2022
Other
Restricted
Tutorial per la piattaforma "TiAssisto" - Corso di formazione per il personale sanitario
Ignesti G, Bruno A, Martinelli M
Corso di formazione per medici di medicina generale e il personale sanitario delle Residenze Sanitarie Assistenziali coinvolto nel progetto TiAssisto, Bando Covid-19 - Regione Toscana.
Ignesti G, Bruno A, Martinelli M
Corso di formazione per medici di medicina generale e il personale sanitario delle Residenze Sanitarie Assistenziali coinvolto nel progetto TiAssisto, Bando Covid-19 - Regione Toscana.
2022
Other
Restricted
Tutorial per la piattaforma "TiAssisto" - Corso di formazione per il personale sanitario - Aggiornamenti
Ignesti G, Bruno A, Martinelli M
Corso di formazione per medici di medicina generale e il personale sanitario delle Residenze Sanitarie Assistenziali coinvolto nel progetto TiAssisto, Bando Covid-19 - Regione Toscana.
Ignesti G, Bruno A, Martinelli M
Corso di formazione per medici di medicina generale e il personale sanitario delle Residenze Sanitarie Assistenziali coinvolto nel progetto TiAssisto, Bando Covid-19 - Regione Toscana.
2022
Other
Restricted
Una piattaforma di tele-assistenza e tele-monitoraggio di pazienti affetti da Covid-19 - Meeting Scientifico TiAssisto
Ignesti G, Martinelli M
Presentazione meeting comitato scientifico progetto Regione Toscana Bando Covid-19 TiAssisto
Ignesti G, Martinelli M
Presentazione meeting comitato scientifico progetto Regione Toscana Bando Covid-19 TiAssisto
2023
Journal article
Open Access
Explaining ensemble models for lung ultrasound classification
Bruno A, Ignesti G, Martinelli M
Correct classification is the main aspect in evaluating the quality of an artificial intelligence system, but what happens when you reach top accuracy and no method explains how it works? In our study, we aim at addressing the black-box problem using an ad-hoc built classifier for lung ultrasound im... ages. [show more]Source: ERCIM NEWS, vol. 134
Bruno A, Ignesti G, Martinelli M
Correct classification is the main aspect in evaluating the quality of an artificial intelligence system, but what happens when you reach top accuracy and no method explains how it works? In our study, we aim at addressing the black-box problem using an ad-hoc built classifier for lung ultrasound im... ages. [show more]Source: ERCIM NEWS, vol. 134
See at:
ercim-news.ercim.eu 
| CNR IRIS | ISTI Repository | CNR IRIS 
2022
Other
Restricted
D3.2- TiAssisto. Design e sviluppo dei moduli SW della piattaforma
Martinelli M, Cicalini D, Pratali L, Ignesti G, Bruno A, Moroni D
Il presente documento è il primo deliverable dell'Obiettivo Operativo 3 "Design e sviluppo dei moduli SW della piattaforma" del progetto TiAssisto e si inserisce nell'attività 3.2: Progettazione e sviluppo di interfacce grafiche personalizzate e user-friendly e soluzioni Web/mobile. Progettazione ... e sviluppo di moduli software basati sul Web per l'interazione dell'utente con i pazienti, servizi TiAssisto per utenti, parenti e medici. Applicazioni Web personalizzate per migliorare la qualità della vita e l'assistenza remota. [show more]
Martinelli M, Cicalini D, Pratali L, Ignesti G, Bruno A, Moroni D
Il presente documento è il primo deliverable dell'Obiettivo Operativo 3 "Design e sviluppo dei moduli SW della piattaforma" del progetto TiAssisto e si inserisce nell'attività 3.2: Progettazione e sviluppo di interfacce grafiche personalizzate e user-friendly e soluzioni Web/mobile. Progettazione ... e sviluppo di moduli software basati sul Web per l'interazione dell'utente con i pazienti, servizi TiAssisto per utenti, parenti e medici. Applicazioni Web personalizzate per migliorare la qualità della vita e l'assistenza remota. [show more]
2022
Other
Restricted
D6.3- TiAssisto Prototipo piattaforma TiAssisto in era Covid -19 nei diversi setting di pazienti
Ignesti G, Bruno A, Deri C, D'Angelo G, Pratali L, Martinelli M
Il presente documento è il terzo deliverable dell'Obiettivo Operativo 6 "Sottomissione comitato etico locale, arruolamento, sviluppo, formazione, test e validazione" del progetto TiAssisto e si inserisce nell'attività 6.3.
