Matheus Alberto de Oliveira Ribeiro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Matheus Alberto de Oliveira Ribeiro has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Fátima Lourdes Santos Nunes
Each - USP
6 shared publications Fátima L. S. Nunes
4 shared publicationsVagner Mendonça Gonçalves
Escola de Artes Ciências e Humanidades Laboratory of Computer Applications for Health Care Universidade de São Paulo Rua Arlindo Bettio 1000 03828-000 São Paulo -SP Brazil
3 shared publicationsFatima L. S. Nunes
2 shared publications- Marco Antonio Gutierrez
Instituto do Coração do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo, Brasil
2 shared publications Stephani S. H. Costa
Escola de Artes Ciências e Humanidades Laboratory of Computer Applications for Health Care Universidade de São Paulo Rua Arlindo Bettio 1000 03828-000 São Paulo -SP Brazil
2 shared publications
Latest Publications
- 22 April 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-20
Using Radiomic Features to Detect Anatomical Errors and Assess Deep Learning-Based Left Ventricle Segmentation in Cardiac MRI
Segmentation of the left ventricle in cardiac magnetic resonance exams is critical for accurate diagnosis and plays a central role in computer-aided diagnosis systems. Among the various automatic methods proposed, deep learning-based approaches have demonstrated promising results, often achieving segmentation quality comparable to that of expert annotations. However, a significant limitation of these methods is their susceptibility to anatomical inconsistencies that may occur arbitrarily and remain undetected by conventional evaluation metrics, thereby compromising clinical interpretation. To address this issue, we explore a novel use of Radiomics to assess the anatomical quality of deep learning segmentations. Specifically, we extract radiomic features from deep learning-based left ventricle segmentations and use them to train machine learning classifiers aimed at identifying segmentations with anatomical errors. We perform extensive cross-validation experiments on five public and one private datasets and analyze classification performance considering different severity levels of anatomical errors. Experimental results indicate that the proposed radiomic-based classifiers achieved very high classification performance (Accuracy, Recall, and Specificity > 95% in most cases). The classifiers were able to detect errors (Recall > 80%) even in less severe cases, where standard metrics such as the Dice similarity coefficient indicate good segmentation quality (Dice > 0.8). Inter-dataset analysis indicates high generalization ability (F1-score > 0.8) and applicability on data from different clinical settings. The results demonstrate that radiomic-based classifiers can be reliably used for automatically detecting anatomical errors in segmentations, reducing the need for ground truth annotations and offering an alternative for quality control assessment of segmentation approaches.
- 22 April 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-20
Using Radiomic Features to Detect Anatomical Errors and Assess Deep Learning-Based Left Ventricle Segmentation in Cardiac MRI
Segmentation of the left ventricle in cardiac magnetic resonance exams is critical for accurate diagnosis and plays a central role in computer-aided diagnosis systems. Among the various automatic methods proposed, deep learning-based approaches have demonstrated promising results, often achieving segmentation quality comparable to that of expert annotations. However, a significant limitation of these methods is their susceptibility to anatomical inconsistencies that may occur arbitrarily and remain undetected by conventional evaluation metrics, thereby compromising clinical interpretation. To address this issue, we explore a novel use of Radiomics to assess the anatomical quality of deep learning segmentations. Specifically, we extract radiomic features from deep learning-based left ventricle segmentations and use them to train machine learning classifiers aimed at identifying segmentations with anatomical errors. We perform extensive cross-validation experiments on five public and one private datasets and analyze classification performance considering different severity levels of anatomical errors. Experimental results indicate that the proposed radiomic-based classifiers achieved very high classification performance (Accuracy, Recall, and Specificity > 95% in most cases). The classifiers were able to detect errors (Recall > 80%) even in less severe cases, where standard metrics such as the Dice similarity coefficient indicate good segmentation quality (Dice > 0.8). Inter-dataset analysis indicates high generalization ability (F1-score > 0.8) and applicability on data from different clinical settings. The results demonstrate that radiomic-based classifiers can be reliably used for automatically detecting anatomical errors in segmentations, reducing the need for ground truth annotations and offering an alternative for quality control assessment of segmentation approaches.
