2021
Journal article
Open Access
Integrating wearable haptics and obstacle avoidance for the visually impaired in indoor navigation: a user-centered approach
Barontini F., Catalano M. G., Pallottino L., Leporini B., Bianchi M.
Recently, in the attempt to increase blind people autonomy and improve their quality of life, a lot of effort has been devoted to develop technological travel aids. These systems can surrogate spatial information about the environment and deliver it to end-users through sensory substitution (auditory, haptic). However, despite the promising research outcomes, these solutions have met scarce acceptance in real-world. Often, this is also due to the limited involvement of real end users in the conceptual and design phases. In this manuscript, we propose a novel indoor navigation system based on wearable haptic technologies. All the developmental phases were driven by continuous feedback from visually impaired persons. The proposed travel aid system consists of a RGB-D camera, a processing unit to compute visual information for obstacle avoidance, and a wearable device, which can provide normal and tangential force cues for guidance in an unknown indoor environment. Experiments with blindfolded subjects and visually impaired participants show that our system could be an effective support during indoor navigation, and a viable tool for training blind people to the usage of travel aids.Source: IEEE transactions on haptics (Print) 14 (2021): 109–122. doi:10.1109/TOH.2020.2996748
DOI: 10.1109/toh.2020.2996748
Metrics:
Barontini F., Catalano M. G., Pallottino L., Leporini B., Bianchi M.
Recently, in the attempt to increase blind people autonomy and improve their quality of life, a lot of effort has been devoted to develop technological travel aids. These systems can surrogate spatial information about the environment and deliver it to end-users through sensory substitution (auditory, haptic). However, despite the promising research outcomes, these solutions have met scarce acceptance in real-world. Often, this is also due to the limited involvement of real end users in the conceptual and design phases. In this manuscript, we propose a novel indoor navigation system based on wearable haptic technologies. All the developmental phases were driven by continuous feedback from visually impaired persons. The proposed travel aid system consists of a RGB-D camera, a processing unit to compute visual information for obstacle avoidance, and a wearable device, which can provide normal and tangential force cues for guidance in an unknown indoor environment. Experiments with blindfolded subjects and visually impaired participants show that our system could be an effective support during indoor navigation, and a viable tool for training blind people to the usage of travel aids.Source: IEEE transactions on haptics (Print) 14 (2021): 109–122. doi:10.1109/TOH.2020.2996748
DOI: 10.1109/toh.2020.2996748
Metrics:
See at:
ISTI Repository 
| IEEE Transactions on Haptics 
| ieeexplore.ieee.org | CNR ExploRA
2021
Journal article
Open Access
Effects of acute and sub-acute hypobaric hypoxia on oxidative stress: a field study in the Alps
Mrakic-Sposta S., Gussoni M., Dellanoce C., Marzorati M., Montorsi M., Rasica L., Pratali L., D'Angelo G., Martinelli M., Bastiani L., Di Natale L., Vezzoli A.
Purpose High altitude results in lower barometric pressure and hence partial pressure of O2 decrease can lead to several molecular and cellular changes, such as generation of reactive oxygen species (ROS). Electron Paramagnetic Resonance technique was adopted in the field, to evaluate the effects of acute and sub-acute hypobaric hypoxia (HH) on ROS production by micro-invasive method. Biological biomarkers, indicators of oxidative stress, renal function and inflammation were investigated too. Methods Fourteen lowlander subjects (mean age 27.3 ± 5.9 years) were exposed to HH at 3269 m s.l. ROS production, related oxidative damage to cellular components, systemic inflammatory response and renal function were determined through blood and urine profile performed at 1st, 2nd, 4th, 7th, and 14th days during sojourn. Results Kinetics of changes during HH exposition showed out significant (range p < 0.05-0.0001) increases that at max corresponds to 38% for ROS production rate, 140% for protein carbonyl, 44% for lipid peroxidation, 42% for DNA damage, 200% for inflammatory cytokines and modifications in renal function (assessed by neopterin concentration: 48%). Conversely, antioxidant capacity significantly (p < 0.0001) decreased - 17% at max. Conclusion This 14 days in-field study describes changes of oxidative-stress biomarkers during HH exposure in lowlanders. The results show an overproduction of ROS and consequent oxidative damage to protein, lipids and DNA with a decrease in antioxidant capacity and the involvement of inflammatory status and a transient renal dysfunction. Exposure at high altitude induces a hypoxic condition during acute and sub-acute phases accompanied by molecular adaptation mechanism indicating acclimatization.Source: European journal of applied physiology (Print) 121 (2021): 297–306. doi:10.1007/s00421-020-04527-x
DOI: 10.1007/s00421-020-04527-x
Metrics:
Mrakic-Sposta S., Gussoni M., Dellanoce C., Marzorati M., Montorsi M., Rasica L., Pratali L., D'Angelo G., Martinelli M., Bastiani L., Di Natale L., Vezzoli A.