Ignesti G, Bruno A, Deri C, D'Angelo G, Pratali L, Martinelli M
Il presente documento è il terzo deliverable dell'Obiettivo Operativo 6 "Sottomissione comitato etico locale, arruolamento, sviluppo, formazione, test e validazione" del progetto TiAssisto e si inserisce nell'attività 6.3.
2022
Other
Restricted
D2.2- TiAssisto Requisiti tecnico-scientifici, integrazione fra analisi delle immagini e l'uso della telemedicina
Ignesti G, Moroni D, Pratali L, Martinelli M
Definizione dei requisiti delle basi scientifiche e tecnologiche, analisi delle conoscenze riguardo l'integrazione delle immagini e sull'uso della telemedicina, identificazione degli standards.
Ignesti G, Moroni D, Pratali L, Martinelli M
Definizione dei requisiti delle basi scientifiche e tecnologiche, analisi delle conoscenze riguardo l'integrazione delle immagini e sull'uso della telemedicina, identificazione degli standards.
2021
Other
Restricted
D3.1- TiAssisto - Identificazione degli standard
Ignesti G, Ragognetti G, Moroni D, Pratali L, Martinelli M
Implementazione Piattaforma del progetto TiAssisto - Attività 3.1 "Design e sviluppo del sistema di gestione dati" di cui rappresenta l'output finale.
Ignesti G, Ragognetti G, Moroni D, Pratali L, Martinelli M
Implementazione Piattaforma del progetto TiAssisto - Attività 3.1 "Design e sviluppo del sistema di gestione dati" di cui rappresenta l'output finale.
2022
Other
Restricted
D5.2 - TiAssisto integrazione ed interoperabilità dei servizi
Bruno A, Ignesti G, Moroni D, Pratali L, Martinelli M
Integrazione ed interoperabilità dei Servizi della piattaforma TiAssisto.
Bruno A, Ignesti G, Moroni D, Pratali L, Martinelli M
Integrazione ed interoperabilità dei Servizi della piattaforma TiAssisto.
2023
Journal article
Open Access
Efficient lung ultrasound classification
Bruno A, Ignesti G, Salvetti O, Moroni D, Martinelli M
A machine learning method for classifying Lung UltraSound is here proposed to provide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advantages (e.g. safety, rapidity, portability, cost-effectiveness) p... rovided by the ultrasound technology over other methods (e.g. X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest LUS public dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art. The complexity of this solution keeps the number of parameters in the same order as an EfficientNet-b0 by adopting specific design choices that are adaptive ensembling with a combination layer, ensembling performed on the deep features, minimal ensemble only two weak models. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where the focus is on an inaccurate weak model versus an accurate model. [show more]Source: BIOENGINEERING, vol. 10 (issue 5)
DOI: 10.3390/bioengineering10050555
Metrics:
Bruno A, Ignesti G, Salvetti O, Moroni D, Martinelli M
A machine learning method for classifying Lung UltraSound is here proposed to provide a point of care tool for supporting a safe, fast and accurate diagnosis, that can also be useful during a pandemic like as SARS-CoV-2. Given the advantages (e.g. safety, rapidity, portability, cost-effectiveness) p... rovided by the ultrasound technology over other methods (e.g. X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest LUS public dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art. The complexity of this solution keeps the number of parameters in the same order as an EfficientNet-b0 by adopting specific design choices that are adaptive ensembling with a combination layer, ensembling performed on the deep features, minimal ensemble only two weak models. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where the focus is on an inaccurate weak model versus an accurate model. [show more]Source: BIOENGINEERING, vol. 10 (issue 5)
DOI: 10.3390/bioengineering10050555
Metrics:
See at:
CNR IRIS | ISTI Repository | www.mdpi.com | CNR IRIS | CNR IRIS
2023
Contribution to conference
Restricted
Efficient lung ultrasound classification
Ignesti G, Bruno A, Martinelli M, Moroni D
