Título:	Enhancing podocyte degenerative changes identification with pathologist collaboration : implications for improved diagnosis in kidney diseases
Autor(es):	Barros, George Oliveira Silva, José Nathan Andrade Muller da Proença, Henrique Machado De Sousa Araújo, Stanley Almeida Wanderley, David Campos Oliveira, Luciano Rebouças de Santos, Washington Luis Conrado dos Duarte, Angelo Amancio Vidal, Flávio de Barros
ORCID:	https://orcid.org/0000-0002-0838-047X https://orcid.org/0000-0001-9952-6755 https://orcid.org/0000-0001-9996-4405 https://orcid.org/0000-0003-1201-9449 https://orcid.org/0000-0001-7183-8853
Afiliação do autor:	Instituto Federal Goiano University of Brasilia, Department of Computer Science Federal University of Bahia, Department of Pathology Oswaldo Ramos Foundation, Department of Pathology, Kidney and Hypertension Hospital, São Paulo Federal University of Minas Gerais, Institute of Nephropathology, Center for Electron Microscopy Federal University of Minas Gerais, Institute of Nephropathology, Center for Electron Microscopy Federal University of Bahia, Intelligent Vision Research Lab Oswaldo Cruz Foundation, Gonçalo Moniz Institute State University of Feira de Santana, Department of Technology University of Brasilia, Department of Computer Science
Assunto:	Rins - doenças - diagnóstico Podocitopatia Processamento de imagens médicas Redes neurais convolucionais
Data de publicação:	10-Set-2024
Editora:	IEEE
Referência:	BARROS, George Oliveira et al. Enhancing podocyte degenerative changes identification with pathologist collaboration: implications for improved diagnosis in kidney diseases. IEEE Journal of Translation Engineering in Heath and Medicine, v. 12, p. 635-642, 2024. DOI: 10.1109/JTEHM.2024.345594. Disponível em: https://ieeexplore.ieee.org/document/10675352. Acesso em: 28 out. 2026.
Abstract:	Podocyte degenerative changes are common in various kidney diseases, and their accurate identification is crucial for pathologists to diagnose and treat such conditions. However, this can be a difficult task, and previous attempts to automate the identification of podocytes have not been entirely successful. To address this issue, this study proposes a novel approach that combines pathologists’ expertise with an automated classifier to enhance the identification of podocytopathies. The study involved building a new dataset of renal glomeruli images, some with and others without podocyte degenerative changes, and developing a convolutional neural network (CNN) based classifier. The results showed that our automated classifier achieved an impressive 90.9% f-score. When the pathologists used as an auxiliary tool to classify a second set of images, the medical group’s average performance increased significantly, from 91.4±12.5% to 96.1±2.9% of f-score. Fleiss’ kappa agreement among the pathologists also increased from 0.59 to 0.83. Conclusion: These findings suggest that automating this task can bring benefits for pathologists to correctly identify images of glomeruli with podocyte degeneration, leading to improved individual accuracy while raising agreement in diagnosing podocytopathies. This approach could have significant implications for the diagnosis and treatment of kidney diseases.
Unidade Acadêmica:	Instituto de Ciências Exatas (IE) Departamento de Ciência da Computação (IE CIC)
Programa de pós-graduação:	Programa de Pós-Graduação em Informática
Licença:	This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
DOI:	10.1109/JTEHM.2024.3455941
Aparece nas coleções:	Artigos publicados em periódicos e afins

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.