementation with technologies.
Neurophysiological data suggest a substantial correct activation of brain networks underlying AO and MI in people with PD, although the occurrence of compensatory mechanisms has been documented.
Regarding the efficacy of training, in general evidence indicates that both these techniques improve mobility and functional activities in PD.
However, these findings should be interpreted with caution due to variety of the study designs, training characteristics, and the modalities in which AO and MI were applied.
Finally, results on long-term effects are still uncertain.
Several elements should be considered to optimize the use of AO and MI in clinical setting, such as the selection of the task, the imagery or the video perspectives, the modalities of training.
However, a comprehensive individual assessment, including motor and cognitive abilities, is essential to select which between AO and MI suite the best to each PD patients.
Much unrealized potential exists for the use AO and MI training to provide personalized intervention aimed at fostering motor learning in both the clinic and home setting.
Published:
13 January 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
Journal of Parkinson’s Disease
Publication type:
Contribution in journal
DOI:
10.3233
JANUARY 2024
Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning
Authors
Claudio Sampieri (Department of Experimental Medicine (DIMES) - UniGe, Functional Unit of Head and Neck Tumors, Hospital Clínic, Barcelona, Otorhinolaryngology Department, Hospital Clínic, Barcelona) - Muhammad Adeel Azam (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) – UniGe) - Alessandro Ioppi (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Department of Otorhinolaryngology-Head and Neck Surgery, “S. Chiara” Hospital, Azienda Provinciale per i Servizi Sanitari (APSS), Trento) - Chiara Baldini (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS – UniGe) - Sara Moccia (The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna) - Dahee Kim (Department of Otorhinolaryngology, Yonsei University College of Medicine, Seoul, Republic of Korea) - Alessandro Tirrito (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Alberto Paderno (Unit of Otorhinolaryngology – Head and Neck Surgery, ASST Spedali Civili of Brescia, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia) - Cesare Piazza (Unit of Otorhinolaryngology – Head and Neck Surgery, ASST Spedali Civili of Brescia, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia) - Leonardo S. Mattos (Department of Advanced Robotics, Istituto Italiano di Tecnologia) - Giorgio Peretti (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Unit of Otorhinolaryngology-Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino)
Abstract
Abstract:
Objective
To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos.
Methods
A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos.
Results
A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70–0.90), Intersection over Union (IoU) = 0.83 (0.73–0.90), Accuracy = 0.97 (0.95–0.99), Inference Speed = 25.6 (25.1–26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos.
Conclusion
SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement.
Published:
4 January 2024
RAISE Affiliate:
Spoke 2
Name of the Journal:
The Laryngoscope
Publication type:
Contribution in journal
DOI:
10.1002
DECEMBER 2023
Robot-Induced Group Conversation Dynamics: A Model to Balance Participation and Unify Communities
Authors
Lucrezia Grassi (RICE Lab at DIBRIS – UniGe) - Carmine Tommaso Recchiuto (RICE Lab - UniGe, RAISE Ecosystem) - Antonio Sgorbissa (Dipartimento di informatica, bioingegneria, robotica e ingegneria dei sistemi - DIBRIS - UniGe, RAISE Ecosystem)
Abstract
Abstract:
The purpose of this research is to study the impact of robot participation in group conversations and assess the effectiveness of different addressing policies.
The study involved a total of 300 participants, who were divided into groups of four and engaged in a dialogue with a humanoid robot.
The robot acted as a moderator, using information obtained during the conversation to determine which speaker to address.
The study found that the policy used by the robot significantly impacted the conversation dynamics.
Specifically, the robot provided more balanced attention to each participant and reduced the number of subgroups.