Purpose High altitude results in lower barometric pressure and hence partial pressure of O2 decrease can lead to several molecular and cellular changes, such as generation of reactive oxygen species (ROS). Electron Paramagnetic Resonance technique was adopted in the field, to evaluate the effects of acute and sub-acute hypobaric hypoxia (HH) on ROS production by micro-invasive method. Biological biomarkers, indicators of oxidative stress, renal function and inflammation were investigated too. Methods Fourteen lowlander subjects (mean age 27.3 ± 5.9 years) were exposed to HH at 3269 m s.l. ROS production, related oxidative damage to cellular components, systemic inflammatory response and renal function were determined through blood and urine profile performed at 1st, 2nd, 4th, 7th, and 14th days during sojourn. Results Kinetics of changes during HH exposition showed out significant (range p < 0.05-0.0001) increases that at max corresponds to 38% for ROS production rate, 140% for protein carbonyl, 44% for lipid peroxidation, 42% for DNA damage, 200% for inflammatory cytokines and modifications in renal function (assessed by neopterin concentration: 48%). Conversely, antioxidant capacity significantly (p < 0.0001) decreased - 17% at max. Conclusion This 14 days in-field study describes changes of oxidative-stress biomarkers during HH exposure in lowlanders. The results show an overproduction of ROS and consequent oxidative damage to protein, lipids and DNA with a decrease in antioxidant capacity and the involvement of inflammatory status and a transient renal dysfunction. Exposure at high altitude induces a hypoxic condition during acute and sub-acute phases accompanied by molecular adaptation mechanism indicating acclimatization.Source: European journal of applied physiology (Print) 121 (2021): 297–306. doi:10.1007/s00421-020-04527-x
DOI: 10.1007/s00421-020-04527-x
Metrics:
See at:
ISTI Repository | European Journal of Applied Physiology and Occupational Physiology | link.springer.com | CNR ExploRA
2021
Contribution to journal
Open Access
Signals and Images in Sea Technologies
Moroni D., Salvetti O.
Source: Journal of marine science and engineering 41 (2021). doi:10.3390/jmse9010041
DOI: 10.3390/jmse9010041
DOI: 10.3390/books978-3-0365-1355-3
Metrics:
Moroni D., Salvetti O.
Source: Journal of marine science and engineering 41 (2021). doi:10.3390/jmse9010041
DOI: 10.3390/jmse9010041
DOI: 10.3390/books978-3-0365-1355-3
Metrics:
See at:
Journal of Marine Science and Engineering | hal.archives-ouvertes.fr | ISTI Repository | Journal of Marine Science and Engineering | Journal of Marine Science and Engineering | ZENODO | doi.org | Hyper Article en Ligne | Hyper Article en Ligne | CNR ExploRA
2021
Report
Unknown
Progetto DiOncoGen CloudPathology - Secondo test di valutazione delle informazioni sul secondo dataset
Martinelli M., Bruno A., Moroni D.
Il presente documento fornisce i risultati del secondo test di valutazione del secondo dataset ricevuto nell'ambito del progetto DiOncoGen-CloudPathology.Source: Project report, DiOncoGen CloudPathology, 2021
Martinelli M., Bruno A., Moroni D.
Il presente documento fornisce i risultati del secondo test di valutazione del secondo dataset ricevuto nell'ambito del progetto DiOncoGen-CloudPathology.Source: Project report, DiOncoGen CloudPathology, 2021
See at: CNR ExploRA
2021
Report
Unknown
Studio Pink - Le linee di sviluppo
Pieroni S., Franchini M., Denoth F., Colantonio S., Tampucci M., Fortunato L., Molinaro S.