The SARS-CoV-2 pandemic has taught us that point-of-care signs quickly or in remote settings are essential. Ultrasound imaging is a fast and common diagnostic tool, which made it a popular choice during the pandemic. Our team implemented a deep learning algorithm with remarkable accuracy (100%) to d... etect signs of COVID-19 and bacterial pneumonia, which can better assist physicians. GradCAM was employed to examine the outcomes and determine whether the network relied on dependable medical indicators for classification. [show more]
Ignesti G, Bruno A, Martinelli M, Moroni D
The SARS-CoV-2 pandemic has taught us that point-of-care signs quickly or in remote settings are essential. Ultrasound imaging is a fast and common diagnostic tool, which made it a popular choice during the pandemic. Our team implemented a deep learning algorithm with remarkable accuracy (100%) to d... etect signs of COVID-19 and bacterial pneumonia, which can better assist physicians. GradCAM was employed to examine the outcomes and determine whether the network relied on dependable medical indicators for classification. [show more]
See at:
CNR IRIS | CNR IRIS | vismac23.github.io
2023
Contribution to conference
Open Access
Trustworthy AI for signals and image processing: a telemedicine perspective
Ignesti G, Bruno A, Moroni D, Martinelli M
Artficial Intelligence is showing unprecedented performance in signals & image processing. Classification, segmentation and generative process seem to have unlimited potential. The roots of Artificial Intelligence are deep in scientific history, but in the world of Big Data and Internet 5.0, its... use and effects have yet to be entirely tested. The black box problem, security, privacy issues, and public opinion are some of the factors that push towards the development of a new concept: "Trustworthy AI". The use of advanced methods, such as EfficientNet & GradCAM, leads to remarkable accuracy and consistent explanation in the classification of ultrasound. Further studies aim at analyzing results could lead to a more robust application of AI in the generalized field of signal and image processing and will lay the foundation for future work on reliable AI. [show more]
Ignesti G, Bruno A, Moroni D, Martinelli M
Artficial Intelligence is showing unprecedented performance in signals & image processing. Classification, segmentation and generative process seem to have unlimited potential. The roots of Artificial Intelligence are deep in scientific history, but in the world of Big Data and Internet 5.0, its... use and effects have yet to be entirely tested. The black box problem, security, privacy issues, and public opinion are some of the factors that push towards the development of a new concept: "Trustworthy AI". The use of advanced methods, such as EfficientNet & GradCAM, leads to remarkable accuracy and consistent explanation in the classification of ultrasound. Further studies aim at analyzing results could lead to a more robust application of AI in the generalized field of signal and image processing and will lay the foundation for future work on reliable AI. [show more]
See at:
CNR IRIS | ISTI Repository | sites.google.com | CNR IRIS
2023
Other
Restricted
Study and development of trustworthy AI application in Medicine
Ignesti G, Moroni D, Martinelli M
National PhD in Artificial Intelligence, section for Society, first year report.
Ignesti G, Moroni D, Martinelli M
National PhD in Artificial Intelligence, section for Society, first year report.
2022
Other
Restricted
D5.1 TiAssisto - Progettazione delle funzionalità di interazione dei servizi per l'utente finale
Ignesti G, Bruno A, Galesi G, Pardini F, Cicalini D, Roth L, Pratali L, Martinelli M
Il presente documento è il primo deliverable dell'Obiettivo Operativo 5 "Servizi per gli utilizzatori finali".
Ignesti G, Bruno A, Galesi G, Pardini F, Cicalini D, Roth L, Pratali L, Martinelli M
Il presente documento è il primo deliverable dell'Obiettivo Operativo 5 "Servizi per gli utilizzatori finali".
2024
Conference article
Open Access
Plant-traits: how citizen science and artificial intelligence can impact natural science
Ignesti G., Moroni D., Martinelli M.