Published:
13 December 2023
RAISE Affiliate:
Spoke 1
Conference name:
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publication type:
Contribution in conference proceedings
DOI:
10.1109
DECEMBER 2023
MultiTab: A Novel Portable Device to Evaluate Multisensory Skills
Authors
Giorgia Bertonati (Unit for Visually Impaired People U-VIP, Italian Institute of Technology, DIBRIS – UniGe) – M. Casado-Palacios (Unit for Visually Impaired People U-VIP, Italian Institute of Technology, DIBRIS – UniGe) - Marco Crepaldi (Head Technologist - Facility Coordinator Electronic Design Laboratory, Italian Institute of Technology) - Alberto Parmiggiani (Italian Institute of Technology) - Antonio Maviglia (Italian Institute of Technology) - Diego Torazza (Mechanical Workshop MW, Italian Institute of Technology) - Claudio Campus (Italian Institute of Technology) - Monica Gori (Italian Institute of Technology)
Abstract
Abstract:
To infer spatial-temporal features of an external event we are guided by multisensory cues, with intensive research showing an enhancement in the perception when information coming from different sensory modalities are integrated.
In this scenario, the motor system seems to also have an important role in boosting perception.
With the present work, we introduce and validate a novel portable technology, named MultiTab, which is able to provide auditory and visual stimulation, as well as to measure the user's manual responses.
Our preliminary results indicate that MultiTab reliably induces multisensory integration in a spatial localization task, shown by significantly reduced manual response times in the localization of audiovisual stimuli compared to unisensory stimuliClinical relevance.
The current work presents a novel portable device that could contribute to the clinical evaluation of multisensory processing as well as spatial perception.
In addition, by promoting and recording manual actions, MultiTab could be especially suitable for the design of rehabilitative protocols using multisensory motor training.
Published:
11 December 2023
RAISE Affiliate:
Spoke 2
Conference name:
Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publication type:
Contribution in conference proceedings
DOI:
10.1109
DECEMBER 2023
Feet Pressure Prediction from Lower Limbs IMU Sensors for Wearable Systems in Remote Monitoring Architectures
Authors
Igor Bisio (Department of Electrical Electronic Telecommunications Engineering and Naval Architecture – UniGe) - Chiara Garibotto (DITEN Department – UniGe) - Fabio Lavagetto (Department of Electrical Electronic Telecommunications Engineering and Naval Architecture – UniGe) - Muhammad Shahid (DITEN Department - UniGe)
Abstract
Abstract:
The eHealth systems are in great demand, particularly during times of outbreak like COVID-19, when there is a shortage of caregivers.
The technological advancements, such as wearable wireless devices, the Internet of Things, and improved machine learning methods have made these systems more reliable.
In modern times, these systems can play a vital role in post-rehabilitation journeys, which have significant social impact and high costs in traditional settings. Cost efficiency, portability, and generalization are key factors in adopting new technology.
In this study, we investigate the potential for optimizing and simplifying hardware in order to increase the cost-effectiveness and versatility of post-stroke eHealth rehabilitation systems.
It leverages the rich information available from Inertial Measurement Unit (IMU) sensors to compensate the need for foot pressure sensing.
We present the first attempt to demonstrate the potential of machine learning, aided by affordable off the shelf motion sensing devices, for foot pressure analysis.
Our proposed foot pressure decoding model is trained in an exercise-agnostic, self-supervised manner that eliminates the need for human annotation.
The algorithm is evaluated using appropriate performance metrics, and our experimental results show very promising performance.
Published:
8 December 2023
RAISE Affiliate:
Spoke 2
Conference name:
IEEE Global Communication Conference 2023
Publication type:
Contribution in conference proceedings
DOI:
10.1109
NOVEMBER 2023
A Software Framework to Encode the Psychological Dimensions of an Artificial Agent
Authors
Alice Nardelli (Dipartimento di informatica, bioingegneria, robotica e ingegneria dei sistemi - DIBRIS – UniGe) - Carmine Recchiuto (Dipartimento di informatica, bioingegneria, robotica e ingegneria dei sistemi - DIBRIS – UniGe) - Antonio Sgorbissa (Dipartimento di informatica, bioingegneria, robotica e ingegneria dei sistemi - DIBRIS - UniGe)
Abstract
Abstract:
Robotic personalities broaden the social dimension of an agent creating feelings of comfort in humans.
In this work, we propose a taxonomy model to generate synthetic personalities based on the Big Five model.
