2018
Other
Open Access
A Portable, Intelligent, Customizable Device for Human Breath Analysis
Germanese D
Breath analysis allows for monitoring the metabolic processes that occur in human body in a non-invasive way. Comparing with other traditional methods such as blood test, breath analysis is harmless to not only the subjects but also the personnel who collect the samples. However, despite its great potential, only few breath tests are commonly used in clinical practice nowadays. Breath analysis has not gained a wider use yet. One of the main reasons is related to standard instrumentation for gas analysis. Standard instrumentation, such as gas chromatography, is expensive and time consuming. Its use, as well as the interpretation of the results, often requires specialized personnel. E-nose systems, based on gas sensor array, are easier to use and able to analyze gases in real time, but, although cheaper than a gas chromatograph, their cost remains high. During my research activity, carried on at the Signals and Images Laboratory (SiLab) of the Institute of Information Science and Technology (ISTI) of the National Research Council (CNR), I design and developed the so called Wize Sniffer (WS), a device able to accurately analyze human breath composition and, at the same time, to overcome the limitations of existing instrumentation for gas analysis. The idea of the Wize Sniffer was born in the framework of SEMEiotic Oriented Technology for Individual's CardiOmetabolic risk self-assessmeNt and Self-monitoring (SE- MEOTICONS, www.semeoticons.eu) European Project, and it was designed for detecting, in human breath, those molecules related to the noxious habits for cardio-metabolic risk. The clinical assumption behind the Wize Sniffer lied in the fact that harmful habits such as alcohol consumption, smoking, unhealthy diet cause a variation in the concentration of a set of molecules (among which carbon monoxide, ethanol, hydrogen, hydrogen sulfide) in the exhaled breath. Therefore, the goal was to realize a portable and easy-to-use device, based on cheap electronics, to be used by anybody at their home. The main contributions of my work were the following: o design and development of a portable, low cost, customizable, easy to use device, able to be used in whichever context of use: I succeeded in this with using cheap commercial discrete gas sensors and an Arduino board, wrote the software and calibrated the system; o development of a method to analyze breath composition and understand individual's cardio-metabolic risk; I also validated it with success on real people. Given such good outcomes, I wanted the Wize Sniffer took a further step forward, towards the diagnosis in particular. The application field regarded the chronic liver impairment, as the studies which involve e-nose systems in the identification of liver disease are still few. In addition, the diagnosis of liver impairment often requires very invasive clinical test (biopsy, for instance). In this proof-of-concept study, the Wize Sniffer showed good diagnosis-oriented properties in discriminating the severity of liver disease (absence of disease, chronic liver disease, cirrhosis, hepatic encephalopathy) on the base of the detected ammonia.Project(s): SEMEOTICONS
Germanese D
Breath analysis allows for monitoring the metabolic processes that occur in human body in a non-invasive way. Comparing with other traditional methods such as blood test, breath analysis is harmless to not only the subjects but also the personnel who collect the samples. However, despite its great potential, only few breath tests are commonly used in clinical practice nowadays. Breath analysis has not gained a wider use yet. One of the main reasons is related to standard instrumentation for gas analysis. Standard instrumentation, such as gas chromatography, is expensive and time consuming. Its use, as well as the interpretation of the results, often requires specialized personnel. E-nose systems, based on gas sensor array, are easier to use and able to analyze gases in real time, but, although cheaper than a gas chromatograph, their cost remains high. During my research activity, carried on at the Signals and Images Laboratory (SiLab) of the Institute of Information Science and Technology (ISTI) of the National Research Council (CNR), I design and developed the so called Wize Sniffer (WS), a device able to accurately analyze human breath composition and, at the same time, to overcome the limitations of existing instrumentation for gas analysis. The idea of the Wize Sniffer was born in the framework of SEMEiotic Oriented Technology for Individual's CardiOmetabolic risk self-assessmeNt and Self-monitoring (SE- MEOTICONS, www.semeoticons.eu) European Project, and it was designed for detecting, in human breath, those molecules related to the noxious habits for cardio-metabolic risk. The clinical assumption behind the Wize Sniffer lied in the fact that harmful habits such as alcohol consumption, smoking, unhealthy diet cause a variation in the concentration of a set of molecules (among which carbon monoxide, ethanol, hydrogen, hydrogen sulfide) in the exhaled breath. Therefore, the goal was to realize a portable and easy-to-use device, based on cheap electronics, to be used by anybody at their home. The main contributions of my work were the following: o design and development of a portable, low cost, customizable, easy to use device, able to be used in whichever context of use: I succeeded in this with using cheap commercial discrete gas sensors and an Arduino board, wrote the software and calibrated the system; o development of a method to analyze breath composition and understand individual's cardio-metabolic risk; I also validated it with success on real people. Given such good outcomes, I wanted the Wize Sniffer took a further step forward, towards the diagnosis in particular. The application field regarded the chronic liver impairment, as the studies which involve e-nose systems in the identification of liver disease are still few. In addition, the diagnosis of liver impairment often requires very invasive clinical test (biopsy, for instance). In this proof-of-concept study, the Wize Sniffer showed good diagnosis-oriented properties in discriminating the severity of liver disease (absence of disease, chronic liver disease, cirrhosis, hepatic encephalopathy) on the base of the detected ammonia.Project(s): SEMEOTICONS
See at:
CNR IRIS 
| ISTI Repository | CNR IRIS 
2014
Other
Open Access
Wize Sniffer 1.0: development of a new portable device designed for selective olfaction
D'Acunto M, Germanese D
Digital semeiotics is one of the newest recent challenges for assessing a number of computational descriptors to atherosclerotic cardiovascular diseases that are leading causes of mortality worldwide. These descriptors can be expressed involving (i) morphometric, biometrics and colorimetric of the face; (ii) spectroscopic analysis of skin and iris, of sub-cutaneous substances and the function of subcutaneous tissues, and (iii) compositional analysis of breath and exhaled. In this paper, we describe the design and functionality of the Wize Sniffer (WS), a new portable device for breath analysis limited to an effective number of substances. Within the SEMEOTICON Project by the WS, we intend a hardware/software tool for both the analysis of volatile organic compounds of breath and a platform for data mining and data integration. The WS should be able to provide useful information about the "breathprint", i.e., the analog of fingerprint for the state of health of an individual.Project(s): SEMEOTICONS
D'Acunto M, Germanese D
Digital semeiotics is one of the newest recent challenges for assessing a number of computational descriptors to atherosclerotic cardiovascular diseases that are leading causes of mortality worldwide. These descriptors can be expressed involving (i) morphometric, biometrics and colorimetric of the face; (ii) spectroscopic analysis of skin and iris, of sub-cutaneous substances and the function of subcutaneous tissues, and (iii) compositional analysis of breath and exhaled. In this paper, we describe the design and functionality of the Wize Sniffer (WS), a new portable device for breath analysis limited to an effective number of substances. Within the SEMEOTICON Project by the WS, we intend a hardware/software tool for both the analysis of volatile organic compounds of breath and a platform for data mining and data integration. The WS should be able to provide useful information about the "breathprint", i.e., the analog of fingerprint for the state of health of an individual.Project(s): SEMEOTICONS
2019
Journal article
Open Access
Radiomics to support precision medicine in oncology
Colantonio S, Barucci A, Germanese D
