2022
Journal article
Open Access
Horticultural therapy may reduce psychological and physiological stress in adolescents with anorexia nervosa: a pilot study
Curzio O., Billeci L., Belmonti V., Colantonio S., Cotrozzi L., De Pasquale C. F., Morales M. A., Nali C., Pascali M. A., Venturi F., Tonacci A., Zannoni N., Maestro S.
Studies in psychiatric populations have found a positive effect of Horticultural therapy (HCT) on reductions in stress levels. The main objective of the present pilot study was to evaluate the impact of the addition of HCT to conventional clinical treatment (Treatment as Usual, TaU) in a sample of six female adolescents with anorexia nervosa restricting type (AN-R), as compared to six AN-R patients, matched for sex and age, under TaU only. This is a prospective, non-profit, pilot study on patients with a previous diagnosis of AN-R and BMI < 16, recruited in 2020 in clinical settings. At enrolment (T0) and after treatment completion (TF), psychiatric assessment was performed. At T0, all the patients underwent: baseline electrocardiogram acquisition with a wearable chest strap for recording heart rate and its variability; skin conductance registration and thermal mapping of the individual's face. An olfactory identification test was administered both to evaluate the olfactory sensoriality and to assess the induced stress. One-way analyses of variance (ANOVAs) were performed to analyze modifications in clinical and physiological variables, considering time (T0, TF) as a within-subjects factor and group (experimental vs. control) as between-subjects factors. When the ANOVA was significant, post hoc analysis was performed by Paired Sample T-tests. Only in the HCT group, stress response levels, as measured by the biological parameters, improved over time. The body uneasiness level and the affective problem measures displayed a significant improvement in the HCT subjects. HCT seems to have a positive influence on stress levels in AN-R.Source: Nutrients 14 (2022). doi:10.3390/nu14245198
DOI: 10.3390/nu14245198
Metrics:
Curzio O., Billeci L., Belmonti V., Colantonio S., Cotrozzi L., De Pasquale C. F., Morales M. A., Nali C., Pascali M. A., Venturi F., Tonacci A., Zannoni N., Maestro S.
Studies in psychiatric populations have found a positive effect of Horticultural therapy (HCT) on reductions in stress levels. The main objective of the present pilot study was to evaluate the impact of the addition of HCT to conventional clinical treatment (Treatment as Usual, TaU) in a sample of six female adolescents with anorexia nervosa restricting type (AN-R), as compared to six AN-R patients, matched for sex and age, under TaU only. This is a prospective, non-profit, pilot study on patients with a previous diagnosis of AN-R and BMI < 16, recruited in 2020 in clinical settings. At enrolment (T0) and after treatment completion (TF), psychiatric assessment was performed. At T0, all the patients underwent: baseline electrocardiogram acquisition with a wearable chest strap for recording heart rate and its variability; skin conductance registration and thermal mapping of the individual's face. An olfactory identification test was administered both to evaluate the olfactory sensoriality and to assess the induced stress. One-way analyses of variance (ANOVAs) were performed to analyze modifications in clinical and physiological variables, considering time (T0, TF) as a within-subjects factor and group (experimental vs. control) as between-subjects factors. When the ANOVA was significant, post hoc analysis was performed by Paired Sample T-tests. Only in the HCT group, stress response levels, as measured by the biological parameters, improved over time. The body uneasiness level and the affective problem measures displayed a significant improvement in the HCT subjects. HCT seems to have a positive influence on stress levels in AN-R.Source: Nutrients 14 (2022). doi:10.3390/nu14245198
DOI: 10.3390/nu14245198
Metrics:
See at:
ISTI Repository 
| CNR ExploRA | www.mdpi.com
2022
Journal article
Open Access
Machine and deep learning prediction of prostate cancer aggressiveness using multiparametric MRI
E. Bertelli, L. Mercatelli, C. Marzi, E. Pachetti, M. Baccini, A. Barucci, S. Colantonio, L. Gherardini, L. Lattavo, M. A. Pascali, S. Agostini, V. Miele
Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score >= 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.Source: Frontiers in oncology 11 (2022). doi:10.3389/fonc.2021.802964
DOI: 10.3389/fonc.2021.802964
Project(s): ProCAncer-I
Metrics:
E. Bertelli, L. Mercatelli, C. Marzi, E. Pachetti, M. Baccini, A. Barucci, S. Colantonio, L. Gherardini, L. Lattavo, M. A. Pascali, S. Agostini, V. Miele
Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score >= 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.Source: Frontiers in oncology 11 (2022). doi:10.3389/fonc.2021.802964
DOI: 10.3389/fonc.2021.802964
Project(s): ProCAncer-I
Metrics:
See at:
ISTI Repository | CNR ExploRA | www.frontiersin.org
2022
Conference article
Open Access
Augmented reality, artificial intelligence and machine learning in Industry 4.0: case studies at SI-Lab
Bruno A, Coscetti S, Leone G. R., Germanese D., Magrini M., Martinelli M., Moroni D., Pascali M. A., Pieri G., Reggiannini M., Tampucci M.