In particular, this paper describes a generalized framework for artificial personalities whose core is a Bidirectional Encoder Representations from Transformers (BERT) model capable of associating behaviors tailored to each personality trait.
The generator is fully integrated within a modular software architecture capable of performing social interaction tasks, being at the same time task-and platform-independent.
The proposed framework has been tested in a pilot experiment where human subjects were asked to interact with a humanoid robot displaying different personality traits.
Results obtained by the statistical analysis of validated questionnaires show interesting insights about the capability of the framework of generating personalities that are clearly perceived by users, and whose personality dimensions are strongly distinguishable.
Published:
13 November 2023
RAISE Affiliate:
Spoke 1
Conference name:
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
Publication type:
Contribution in conference proceedings
DOI:
10.1109
NOVEMBER 2023
Diversity-Aware Verbal Interaction Between a Robot and People With Spinal Cord Injury
Authors
Lucrezia Grassi (RICE Lab at DIBRIS University of Genoa) - Danilo Canepa (Department of Informatics Bioengineering Robotics, and Systems Engineering, University of Genoa) - Amy Bellitto (Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS), University of Genova) - Maura Casadio (DIBRIS University of Genova) - Antonino Massone (S.C. Unità Spinale Unipolare Santa Corona Hospital ASL2 Savonese)
Abstract
Abstract:
This article explores the acceptance of a humanoid robot designed to engage in conversations with clinicians and individuals with spinal cord injuries.
Building upon prior research, we introduce the concept of “diversity-aware” robots, which possess the capability to interact with people while adapting to their culture, age, gender, preferences, and physical and mental conditions.
These robots are connected to a cloud system specifically designed to consider these factors, enabling them to adapt to the context and individuals they interact with.
Our experiments involved the NAO robot interacting with both clinicians and individuals with spinal cord injuries in a hospital environment.
Subsequent to the interaction, participants completed a questionnaire and underwent an interview.
The collected data were analyzed to assess the system’s acceptability and its persistence beyond the initial novelty effect.
Furthermore, we investigated whether clinicians exhibited a lower predisposition towards the system and expressed greater concerns than end-users about using the robot, which could potentially hinder the adoption of the system.
Published:
13 November 2023
RAISE Affiliate:
Spoke 2
Conference name:
IEEE International Workshop on Robot and Human Communication (RO-MAN)
Publication type:
Contribution in conference proceedings
DOI:
10.1109
NOVEMBER 2023
Reconstruction and Preservation of Feature Curves in 3D Point Cloud Processing
Authors
Ulderico Fugacci (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Chiara Romanengo (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Bianca Falcidieno (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Silvia Biasotti (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
Given a 3D point cloud, we propose a method for suitably resampling the cloud while reconstructing and preserving the feature curves to which some points are identified to belong.
The first phase of our strategy enriches the cloud by approximating the curvilinear profiles outlined by the feature points with piece-wise polynomial parametric space curves through the use of the Hough transform.
The second phase describes how the removal of a point or its insertion can be performed without affecting the approximated profiles and preserving the enriched structure of the cloud.
The combination of the two steps provides multiple possibilities for processing a point cloud by varying its size or improving its density homogeneity without affecting the retrieved feature curves.
The various capabilities of our approach are investigated to produce simplification, refinement, and resampling techniques whose effectiveness is evaluated through experiments and comparisons.
Published:
10 November 2023
RAISE Affiliate:
Spoke 1
Name of the Journal:
Computer-Aided Design
Publication type:
Contribution in journal
DOI:
10.1016
NOVEMBER 2023
Vesicular CLC chloride/proton exchangers in health and diseases
Authors
Alessandra Picollo (Institute of Biophysics, National Research, RAISE Ecosystem)
Abstract
Abstract:
Chloride is one of the most abundant anions in the human body; it is implicated in several physiological processes such as the transmission of action potentials, transepithelial salt transport, maintenance of cellular homeostasis, regulation of osmotic pressure and intracellular pH, and synaptic transmission.