Precision health, the future of patient care, is dependent on artificial intelligence. Of the information contained in a digital medical image, visual analysis can only extract about 10%. Radiomics aims to extract an enormous wealth of quantitative data from biomedical images, which could not be processed through simple visual analysis, but is capable of providing more information on the underlying pathophysiological phenomena and biological processes within human body. The subsequent mining of these quantitative data can offer very useful information on the aggressiveness of the disease under investigation, opening at the tailoring of the therapies based on a patient's needs and at the monitoring of the response to care. Therefore, by using specific mathematical algorithms and artificial intelligence techniques, radiomics provides very powerful support for precision medicine, especially in oncology.Source: ERCIM NEWS, pp. 15-16
Colantonio S, Barucci A, Germanese D
Precision health, the future of patient care, is dependent on artificial intelligence. Of the information contained in a digital medical image, visual analysis can only extract about 10%. Radiomics aims to extract an enormous wealth of quantitative data from biomedical images, which could not be processed through simple visual analysis, but is capable of providing more information on the underlying pathophysiological phenomena and biological processes within human body. The subsequent mining of these quantitative data can offer very useful information on the aggressiveness of the disease under investigation, opening at the tailoring of the therapies based on a patient's needs and at the monitoring of the response to care. Therefore, by using specific mathematical algorithms and artificial intelligence techniques, radiomics provides very powerful support for precision medicine, especially in oncology.Source: ERCIM NEWS, pp. 15-16
See at:
ercim-news.ercim.eu | CNR IRIS | ISTI Repository | CNR IRIS
2023
Journal article
Open Access
Computer vision tasks for ambient intelligence in children's health
Germanese D, Colantonio S, Del Coco M, Carcagni P, Leo M
Computer vision is a powerful tool for healthcare applications since it can provide objective diagnosis and assessment of pathologies, not depending on clinicians’ skills and experiences. It can also help speed-up population screening, reducing health care costs and improving the quality of service. Several works summarise applications and systems in medical imaging, whereas less work is devoted to surveying approaches for healthcare goals using ambient intelligence, i.e., observing individuals in natural settings. Even more, there is a lack of papers providing a survey of works exhaustively covering computer vision applications for children’s health, which is a particularly challenging research area considering that most existing computer vision technologies have been trained and tested only on adults. The aim of this paper is then to survey, for the first time in the literature, the papers covering children’s health-related issues by ambient intelligence methods and systems relying on computer vision.Source: INFORMATION, vol. 14 (issue 10)
Germanese D, Colantonio S, Del Coco M, Carcagni P, Leo M
Computer vision is a powerful tool for healthcare applications since it can provide objective diagnosis and assessment of pathologies, not depending on clinicians’ skills and experiences. It can also help speed-up population screening, reducing health care costs and improving the quality of service. Several works summarise applications and systems in medical imaging, whereas less work is devoted to surveying approaches for healthcare goals using ambient intelligence, i.e., observing individuals in natural settings. Even more, there is a lack of papers providing a survey of works exhaustively covering computer vision applications for children’s health, which is a particularly challenging research area considering that most existing computer vision technologies have been trained and tested only on adults. The aim of this paper is then to survey, for the first time in the literature, the papers covering children’s health-related issues by ambient intelligence methods and systems relying on computer vision.Source: INFORMATION, vol. 14 (issue 10)
See at:
CNR IRIS | www.mdpi.com | CNR IRIS
2024
Other
Embargo
Monitoraggio della termoregolazione neonatale in contesto ospedaliero: verso un approccio integrato e non invasivo
Cancello Tortora C., Del Corso G., Germanese D., Positano V., Vozzi G.
La termoregolazione, ovvero la capacità di mantenere una temperatura adeguata, è una questione di notevole interesse e complessità nella comunità scientifica nell'ambito della neonatologia. Nei primi istanti di vita i neonati, sia pre-termine che a termine, presentano sistemi di regolazione della temperatura immaturi che li rendono vulnerabili alle condizioni subottimali extra-uterine. Questa tesi, svolta presso il Laboratorio Segnali e Immagini dell'Istituto di Scienze e Tecnologie dell'Informazione del CNR di Pisa, propone di monitorare, in contesto ospedaliero, mediante un sistema integrato e non invasivo, le variazioni di temperatura del neonato nelle prime ore di vita. L’obiettivo è quello di preparare il terreno per uno studio più ampio che, attraverso l’acquisizione e la valutazione di pattern termici sul neonato, sarà in grado di valutare lo stato patologico del neonato. Inoltre, verrà valutato se la stabilizzazione termica possa essere migliorata con l’attuazione di una pratica, nota come contatto pelle a pelle (SSC), tra madre e neonato, o eventualmente tra padre e neonato. L’ hardware del dispositivo è stato realizzato dal Centro di Formazione e Simulazione Neonatale (centro NINA) dell'Azienda Ospedaliero Universitaria Pisana. L'idea di monitorare i pattern termici di un neonato in maniera non invasiva si è tradotta in un dispositivo estremamente compatto e portatile, costituito da: (i) una termocamera, mediante la quale acquisire le immagini termiche del neonato, (ii) una telecamera rgb per acquisire le immagini del neonato nello spettro del visibile, estrarre lo scheletro per definire automaticamente i distretti anatomici di interesse, (iii) un sensore per la misurazione puntuale della temperatura, (iv) un sensore di umidità e temperatura ambientale per monitorare le condizioni ambientali della stanza in cui si trova il neonato, (v) un Raspeberry Pi per la gestione e l'integrazione di questi componenti nonchè l'estrazione e la pre-elaborazione dei dati. Il Software di controllo ed elaborazione sviluppato in questa tesi è stato scritto in linguaggio Python (v. 3.11) e gestisce gli stati del sistema, in particolare l’acquisizione sincrona di immagini termiche ed RGB, l’estrazione di dati e l’anonimizzazione delle immagini RGB dei neonati. L’elaborazione delle immagini RGB viene effettuata in locale dal Raspberry e comprende l’estrazione automatica delle regioni anatomiche di interesse (ROI) mediante tecniche allo stato dell’arte (i.e., libreria MediaPipe). Successivamente, queste ROI vengono trasposte sulle corrispondenti immagini termiche tramite una matrice di trasformazione omografica opportunamente calibrata tenendo in considerazione il vincolo rigido tra le due camere e le rispettive distanze focali. Queste ROI prendono come riferimento per il punto centrale il landmark estratto e come raggio le proporzioni tra due landmarks vicini e le dimensioni stimate del distretto anatomico di interesse. Esse rappresentano il punto di partenza dell’elaborazione delle immagini termiche. Dopo una fase iniziale di pre-processing, in cui il rumore di fondo è stato eliminato con varie tecniche di filtraggio, il contrasto tra le varie regioni è stato aumentato. Questo processo è stato propedeutico all’estrazione degli istogrammi, il cui andamento fornisce informazioni sulla presenza o meno di sfondo. Se lo sfondo è presente, viene avviato il segmentatore FastSAM, basato su una rete neurale convolutiva (CNN) allo stato dell'arte, che segmenta il distretto anatomico per evitare di includere lo sfondo nell’elaborazione. Un’interfaccia utente user-friendly ha permesso di gestire i landmarks provenienti dallo scheletro e di realizzare in maniera completamente automatica delle regioni di interesse (ROI) adattive sull’immagine termica. Dalla singola ROI sono state estratte dei pattern termici e delle features che estendessero quelle tradizionali come mediana e intervallo interquartile attraverso l’implementazione di una matrice di texture che deriva da descrittori matematici quantitativi di texture (della famiglia GLSZM- Gray level size zone matrix) che forniscono informazioni sull’eterogeneità termica delle ROI. La matrice è stata utile per estrarre un punteggio (score) da attribuire alla singola ROI evidenziando come un paziente con vaste aree di temperatura accettabile avesse un punteggio maggiore rispetto ad un paziente con zone molte fredde ed un’alta variabilità nella temperatura. Infine, sono state definite anche delle features a livello globale che mettono in relazione le misure ottenute dalla ROI sul viso (riferimento clinico neonatale) con quelle sul torace e sugli arti. Il sistema è stato validato prima in un contesto sperimentale controllato, la validazione finale e la conseguente acquisizione di dati sono avvenute in ambito ospedaliero, nel reparto di neonatologia dell'Azienda Ospedaliera Universitaria Pisana, utilizzando un fantoccio che simulava il comportamento termico di un neonato.