In recent years, the impressive advances in artificial intelligence, computer vision, pervasive computing, and augmented reality made them rise to pillars of the fourth industrial revolution. This short paper aims to provide a brief survey of current use cases in factory applications and industrial inspection under active development at the Signals and Images Lab, ISTI-CNR, Pisa.Source: Ital-IA 2022 - Convegno nazionale CINI sull'Intelligenza Artificiale, Torino, Italy, 9-11/02/2022
DOI: 10.5281/zenodo.6322733
Metrics:
Bruno A, Coscetti S, Leone G. R., Germanese D., Magrini M., Martinelli M., Moroni D., Pascali M. A., Pieri G., Reggiannini M., Tampucci M.
In recent years, the impressive advances in artificial intelligence, computer vision, pervasive computing, and augmented reality made them rise to pillars of the fourth industrial revolution. This short paper aims to provide a brief survey of current use cases in factory applications and industrial inspection under active development at the Signals and Images Lab, ISTI-CNR, Pisa.Source: Ital-IA 2022 - Convegno nazionale CINI sull'Intelligenza Artificiale, Torino, Italy, 9-11/02/2022
DOI: 10.5281/zenodo.6322733
Metrics:
See at:
ISTI Repository | CNR ExploRA | www.ital-ia2022.it
2022
Conference article
Open Access
Exploring UAVs for structural health monitoring
Germanese D., Moroni D., Pascali M. A., 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.Source: D-SITe 2022 - Drones. Systems of Information on culTural hEritage. For a spatial and social investigation, pp. 640–643, Pavia, Italy, 16-18/06/2022
Germanese D., Moroni D., Pascali M. A., 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.Source: D-SITe 2022 - Drones. Systems of Information on culTural hEritage. For a spatial and social investigation, pp. 640–643, Pavia, Italy, 16-18/06/2022
See at:
ISTI Repository | CNR ExploRA | www.dsiteconference.com
2022
Contribution to book
Open Access
On the effectiveness of 3D vision transformers for the prediction of prostate cancer aggressiveness
Pachetti E., Colantonio S., Pascali M. A.
Prostate cancer is the most frequent male neoplasm in European men. To date, the gold standard for determining the aggressiveness of this tumor is the biopsy, an invasive and uncomfortable procedure. Before the biopsy, physicians recommend an investigation by multiparametric magnetic resonance imaging, which may serve the radiologist to gather an initial assessment of the tumor. The study presented in this work aims to investigate the role of Vision Transformers in predicting prostate cancer aggressiveness based only on imaging data. We designed a 3D Vision Transformer able to process volumetric scans, and we optimized it on the ProstateX-2 challenge dataset by training it from scratch. As a term of comparison, we also designed a 3D Convolutional Neural Network, and we optimized it in a similar fashion. The results obtained by our preliminary investigations show that Vision Transformers, even without extensive optimization and customization, can ensure an improved performance with respect to Convolutional Neural Networks and might be comparable with other more fine-tuned solutions.Source: Image Analysis and Processing, edited by Mazzeo P.L., Frontoni E., Sclaroff S., Distante C., pp. 317–328. Switzerland: Springer International Publishing, 2022
DOI: 10.1007/978-3-031-13324-4_27
Project(s): ProCAncer-I
Metrics:
Pachetti E., Colantonio S., Pascali M. A.
Prostate cancer is the most frequent male neoplasm in European men. To date, the gold standard for determining the aggressiveness of this tumor is the biopsy, an invasive and uncomfortable procedure. Before the biopsy, physicians recommend an investigation by multiparametric magnetic resonance imaging, which may serve the radiologist to gather an initial assessment of the tumor. The study presented in this work aims to investigate the role of Vision Transformers in predicting prostate cancer aggressiveness based only on imaging data. We designed a 3D Vision Transformer able to process volumetric scans, and we optimized it on the ProstateX-2 challenge dataset by training it from scratch. As a term of comparison, we also designed a 3D Convolutional Neural Network, and we optimized it in a similar fashion. The results obtained by our preliminary investigations show that Vision Transformers, even without extensive optimization and customization, can ensure an improved performance with respect to Convolutional Neural Networks and might be comparable with other more fine-tuned solutions.Source: Image Analysis and Processing, edited by Mazzeo P.L., Frontoni E., Sclaroff S., Distante C., pp. 317–328. Switzerland: Springer International Publishing, 2022
DOI: 10.1007/978-3-031-13324-4_27
Project(s): ProCAncer-I
Metrics:
See at:
ISTI Repository | link.springer.com 
| CNR ExploRA
2022
Journal article
Open Access
A topological machine learning pipeline for classification
Conti F., Moroni D., Pascali M. A.