The balance between the extracellular and intracellular chloride concentrations is controlled by the interplay of ion channels and transporters embedded in the cellular membranes.
Vesicular members of the CLC chloride protein family (vCLCs) are chloride/proton exchangers expressed in the membrane of the intracellular organelles, where they control vesicular acidification and luminal chloride concentration.
It is well known that mutations in CLCs cause bone, kidney, and lysosomal genetic diseases. However, the role of CLC exchangers in neurological disorders is only now emerging with the identification of pathogenic CLCN gene variants in patients with severe neuronal and intellectual dysfunctions.
This review will provide an overview of the recent advances in understanding the role of the vesicular CLC chloride/proton exchangers in human pathophysiology.
Published:
7 November 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Frontiers in Pharmacology
Publication type:
Contribution in journal
DOI:
10.3389
NOVEMBER 2023
Automatic delineation of laryngeal squamous cell carcinoma during endoscopy
Authors
Muhammad Adeel Azam (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) – UniGe) - Claudio Sampieri (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Alessandro Ioppi (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Unit of Otorhinolaryngology-Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino) - Muhammad Ashir Azam (Department of Information and Communication Engineering, The Islamia University of Bahawalpur) - Chiara Baldini (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS – UniGe) - Shunlei Li (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) – UniGe) - Sara Moccia (The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna) - Giorgio Peretti (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Unit of Otorhinolaryngology-Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino)- Leonardo S. Mattos (Department of Advanced Robotics, Istituto Italiano di Tecnologia)
Abstract
Abstract:
White Light (WL) and Narrow Band Imaging (NBI) endoscopy are widely used to assess the superficial spreading of laryngeal squamous cell carcinoma (LSCC).
However, the analysis of images requires a high level of attention and extensive clinical expertise, leading to inter-clinician variability on the assessment of tumor margins.
Computer-aided segmentation can automate the identification of LSCC margins, supporting clinicians in this challenging task.
In this paper, we present SegMENT-Plus, a Deep Learning segmentation convolutional network specifically developed and optimized for accurate delineation of LSCC. SegMENT-Plus uses EfficienstNetB5 as encoder with a new modified Atrous Spatial Pyramid Pooling (m-ASPP) block that integrates Channel Block Attention Module (CBAM) and Squeeze Excitation (SE).
In this new architecture, CBAM extracts local and global LSCC features from the encoder, while the SE block refines cancer segmentation on each dilated convolution output.
SegMENT-Plus was trained and evaluated on a multi-center dataset including clinical data from three different hospitals. A total of 4289 annotated laryngeal images from 766 patients were included in this study.
The experiments showed that SegMENT-Plus achieved a Dice Similarity Coefficient (DSC) between 81.4% and 84.9% and an Intersection over
Union (IOU) between 81.8% and 85.7% on the data from the different hospitals, attesting its high performance and generalization capability.
The proposed segmentation architecture also demonstrated statistically significant improvement in DSC and IoU compared to other state of the art architectures, showing that this work is a concrete foundation towards a clinical system for the automatic delineation of LSCC margins in endoscopic images.
Published:
2 November 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Biomedical Signal Processing and Control
Publication type:
Contribution in journal
DOI:
10.1016
OCTOBER 2023
Out-of-Sample Extension of the Fuzzy Transform
Authors
Giuseppe Patané (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
This article addresses the definition and computation of the out-of-sample membership functions and the resulting out-of-sample fuzzy transform (FT), which extend their discrete counterparts to the continuous case.
Through the out-of-sample FT, we introduce a coherent analysis of the discrete and continuous FTs, which is applied to extrapolate the behavior of the FT on new data and to achieve an accurate approximation of the continuous FT of signals on arbitrary data.
To this end, we apply either an approximated approach, which considers the link between integral kernels and the spectrum of the corresponding Gram matrix, or an interpolation of the discrete kernel eigenfunctions with radial basis functions.
In this setting, we show the generality of the proposed approach to the input data (e.g., graphs, 3-D domains) and signal reconstruction.