Cancello Tortora C., Del Corso G., Germanese D., Positano V., Vozzi G.
La termoregolazione, ovvero la capacità di mantenere una temperatura adeguata, è una questione di notevole interesse e complessità nella comunità scientifica nell'ambito della neonatologia. Nei primi istanti di vita i neonati, sia pre-termine che a termine, presentano sistemi di regolazione della temperatura immaturi che li rendono vulnerabili alle condizioni subottimali extra-uterine. Questa tesi, svolta presso il Laboratorio Segnali e Immagini dell'Istituto di Scienze e Tecnologie dell'Informazione del CNR di Pisa, propone di monitorare, in contesto ospedaliero, mediante un sistema integrato e non invasivo, le variazioni di temperatura del neonato nelle prime ore di vita. L’obiettivo è quello di preparare il terreno per uno studio più ampio che, attraverso l’acquisizione e la valutazione di pattern termici sul neonato, sarà in grado di valutare lo stato patologico del neonato. Inoltre, verrà valutato se la stabilizzazione termica possa essere migliorata con l’attuazione di una pratica, nota come contatto pelle a pelle (SSC), tra madre e neonato, o eventualmente tra padre e neonato. L’ hardware del dispositivo è stato realizzato dal Centro di Formazione e Simulazione Neonatale (centro NINA) dell'Azienda Ospedaliero Universitaria Pisana. L'idea di monitorare i pattern termici di un neonato in maniera non invasiva si è tradotta in un dispositivo estremamente compatto e portatile, costituito da: (i) una termocamera, mediante la quale acquisire le immagini termiche del neonato, (ii) una telecamera rgb per acquisire le immagini del neonato nello spettro del visibile, estrarre lo scheletro per definire automaticamente i distretti anatomici di interesse, (iii) un sensore per la misurazione puntuale della temperatura, (iv) un sensore di umidità e temperatura ambientale per monitorare le condizioni ambientali della stanza in cui si trova il neonato, (v) un Raspeberry Pi per la gestione e l'integrazione di questi componenti nonchè l'estrazione e la pre-elaborazione dei dati. Il Software di controllo ed elaborazione sviluppato in questa tesi è stato scritto in linguaggio Python (v. 3.11) e gestisce gli stati del sistema, in particolare l’acquisizione sincrona di immagini termiche ed RGB, l’estrazione di dati e l’anonimizzazione delle immagini RGB dei neonati. L’elaborazione delle immagini RGB viene effettuata in locale dal Raspberry e comprende l’estrazione automatica delle regioni anatomiche di interesse (ROI) mediante tecniche allo stato dell’arte (i.e., libreria MediaPipe). Successivamente, queste ROI vengono trasposte sulle corrispondenti immagini termiche tramite una matrice di trasformazione omografica opportunamente calibrata tenendo in considerazione il vincolo rigido tra le due camere e le rispettive distanze focali. Queste ROI prendono come riferimento per il punto centrale il landmark estratto e come raggio le proporzioni tra due landmarks vicini e le dimensioni stimate del distretto anatomico di interesse. Esse rappresentano il punto di partenza dell’elaborazione delle immagini termiche. Dopo una fase iniziale di pre-processing, in cui il rumore di fondo è stato eliminato con varie tecniche di filtraggio, il contrasto tra le varie regioni è stato aumentato. Questo processo è stato propedeutico all’estrazione degli istogrammi, il cui andamento fornisce informazioni sulla presenza o meno di sfondo. Se lo sfondo è presente, viene avviato il segmentatore FastSAM, basato su una rete neurale convolutiva (CNN) allo stato dell'arte, che segmenta il distretto anatomico per evitare di includere lo sfondo nell’elaborazione. Un’interfaccia utente user-friendly ha permesso di gestire i landmarks provenienti dallo scheletro e di realizzare in maniera completamente automatica delle regioni di interesse (ROI) adattive sull’immagine termica. Dalla singola ROI sono state estratte dei pattern termici e delle features che estendessero quelle tradizionali come mediana e intervallo interquartile attraverso l’implementazione di una matrice di texture che deriva da descrittori matematici quantitativi di texture (della famiglia GLSZM- Gray level size zone matrix) che forniscono informazioni sull’eterogeneità termica delle ROI. La matrice è stata utile per estrarre un punteggio (score) da attribuire alla singola ROI evidenziando come un paziente con vaste aree di temperatura accettabile avesse un punteggio maggiore rispetto ad un paziente con zone molte fredde ed un’alta variabilità nella temperatura. Infine, sono state definite anche delle features a livello globale che mettono in relazione le misure ottenute dalla ROI sul viso (riferimento clinico neonatale) con quelle sul torace e sugli arti. Il sistema è stato validato prima in un contesto sperimentale controllato, la validazione finale e la conseguente acquisizione di dati sono avvenute in ambito ospedaliero, nel reparto di neonatologia dell'Azienda Ospedaliera Universitaria Pisana, utilizzando un fantoccio che simulava il comportamento termico di un neonato.
2016
Conference article
Open Access
Design of a breath analysis device for self-monitoring and remote health-care
Germanese D, D'Acunto M, Salvetti O
Technique as new as promising, breath analysis enables the monitoring of biochemical processes in human body in a non-invasive way. This is why it is drawing, more and more, the attention of scientific community: many studies have been addressed in order to find a correlation between breath volatile organic compounds (VOCs) and several diseases. Despite its potential, breath analysis is still far from being used in clinical practice. These are some of the principal reasons: (i)high costs for the standard analytical instrumentation; (ii)need of specialized personnel for the interpretation of the results; (iii)lack of standardized procedures to collect breath samples. Our aim is to develop a device, which we call Wize Sniffer (WS), based on commercial gas sensors, which is: (i)able to analyse breath gases in real time; (ii)portable; (iii)low-cost; (iv)easy-to-use also for non-specialized personnel. Another aim is to foster homecare, that means promote the purchase and the use, also in home environment, of such device. The Wize Sniffer is composed of three modules: signal measurement, signal conditioning and signal processing. To satisfy the goal of developing a device by using low-cost technology, its core is composed of an array of commercial, low cost, semiconductor-based gas sensors, and a widely employed open source controller: an Arduino board. To promote the use of such device also in home environment, and foster its daily use, it is programmed in order to send breath test results also to a remote pc: the pc of user's physician, for example. In addition, the design of the Wize Sniffer is based on a modular configuration, thus enabling to change the type of the gas sensors according to the breath molecules to be detected. In this case, we focus our attention to the prevention of cardio-metabolic risk, for which the healthcare systems are registering an exponential growth of social costs, by monitoring those dangerous habits for cardio-metabolic risk itself.