In this work, we develop a pipeline that associates Persistence Diagrams to digital data via the most appropriate filtration for the type of data considered. Using a grid search approach, this pipeline determines optimal representation methods and parameters. The development of such a topological pipeline for Machine Learning involves two crucial steps that strongly affect its performance: firstly, digital data must be represented as an algebraic object with a proper associated filtration in order to compute its topological summary, the Persistence Diagram. Secondly, the persistence diagram must be transformed with suitable representation methods in order to be introduced in a Machine Learning algorithm. We assess the performance of our pipeline, and in parallel, we compare the different representation methods on popular benchmark datasets. This work is a first step toward both an easy and ready-to-use pipeline for data classification using persistent homology and Machine Learning, and to understand the theoretical reasons why, given a dataset and a task to be performed, a pair (filtration, topological representation) is better than another.Source: Mathematics 10 (2022). doi:10.3390/math10173086
DOI: 10.3390/math10173086
Metrics:
Conti F., Moroni D., Pascali M. A.
In this work, we develop a pipeline that associates Persistence Diagrams to digital data via the most appropriate filtration for the type of data considered. Using a grid search approach, this pipeline determines optimal representation methods and parameters. The development of such a topological pipeline for Machine Learning involves two crucial steps that strongly affect its performance: firstly, digital data must be represented as an algebraic object with a proper associated filtration in order to compute its topological summary, the Persistence Diagram. Secondly, the persistence diagram must be transformed with suitable representation methods in order to be introduced in a Machine Learning algorithm. We assess the performance of our pipeline, and in parallel, we compare the different representation methods on popular benchmark datasets. This work is a first step toward both an easy and ready-to-use pipeline for data classification using persistent homology and Machine Learning, and to understand the theoretical reasons why, given a dataset and a task to be performed, a pair (filtration, topological representation) is better than another.Source: Mathematics 10 (2022). doi:10.3390/math10173086
DOI: 10.3390/math10173086
Metrics:
See at:
ISTI Repository | CNR ExploRA | www.mdpi.com
2022
Conference article
Restricted
On the applicability of prototypical part learning in medical images: breast masses classification using ProtoPNet
Carloni G., Berti A., Iacconi C., Pascali M. A., Colantonio S.
Deep learning models have become state-of-the-art in many areas, ranging from computer vision to agriculture research. However, concerns have been raised with respect to the transparency of their decisions, especially in the image domain. In this regard, Explainable Artificial Intelligence has been gaining popularity in recent years. The ProtoPNet model, which breaks down an image into prototypes and uses evidence gathered from the prototypes to classify an image, represents an appealing approach. Still, questions regarding its effectiveness arise when the application domain changes from real-world natural images to gray-scale medical images. This work explores the applicability of prototypical part learning in medical imaging by experimenting with ProtoPNet on a breast masses classification task. The two considered aspects were the classification capabilities and the validity of explanations. We looked for the optimal model's hyperparameter configuration via a random search. We trained the model in a five-fold CV supervised framework, with mammogram images cropped around the lesions and ground-truth labels of benign/malignant masses. Then, we compared the performance metrics of ProtoPNet to that of the corresponding base architecture, which was ResNet18, trained under the same framework. In addition, an experienced radiologist provided a clinical viewpoint on the quality of the learned prototypes, the patch activations, and the global explanations. We achieved a Recall of 0.769 and an area under the receiver operating characteristic curve of 0.719 in our experiments. Even though our findings are non-optimal for entering the clinical practice yet, the radiologist found ProtoPNet's explanations very intuitive, reporting a high level of satisfaction. Therefore, we believe that prototypical part learning offers a reasonable and promising trade-off between classification performance and the quality of the related explanation.Source: ICPR 2022 - International Conference on Pattern Recognition - Artificial Intelligence for Healthcare Applications 2nd International Workshop, Montreal, Canada, 21-25/08/2022
Carloni G., Berti A., Iacconi C., Pascali M. A., Colantonio S.