Questo documento descrive le linee di sviluppo dello studio P.I.N.K., già previste come parte integrante del progetto fin dall'avvio delle attività, che si fondano sull'attivazione di studi ad hoc trasversali alle diverse tematiche trattate. Sono di fatto tre linee di ricerca parallele che partono dalla solida base di conoscenza creata all'interno di P.I.N.K. nei suoi primi tre anni di vita: linea 1 riguardante Imaging e Radiomica, linea 2 riguardante la dosimetria personalizzata, linea 3 riguardante la nutrizione e stile di vita.Source: Project report, Studio Pink, 2021
Pieroni S., Franchini M., Denoth F., Colantonio S., Tampucci M., Fortunato L., Molinaro S.
Questo documento descrive le linee di sviluppo dello studio P.I.N.K., già previste come parte integrante del progetto fin dall'avvio delle attività, che si fondano sull'attivazione di studi ad hoc trasversali alle diverse tematiche trattate. Sono di fatto tre linee di ricerca parallele che partono dalla solida base di conoscenza creata all'interno di P.I.N.K. nei suoi primi tre anni di vita: linea 1 riguardante Imaging e Radiomica, linea 2 riguardante la dosimetria personalizzata, linea 3 riguardante la nutrizione e stile di vita.Source: Project report, Studio Pink, 2021
See at: CNR ExploRA
2021
Report
Unknown
Barilla AgroSat+ Server, Client e Modelli
Bruno A., Moroni D., Martinelli M.
Server, Client e Modelli del Progetto Barilla AgroSat+Source: ISTI Project report, Barilla Agrosat+, 2021
Bruno A., Moroni D., Martinelli M.
Server, Client e Modelli del Progetto Barilla AgroSat+Source: ISTI Project report, Barilla Agrosat+, 2021
See at: CNR ExploRA
2021
Report
Unknown
Using random forests to classify vessels from naive geometrical features
Salerno E.
This report is concerned with the application of Random Forest classification methods to the identification of ship types in moderate-resolution SAR images. After a brief presentation of the theory and and the features of this class of methods, we select an R package useful to train, test and execute the classifier. Some experiments are then reported using naive geometrical features extracted from a few thousands of targets in the OpenSARShip data set. All the ship chips extracted are derived from IW GRD Sentinel 1 C-band SAR images, accompanied by AIS and MarineTraffic ground-truth data. The ideal performance of this classifier is evaluated through the standard classification indices, with respect to the ship types that are sufficiently represented in the subsets considered.Source: ISTI Working papers, 2021
Salerno E.
This report is concerned with the application of Random Forest classification methods to the identification of ship types in moderate-resolution SAR images. After a brief presentation of the theory and and the features of this class of methods, we select an R package useful to train, test and execute the classifier. Some experiments are then reported using naive geometrical features extracted from a few thousands of targets in the OpenSARShip data set. All the ship chips extracted are derived from IW GRD Sentinel 1 C-band SAR images, accompanied by AIS and MarineTraffic ground-truth data. The ideal performance of this classifier is evaluated through the standard classification indices, with respect to the ship types that are sufficiently represented in the subsets considered.Source: ISTI Working papers, 2021
See at: CNR ExploRA
2021
Report
Unknown
NAUTILOS - H - Requirement No. 1
Pieri G., Deluca R., Chatzinikolaou E.
The procedures and criteria that will be used to identify/recruit research participants, as well as the informed consent procedures that will be implemented for the participation of humans external to NAUTILOS to the project activities and in regard to their data processing are presented in this document. Templates of the informed consent/assent forms and information sheets covering the voluntary participation and data protection issues, in the English version are provided.Source: Project report, NAUTILOS, D13.1, 2021
Project(s): NAUTILOS
Pieri G., Deluca R., Chatzinikolaou E.
The procedures and criteria that will be used to identify/recruit research participants, as well as the informed consent procedures that will be implemented for the participation of humans external to NAUTILOS to the project activities and in regard to their data processing are presented in this document. Templates of the informed consent/assent forms and information sheets covering the voluntary participation and data protection issues, in the English version are provided.Source: Project report, NAUTILOS, D13.1, 2021
Project(s): NAUTILOS
See at: CNR ExploRA
2021
Report
Unknown
NAUTILOS - POPD - Requirement No. 2
Pieri G., Gianvincenzo A., Novellino A., Deluca R.