- 28 November 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 200, 111337
Sequential and ensemble hybrid approaches for left ventricle segmentation in cardiac MR: A systematic mapping
- 28 November 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 200, 111337
Sequential and ensemble hybrid approaches for left ventricle segmentation in cardiac MR: A systematic mapping
- Open Access
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 67-72
Investigating Cardiac Magnetic Resonance Imaging Feature Descriptors for Generalization of Cardiomyopathy Classification Models
Supervised Machine Learning (SML) models can help physicians to compose more accurate diagnoses. Due to the diversity of machines, systems, and protocols, exams conducted at different centers may have high variability, decreasing the model generalization ability. This paper aims to evaluate generalization ability of SML models for cardiomyopathy classification in Cardiac Magnetic Resonance Imaging (CMRI), using a set of left ventricle morphological and motion features. We performed cross-validation tests on two public CMRI databases, comparing intraand inter-dataset performances. The results are promising and demonstrate that the implemented features can contribute to building generalizable classification models.
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 67-72
Open AccessInvestigating Cardiac Magnetic Resonance Imaging Feature Descriptors for Generalization of Cardiomyopathy Classification Models
Supervised Machine Learning (SML) models can help physicians to compose more accurate diagnoses. Due to the diversity of machines, systems, and protocols, exams conducted at different centers may have high variability, decreasing the model generalization ability. This paper aims to evaluate generalization ability of SML models for cardiomyopathy classification in Cardiac Magnetic Resonance Imaging (CMRI), using a set of left ventricle morphological and motion features. We performed cross-validation tests on two public CMRI databases, comparing intraand inter-dataset performances. The results are promising and demonstrate that the implemented features can contribute to building generalizable classification models.
- Open Access
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 943-954
Generalization of Cardiomyopathy Classification Models Based on Feature Descriptors from Magnetic Resonance Imaging
Supervised Machine Learning (SML) models can help physicians to compose more accurate diagnoses. Due to the diversity of machines, systems, and protocols, exams conducted at different centers may have high variability, decreasing the generalization ability of these models. This paper aims to evaluate generalization ability of SML models for cardiomyopathy classification in Cardiac Magnetic Resonance Imaging (CMRI), using a set of left ventricle morphological and motion features. We performed cross-validation tests on two public CMRI databases, comparing intraand inter-dataset performances. The results are promising and demonstrate that the implemented features can contribute to building generalizable classification models.
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 943-954
Open AccessGeneralization of Cardiomyopathy Classification Models Based on Feature Descriptors from Magnetic Resonance Imaging
Supervised Machine Learning (SML) models can help physicians to compose more accurate diagnoses. Due to the diversity of machines, systems, and protocols, exams conducted at different centers may have high variability, decreasing the generalization ability of these models. This paper aims to evaluate generalization ability of SML models for cardiomyopathy classification in Cardiac Magnetic Resonance Imaging (CMRI), using a set of left ventricle morphological and motion features. We performed cross-validation tests on two public CMRI databases, comparing intraand inter-dataset performances. The results are promising and demonstrate that the implemented features can contribute to building generalizable classification models.
- Open Access
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 79-84
A Prototype for Interactive Information Visualization as Support for Computer-Aided Diagnosis
Computer-Aided Diagnosis (CAD) can offer a second opinion to help physicians compose a more precise diagnosis, and interactive Information Visualization (IV) tools can complement CAD systems by providing a more intuitive way to interpret data from patients and exams. In this study, we developed an interactive IV prototype to improve comprehension of a flexible database for a CAD system in the cardiomyopathies context. This prototype is integrated with a web application to retrieve Cardiac Magnetic Resonance exams, and a qualitative evaluation conducted with health professionals showed that IV provided valuable data analysis capability. The results have shown that the integration of advanced visualization tools in our developed prototype can enhance clinical decision-making, improving the effectiveness of CAD systems.