Deep learning models have become state-of-the-art in many areas, ranging from computer vision to agriculture research. However, concerns have been raised with respect to the transparency of their decisions, especially in the image domain. In this regard, Explainable Artificial Intelligence has been gaining popularity in recent years. The ProtoPNet model, which breaks down an image into prototypes and uses evidence gathered from the prototypes to classify an image, represents an appealing approach. Still, questions regarding its effectiveness arise when the application domain changes from real-world natural images to gray-scale medical images. This work explores the applicability of prototypical part learning in medical imaging by experimenting with ProtoPNet on a breast masses classification task. The two considered aspects were the classification capabilities and the validity of explanations. We looked for the optimal model's hyperparameter configuration via a random search. We trained the model in a five-fold CV supervised framework, with mammogram images cropped around the lesions and ground-truth labels of benign/malignant masses. Then, we compared the performance metrics of ProtoPNet to that of the corresponding base architecture, which was ResNet18, trained under the same framework. In addition, an experienced radiologist provided a clinical viewpoint on the quality of the learned prototypes, the patch activations, and the global explanations. We achieved a Recall of 0.769 and an area under the receiver operating characteristic curve of 0.719 in our experiments. Even though our findings are non-optimal for entering the clinical practice yet, the radiologist found ProtoPNet's explanations very intuitive, reporting a high level of satisfaction. Therefore, we believe that prototypical part learning offers a reasonable and promising trade-off between classification performance and the quality of the related explanation.Source: ICPR 2022 - International Conference on Pattern Recognition - Artificial Intelligence for Healthcare Applications 2nd International Workshop, Montreal, Canada, 21-25/08/2022
See at:
CNR ExploRA
2022
Conference article
Open Access
Data models for an imaging bio-bank for colorectal, prostate and gastric cancer: the NAVIGATOR project
Berti A., Carloni G., Colantonio S., Pascali M. A., Manghi P., Pagano P., Buongiorno R., Pachetti E., Caudai C., Di Gangi D., Carlini E., Falaschi Z., Ciarrocchi E., Neri E., Bertelli E., Miele V., Carpi R., Bagnacci G., Di Meglio N., Mazzei M. A., Barucci A.
Researchers nowadays may take advantage of broad collections of medical data to develop personalized medicine solutions. Imaging bio-banks play a fundamental role, in this regard, by serving as organized repositories of medical images associated with imaging biomarkers. In this context, the NAVIGATOR Project aims to advance colorectal, prostate, and gastric oncology translational research by leveraging quantitative imaging and multi-omics analyses. As Project's core, an imaging bio-bank is being designed and implemented in a web-accessible Virtual Research Environment (VRE). The VRE serves to extract the imaging biomarkers and further process them within prediction algorithms. In our work, we present the realization of the data models for the three cancer use-cases of the Project. First, we carried out an extensive requirements analysis to fulfill the necessities of the clinical partners involved in the Project. Then, we designed three separate data models utilizing entity-relationship diagrams. We found diagrams' modeling for colorectal and prostate cancers to be more straightforward, while gastric cancer required a higher level of complexity. Future developments of this work would include designing a common data model following the Observational Medical Outcomes Partnership Standards. Indeed, a common data model would standardize the logical infrastructure of data models and make the bio-bank easily interoperable with other bio-banks.Source: BHI '22 - IEEE-EMBS International Conference on Biomedical and Health Informatics, Ioannina, Greece, 27-30/09/2022
DOI: 10.1109/bhi56158.2022.9926910
Metrics:
Berti A., Carloni G., Colantonio S., Pascali M. A., Manghi P., Pagano P., Buongiorno R., Pachetti E., Caudai C., Di Gangi D., Carlini E., Falaschi Z., Ciarrocchi E., Neri E., Bertelli E., Miele V., Carpi R., Bagnacci G., Di Meglio N., Mazzei M. A., Barucci A.
Researchers nowadays may take advantage of broad collections of medical data to develop personalized medicine solutions. Imaging bio-banks play a fundamental role, in this regard, by serving as organized repositories of medical images associated with imaging biomarkers. In this context, the NAVIGATOR Project aims to advance colorectal, prostate, and gastric oncology translational research by leveraging quantitative imaging and multi-omics analyses. As Project's core, an imaging bio-bank is being designed and implemented in a web-accessible Virtual Research Environment (VRE). The VRE serves to extract the imaging biomarkers and further process them within prediction algorithms. In our work, we present the realization of the data models for the three cancer use-cases of the Project. First, we carried out an extensive requirements analysis to fulfill the necessities of the clinical partners involved in the Project. Then, we designed three separate data models utilizing entity-relationship diagrams. We found diagrams' modeling for colorectal and prostate cancers to be more straightforward, while gastric cancer required a higher level of complexity. Future developments of this work would include designing a common data model following the Observational Medical Outcomes Partnership Standards. Indeed, a common data model would standardize the logical infrastructure of data models and make the bio-bank easily interoperable with other bio-banks.Source: BHI '22 - IEEE-EMBS International Conference on Biomedical and Health Informatics, Ioannina, Greece, 27-30/09/2022
DOI: 10.1109/bhi56158.2022.9926910
Metrics:
See at:
ISTI Repository | ieeexplore.ieee.org | CNR ExploRA
2022
Contribution to journal
Open Access
On some scientific results of the IMTA-VIII-2022: 8th International Workshop "Image Mining: Theory and Applications"
Gurevich I. B., Moroni D., Pascali M. A., Yashina V. V.
Source: Pattern recognition and image analysis 32 (2022): 460–465. doi:10.1134/S1054661822030312
DOI: 10.1134/s1054661822030312
Metrics:
Gurevich I. B., Moroni D., Pascali M. A., Yashina V. V.
