Cassiano Pereira de Barros
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cassiano Pereira de Barros has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
Adham Do Amaral e Castro
Graduate Program in Medicine (Clinical Radiology), Imaging Diagnosis Department, Universidade Federal de São Paulo (UNIFESP), São Paulo, Brazil
1 shared publicationAdriano Brandão dos Santos
1 shared publicationAna Carolina de Lima Augusto
Division of Radiology, Delboni Medicina Diagnóstica, DASA, São Paulo, Brazil
1 shared publicationAndre Cesar Ozawa Rodrigues
Division of Radiology, Delboni Medicina Diagnóstica, DASA, São Paulo, Brazil
1 shared publicationAndre Yui Aihara
Graduate Program in Medicine (Clinical Radiology), Imaging Diagnosis Department, Universidade Federal de São Paulo (UNIFESP), São Paulo, Brazil
1 shared publicationAyumi Aihara
Faculdade de Ciências Médicas, Santa Casa de Misericórdia de São Paulo, São Paulo, Brazil
1 shared publication
Latest Publications
- Open Access
- 2 June 2026
- Published by Elsevier in Cancer Epidemiology
- Vol. 103, 103123
Trends and burden of oncologic emergencies in Brazil: A nationwide time series analysis (2008–2024)
- 2 June 2026
- Published by Elsevier in Cancer Epidemiology
- Vol. 103, 103123
Open AccessTrends and burden of oncologic emergencies in Brazil: A nationwide time series analysis (2008–2024)
- Open Access
- 23 March 2026
- Published by Springer Nature in Skeletal Radiology
- Vol. 55 (7) , 1617-1625
Deep learning-based identification of aberrant anterior tibial artery on knee MRI: a brazilian multicenter study
Objective: To develop and validate a deep learning model for the detection of aberrant anterior tibial artery (AATA) on axial T2-weighted knee MRI, given the surgical relevance of unrecognized AATA and the lack of automated detection tools. Materials and methods: This retrospective study included 70,260 MRI images from 2315 examinations (1441 without AATA and 874 with AATA) collected after institutional review board approval. Musculoskeletal radiologists performed image-level annotations. Data were split at the patient level into training, validation, and internal test sets; an independent dataset from another institution served as an external test set. A convolutional neural network was implemented in Python and PyTorch. Model performance was assessed at the patient level. Results: At the slice level, the model achieved an F1-score of 0.838 on the internal test set. Patient-level classification using the validation-derived threshold (0.17) yielded F1-scores of 0.966 on the validation set, 0.979 on the internal test set, and 0.786 on the external test set. The area under the receiver operating characteristic curve for the external cohort was 0.97, indicating strong generalization despite a decrease in precision due to false positives. Conclusion: To our knowledge, this is the first study to apply artificial intelligence for automated detection of AATA on knee MRI. The proposed deep learning model performs this task with high sensitivity. Despite reduced precision in the external cohort, it demonstrates strong potential for enhancing preoperative risk assessment and surgical planning. Broader multicenter validation is warranted before clinical deployment.
- 23 March 2026
- Published by Springer Nature in Skeletal Radiology
- Vol. 55 (7) , 1617-1625
Open AccessDeep learning-based identification of aberrant anterior tibial artery on knee MRI: a brazilian multicenter study
Objective: To develop and validate a deep learning model for the detection of aberrant anterior tibial artery (AATA) on axial T2-weighted knee MRI, given the surgical relevance of unrecognized AATA and the lack of automated detection tools. Materials and methods: This retrospective study included 70,260 MRI images from 2315 examinations (1441 without AATA and 874 with AATA) collected after institutional review board approval. Musculoskeletal radiologists performed image-level annotations. Data were split at the patient level into training, validation, and internal test sets; an independent dataset from another institution served as an external test set. A convolutional neural network was implemented in Python and PyTorch. Model performance was assessed at the patient level. Results: At the slice level, the model achieved an F1-score of 0.838 on the internal test set. Patient-level classification using the validation-derived threshold (0.17) yielded F1-scores of 0.966 on the validation set, 0.979 on the internal test set, and 0.786 on the external test set. The area under the receiver operating characteristic curve for the external cohort was 0.97, indicating strong generalization despite a decrease in precision due to false positives. Conclusion: To our knowledge, this is the first study to apply artificial intelligence for automated detection of AATA on knee MRI. The proposed deep learning model performs this task with high sensitivity. Despite reduced precision in the external cohort, it demonstrates strong potential for enhancing preoperative risk assessment and surgical planning. Broader multicenter validation is warranted before clinical deployment.