Citizen science has emerged as a valuable resource for scientific research, providing large volumes of data for training deep learning models. However, the quality and accuracy of crowd-sourced data pose significant challenges for supervised learning tasks such as plant trait detection. This study i... nvestigates the application of AI techniques to address these issues within natural science. We explore the potential of multi-modal data analysis and ensemble methods to improve the accuracy of plant trait classification using citizen science data. Additionally, we examine the effectiveness of transfer learning from authoritative datasets like PlantVillage to enhance model performance on open- access platforms such as iNaturalist. By analysing the strengths and limitations of AI-driven approaches in this context, we aim to contribute to developing robust and reliable methods for utilising citizen science data in natural science. [show more]Source: ANNALS OF COMPUTER SCIENCE AND INFORMATION SYSTEMS, vol. 39, pp. 625-630. Belgrade, Serbia, 9-11/09/2024
DOI: 10.15439/2024f8703
Metrics:
Ignesti G., Moroni D., Martinelli M.
Citizen science has emerged as a valuable resource for scientific research, providing large volumes of data for training deep learning models. However, the quality and accuracy of crowd-sourced data pose significant challenges for supervised learning tasks such as plant trait detection. This study i... nvestigates the application of AI techniques to address these issues within natural science. We explore the potential of multi-modal data analysis and ensemble methods to improve the accuracy of plant trait classification using citizen science data. Additionally, we examine the effectiveness of transfer learning from authoritative datasets like PlantVillage to enhance model performance on open- access platforms such as iNaturalist. By analysing the strengths and limitations of AI-driven approaches in this context, we aim to contribute to developing robust and reliable methods for utilising citizen science data in natural science. [show more]Source: ANNALS OF COMPUTER SCIENCE AND INFORMATION SYSTEMS, vol. 39, pp. 625-630. Belgrade, Serbia, 9-11/09/2024
DOI: 10.15439/2024f8703
Metrics:
See at:
IRIS Cnr | annals-csis.org | Annals of computer science and information systems | IRIS Cnr | Archivio della Ricerca - Università di Pisa | CNR IRIS | CNR IRIS
2024
Conference article
Open Access
Towards the actual deployment of robust, adaptable, and maintainable AI models for sustainable agriculture
Ignesti G., Moroni D., Martinelli M.
In the past two decades, computer vision and arti- ficial intelligence (AI) have made significant strides in delivering practical solutions to aid farmers directly in the fields, thereby contributing to the integration of advanced technology in pre- cision agriculture. However, extending these metho... ds to diverse crops and broader applications, including low-resource situations, raises several concerns. Indeed, the adaptability of AI methods to new cases and domains is not always straightforward. Moreover, the dynamic global panorama requires a continuous adaptation and refinement of artificial intelligence models. In this position paper, we examine the current opportunities and challenges, and propose a new approach to address these issues, currently in the implementation phase at CNR-ISTI. [show more]Source: ACSIS PUBLICATIONS, vol. 40, pp. 33-39. Belgrade, Serbia, 9-11/09/2024
DOI: 10.15439/2024f2991
Metrics:
Ignesti G., Moroni D., Martinelli M.
In the past two decades, computer vision and arti- ficial intelligence (AI) have made significant strides in delivering practical solutions to aid farmers directly in the fields, thereby contributing to the integration of advanced technology in pre- cision agriculture. However, extending these metho... ds to diverse crops and broader applications, including low-resource situations, raises several concerns. Indeed, the adaptability of AI methods to new cases and domains is not always straightforward. Moreover, the dynamic global panorama requires a continuous adaptation and refinement of artificial intelligence models. In this position paper, we examine the current opportunities and challenges, and propose a new approach to address these issues, currently in the implementation phase at CNR-ISTI. [show more]Source: ACSIS PUBLICATIONS, vol. 40, pp. 33-39. Belgrade, Serbia, 9-11/09/2024
DOI: 10.15439/2024f2991
Metrics:
See at:
annals-csis.org | Annals of computer science and information systems | IRIS Cnr | Archivio della Ricerca - Università di Pisa | CNR IRIS | CNR IRIS
2024
Other
Restricted
D4.2 (2) – TiAssisto: Implementazione dei servizi intelligenti di supporto alla decisione
Ignesti G., Deri C., D’angelo G., Moroni D., Pratali L., Martinelli M.