Source: Pattern recognition and image analysis 32 (2022): 460–465. doi:10.1134/S1054661822030312
DOI: 10.1134/s1054661822030312
Metrics:
See at:
link.springer.com | ISTI Repository | CNR ExploRA
2022
Report
Open Access
Studio e analisi delle architetture di reti convolutive
Moroni D., Papini O., Pascali M. A., Pieri G., Reggiannini M.
Questo rapporto tecnico di progetto è il risultato del contributo fornito dal Laboratorio Segnali e Immagini dell'ISTI-CNR per il documento di progetto RTOD-SYS-SDD-010-INT per il progetto RTOD (Real-Time Object Detection mediante Machine Learning basato su tecnologia Low-Power GPU). In particolare, il rapporto studia e discute delle varie possibilità di architetture di reti convolutive che sono state valutate e che potranno essere utilizzate nel contesto del progetto per effettuare delle categorizzazioni di immagini mediante algoritmi di machine learning.Source: ISTI Technical Report, ISTI-2022-TR/022, 2022
DOI: 10.32079/isti-tr-2022/022
Metrics:
Moroni D., Papini O., Pascali M. A., Pieri G., Reggiannini M.
Questo rapporto tecnico di progetto è il risultato del contributo fornito dal Laboratorio Segnali e Immagini dell'ISTI-CNR per il documento di progetto RTOD-SYS-SDD-010-INT per il progetto RTOD (Real-Time Object Detection mediante Machine Learning basato su tecnologia Low-Power GPU). In particolare, il rapporto studia e discute delle varie possibilità di architetture di reti convolutive che sono state valutate e che potranno essere utilizzate nel contesto del progetto per effettuare delle categorizzazioni di immagini mediante algoritmi di machine learning.Source: ISTI Technical Report, ISTI-2022-TR/022, 2022
DOI: 10.32079/isti-tr-2022/022
Metrics:
See at:
ISTI Repository | CNR ExploRA
2022
Report
Restricted
DEL-27: Nota tecnica sulle metodologie per la validazione di algoritmi di Machine Learning
D. Moroni, O. Papini, M. A. Pascali, G. Pieri, M. Reggiannini
La presente nota tecnica rappresenta l'output del work package 3102 dal titolo "Identificazione delle metodologie per la validazione di algoritmi di Machine Learning". L'obiettivo chiave è quello di identificare delle metodologie adatte alle reti neurali già studiate e proposte nel corso del progetto RTOD in modo da studiarne l'affidabilità e abilitarne il loro impiego anche in scenari operativi.Source: ISTI Project report, RTOD-TN-ML-027, 2022
D. Moroni, O. Papini, M. A. Pascali, G. Pieri, M. Reggiannini
La presente nota tecnica rappresenta l'output del work package 3102 dal titolo "Identificazione delle metodologie per la validazione di algoritmi di Machine Learning". L'obiettivo chiave è quello di identificare delle metodologie adatte alle reti neurali già studiate e proposte nel corso del progetto RTOD in modo da studiarne l'affidabilità e abilitarne il loro impiego anche in scenari operativi.Source: ISTI Project report, RTOD-TN-ML-027, 2022
See at:
CNR ExploRA
2022
Journal article
Open Access
NAVIGATOR: an Italian regional imaging biobank to promote precision medicine for oncologic patients
Borgheresi R., Barucci A., Colantonio S., Aghakhanyan G., Assante M., Bertelli E., Carlini E., Carpi R., Caudai C., Cavallero D., Cioni D., Cirillo R., Colcelli V., Dell'Amico A., Di Gangi D., Erba P. A., Faggioni L., Falaschi Z., Gabelloni M., Gini R., Lelii L., Liò P., Lorito A., Lucarini S., Manghi P., Mangiacrapa F., Marzi C., Mazzei M. A., Mercatelli L., Mirabile A., Mungai F., Miele V., Olmastroni M., Pagano P., Paiar F., Panichi G., Pascali M. A., Pasquinelli F., Shortrede J. E., Tumminello L., Volterrani L., Neri E., On Behalf Of The Navigator Consortium Group
NAVIGATOR is an Italian regional project to boost precision medicine in oncology with the aim to make it more predictive, preventive, and personalised by advancing translational research based on quantitative imaging and integrative omics analyses. The project's goal is to develop an open imaging biobank for the collection and preservation of a large amount of standardised imaging multimodal datasets, including computed tomography, magnetic resonance imaging, and positron emission tomography data, together with the corresponding patient-related and omics-related relevant information extracted from regional healthcare services using an adapted privacy-preserving model. The project is based on an open-source imaging biobank and an open-science oriented virtual research environment (VRE). Available integrative omics and multi-imaging data of three use cases (prostate cancer, rectal cancer, and gastric cancer) will be collected. All data confined in NAVIGATOR (i.e. standard and novel imaging biomarkers, non-imaging data, health agency data) will be used to create a digital patient model, to support the reliable prediction of the disease phenotype and risk stratification. The VRE that relies on a well-established infrastructure, called D4Science.org, will further provide a multiset infrastructure for processing the integrative omics data, extracting specific radiomic signatures, and for identification and testing of novel imaging biomarkers through big data analytics and artificial intelligence.Source: European radiology experimental Online 6 (2022). doi:10.1186/s41747-022-00306-9