Germanese D, D'Acunto M, Salvetti O
Technique as new as promising, breath analysis enables the monitoring of biochemical processes in human body in a non-invasive way. This is why it is drawing, more and more, the attention of scientific community: many studies have been addressed in order to find a correlation between breath volatile organic compounds (VOCs) and several diseases. Despite its potential, breath analysis is still far from being used in clinical practice. These are some of the principal reasons: (i)high costs for the standard analytical instrumentation; (ii)need of specialized personnel for the interpretation of the results; (iii)lack of standardized procedures to collect breath samples. Our aim is to develop a device, which we call Wize Sniffer (WS), based on commercial gas sensors, which is: (i)able to analyse breath gases in real time; (ii)portable; (iii)low-cost; (iv)easy-to-use also for non-specialized personnel. Another aim is to foster homecare, that means promote the purchase and the use, also in home environment, of such device. The Wize Sniffer is composed of three modules: signal measurement, signal conditioning and signal processing. To satisfy the goal of developing a device by using low-cost technology, its core is composed of an array of commercial, low cost, semiconductor-based gas sensors, and a widely employed open source controller: an Arduino board. To promote the use of such device also in home environment, and foster its daily use, it is programmed in order to send breath test results also to a remote pc: the pc of user's physician, for example. In addition, the design of the Wize Sniffer is based on a modular configuration, thus enabling to change the type of the gas sensors according to the breath molecules to be detected. In this case, we focus our attention to the prevention of cardio-metabolic risk, for which the healthcare systems are registering an exponential growth of social costs, by monitoring those dangerous habits for cardio-metabolic risk itself.
See at:
CNR IRIS | ISTI Repository | CNR IRIS | CNR IRIS
2016
Other
Restricted
SEMEOTICONS - Software Integration and Wize Mirror user manual
Martinelli M, Germanese D, Pascali M A, Mazzarisi A, Henriquez P, Vitali I
This deliverable reports the results of software integration of the WM prototype and includes the User Manual for the final prototype of the Wize Mirror (WM) as finalized during the last software integration phase that has set up the complete system (see D8.5.1).Project(s): SEMEOTICONS
Martinelli M, Germanese D, Pascali M A, Mazzarisi A, Henriquez P, Vitali I
This deliverable reports the results of software integration of the WM prototype and includes the User Manual for the final prototype of the Wize Mirror (WM) as finalized during the last software integration phase that has set up the complete system (see D8.5.1).Project(s): SEMEOTICONS
2015
Other
Restricted
SEMEOTICONS - Final specification of system requirements and functionalities
Colantonio S, Germanese D, Martinelli M, Righi M, Coppini G, Chiarugi F, Pediaditis M, Stromberg T, Bjorgan A, Henriquez P, Matuszewski B J, Nicoletta A, Vitali I, Miliarakis A, Assimakopoulou C
This deliverable summarizes the final set of system requirements and functional specifications of the Wize Mirror and its components. It merges together and add new updates to D2.1.1 "Initial specification of system requirements and functionalities" and D2.1.2 "Revised specification of system requirements and functionalities".Project(s): SEMEOTICONS
Colantonio S, Germanese D, Martinelli M, Righi M, Coppini G, Chiarugi F, Pediaditis M, Stromberg T, Bjorgan A, Henriquez P, Matuszewski B J, Nicoletta A, Vitali I, Miliarakis A, Assimakopoulou C
This deliverable summarizes the final set of system requirements and functional specifications of the Wize Mirror and its components. It merges together and add new updates to D2.1.1 "Initial specification of system requirements and functionalities" and D2.1.2 "Revised specification of system requirements and functionalities".Project(s): SEMEOTICONS
2015
Other
Restricted
SEMEOTICONS - Revised specification of system requirements and functionalities
Colantonio S, Germanese D, Righi M, Martinelli M, Coppini G, Morales M, Chiarugi F, Pediaditis M, Stromberg T, Randeberg L, Vitali I
This deliverable reports on requirements and specifications for the Wize Mirror prototype from the research, scientific and technological innovation perspective.In this document, we report the amendments and/or corrections to: - medical requirements, also in accordance with the final release of the face semeiotic model of cardio-metabolic risk as reported in deliverable D1.1.2 "Final Semeiotic Model of Cardio-Metabolic Risk"; - methodological requirements, by refining the guidelines for the development of the core research methods; - technological requirements, by further specifying the needs for hardware and software resources.Project(s): SEMEOTICONS
Colantonio S, Germanese D, Righi M, Martinelli M, Coppini G, Morales M, Chiarugi F, Pediaditis M, Stromberg T, Randeberg L, Vitali I
This deliverable reports on requirements and specifications for the Wize Mirror prototype from the research, scientific and technological innovation perspective.In this document, we report the amendments and/or corrections to: - medical requirements, also in accordance with the final release of the face semeiotic model of cardio-metabolic risk as reported in deliverable D1.1.2 "Final Semeiotic Model of Cardio-Metabolic Risk"; - methodological requirements, by refining the guidelines for the development of the core research methods; - technological requirements, by further specifying the needs for hardware and software resources.Project(s): SEMEOTICONS
2015
Other
Restricted
SEMEOTICONS - Data analysis and fusion strategies
Colantonio S, Giorgi D, Germanese D, Pascali M A, Coppini G, Favilla R
The present document is the first deliverable of Task 6.2 - Wellness index definition and correlation to cardio-metabolic risk. The objective of Task 6.2 is to define a data fusion strategy for the semantic integration of the data collected by the Wize Mirror, and the delivery of a Wellness Index. The document reports the activity undertaken in-between month 6 and month 16, with the approximated workload of 15 person months. It introduces methods for data processing and fusion, according to the medical semeiotic model defined in WP1, and sets the basis for the definition and evaluation of the Wellness Index.Project(s): SEMEOTICONS
Colantonio S, Giorgi D, Germanese D, Pascali M A, Coppini G, Favilla R
The present document is the first deliverable of Task 6.2 - Wellness index definition and correlation to cardio-metabolic risk. The objective of Task 6.2 is to define a data fusion strategy for the semantic integration of the data collected by the Wize Mirror, and the delivery of a Wellness Index. The document reports the activity undertaken in-between month 6 and month 16, with the approximated workload of 15 person months. It introduces methods for data processing and fusion, according to the medical semeiotic model defined in WP1, and sets the basis for the definition and evaluation of the Wellness Index.Project(s): SEMEOTICONS
2018
Other
Open Access
MOSCARDO - Metodi per il riconoscimento di immagini e ricostruzione 3D
Moroni D, Germanese D, Leone Gr Pascali Ma, Tampucci M
L'attività 3.3 prevede lo studio e l'applicazione di metodi di image processing e computer vision per: -l'analisi di crepe, ammaloramenti e spostamenti relativi che possano danneggiare l'integrità strutturale degli edifici presi in esame; -la ricostruzione 3D degli scenari di interesse; Per quanto riguarda l'analisi e il monitoraggio degli artefatti strutturali, sono stati studiati i diversi metodi, invasivi e non invasivi (o contact-less), presenti in letteratura, al fine di sostituire quello più classico ma anche più laborioso e soggetto ad errori: l'ispezione visiva. In seguito sono descritti nel dettaglio gli approcci studiati, da quelli più invasivi, che sfruttano ad esempio sensori e/o sonde applicati alla superficie di interesse, a quelli meno invasivi, basati su target riflettenti, fino a quelli contact-less, basati sul solo processamento di immagini acquisite mediante termocamere o camere che lavorano nello spettro del visibile. Per quanto riguarda gli aspetti di ricostruzione 3D, sono state studiate tecniche di fotogrammetria per la ricostruzione tridimensionale delle strutture da monitorare. In particolare, sono stati analizzati vari software e algoritmi di fotogrammetria disponibili sia open source sia commerciali. Fra i vari prodotti analizzati è stato scelto, vista la qualità del risultato prodotto di orientarci verso l'adozione del software Photoscan di Agisoft. Il software, prese in ingresso una serie di immagini, determina l'angolo di acquisizione di ogni immagine. Esso calcola dapprima una nuvola sparsa e, successivamente, una nuvola densa. È possibile intervenire manualmente sui punti delle nuvole per apportare qualche correzione. In seguito, viene creata la mesh tridimensionale a partire dalla nuvola densa e, a partire dalle immagini originali, viene e generata una opportuna texture che va a coprire la mesh 3D. Il deliverable è così strutturato: nella Sezione 3 sono illustrati gli scenari di interesse (il Voltone e la Fortezza Vecchia a Livorno) e i punti critici da monitorare; nella Sezione 4 è descritto il set-up di acquisizione delle immagini; la Sezione 5 è quella dedicata allo studio dei metodi di analisi e monitoraggio di fessure e crepe; nella Sezione 6 saranno invece esplorati i metodi di ricostruzione 3D.