Published:
23 October 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
IEEE Transactions on Fuzzy Systems
Publication type:
Contribution in journal
DOI:
10.1109
JULY 2023
GEO-Nav: A geometric dataset of voltage-gated sodium channels
Authors
Andrea Raffo (Department of Biosciences, University of Oslo) - Ulderico Fugacci (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Silvia Biasotti (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
Voltage-gated sodium (Nav) channels constitute a prime target for drug design and discovery, given their implication in various diseases such as epilepsy, migraine and ataxia to name a few.
In this regard, performing morphological analysis is a crucial step in comprehensively understanding their biological function and mechanism, as well as in uncovering subtle details of their mechanism that may be elusive to experimental observations.
Despite their tremendous therapeutic potential, drug design resources are deficient, particularly in terms of accurate and comprehensive geometric information.
This paper presents a geometric dataset of molecular surfaces that are representative of Nav channels in mammals.
For each structure we provide three representations and a number of geometric measures, including length, volume and straightness of the recognized channels.
To demonstrate the effective use of GEO-Nav, we have tested it on two methods belonging to two different categories of approaches: a sphere-based and a tessellation-based method.
Published:
24 July 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Computers & Graphics
Publication type:
Contribution in journal
DOI:
10.1016
JULY 2023
Spectral Laplace Transform of Signals on Arbitrary Domains
Authors
Giuseppe Patané (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
The Laplace transform is a central mathematical tool for analysing 1D/2D signals and for the solution to PDEs; however, its definition and computation on arbitrary data is still an open research problem.
We introduce the Laplace transform on arbitrary domains and focus on the spectral Laplace transform, which is defined by applying a 1D filter to the Laplacian spectrum of the input domain.
The spectral Laplace transform satisfies standard properties of the 1D and 2D transforms, such as dilation, translation, scaling, derivation, localisation, and relations with the Fourier transform.
The spectral Laplace transform is enough general to be applied to signals defined on different discrete data, such as graphs, 3D surface meshes, and point sets. Working in the spectral domain and applying polynomial and rational polynomial approximations, we achieve a stable computation of the spectral Laplace Transform.
As main applications, we discuss the computation of the spectral Laplace Transform of functions defined on arbitrary domains (e.g., 2D and 3D surfaces, graphs), the solution of the heat diffusion equation, and graph signal processing.
Published:
18 July 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Journal of Scientific Computing
Publication type:
Contribution in journal
DOI:
10.1007
JUNE 2023
Quality of word and concept embeddings in targetted biomedical domains
Authors
Salvatore Giancani (Institut de Neurosciences de la Timone, Unité Mixte de Recherche 7289 Centre National de la Recherce Scientifique and Aix-Marseille Université, Faculty of Medicine) - Riccardo Albertoni (Istituto di Matematica Applicata e Tecnologie Informatiche, CNR) - Chiara Eva Catalano (Istituto di Matematica Applicata e Tecnologie Informatiche, CNR)
Abstract
Abstract:
Embeddings are fundamental resources often reused for building intelligent systems in the biomedical context.
As a result, evaluating the quality of previously trained embeddings and ensuring they cover the desired information is critical for the success of applications.
This paper proposes a new evaluation methodology to test the coverage of embeddings against a targetted domain of interest.
It defines measures to assess the terminology, similarity, and analogy coverage, which are core aspects of the embeddings.
Then, it discusses the experimentation carried out on existing biomedical embeddings in the specific context of pulmonary diseases.
The proposed methodology and measures are general and may be applied to any application domain.