This document is intended to provide recommendation on the procedures of the Information Systems and is inspired by the principles of correctness and diligence and is adopted in compliance with the provisions contained in the Privacy code and in the General Data Protection Regulation of the European Union.Source: Project report, Nautilos, D13.2, 2021
Project(s): NAUTILOS
Pieri G., Gianvincenzo A., Novellino A., Deluca R.
This document is intended to provide recommendation on the procedures of the Information Systems and is inspired by the principles of correctness and diligence and is adopted in compliance with the provisions contained in the Privacy code and in the General Data Protection Regulation of the European Union.Source: Project report, Nautilos, D13.2, 2021
Project(s): NAUTILOS
See at: CNR ExploRA
2021
Report
Unknown
NAUTILOS - A - Requirement No. 3
Pieri G.
This deliverable describes the general nature of the experiments with animals and the procedures that will be performed within NAUTILOS, in order to ensure animal welfare and adherence to EU Directive 2010/63/EU and the Three Rs guidelines principle. Moreover, information about existing expertise and experiences of the involved partners are reported.Source: Project report, NAUTILOS, D13.3, 2021
Project(s): NAUTILOS
Pieri G.
This deliverable describes the general nature of the experiments with animals and the procedures that will be performed within NAUTILOS, in order to ensure animal welfare and adherence to EU Directive 2010/63/EU and the Three Rs guidelines principle. Moreover, information about existing expertise and experiences of the involved partners are reported.Source: Project report, NAUTILOS, D13.3, 2021
Project(s): NAUTILOS
See at: CNR ExploRA
2021
Report
Unknown
NAUTILOS - NEC - Requirement No. 4
Pieri G.
This deliverable describes the ethical issues concerning the research performed outside the EU, both in terms of ethical compliance with EU standards, and in terms of the detail of the materials that will be imported/exported from and to non-EU countries to a member state.Source: Project report, NAUTILOS, D13.4, 2021
Project(s): NAUTILOS
Pieri G.
This deliverable describes the ethical issues concerning the research performed outside the EU, both in terms of ethical compliance with EU standards, and in terms of the detail of the materials that will be imported/exported from and to non-EU countries to a member state.Source: Project report, NAUTILOS, D13.4, 2021
Project(s): NAUTILOS
See at: CNR ExploRA
2021
Report
Unknown
NAUTILOS - EPQ - Requirement No. 5
Pieri G.
The deliverable presents and discusses the procedures and measures to mitigate environmental risks happening during the Project. Moreover, the application of health and safety procedures, conforming to the relevant guidelines and legislations are described, together with the measures minimising impact on endangered species or protected areas involved in the project activities.Source: Project report, NAUTILOS, D13.5, 2021
Project(s): NAUTILOS
Pieri G.
The deliverable presents and discusses the procedures and measures to mitigate environmental risks happening during the Project. Moreover, the application of health and safety procedures, conforming to the relevant guidelines and legislations are described, together with the measures minimising impact on endangered species or protected areas involved in the project activities.Source: Project report, NAUTILOS, D13.5, 2021
Project(s): NAUTILOS
See at: CNR ExploRA
2021
Report
Unknown
Ti Assisto - Sistema Informativo
Martinelli M., Deluca R., Moroni D.
Il sistema informativo, le piattaforme pregresse, privacy, requisiti
Martinelli M., Deluca R., Moroni D.
Il sistema informativo, le piattaforme pregresse, privacy, requisiti
See at: CNR ExploRA
2021
Bachelor thesis
Open Access
PsicoTableau: sperimentazione artistica sui livelli di attivazione e valenza emotiva attuata mediante sensori biomedici
Ratto C.
Questo lavoro di tesi consiste nello studio e nella realizzazione di un'installazione audiovisiva reattiva allo stato emotivo del visitatore. Sebbene il lavoro si inserisca in un panorama ormai ben consolidato come quello delle arti elettroniche interattive, la particolare modalità di interazione uomo-macchina che utilizza la caratterizza sufficientemente da renderla sicuramente non comune. Laddove la maggior parte delle opere interattive presuppone di utilizzare la presenza fisica e la gestualità per attivare e/o controllare i contenuti, siano essi audio video o cinetici, in questo lavoro si è scelto di utilizzare lo stato emotivo come impalpabile catalizzatore dei media. La filosofia adottata sposta quindi il valore estetico dell'opera dagli aspetti più "retinici" a quelli più concettuali: è il meccanismo in sé che costituisce l'operazione estetica, non (solo) i risultati/output che produce e controlla.