Moroni D, Germanese D, Leone Gr Pascali Ma, Tampucci M
L'attività 3.3 prevede lo studio e l'applicazione di metodi di image processing e computer vision per: -l'analisi di crepe, ammaloramenti e spostamenti relativi che possano danneggiare l'integrità strutturale degli edifici presi in esame; -la ricostruzione 3D degli scenari di interesse; Per quanto riguarda l'analisi e il monitoraggio degli artefatti strutturali, sono stati studiati i diversi metodi, invasivi e non invasivi (o contact-less), presenti in letteratura, al fine di sostituire quello più classico ma anche più laborioso e soggetto ad errori: l'ispezione visiva. In seguito sono descritti nel dettaglio gli approcci studiati, da quelli più invasivi, che sfruttano ad esempio sensori e/o sonde applicati alla superficie di interesse, a quelli meno invasivi, basati su target riflettenti, fino a quelli contact-less, basati sul solo processamento di immagini acquisite mediante termocamere o camere che lavorano nello spettro del visibile. Per quanto riguarda gli aspetti di ricostruzione 3D, sono state studiate tecniche di fotogrammetria per la ricostruzione tridimensionale delle strutture da monitorare. In particolare, sono stati analizzati vari software e algoritmi di fotogrammetria disponibili sia open source sia commerciali. Fra i vari prodotti analizzati è stato scelto, vista la qualità del risultato prodotto di orientarci verso l'adozione del software Photoscan di Agisoft. Il software, prese in ingresso una serie di immagini, determina l'angolo di acquisizione di ogni immagine. Esso calcola dapprima una nuvola sparsa e, successivamente, una nuvola densa. È possibile intervenire manualmente sui punti delle nuvole per apportare qualche correzione. In seguito, viene creata la mesh tridimensionale a partire dalla nuvola densa e, a partire dalle immagini originali, viene e generata una opportuna texture che va a coprire la mesh 3D. Il deliverable è così strutturato: nella Sezione 3 sono illustrati gli scenari di interesse (il Voltone e la Fortezza Vecchia a Livorno) e i punti critici da monitorare; nella Sezione 4 è descritto il set-up di acquisizione delle immagini; la Sezione 5 è quella dedicata allo studio dei metodi di analisi e monitoraggio di fessure e crepe; nella Sezione 6 saranno invece esplorati i metodi di ricostruzione 3D.
See at:
CNR IRIS | ISTI Repository | CNR IRIS
2019
Journal article
Open Access
An E-Nose for the Monitoring of Severe Liver Impairment: A Preliminary Study
Germanese D, Colantonio S, D'Acunto M, Romagnoli V, Salvati A, Brunetto M
Biologically inspired to mammalian olfactory system, electronic noses became popular during the last three decades. In literature, as well as in daily practice, a wide range of applications are reported. Nevertheless, the most pioneering one has been (and still is) the assessment of the human breath composition. In this study, we used a prototype of electronic nose, called Wize Sniffer (WS) and based it on an array of semiconductor gas sensor, to detect ammonia in the breath of patients suffering from severe liver impairment. In the setting of severely impaired liver, toxic substances, such as ammonia, accumulate in the systemic circulation and in the brain. This may result in Hepatic Encephalopathy (HE), a spectrum of neuro-psychiatric abnormalities which include changes in cognitive functions, consciousness, and behaviour. HE can be detected only by specific but time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. In the presented proof-of-concept study, we aimed at investigating the possibility of discriminating the severity degree of liver impairment on the basis of the detected breath ammonia, in view of the detection of HE at its early stage.Source: SENSORS (BASEL), vol. 19 (issue 17)
Germanese D, Colantonio S, D'Acunto M, Romagnoli V, Salvati A, Brunetto M
Biologically inspired to mammalian olfactory system, electronic noses became popular during the last three decades. In literature, as well as in daily practice, a wide range of applications are reported. Nevertheless, the most pioneering one has been (and still is) the assessment of the human breath composition. In this study, we used a prototype of electronic nose, called Wize Sniffer (WS) and based it on an array of semiconductor gas sensor, to detect ammonia in the breath of patients suffering from severe liver impairment. In the setting of severely impaired liver, toxic substances, such as ammonia, accumulate in the systemic circulation and in the brain. This may result in Hepatic Encephalopathy (HE), a spectrum of neuro-psychiatric abnormalities which include changes in cognitive functions, consciousness, and behaviour. HE can be detected only by specific but time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. In the presented proof-of-concept study, we aimed at investigating the possibility of discriminating the severity degree of liver impairment on the basis of the detected breath ammonia, in view of the detection of HE at its early stage.Source: SENSORS (BASEL), vol. 19 (issue 17)
See at:
CNR IRIS | ISTI Repository | www.mdpi.com | CNR IRIS
2019
Conference article
Restricted
Radiomics to predict prostate cancer aggressiveness: a preliminary study
Germanese D, Mercatelli L, Colantonio S, Miele V, Pascali Ma, Caudai C, Zoppetti N, Carpi R, Barucci A, Bertelli E, Agostini S
Radiomics is encouraging a paradigm shift in oncological diagnostics towards the symbiosis of radiology and Artificial Intelligence (AI) techniques. The aim is to exploit very accurate, robust image processing algorithms and provide quantitative information about the phenotypic differences of cancer traits. By exploring the association between this quantitative information and patients' prognosis, AI algorithms are boosting the power of radiomics in the perspective of precision oncology. However, the choice of the most suitable AI method can determine the success of a radiomic application. The current state-of-the art methods in radiomics aim at extracting statistical features from biomedical images and, then, process them with Machine Learning (ML) techniques. Many works have been reported in the literature presenting various combinations of radiomic features and ML methods. In this preliminary study, we aim to analyse the performance of a radiomic approach to predict prostate cancer (PCa) aggressiveness from multiarametric Magnetic Resonance Imaging (mp-MRI). Clinical mp-MRI data were collected from patients with histology-confirmed PCa and labelled by a team of expert radiologists. Such data were used to extract and select two sets of radiomic features; hence, the classification performances of five classifiers were assessed. This analysis is meant as a preliminary step towards the overall goal of investigating the potential of radiomic-based analyses.
Germanese D, Mercatelli L, Colantonio S, Miele V, Pascali Ma, Caudai C, Zoppetti N, Carpi R, Barucci A, Bertelli E, Agostini S
Radiomics is encouraging a paradigm shift in oncological diagnostics towards the symbiosis of radiology and Artificial Intelligence (AI) techniques. The aim is to exploit very accurate, robust image processing algorithms and provide quantitative information about the phenotypic differences of cancer traits. By exploring the association between this quantitative information and patients' prognosis, AI algorithms are boosting the power of radiomics in the perspective of precision oncology. However, the choice of the most suitable AI method can determine the success of a radiomic application. The current state-of-the art methods in radiomics aim at extracting statistical features from biomedical images and, then, process them with Machine Learning (ML) techniques. Many works have been reported in the literature presenting various combinations of radiomic features and ML methods. In this preliminary study, we aim to analyse the performance of a radiomic approach to predict prostate cancer (PCa) aggressiveness from multiarametric Magnetic Resonance Imaging (mp-MRI). Clinical mp-MRI data were collected from patients with histology-confirmed PCa and labelled by a team of expert radiologists. Such data were used to extract and select two sets of radiomic features; hence, the classification performances of five classifiers were assessed. This analysis is meant as a preliminary step towards the overall goal of investigating the potential of radiomic-based analyses.