DOI: 10.1186/s41747-022-00306-9
Metrics:
Borgheresi R., Barucci A., Colantonio S., Aghakhanyan G., Assante M., Bertelli E., Carlini E., Carpi R., Caudai C., Cavallero D., Cioni D., Cirillo R., Colcelli V., Dell'Amico A., Di Gangi D., Erba P. A., Faggioni L., Falaschi Z., Gabelloni M., Gini R., Lelii L., Liò P., Lorito A., Lucarini S., Manghi P., Mangiacrapa F., Marzi C., Mazzei M. A., Mercatelli L., Mirabile A., Mungai F., Miele V., Olmastroni M., Pagano P., Paiar F., Panichi G., Pascali M. A., Pasquinelli F., Shortrede J. E., Tumminello L., Volterrani L., Neri E., On Behalf Of The Navigator Consortium Group
NAVIGATOR is an Italian regional project to boost precision medicine in oncology with the aim to make it more predictive, preventive, and personalised by advancing translational research based on quantitative imaging and integrative omics analyses. The project's goal is to develop an open imaging biobank for the collection and preservation of a large amount of standardised imaging multimodal datasets, including computed tomography, magnetic resonance imaging, and positron emission tomography data, together with the corresponding patient-related and omics-related relevant information extracted from regional healthcare services using an adapted privacy-preserving model. The project is based on an open-source imaging biobank and an open-science oriented virtual research environment (VRE). Available integrative omics and multi-imaging data of three use cases (prostate cancer, rectal cancer, and gastric cancer) will be collected. All data confined in NAVIGATOR (i.e. standard and novel imaging biomarkers, non-imaging data, health agency data) will be used to create a digital patient model, to support the reliable prediction of the disease phenotype and risk stratification. The VRE that relies on a well-established infrastructure, called D4Science.org, will further provide a multiset infrastructure for processing the integrative omics data, extracting specific radiomic signatures, and for identification and testing of novel imaging biomarkers through big data analytics and artificial intelligence.Source: European radiology experimental Online 6 (2022). doi:10.1186/s41747-022-00306-9
DOI: 10.1186/s41747-022-00306-9
Metrics:
See at:
eurradiolexp.springeropen.com | ISTI Repository | CNR ExploRA
2022
Report
Open Access
SI-Lab annual research report 2021
Righi M., Leone G. R., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Berti A., Bruno A., Buongiorno R., Carloni G., Conti F., Germanese D., Ignesti G., Matarese F., Omrani A., Pachetti E., Papini O., Benassi A., Bertini G., Coltelli P., Tarabella L., Straface S., Salvetti O., Moroni D.
The Signal & Images Laboratory is an interdisciplinary research group in computer vision, signal analysis, intelligent vision systems and multimedia data understanding. It is part of the Institute of Information Science and Technologies (ISTI) of the National Research Council of Italy (CNR). This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2021.Source: ISTI Annual reports, 2022
DOI: 10.32079/isti-ar-2022/003
Metrics:
Righi M., Leone G. R., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Berti A., Bruno A., Buongiorno R., Carloni G., Conti F., Germanese D., Ignesti G., Matarese F., Omrani A., Pachetti E., Papini O., Benassi A., Bertini G., Coltelli P., Tarabella L., Straface S., Salvetti O., Moroni D.
The Signal & Images Laboratory is an interdisciplinary research group in computer vision, signal analysis, intelligent vision systems and multimedia data understanding. It is part of the Institute of Information Science and Technologies (ISTI) of the National Research Council of Italy (CNR). This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2021.Source: ISTI Annual reports, 2022
DOI: 10.32079/isti-ar-2022/003
Metrics:
See at:
ISTI Repository | CNR ExploRA
2022
Restricted
Studio PINK - Protocollo di studio per la linea di ricerca su Imaging e Radiomica
Pieroni S., Franchini M., Salvatori M., Anastasi G., Colantonio S., Pascali M. A., Trombadori C., Palma S., Belli P., Nicolucci A.