Ratto C.
Questo lavoro di tesi consiste nello studio e nella realizzazione di un'installazione audiovisiva reattiva allo stato emotivo del visitatore. Sebbene il lavoro si inserisca in un panorama ormai ben consolidato come quello delle arti elettroniche interattive, la particolare modalità di interazione uomo-macchina che utilizza la caratterizza sufficientemente da renderla sicuramente non comune. Laddove la maggior parte delle opere interattive presuppone di utilizzare la presenza fisica e la gestualità per attivare e/o controllare i contenuti, siano essi audio video o cinetici, in questo lavoro si è scelto di utilizzare lo stato emotivo come impalpabile catalizzatore dei media. La filosofia adottata sposta quindi il valore estetico dell'opera dagli aspetti più "retinici" a quelli più concettuali: è il meccanismo in sé che costituisce l'operazione estetica, non (solo) i risultati/output che produce e controlla.
See at:
ISTI Repository | www.youtube.com | CNR ExploRA
2021
Report
Unknown
Naive bayes for naive geometry: classifying vessels from length and beam
Salerno E.
This report is concerned with the application of a Naive Bayes classification method to the identification of ship types in moderate-resolution SAR images. After a brief presentation of the principles behind the method, a simple implementation and an extensive experimentation on naive geometrical features extracted from a few thousands of targets in the OpenSARShip data set are presented. All the ship chips extracted are derived from IW GRD Sentinel 1 C-band SAR images, accompanied by AIS and MarineTraffic ground-truth data. The ideal performance of this Naive Bayes is evaluated through the standard classification indices, with respect to the ship types that are sufficiently represented in the subsets considered.Source: ISTI Working papers, 2021
Salerno E.
This report is concerned with the application of a Naive Bayes classification method to the identification of ship types in moderate-resolution SAR images. After a brief presentation of the principles behind the method, a simple implementation and an extensive experimentation on naive geometrical features extracted from a few thousands of targets in the OpenSARShip data set are presented. All the ship chips extracted are derived from IW GRD Sentinel 1 C-band SAR images, accompanied by AIS and MarineTraffic ground-truth data. The ideal performance of this Naive Bayes is evaluated through the standard classification indices, with respect to the ship types that are sufficiently represented in the subsets considered.Source: ISTI Working papers, 2021
See at: CNR ExploRA
2021
Report
Unknown
Barilla Agrosat+ Organi, aggiornamenti, confronti
Bruno A., Moroni D., Martinelli M.
Aggiornamenti e confronti. Progetto Barilla Agrosat+Source: ISTI Project report, AgroSat+, 2021
Bruno A., Moroni D., Martinelli M.
Aggiornamenti e confronti. Progetto Barilla Agrosat+Source: ISTI Project report, AgroSat+, 2021
See at: CNR ExploRA
2021
Book
Unknown
La stella di Deotisalvi
Tarabella L.
Deotisalvi è l'Architetto del secolo d'oro, il XII. Della sua vita non si sa niente. Forse veniva dall'Oriente. Forse era un frate. Di lui sono rimasti i suoi monumenti e, nelle parole di Silvano Burgalassi, i monumenti parlano di per sé ... perché ci sono. Questo è un racconto del tutto fantasioso sulla vita di Deotisalvi ispirato dalla geometria dei suoi monumenti. I monumenti della Piazza sono la mente e la vita artistica di Deotisalvi: una mente ed una vita spirituale e geometrica. E neanche matematica (caso mai aritmetica) ma geometrica.Perché la matematica come la pensiamo, la conosciamo e la utilizziamo ora all'epoca non esisteva. La geometria è nella Natura.La matematica è nella mente dell'uomo. La geometria è il collegamento tra l'uomo e la Natura.
Tarabella L.
Deotisalvi è l'Architetto del secolo d'oro, il XII. Della sua vita non si sa niente. Forse veniva dall'Oriente. Forse era un frate. Di lui sono rimasti i suoi monumenti e, nelle parole di Silvano Burgalassi, i monumenti parlano di per sé ... perché ci sono. Questo è un racconto del tutto fantasioso sulla vita di Deotisalvi ispirato dalla geometria dei suoi monumenti. I monumenti della Piazza sono la mente e la vita artistica di Deotisalvi: una mente ed una vita spirituale e geometrica. E neanche matematica (caso mai aritmetica) ma geometrica.Perché la matematica come la pensiamo, la conosciamo e la utilizziamo ora all'epoca non esisteva. La geometria è nella Natura.La matematica è nella mente dell'uomo. La geometria è il collegamento tra l'uomo e la Natura.