See at:
CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2019
Conference article
Open Access
May radiomic data predict prostate cancer aggressiveness?
Germanese D, Colantonio S, Caudai C, Pascali Ma, Barucci A, Zoppetti N, Agostini S, Bertelli E, Mercatelli L, Miele V, Carpi R
Radiomics can quantify tumor phenotypic characteristics non-invasively by defining a signature correlated with biological information. Thanks to algorithms derived from computer vision to extract features from images, and machine learning methods to mine data, Radiomics is the perfect case study of application of Artificial Intelligence in the context of precision medicine. In this study we investigated the association between radiomic features extracted from multi-parametric magnetic resonance imaging (mp-MRI)of prostate cancer (PCa) and the tumor histologic subtypes (using Gleason Score) using machine learning algorithms, in order to identify which of the mp-MRI derived radiomic features can distinguish high and low risk PCa.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 65-75. Salerno, Italy, 6 September, 2019
Germanese D, Colantonio S, Caudai C, Pascali Ma, Barucci A, Zoppetti N, Agostini S, Bertelli E, Mercatelli L, Miele V, Carpi R
Radiomics can quantify tumor phenotypic characteristics non-invasively by defining a signature correlated with biological information. Thanks to algorithms derived from computer vision to extract features from images, and machine learning methods to mine data, Radiomics is the perfect case study of application of Artificial Intelligence in the context of precision medicine. In this study we investigated the association between radiomic features extracted from multi-parametric magnetic resonance imaging (mp-MRI)of prostate cancer (PCa) and the tumor histologic subtypes (using Gleason Score) using machine learning algorithms, in order to identify which of the mp-MRI derived radiomic features can distinguish high and low risk PCa.Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 65-75. Salerno, Italy, 6 September, 2019
See at:
CNR IRIS | link.springer.com | ISTI Repository | CNR IRIS | CNR IRIS
2019
Conference article
Open Access
Towards chronic liver dysfunction self-monitoring: a proof-of-concept study
Germanese D, Colantonio S, D'Acunto M, Brunetto M, Romagnoli V, Salvati A
The liver is our very own chemical processing plant as it plays a vital role in maintaining the body's metabolic balance. Liver's health is assessed by a group of clinical tests (such as blood tests, ultrasonographic imaging, liver biopsy) most of which are invasive and burdensome for the patients. In the setting of severely scarred liver, toxic substances, such as ammonia, have fewer opportunities to be detoxified. Accumulation of ammonia in the systemic circulation and in the brain may result in Hepatic Encephalopathy (HE), a spectrum of neuropsychiatric abnormalities which entails changes in consciousness, intellectual functions, behavior. Minimal HE has attracted increasing attention, as it does not cause detectable changes in personality or behaviour, but the complex and sustained attention is impaired. Hence, it can be detected only by specific but biased, time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. The obstrusivity of the majority of the liver function clinical tests, and, in case of minimal HE, the lack of reliable examinations, are encouraging the scientific community to look for alternative diagnostic methods. For this purpose, the exploitation of a non-invasive technique such as breath analysis, to identify chronic liver disease, discriminate among its degree of severity and detect the onset of HE, could be a step forward for clinical diagnosis. In this paper, we report a proof-of-concept study that aimed at detecting ammonia in the breath of patients suffering from chronic liver disease by means of a low-cost, easy-to-use, gas-sensors based device. Not only, we also aimed at investigating the possibility of discriminating the several severity degree of liver impairment on the basis of the detected ammonia.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, vol. 2019-June. Barcelona, Spain, 29 June - 3 July, 2019
Germanese D, Colantonio S, D'Acunto M, Brunetto M, Romagnoli V, Salvati A
The liver is our very own chemical processing plant as it plays a vital role in maintaining the body's metabolic balance. Liver's health is assessed by a group of clinical tests (such as blood tests, ultrasonographic imaging, liver biopsy) most of which are invasive and burdensome for the patients. In the setting of severely scarred liver, toxic substances, such as ammonia, have fewer opportunities to be detoxified. Accumulation of ammonia in the systemic circulation and in the brain may result in Hepatic Encephalopathy (HE), a spectrum of neuropsychiatric abnormalities which entails changes in consciousness, intellectual functions, behavior. Minimal HE has attracted increasing attention, as it does not cause detectable changes in personality or behaviour, but the complex and sustained attention is impaired. Hence, it can be detected only by specific but biased, time-consuming and burdensome examinations, such as blood ammonia levels assessment and neuro-psychological tests. The obstrusivity of the majority of the liver function clinical tests, and, in case of minimal HE, the lack of reliable examinations, are encouraging the scientific community to look for alternative diagnostic methods. For this purpose, the exploitation of a non-invasive technique such as breath analysis, to identify chronic liver disease, discriminate among its degree of severity and detect the onset of HE, could be a step forward for clinical diagnosis. In this paper, we report a proof-of-concept study that aimed at detecting ammonia in the breath of patients suffering from chronic liver disease by means of a low-cost, easy-to-use, gas-sensors based device. Not only, we also aimed at investigating the possibility of discriminating the several severity degree of liver impairment on the basis of the detected ammonia.Source: PROCEEDINGS - IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, vol. 2019-June. Barcelona, Spain, 29 June - 3 July, 2019
See at:
CNR IRIS | ieeexplore.ieee.org | ISTI Repository | CNR IRIS | CNR IRIS
2020
Other
Open Access
Analisi di immagini tomografiche ad alta risoluzione attraverso reti neurali convoluzionali per lo studio delle interstiziopatie polmonari
Buongiorno R, Colantonio S, Germanese D
Le interstiziopatie polmonari (Interstitial Lung Disease, ILD) sono patologie croniche che causano la cicatrizzazione del parenchima polmonare e dell'interstizio alveolare e la compromissione della funzionalità respiratoria. Dal momento che sono più di 200 le patologie raggruppate nella categoria delle ILD, una precisa identificazione è fondamentale per individuare la terapia migliore e formulare una prognosi. L'esame radiologico di riferimento è la tomografia computerizzata del torace ad alta risoluzione (High Resolution Computed Tomography, HRCT) e rappresenta un passaggio cruciale nel processo di diagnosi; nell'analizzare le immagini, infatti, il radiologo deve stabilire se vi è Usual Interstitial Pneumoniae (UIP), ovvero presenza di pattern istopatologici tipici della malattia, e valutarne l'estensione, correlata con la gravità delle alterazioni fisiologiche. Tuttavia, l'incidenza rara delle interstiziopatie fa sì che non tutti i radiologi abbiano un grado di esperienza adatto a individuare visivamente l'anomalia. Inoltre, la malattia si diffonde lungo tutti i polmoni e la segmentazione manuale risulta faticosa. Nel tentativo di rimediare alla variabilità intra- ed inter-osservatore, sono state sviluppate tecniche per il riconoscimento automatico dei pattern UIP; vi sono approcci basati sull'analisi dell'istogramma e della texture dell'immagine ma, dal momento che i classificatori sono stati addestrati su label definite da operatori clinici diversi, presentano comunque un bias che è causa di identificazioni errate, o mancate, dei pattern. Il deep learning, invece, si distingue dalle tecniche tradizionali perché fornisce strumenti che imparano autonomamente a classificare i dati. L'obiettivo del lavoro è stato, quindi, progettare e sviluppare la UIP-net, una rete neurale convoluzionale ad-hoc per la segmentazione automatica dei pattern UIP in immagini HRCT di pazienti con Fibrosi Idiopatica Polmonare (IPF), che è una sotto-categoria delle ILD.DOI: 10.32079/isti-tr-2020/007