Published:
2 June 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Heliyon
Publication type:
Contribution in journal
DOI:
10.1016
JUNE 2023
Biophysical Aspects of Neurodegenerative and Neurodevelopmental Disorders Involving Endo-/Lysosomal CLC Cl/H+ Antiporters
Authors
Maria Antonietta Coppola (Istituto di Biofisica, Consiglio Nazionale delle Ricerche, Department of Pharmacy–Drug Sciences, University of Bari) - Abraham Tettey-Matey (Istituto di Biofisica, Consiglio Nazionale delle Ricerche) - Paola Imbrici (Department of Pharmacy–Drug Sciences, University of Bari) - Paola Gavazzo (Istituto di Biofisica, Consiglio Nazionale delle Ricerche) - Antonella Liantonio (Department of Pharmacy–Drug Sciences, University of Bari) - Michael Pusch (Istituto di Biofisica, Consiglio Nazionale delle Ricerche, RAISE Ecosystem)
Abstract
Abstract:
Endosomes and lysosomes are intracellular vesicular organelles with important roles in cell functions such as protein homeostasis, clearance of extracellular material, and autophagy.
Endolysosomes are characterized by an acidic luminal pH that is critical for proper function.
Five members of the gene family of voltage-gated ChLoride Channels (CLC proteins) are localized to endolysosomal membranes, carrying out anion/proton exchange activity and thereby regulating pH and chloride concentration.
Mutations in these vesicular CLCs cause global developmental delay, intellectual disability, various psychiatric conditions, lysosomal storage diseases, and neurodegeneration, resulting in severe pathologies or even death.
Currently, there is no cure for any of these diseases. Here, we review the various diseases in which these proteins are involved and discuss the peculiar biophysical properties of the WT transporter and how these properties are altered in specific neurodegenerative and neurodevelopmental disorders.
Published:
2 June 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Life
Publication type:
Contribution in journal
DOI:
10.3390
MAY 2023
Super-resolution of 2D ultrasound images and videos
Authors
Simone Cammarasana (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Paolo Nicolardi (Esaote S.p.A) - Giuseppe Patanè (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
This paper proposes a novel deep-learning framework for super-resolution ultrasound images and videos in terms of spatial resolution and line reconstruction.
To this end, we up-sample the acquired low-resolution image through a vision-based interpolation method; then, we train a learning-based model to improve the quality of the up-sampling. We qualitatively and quantitatively test our model on different anatomical districts (e.g., cardiac, obstetric) images and with different up-sampling resolutions (i.e., 2X, 4X).
Our method improves the PSNR median value with respect to SOTA methods of on obstetric 2X raw images, on cardiac 2X raw images, and on abdominal raw 4X images; it also improves the number of pixels with a low prediction error of on obstetric 4X raw images, on cardiac 4X raw images, and on abdominal 4X raw images.
The proposed method is then applied to the spatial super-resolution of 2D videos, by optimising the sampling of lines acquired by the probe in terms of the acquisition frequency. Our method specialises trained networks to predict the high-resolution target through the design of the network architecture and the loss function, taking into account the anatomical district and the up-sampling factor and exploiting a large ultrasound data set.
The use of deep learning on large data sets overcomes the limitations of vision-based algorithms that are general and do not encode the characteristics of the data.
Furthermore, the data set can be enriched with images selected by medical experts to further specialise the individual networks.
Through learning and high-performance computing, the proposed super-resolution is specialised to different anatomical districts by training multiple networks.
Furthermore, the computational demand is shifted to centralised hardware resources with a real-time execution of the network’s prediction on local devices.
Published:
17 May 2023
RAISE Affiliate:
Spoke 2
Name of the Journal:
Medical & Biological Engineering & Computing
Publication type:
Contribution in journal
DOI:
10.1007
NOVEMBER 2022
Three-Dimensional Anatomical Analysis of Muscle–Skeletal Districts
Authors
Martina Paccini (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Giuseppe Patanè (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR) - Michela Spagnuolo (Istituto di Matematica Applicata e Tecnologie Informatiche “E. Magenes”, CNR)
Abstract
Abstract:
This work addresses the patient-specific characterisation of the morphology and pathologies of muscle–skeletal districts (e.g., wrist, spine) to support diagnostic activities and follow-up exams through the integration of morphological and tissue information.
We propose different methods for the integration of morphological information, retrieved from the geometrical analysis of 3D surface models, with tissue information extracted from volume images.
For the qualitative and quantitative validation, we discuss the localisation of bone erosion sites on the wrists to monitor rheumatic diseases and the characterisation of the three functional regions of the spinal vertebrae to study the presence of osteoporotic fractures.