Il presente documento è il primo deliverable dell’Obiettivo Operativo 4 “Implementazione dei servizi intelligenti di supporto alla decisione (IDSS)” L'obiettivo è trasferire le conoscenze acquisite mediante i sistemi di intelligenza artificiale (IA) grazie alle fasi di apprendimento eseguite sui d... ati acquisiti dai dispositivi in un insieme di protocolli basati sui principi della evidence-based medicine in modo da fornire e un supporto decisionale fattibile e affidabile. È evidente che tutte queste funzionalità necessitano di servizi specifici per essere adeguatamente sfruttate, per la cui definizione sarà necessaria una forte collaborazione con la controparte clinica. In particolare si eseguiranno le seguenti sotto attività: - Trasformazione del flusso del nuovo protocollo di cura in un insieme organico e formalizzato di suggerimenti e di regole definite dai medici in una forma adeguata per l'implementazione nell’IDSS. Ciò sarà derivato dall'attività 2.1 e dalla conoscenza estratta mediante paradigmi di intelligenza artificiale dai dati raccolti. - Definizione e implementazione degli score e dei suggerimenti sul rischio. [show more]Project(s): TiAssisto
Ignesti G., Deri C., D’angelo G., Moroni D., Pratali L., Martinelli M.
Il presente documento è il primo deliverable dell’Obiettivo Operativo 4 “Implementazione dei servizi intelligenti di supporto alla decisione (IDSS)” L'obiettivo è trasferire le conoscenze acquisite mediante i sistemi di intelligenza artificiale (IA) grazie alle fasi di apprendimento eseguite sui d... ati acquisiti dai dispositivi in un insieme di protocolli basati sui principi della evidence-based medicine in modo da fornire e un supporto decisionale fattibile e affidabile. È evidente che tutte queste funzionalità necessitano di servizi specifici per essere adeguatamente sfruttate, per la cui definizione sarà necessaria una forte collaborazione con la controparte clinica. In particolare si eseguiranno le seguenti sotto attività: - Trasformazione del flusso del nuovo protocollo di cura in un insieme organico e formalizzato di suggerimenti e di regole definite dai medici in una forma adeguata per l'implementazione nell’IDSS. Ciò sarà derivato dall'attività 2.1 e dalla conoscenza estratta mediante paradigmi di intelligenza artificiale dai dati raccolti. - Definizione e implementazione degli score e dei suggerimenti sul rischio. [show more]Project(s): TiAssisto
2025
Conference article
Open Access
You've got the wrong number: evaluating deep learning training paradigms using handwritten digit recognition data
Ignesti G., Martinelli M., Moroni D.
To build more accurate and trustworthy artificial intelligence algorithms in deep learning, it is essential to understand the mechanisms driving classification systems to identify their targets. Typically, post hoc methods provide insights into this process. In this preliminary work, we shift the re... construction of the class activation map to the training phase to evaluate how the model's performance changes compared to standard classification approaches. The MNIST dataset and its variants, such as Fashion MNIST, consist of well-defined images that facilitate testing this type of training process. Specifically, the classification targets are the only significant content in the images, excluding the background, allowing for a direct comparison of the reconstruction against the input images. To enhance the guidance of the network, we introduce a contrastive loss term to complement the standard classification function, which often uses categorical cross-entropy. By comparing the accuracy and the extracted pattern of the standard approach with the proposed method, we can gain valuable insights into the network's learning process. This approach aims toimprove the interpretability and effectiveness of the model during training, ultimately leading to higher classification accuracy and reliability. [show more]Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 34 (issue 4), pp. 978-983. Kolkata, India, 1-5/12/2024
Ignesti G., Martinelli M., Moroni D.