Metrics:
Buongiorno R, Colantonio S, Germanese D
Le interstiziopatie polmonari (Interstitial Lung Disease, ILD) sono patologie croniche che causano la cicatrizzazione del parenchima polmonare e dell'interstizio alveolare e la compromissione della funzionalità respiratoria. Dal momento che sono più di 200 le patologie raggruppate nella categoria delle ILD, una precisa identificazione è fondamentale per individuare la terapia migliore e formulare una prognosi. L'esame radiologico di riferimento è la tomografia computerizzata del torace ad alta risoluzione (High Resolution Computed Tomography, HRCT) e rappresenta un passaggio cruciale nel processo di diagnosi; nell'analizzare le immagini, infatti, il radiologo deve stabilire se vi è Usual Interstitial Pneumoniae (UIP), ovvero presenza di pattern istopatologici tipici della malattia, e valutarne l'estensione, correlata con la gravità delle alterazioni fisiologiche. Tuttavia, l'incidenza rara delle interstiziopatie fa sì che non tutti i radiologi abbiano un grado di esperienza adatto a individuare visivamente l'anomalia. Inoltre, la malattia si diffonde lungo tutti i polmoni e la segmentazione manuale risulta faticosa. Nel tentativo di rimediare alla variabilità intra- ed inter-osservatore, sono state sviluppate tecniche per il riconoscimento automatico dei pattern UIP; vi sono approcci basati sull'analisi dell'istogramma e della texture dell'immagine ma, dal momento che i classificatori sono stati addestrati su label definite da operatori clinici diversi, presentano comunque un bias che è causa di identificazioni errate, o mancate, dei pattern. Il deep learning, invece, si distingue dalle tecniche tradizionali perché fornisce strumenti che imparano autonomamente a classificare i dati. L'obiettivo del lavoro è stato, quindi, progettare e sviluppare la UIP-net, una rete neurale convoluzionale ad-hoc per la segmentazione automatica dei pattern UIP in immagini HRCT di pazienti con Fibrosi Idiopatica Polmonare (IPF), che è una sotto-categoria delle ILD.DOI: 10.32079/isti-tr-2020/007
Metrics:
See at:
CNR IRIS | ISTI Repository | CNR IRIS
2020
Journal article
Open Access
Can Magnetic Resonance Radiomics Analysis Discriminate Parotid Gland Tumors? A Pilot Study
Gabelloni M, Faggioni L, Attanasio S, Vani V, Goddi A, Colantonio S, Germanese D, Caudai C, Bruschini L, Scarano M, Seccia V, Neri E
Our purpose is to evaluate the performance of magnetic resonance (MR) radiomics analysis for differentiating between malignant and benign parotid neoplasms and, among the latter, between pleomorphic adenomas and Warthin tumors. We retrospectively evaluated 75 T2-weighted images of parotid gland lesions, of which 61 were benign tumors (32 pleomorphic adenomas, 23 Warthin tumors and 6 oncocytomas) and 14 were malignant tumors. A receiver operating characteristics (ROC) curve analysis was performed to find the threshold values for the most discriminative features and determine their sensitivity, specificity and area under the ROC curve (AUROC). The most discriminative features were used to train a support vector machine classifier. The best classification performance was obtained by comparing a pleomorphic adenoma with a Warthin tumor (yielding sensitivity, specificity and a diagnostic accuracy as high as 0.8695, 0.9062 and 0.8909, respectively) and a pleomorphic adenoma with malignant tumors (sensitivity, specificity and a diagnostic accuracy of 0.6666, 0.8709 and 0.8043, respectively). Radiomics analysis of parotid tumors on conventional T2-weighted MR images allows the discrimination of pleomorphic adenomas from Warthin tumors and malignant tumors with a high sensitivity, specificity and diagnostic accuracy.Source: DIAGNOSTICS, vol. 10 (issue 11)
Gabelloni M, Faggioni L, Attanasio S, Vani V, Goddi A, Colantonio S, Germanese D, Caudai C, Bruschini L, Scarano M, Seccia V, Neri E
Our purpose is to evaluate the performance of magnetic resonance (MR) radiomics analysis for differentiating between malignant and benign parotid neoplasms and, among the latter, between pleomorphic adenomas and Warthin tumors. We retrospectively evaluated 75 T2-weighted images of parotid gland lesions, of which 61 were benign tumors (32 pleomorphic adenomas, 23 Warthin tumors and 6 oncocytomas) and 14 were malignant tumors. A receiver operating characteristics (ROC) curve analysis was performed to find the threshold values for the most discriminative features and determine their sensitivity, specificity and area under the ROC curve (AUROC). The most discriminative features were used to train a support vector machine classifier. The best classification performance was obtained by comparing a pleomorphic adenoma with a Warthin tumor (yielding sensitivity, specificity and a diagnostic accuracy as high as 0.8695, 0.9062 and 0.8909, respectively) and a pleomorphic adenoma with malignant tumors (sensitivity, specificity and a diagnostic accuracy of 0.6666, 0.8709 and 0.8043, respectively). Radiomics analysis of parotid tumors on conventional T2-weighted MR images allows the discrimination of pleomorphic adenomas from Warthin tumors and malignant tumors with a high sensitivity, specificity and diagnostic accuracy.Source: DIAGNOSTICS, vol. 10 (issue 11)
See at:
CNR IRIS | ISTI Repository | www.mdpi.com | CNR IRIS
2021
Conference article
Open Access
UIP-net: a decoder-encoder CNN for the detection and quantification of usual interstitial pneumoniae pattern in lung CT scan images
Buongiorno R., Germanese D., Romei C., Tavanti L., De Liperi A., Colantonio S.
A key step of the diagnosis of Idiopathic Pulmonary Fibrosis (IPF) is the examination of high-resolution computed tomography images (HRCT). IPF exhibits a typical radiological pattern, named Usual Interstitial Pneumoniae (UIP) pattern, which can be detected in non-invasive HRCT investigations, thus avoiding surgical lung biopsy. Unfortunately, the visual recognition and quantification of UIP pattern can be challenging even for experienced radiologists due to the poor inter and intra-reader agreement. This study aimed to develop a tool for the semantic segmentation and the quantification of UIP pattern in patients with IPF using a deep-learning method based on a Convolutional Neural Network (CNN), called UIP-net. The proposed CNN, based on an encoder-decoder architecture, takes as input a thoracic HRCT image and outputs a binary mask for the automatic discrimination between UIP pattern and healthy lung parenchyma. To train and evaluate the CNN, a dataset of 5000 images, derived by 20 CT scans of different patients, was used. The network performance yielded 96.7% BF-score and 85.9% sensitivity. Once trained and tested, the UIP-net was used to obtain the segmentations of other 60 CT scans of different patients to estimate the volume of lungs affected by the UIP pattern. The measurements were compared with those obtained using the reference software for the automatic detection of UIP pattern, named Computer Aided Lungs Informatics for Pathology Evaluation and Rating (CALIPER), through the Bland-Altman plot. The network performance assessed in terms of both BF-score and sensitivity on the test-set and resulting from the comparison with CALIPER demonstrated that CNNs have the potential to reliably detect and quantify pulmonary disease in order to evaluate its progression and become a supportive tool for radiologists.Source: ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges, pp. 389–405, Milan, Italy - Virtual event, 10-15/01/2021
DOI: 10.1007/978-3-030-68763-2_30
Metrics:
Buongiorno R., Germanese D., Romei C., Tavanti L., De Liperi A., Colantonio S.