L'approccio personalizzato a prevenzione, diagnosi e cura rappresenta il caposaldo della medicina di precisione e si integra, come elemento fondante, nella medicina multiomica, l'ultima frontiera delle scienze mediche. Si tratta di un approccio basato sulla modellazione delle caratteristiche dei singoli e della variabilità di queste, in contrapposizione all'approccio classico basato su protocolli generalizzati ricavati da valutazioni (medie) su intere popolazioni. Seguire un approccio personalizzato presuppone la necessità di integrare dati eterogenei su singolo paziente con un intento olistico (e.g., dati clinici, stile di vita, alimentazione, esposizione ambientali ecc.), e possibilmente in un'ottica omica (i.e., attraverso tecnologie di analisi che consentono la produzione di informazioni/dati, in numero molto elevato e nel tempo, per la descrizione e l'interpretazione di processi o sistemi). Il disegno dello studio PINK è coerente con questa impostazione, consapevole dell'enorme potenziale che i dati e le informazioni raccolte fino ad oggi abbiano per la ricerca sul cancro al seno. In questo contesto, il tavolo di approfondimento su imaging e radiomica si colloca come un elemento centrale per la creazione di un ambiente di ricerca che, integrando i dati provenienti dalla piattaforma di inserimento implementata dall'impianto principale dello studio PINK, i dati di imaging e i questionari sullo stile vita, permetterà, attraverso differenti metodi di analisi (e.g., tecniche di analisi di immagini, Big Data analytics e intelligenza artificiale) di perseguire molteplici scenari di approfondimento relativi all'intero processo patologico del tumore mammario, dalla stima del rischio individuale, alla diagnosi precoce fino al monitoraggio della evoluzione della malattia.
Pieroni S., Franchini M., Salvatori M., Anastasi G., Colantonio S., Pascali M. A., Trombadori C., Palma S., Belli P., Nicolucci A.
L'approccio personalizzato a prevenzione, diagnosi e cura rappresenta il caposaldo della medicina di precisione e si integra, come elemento fondante, nella medicina multiomica, l'ultima frontiera delle scienze mediche. Si tratta di un approccio basato sulla modellazione delle caratteristiche dei singoli e della variabilità di queste, in contrapposizione all'approccio classico basato su protocolli generalizzati ricavati da valutazioni (medie) su intere popolazioni. Seguire un approccio personalizzato presuppone la necessità di integrare dati eterogenei su singolo paziente con un intento olistico (e.g., dati clinici, stile di vita, alimentazione, esposizione ambientali ecc.), e possibilmente in un'ottica omica (i.e., attraverso tecnologie di analisi che consentono la produzione di informazioni/dati, in numero molto elevato e nel tempo, per la descrizione e l'interpretazione di processi o sistemi). Il disegno dello studio PINK è coerente con questa impostazione, consapevole dell'enorme potenziale che i dati e le informazioni raccolte fino ad oggi abbiano per la ricerca sul cancro al seno. In questo contesto, il tavolo di approfondimento su imaging e radiomica si colloca come un elemento centrale per la creazione di un ambiente di ricerca che, integrando i dati provenienti dalla piattaforma di inserimento implementata dall'impianto principale dello studio PINK, i dati di imaging e i questionari sullo stile vita, permetterà, attraverso differenti metodi di analisi (e.g., tecniche di analisi di immagini, Big Data analytics e intelligenza artificiale) di perseguire molteplici scenari di approfondimento relativi all'intero processo patologico del tumore mammario, dalla stima del rischio individuale, alla diagnosi precoce fino al monitoraggio della evoluzione della malattia.
See at:
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 | CNR ExploRA | link.springer.com
2021
Report
Open Access
SI-Lab Annual Research Report 2020
Leone G. R., Righi M., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Buongiorno R., Bruno A., Germanese D., Matarese F., Coscetti S., Coltelli P., Jalil B., Benassi A., Bertini G., Salvetti O., Moroni D.
The Signal & Images Laboratory (http://si.isti.cnr.it/) is an interdisciplinary research group in computer vision, signal analysis, smart vision systems and multimedia data understanding. It is part of the Institute for Information Science and Technologies of the National Research Council of Italy. This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2020.Source: ISTI Annual Report, ISTI-2021-AR/001, pp.1–38, 2021
DOI: 10.32079/isti-ar-2021/001
Metrics:
Leone G. R., Righi M., Carboni A., Caudai C., Colantonio S., Kuruoglu E. E., Leporini B., Magrini M., Paradisi P., Pascali M. A., Pieri G., Reggiannini M., Salerno E., Scozzari A., Tonazzini A., Fusco G., Galesi G., Martinelli M., Pardini F., Tampucci M., Buongiorno R., Bruno A., Germanese D., Matarese F., Coscetti S., Coltelli P., Jalil B., Benassi A., Bertini G., Salvetti O., Moroni D.