To build more accurate and trustworthy artificial intelligence algorithms in deep learning, it is essential to understand the mechanisms driving classification systems to identify their targets. Typically, post hoc methods provide insights into this process. In this preliminary work, we shift the re... construction of the class activation map to the training phase to evaluate how the model's performance changes compared to standard classification approaches. The MNIST dataset and its variants, such as Fashion MNIST, consist of well-defined images that facilitate testing this type of training process. Specifically, the classification targets are the only significant content in the images, excluding the background, allowing for a direct comparison of the reconstruction against the input images. To enhance the guidance of the network, we introduce a contrastive loss term to complement the standard classification function, which often uses categorical cross-entropy. By comparing the accuracy and the extracted pattern of the standard approach with the proposed method, we can gain valuable insights into the network's learning process. This approach aims toimprove the interpretability and effectiveness of the model during training, ultimately leading to higher classification accuracy and reliability. [show more]Source: PATTERN RECOGNITION AND IMAGE ANALYSIS, vol. 34 (issue 4), pp. 978-983. Kolkata, India, 1-5/12/2024
See at:
CNR IRIS | imta.isti.cnr.it | CNR IRIS | CNR IRIS
2021
Other
Restricted
D4.2: TiAssisto - Implementazione dei servizi intelligenti di supporto alla decisione
Ignesti G, Deri C, D'Angelo G, Moroni D, Pratali L, Martinelli M
Implementazione dei servizi intelligenti di supporto alla decisione (IDSS).
Ignesti G, Deri C, D'Angelo G, Moroni D, Pratali L, Martinelli M
Implementazione dei servizi intelligenti di supporto alla decisione (IDSS).
2024
Conference article
Restricted
Assessment of dance movement therapy outcomes: a preliminary proposal
Daoudagh S., Ignesti G., Moroni D., Sebastiani L., Paradisi P.
Context: Dance Movement Therapy (DMT) is a therapeutic modality that utilizes movement to promote holistic well-being. Current DMT assessment methods rely heavily on the subjective judgment of the DMT professional. Objective: Our research aims to develop a framework composed of different components ... with specific functionalities that can be integrated with the DMT modality to improve the objectivity and efficiency of DMT evaluations. Method: The DMT framework consists of an experimental protocol for data collection and a reference-supporting architecture that includes components for video analysis, physiological signal management, and evaluation tools. Artificial Intelligence (AI) based human pose estimation techniques are also employed to derive the DMT participants’ poses during the DMT sessions for more reliable movement analysis. Results: Our preliminary results consist of demonstrating the effectiveness of the AI-based pose estimation tool, YOLO-NAS-Pose, in accurately detecting participants’ poses. Conclusion: The proposed framework offers a promising approach to improving DMT practices by integrating and leveraging AI-based human pose estimation to evaluate participants’ movement in the DMT setting objectively. Future research will focus on refining the framework and developing user-friendly tools for widespread adoption in real DMT contexts. [show more]Project(s): Tuscany Health Ecosystem
Daoudagh S., Ignesti G., Moroni D., Sebastiani L., Paradisi P.
Context: Dance Movement Therapy (DMT) is a therapeutic modality that utilizes movement to promote holistic well-being. Current DMT assessment methods rely heavily on the subjective judgment of the DMT professional. Objective: Our research aims to develop a framework composed of different components ... with specific functionalities that can be integrated with the DMT modality to improve the objectivity and efficiency of DMT evaluations. Method: The DMT framework consists of an experimental protocol for data collection and a reference-supporting architecture that includes components for video analysis, physiological signal management, and evaluation tools. Artificial Intelligence (AI) based human pose estimation techniques are also employed to derive the DMT participants’ poses during the DMT sessions for more reliable movement analysis. Results: Our preliminary results consist of demonstrating the effectiveness of the AI-based pose estimation tool, YOLO-NAS-Pose, in accurately detecting participants’ poses. Conclusion: The proposed framework offers a promising approach to improving DMT practices by integrating and leveraging AI-based human pose estimation to evaluate participants’ movement in the DMT setting objectively. Future research will focus on refining the framework and developing user-friendly tools for widespread adoption in real DMT contexts. [show more]Project(s): Tuscany Health Ecosystem