A key step of the diagnosis of Idiopathic Pulmonary Fibrosis (IPF) is the examination of high-resolution computed tomography images (HRCT). IPF exhibits a typical radiological pattern, named Usual Interstitial Pneumoniae (UIP) pattern, which can be detected in non-invasive HRCT investigations, thus avoiding surgical lung biopsy. Unfortunately, the visual recognition and quantification of UIP pattern can be challenging even for experienced radiologists due to the poor inter and intra-reader agreement. This study aimed to develop a tool for the semantic segmentation and the quantification of UIP pattern in patients with IPF using a deep-learning method based on a Convolutional Neural Network (CNN), called UIP-net. The proposed CNN, based on an encoder-decoder architecture, takes as input a thoracic HRCT image and outputs a binary mask for the automatic discrimination between UIP pattern and healthy lung parenchyma. To train and evaluate the CNN, a dataset of 5000 images, derived by 20 CT scans of different patients, was used. The network performance yielded 96.7% BF-score and 85.9% sensitivity. Once trained and tested, the UIP-net was used to obtain the segmentations of other 60 CT scans of different patients to estimate the volume of lungs affected by the UIP pattern. The measurements were compared with those obtained using the reference software for the automatic detection of UIP pattern, named Computer Aided Lungs Informatics for Pathology Evaluation and Rating (CALIPER), through the Bland-Altman plot. The network performance assessed in terms of both BF-score and sensitivity on the test-set and resulting from the comparison with CALIPER demonstrated that CNNs have the potential to reliably detect and quantify pulmonary disease in order to evaluate its progression and become a supportive tool for radiologists.Source: ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges, pp. 389–405, Milan, Italy - Virtual event, 10-15/01/2021
DOI: 10.1007/978-3-030-68763-2_30
Metrics:
See at:
link.springer.com | ISTI Repository | link.springer.com | CNR ExploRA
2021
Conference article
Open Access
A deep learning approach for hepatic steatosis estimation from ultrasound imaging
Colantonio S, Salvati A, Caudai C, Bonino F, De Rosa L, Pascali Ma, Germanese D, Brunetto Mr, Faita F
This paper proposes a simple convolutional neural model as a novel method to predict the level of hepatic steatosis from ultrasound data. Hepatic steatosis is the major histologic feature of non-alcoholic fatty liver disease (NAFLD), which has become a major global health challenge. Recently a new definition for FLD, that take into account the risk factors and clinical characteristics of subjects, has been suggested; the proposed criteria for Metabolic Disfunction-Associated Fatty Liver Disease (MAFLD) are based on histological (biopsy), imaging or blood biomarker evidence of fat accumulation in the liver (hepatic steatosis), in subjects with overweight/obesity or presence of type 2 diabetes mellitus. In lean or normal weight, non-diabetic individuals with steatosis, MAFLD is diagnosed when at least two metabolic abnormalities are present. Ultrasound examinations are the most used technique to non-invasively identify liver steatosis in a screening settings. However, the diagnosis is operator dependent, as accurate image processing techniques have not entered yet in the diagnostic routine. In this paper, we discuss the adoption of simple convolutional neural models to estimate the degree of steatosis from echographic images in accordance with the state-of-the-art magnetic resonance spectroscopy measurements (expressed as percentage of the estimated liver fat). More than 22,000 ultrasound images were used to train three networks, and results show promising performances in our study (150 subjects).Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 703-714. Rhodes, Greece, 29/09/2021,1/10/ 2021
Colantonio S, Salvati A, Caudai C, Bonino F, De Rosa L, Pascali Ma, Germanese D, Brunetto Mr, Faita F
This paper proposes a simple convolutional neural model as a novel method to predict the level of hepatic steatosis from ultrasound data. Hepatic steatosis is the major histologic feature of non-alcoholic fatty liver disease (NAFLD), which has become a major global health challenge. Recently a new definition for FLD, that take into account the risk factors and clinical characteristics of subjects, has been suggested; the proposed criteria for Metabolic Disfunction-Associated Fatty Liver Disease (MAFLD) are based on histological (biopsy), imaging or blood biomarker evidence of fat accumulation in the liver (hepatic steatosis), in subjects with overweight/obesity or presence of type 2 diabetes mellitus. In lean or normal weight, non-diabetic individuals with steatosis, MAFLD is diagnosed when at least two metabolic abnormalities are present. Ultrasound examinations are the most used technique to non-invasively identify liver steatosis in a screening settings. However, the diagnosis is operator dependent, as accurate image processing techniques have not entered yet in the diagnostic routine. In this paper, we discuss the adoption of simple convolutional neural models to estimate the degree of steatosis from echographic images in accordance with the state-of-the-art magnetic resonance spectroscopy measurements (expressed as percentage of the estimated liver fat). More than 22,000 ultrasound images were used to train three networks, and results show promising performances in our study (150 subjects).Source: COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE (PRINT), pp. 703-714. Rhodes, Greece, 29/09/2021,1/10/ 2021
See at:
CNR IRIS | link.springer.com | CNR IRIS | CNR IRIS
2022
Conference article
Open Access
Exploring UAVs for structural health monitoring
Germanese D, Moroni D, Pascali Ma, Tampucci M, Berton A
The preservation and maintenance of architectural heritage on a large scale deserve the design, development, and exploitation of innovative methodologies and tools for sustainable Structural Heritage Monitoring (SHM). In the framework of the Moscardo Project (https://www.moscardo.it/), the role of Unmanned Aerial Vehicles (UAVs) in conjunction with a broader IoT platform for SHM has been investigated. UAVs resulted in significant aid for a safe, fast and routinely operated inspection of buildings in synergy with data collected in situ thanks to a network of pervasive wireless sensors (Bacco et al. 2020). The main idea has been to deploy an acquisition layer made of a network of low power sensors capable of collecting environmental parameters and building vibration modes. This layer has been connected to a service layer through gateways capable of performing data analysis and presenting aggregated results thanks to an integrated dashboard. In this architecture, the UAV has emerged as a particular network node for extending the acquisition layer by adding several imaging capabilities.
Germanese D, Moroni D, Pascali Ma, Tampucci M, Berton A
The preservation and maintenance of architectural heritage on a large scale deserve the design, development, and exploitation of innovative methodologies and tools for sustainable Structural Heritage Monitoring (SHM). In the framework of the Moscardo Project (https://www.moscardo.it/), the role of Unmanned Aerial Vehicles (UAVs) in conjunction with a broader IoT platform for SHM has been investigated. UAVs resulted in significant aid for a safe, fast and routinely operated inspection of buildings in synergy with data collected in situ thanks to a network of pervasive wireless sensors (Bacco et al. 2020). The main idea has been to deploy an acquisition layer made of a network of low power sensors capable of collecting environmental parameters and building vibration modes. This layer has been connected to a service layer through gateways capable of performing data analysis and presenting aggregated results thanks to an integrated dashboard. In this architecture, the UAV has emerged as a particular network node for extending the acquisition layer by adding several imaging capabilities.
See at:
CNR IRIS | ISTI Repository | ISTI Repository | www.dsiteconference.com | CNR IRIS | CNR IRIS