The Signal & Images Laboratory (http://si.isti.cnr.it/) is an interdisciplinary research group in computer vision, signal analysis, smart vision systems and multimedia data understanding. It is part of the Institute for Information Science and Technologies of the National Research Council of Italy. This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2020.Source: ISTI Annual Report, ISTI-2021-AR/001, pp.1–38, 2021
DOI: 10.32079/isti-ar-2021/001
Metrics:
See at:
ISTI Repository | CNR ExploRA
2021
Journal 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 characterized 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: Pattern recognition and image analysis 31 (2021): 443–453. doi:10.1134/S1054661821030184
DOI: 10.1134/s1054661821030184
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 characterized 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: Pattern recognition and image analysis 31 (2021): 443–453. doi:10.1134/S1054661821030184
DOI: 10.1134/s1054661821030184
Metrics:
See at:
ISTI Repository | link.springer.com | CNR ExploRA
2021
Conference article
Restricted
A deep learning approach for hepatic steatosis estimation from ultrasound imaging
Colantonio S., Salvati A., Caudai C., Bonino F., De Rosa L., Pascali M. A., Germanese D., Brunetto M. R., 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: ICCCI 2021 - 13th International Conference on Computational Collective Intelligence, pp. 703–714, Rhodes, Greece, 29/09/2021,1/10/ 2021
DOI: 10.1007/978-3-030-88113-9_57
Metrics:
Colantonio S., Salvati A., Caudai C., Bonino F., De Rosa L., Pascali M. A., Germanese D., Brunetto M. R., 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: ICCCI 2021 - 13th International Conference on Computational Collective Intelligence, pp. 703–714, Rhodes, Greece, 29/09/2021,1/10/ 2021
DOI: 10.1007/978-3-030-88113-9_57
Metrics:
See at:
link.springer.com | CNR ExploRA
2021
Contribution to journal
Open Access
On some scientific results of the ICPR-2020
Gurevich I. B., Moroni D., Pascali M. A., Yashina V. V.
Source: Pattern recognition and image analysis 31 (2021): 357–363. doi:10.1134/S1054661821030093
DOI: 10.1134/s1054661821030093
Metrics:
Gurevich I. B., Moroni D., Pascali M. A., Yashina V. V.
Source: Pattern recognition and image analysis 31 (2021): 357–363. doi:10.1134/S1054661821030093
DOI: 10.1134/s1054661821030093
Metrics:
See at:
link.springer.com | ISTI Repository | CNR ExploRA | Pattern Recognition and Image Analysis | Pattern Recognition and Image Analysis
2021
Conference article
Open Access
Discriminating stress from cognitive load using contactless thermal imaging devices
Gioia F., Pascali M. A., Greco A., Colantonio S., Scilingo E. P.
This study proposes long wave infrared technology as a contactless alternative to wearable devices for stress detection. To this aim, we studied the change in facial thermal distribution of 17 healthy subjects in response to different stressors (Stroop Test, Mental Arithmetic Test). During the experimental sessions the electrodermal activity (EDA) and the facial thermal response were simultaneously recorded from each subject. It is well known from the literature that EDA can be considered a reliable marker for the psychological state variation, therefore we used it as a reference signal to validate the thermal results. Statistical analysis was performed to evaluate significant differences in the thermal features between stress and non-stress conditions, as well as between stress and cognitive load. Our results are in line with the outcomes of previous studies and show significant differences in the temperature trends over time between stress and resting conditions. As a new result, we found that the mean temperature changes of some less studied facial regions, e.g., the right cheek, are able not only to significantly discriminate between resting and stressful conditions, but also allow to recognize the typology of stressors. This outcome not only directs future studies to consider the thermal patterns of less explored facial regions as possible correlates of mental states, but more importantly it suggests that different psychological states could potentially be discriminated in a contactless manner.Source: EMBC 2021 - 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 608–611, Online Conference, 30/10/2021, 5/11/2021
DOI: 10.1109/embc46164.2021.9630860
Metrics:
Gioia F., Pascali M. A., Greco A., Colantonio S., Scilingo E. P.
This study proposes long wave infrared technology as a contactless alternative to wearable devices for stress detection. To this aim, we studied the change in facial thermal distribution of 17 healthy subjects in response to different stressors (Stroop Test, Mental Arithmetic Test). During the experimental sessions the electrodermal activity (EDA) and the facial thermal response were simultaneously recorded from each subject. It is well known from the literature that EDA can be considered a reliable marker for the psychological state variation, therefore we used it as a reference signal to validate the thermal results. Statistical analysis was performed to evaluate significant differences in the thermal features between stress and non-stress conditions, as well as between stress and cognitive load. Our results are in line with the outcomes of previous studies and show significant differences in the temperature trends over time between stress and resting conditions. As a new result, we found that the mean temperature changes of some less studied facial regions, e.g., the right cheek, are able not only to significantly discriminate between resting and stressful conditions, but also allow to recognize the typology of stressors. This outcome not only directs future studies to consider the thermal patterns of less explored facial regions as possible correlates of mental states, but more importantly it suggests that different psychological states could potentially be discriminated in a contactless manner.Source: EMBC 2021 - 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 608–611, Online Conference, 30/10/2021, 5/11/2021
DOI: 10.1109/embc46164.2021.9630860
Metrics:
See at:
ISTI Repository | ieeexplore.ieee.org | CNR ExploRA