The proposed approach supports the quantitative and visual evaluation of possible damages, surgery planning, and early diagnosis or follow-up studies.
Finally, our analysis is general enough to be applied to different districts.
Published:
25 November 2022
RAISE Affiliate:
Spoke 2
Name of the Journal:
Applied Sciences
Publication type:
Contribution in journal
DOI:
10.3390
JUNE 2022
Videomics of the upper aero-digestive tract cancer: Deep learning applied to white light and Narrow Band Imaging for automatic segmentation of endoscopic images
Authors
Muhammad Adeel Azam (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) – UniGe) - Claudio Sampieri (Department of Experimental Medicine (DIMES) - UniGe, Functional Unit of Head and Neck Tumors, Hospital Clínic, Barcelona, Otorhinolaryngology Department, Hospital Clínic, Barcelona) - Alessandro Ioppi (Department of Otorhinolaryngology-Head and Neck Surgery, "S. Chiara" Hospital, Azienda Provinciale per i Servizi Sanitari (APSS) Trento, Istituto Nazionale per la Ricerca sul Cancro, IRCCS Azienda Ospedaliera Universitaria San Martino) - Pietro Benzi (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe) - Giorgio Gregory Giordano (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Marta De Vecchi (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Valentina Campagnari (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Shunlei Li (Department of Advanced Robotics, Istituto Italiano di Tecnologia) - Luca Guastini (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Alberto Paderno (Unit of Otorhinolaryngology – Head and Neck Surgery, ASST Spedali Civili of Brescia, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia) - Sara Moccia (The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna) - Cesare Piazza (Unit of Otorhinolaryngology – Head and Neck Surgery, ASST Spedali Civili of Brescia, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia) - Leonardo S. Mattos (Department of Advanced Robotics, Istituto Italiano di Tecnologia) - Giorgio Peretti (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Unit of Otorhinolaryngology-Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino)
Abstract
Abstract:
Introduction
Narrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images.
Materials and Methods
A dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets.
Results
219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%.
Conclusion
SegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.
Published:
1 June 2022
RAISE Affiliate:
Spoke 2
Name of the Journal:
Frontiers in Oncology
Publication type:
Contribution in journal
DOI:
10.3389
MAY 2022
Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection
Authors
Muhammad Adeel Azam (Department of Advanced Robotics, Istituto Italiano di Tecnologia, Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi (DIBRIS) – UniGe) - Claudio Sampieri (Department of Experimental Medicine (DIMES) - UniGe, Functional Unit of Head and Neck Tumors, Hospital Clínic, Barcelona, Otorhinolaryngology Department, Hospital Clínic, Barcelona) - Alessandro Ioppi (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Stefano Africano (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Alberto Vallin (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Davide Mocellin (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Marco Fragale (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Luca Guastini (Unit of Otorhinolaryngology – Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino, Department of Surgical Sciences and Integrated Diagnostics (DISC) – UniGe) - Sara Moccia (The BioRobotics Institute and Department of Excellence in Robotics and AI, Scuola Superiore Sant'Anna) - Cesare Piazza (Unit of Otorhinolaryngology – Head and Neck Surgery, ASST Spedali Civili of Brescia, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia) - Leonardo S. Mattos (Department of Advanced Robotics, Istituto Italiano di Tecnologia) - Giorgio Peretti (Department of Experimental Medicine (DIMES) - UniGe, Department of Surgical Sciences and Integrated Diagnostics (DISC) - UniGe, Unit of Otorhinolaryngology-Head and Neck Surgery, IRCCS Ospedale Policlinico San Martino)
Abstract
Abstract:
Objectives
To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN).
Study Design
Experimental study with retrospective data.
Methods
Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies.
Results
Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m—TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided.
Conclusion
This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing.
Published:
14 May 2022
RAISE Affiliate:
Spoke 2
Name of the Journal:
The Laryngoscope
Publication type:
Contribution in journal
DOI:
10.1002