- 9 June 2025
- Published by Sociedade Brasileira de Computação
- p. 79-84
Open AccessA Prototype for Interactive Information Visualization as Support for Computer-Aided Diagnosis
Computer-Aided Diagnosis (CAD) can offer a second opinion to help physicians compose a more precise diagnosis, and interactive Information Visualization (IV) tools can complement CAD systems by providing a more intuitive way to interpret data from patients and exams. In this study, we developed an interactive IV prototype to improve comprehension of a flexible database for a CAD system in the cardiomyopathies context. This prototype is integrated with a web application to retrieve Cardiac Magnetic Resonance exams, and a qualitative evaluation conducted with health professionals showed that IV provided valuable data analysis capability. The results have shown that the integration of advanced visualization tools in our developed prototype can enhance clinical decision-making, improving the effectiveness of CAD systems.
- 21 April 2023
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 142, 104366
Left ventricle segmentation combining deep learning and deformable models with anatomical constraints
- 21 April 2023
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 142, 104366
Left ventricle segmentation combining deep learning and deformable models with anatomical constraints
- 16 May 2022
- Published by Sociedade Brasileira de Computação
- p. 113-126
Segmentação do ventrículo esquerdo em exames de Ressonância Magnética Cardíaca com aprendizado profundo e modelos deformáveis contendo restrições de forma
Sistemas de Informação estão evoluindo para processar dados multimídia. A segmentação automática do ventrículo esquerdo em exames médicos para auxílio ao diagnóstico é um desafio multidisciplinar da área de Cardiologia. Diversas abordagens têm sido propostas, com destaque para redes de aprendizado profundo, que têm obtido excelente desempenho, mas ainda produzem segmentações com erros anatômicos. Considerando essa limitação, esse trabalho apresenta um método de segmentação híbrido que combina aprendizado profundo e modelos deformáveis com restrições de forma. A combinação favorece a produção de segmentações anatomicamente mais consistentes. Resultados indicam que o método é competitivo e oferece boa generalização.
- 16 May 2022
- Published by Sociedade Brasileira de Computação
- p. 113-126
Segmentação do ventrículo esquerdo em exames de Ressonância Magnética Cardíaca com aprendizado profundo e modelos deformáveis contendo restrições de forma
Sistemas de Informação estão evoluindo para processar dados multimídia. A segmentação automática do ventrículo esquerdo em exames médicos para auxílio ao diagnóstico é um desafio multidisciplinar da área de Cardiologia. Diversas abordagens têm sido propostas, com destaque para redes de aprendizado profundo, que têm obtido excelente desempenho, mas ainda produzem segmentações com erros anatômicos. Considerando essa limitação, esse trabalho apresenta um método de segmentação híbrido que combina aprendizado profundo e modelos deformáveis com restrições de forma. A combinação favorece a produção de segmentações anatomicamente mais consistentes. Resultados indicam que o método é competitivo e oferece boa generalização.
- Open Access
- 31 January 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 54 (11s) , 1-38
Left Ventricle Segmentation in Cardiac MR: A Systematic Mapping of the Past Decade
Left ventricle segmentation in short-axis cardiac magnetic resonance images is important to diagnose heart disease. However, repetitive manual segmentation of these images requires considerable human effort and can decrease diagnostic accuracy. In recent years, several fully and semi-automatic approaches have been proposed, mainly using image-based, atlas, graph, deformable model, and artificial intelligence methods. This article presents a systematic mapping on left ventricle segmentation, considering 74 studies published in the past decade. The main contributions of this review are definition of the main segmentation challenges in these images; proposal of a new schematization, dividing the segmentation process into stages; categorization and analysis of the segmentation methods, including hybrid combinations; and analysis of the evaluation process, metrics, and databases. The performance of the methods in the most used public database is assessed, and the main limitations, weaknesses, and strengths of each method category are presented. Finally, trends, challenges, and research opportunities are discussed. The analysis indicates that methods from all categories can achieve good performance, and hybrid methods combining deep learning and deformable models obtain the best results. Methods still fail in specific slices, segment wrong regions, and produce anatomically impossible segmentations.