See at: CNR ExploRA
2021
Report
Open Access
Technical report on the development and interpretation of convolutional neural networks for the classification of multiparametric MRI images on unbalanced datasets. Case study: prostate cancer
Pachetti E., Colantonio S.
This report summarized the activities carried out to define, train and validate Deep Learning models for the classification of medical imaging data. The issue of unbalanced datasets was faced by applying some data augmentation techniques, based on transformation of the original images. Such techniques were compared to verify their impact in a frame where object morphology is relevant. Multimodal deep learning models were defined to exploit the information contained in heterogeneous imaging data and cope with data distribution imbalance. To verify the inner functioning of the deep learning models, the LIME algorithm was applied, thus checking that the regions that contribute to the classification were the real meaningful ones. The case study used to was the categorization of prostate cancer aggressiveness based on Magnetic Resonance Imaging (MRI) data. The aggressiveness was determined, as a ground truth, via tissue biopsy and expressed with a score from 2 to 10 known as Gleason Score, which is obtained as the sum of two values, each one from 1 to 5, associated with the two most common patterns in the tumor tissue histological sample.Source: ISTI Technical Report, ISTI-2021-TR/005, pp.1–16, 2021
Pachetti E., Colantonio S.
This report summarized the activities carried out to define, train and validate Deep Learning models for the classification of medical imaging data. The issue of unbalanced datasets was faced by applying some data augmentation techniques, based on transformation of the original images. Such techniques were compared to verify their impact in a frame where object morphology is relevant. Multimodal deep learning models were defined to exploit the information contained in heterogeneous imaging data and cope with data distribution imbalance. To verify the inner functioning of the deep learning models, the LIME algorithm was applied, thus checking that the regions that contribute to the classification were the real meaningful ones. The case study used to was the categorization of prostate cancer aggressiveness based on Magnetic Resonance Imaging (MRI) data. The aggressiveness was determined, as a ground truth, via tissue biopsy and expressed with a score from 2 to 10 known as Gleason Score, which is obtained as the sum of two values, each one from 1 to 5, associated with the two most common patterns in the tumor tissue histological sample.Source: ISTI Technical Report, ISTI-2021-TR/005, pp.1–16, 2021
See at:
ISTI Repository | CNR ExploRA
2021
Conference article
Open Access
Learning topology: bridging computational topology and machine learning
Moroni D., Pascali M. A.
Topology is a classical branch of mathematics, born essentially from Euler's studies in the XVII century, which deals with the abstract notion of shape and geometry. Last decades were characterised by a renewed interest in topology and topology-based tools, due to the birth of computational topology and Topological Data Analysis (TDA). A large and novel family of methods and algorithms computing topological features and descriptors (e.g. persistent homology) have proved to be effective tools for the analysis of graphs, 3d objects, 2D images, and even heterogeneous datasets. This survey is intended to be a concise but complete compendium that, offering the essential basic references, allows you to orient yourself among the recent advances in TDA and its applications, with an eye to those related to machine learning and deep learning.Source: ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges, Milan, Italy - Fully virtual event, 11/01/2021
DOI: 10.1007/978-3-030-68821-9_20
Metrics:
Moroni D., Pascali M. A.
Topology is a classical branch of mathematics, born essentially from Euler's studies in the XVII century, which deals with the abstract notion of shape and geometry. Last decades were characterised by a renewed interest in topology and topology-based tools, due to the birth of computational topology and Topological Data Analysis (TDA). A large and novel family of methods and algorithms computing topological features and descriptors (e.g. persistent homology) have proved to be effective tools for the analysis of graphs, 3d objects, 2D images, and even heterogeneous datasets. This survey is intended to be a concise but complete compendium that, offering the essential basic references, allows you to orient yourself among the recent advances in TDA and its applications, with an eye to those related to machine learning and deep learning.Source: ICPR 2021: Pattern Recognition. ICPR International Workshops and Challenges, Milan, Italy - Fully virtual event, 11/01/2021
DOI: 10.1007/978-3-030-68821-9_20
Metrics:
See at:
link.springer.com | ISTI Repository | link.springer.com | CNR ExploRA
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