- 31 January 2022
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 54 (11s) , 1-38
Open AccessLeft Ventricle Segmentation in Cardiac MR: A Systematic Mapping of the Past Decade
Left ventricle segmentation in short-axis cardiac magnetic resonance images is important to diagnose heart disease. However, repetitive manual segmentation of these images requires considerable human effort and can decrease diagnostic accuracy. In recent years, several fully and semi-automatic approaches have been proposed, mainly using image-based, atlas, graph, deformable model, and artificial intelligence methods. This article presents a systematic mapping on left ventricle segmentation, considering 74 studies published in the past decade. The main contributions of this review are definition of the main segmentation challenges in these images; proposal of a new schematization, dividing the segmentation process into stages; categorization and analysis of the segmentation methods, including hybrid combinations; and analysis of the evaluation process, metrics, and databases. The performance of the methods in the most used public database is assessed, and the main limitations, weaknesses, and strengths of each method category are presented. Finally, trends, challenges, and research opportunities are discussed. The analysis indicates that methods from all categories can achieve good performance, and hybrid methods combining deep learning and deformable models obtain the best results. Methods still fail in specific slices, segment wrong regions, and produce anatomically impossible segmentations.
- 9 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3505-3512
Evaluating the pre-processing impact on the generalization of deep learning networks for left ventricle segmentation
Deep learning networks have obtained promising results for left ventricle segmentation in magnetic resonance images. Training with datasets containing low diversity of examples impacts the generalization ability of these networks, which is a problem in the medical image context. Strategies such as data augmentation and post-processing techniques have been applied to improve learning and generalization, but the influence of pre-processing methods is still underexplored. This work aims to evaluate the impact of pre-processing steps on the generalization of deep learning networks for left ventricle segmentation. Experiments were conducted with public datasets considering different configurations of pre-processing steps. We also compare a novel approach for automatic region of interest (ROI) detection in relation to manual approaches. The results suggest that pre-processing procedures favor the generalization, even when other strategies are not present. New methods to detect the ROI with size invariability are promising to obtain adequate generalization ability in deep learning networks.
- 9 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3505-3512
Evaluating the pre-processing impact on the generalization of deep learning networks for left ventricle segmentation
Deep learning networks have obtained promising results for left ventricle segmentation in magnetic resonance images. Training with datasets containing low diversity of examples impacts the generalization ability of these networks, which is a problem in the medical image context. Strategies such as data augmentation and post-processing techniques have been applied to improve learning and generalization, but the influence of pre-processing methods is still underexplored. This work aims to evaluate the impact of pre-processing steps on the generalization of deep learning networks for left ventricle segmentation. Experiments were conducted with public datasets considering different configurations of pre-processing steps. We also compare a novel approach for automatic region of interest (ROI) detection in relation to manual approaches. The results suggest that pre-processing procedures favor the generalization, even when other strategies are not present. New methods to detect the ROI with size invariability are promising to obtain adequate generalization ability in deep learning networks.
- Open Access
- 8 November 2020
- Published by Universidade Federal da Paraíba in Comunicações em Informática
- Vol. 4 (2) , 39-42
Virtual Reality, Augmented Reality and Beyond: Laboratory of Computer Applications for Health Care at University of São Paulo
The Laboratory of Computer Applications for Health Care at University of São Paulo develop multidisciplinary research involving Computer Science areas and other knowledge fields such as Physiotherapy, Psychiatry, Radiology, and Cardiology. Most studies use concepts besides Computer Science, by aggregating knowledge to solve real problems. In this paper we present the main projects in Virtual Reality and Augmented Reality areas, highlighting serious games, computer-aided diagnosis and therapy, simulation and training. Besides the social and scientific impact inherent to the type of the developed research, some systems are available to health professionals in order to allow technology transfer and consequent technological and economic impact in daily activities of health tasks.
- 8 November 2020
- Published by Universidade Federal da Paraíba in Comunicações em Informática
- Vol. 4 (2) , 39-42
Open AccessVirtual Reality, Augmented Reality and Beyond: Laboratory of Computer Applications for Health Care at University of São Paulo
The Laboratory of Computer Applications for Health Care at University of São Paulo develop multidisciplinary research involving Computer Science areas and other knowledge fields such as Physiotherapy, Psychiatry, Radiology, and Cardiology. Most studies use concepts besides Computer Science, by aggregating knowledge to solve real problems. In this paper we present the main projects in Virtual Reality and Augmented Reality areas, highlighting serious games, computer-aided diagnosis and therapy, simulation and training. Besides the social and scientific impact inherent to the type of the developed research, some systems are available to health professionals in order to allow technology transfer and consequent technological and economic impact in daily activities of health tasks.