Advancing thyroid pathologies detection with recurrent neural networks and micro-FTIR hyperspectral imaging
Carregando...
Data
Data de publicação
2023
Autores IPEN
Orientador
Título da Revista
ISSN da Revista
Título do Volume
É parte de
É parte de
É parte de
É parte de
INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, 36th
ODS
Exportar
Resumo
Thyroid disorders are a complex group of diseases that require an accurate diagnosis for effective treatment. Fine-needle aspiration biopsies can assist in detecting many thyroid diseases. These materials can be analyzed visually using traditional computer vision methods, despite the limitations of complex samples. To address this problem, we propose a novel approach that uses hyperspectral imaging (HSI) to analyze thyroid biological samples. HSI measures the absorbance of infrared light by biological samples using a micro Fourier transform infrared spectroscopy (micro-FTIR) and converts this data into hyperspectral images. In this study, we used HSI to train and validate a recurrent neural network to classify thyroid samples as healthy, cancerous, or goiter. Our experiments, based on the k-fold cross-validation, achieved an overall accuracy of 96.88%, a sensitivity of 96.87%, and a specificity of 98.45%. These results demonstrate the potential of hyperspectral imaging as a tool to assist pathologists in the diagnosis of thyroid disease.
Como referenciar
BAFFA, MATHEUS de F.O.; BACHMANN, LUCIANO; ZEZELL, DENISE M.; PEREIRA, THIAGO M.; DESERNO, THOMAS M.; FELIPE, JOAQUIM C. Advancing thyroid pathologies detection with recurrent neural networks and micro-FTIR hyperspectral imaging. In: ALMEIDA, JOAO R. (ed.); SPILIOPOULOU, MYRA (ed.); ANDRADES, JOSE A.B. (ed.); PLACIDI, GIUSEPPE (ed.); GONZALEZ, ALEJANDRO R. (ed.); SICILIA, ROSA (ed.); KANE, BRIDGET (ed.). In: INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, 36th, June 22-24, 2023, L’Aquila, Italy. Proceedings... Piscataway, NJ, USA: IEEE, 2023. p. 611-615. DOI: 10.1109/CBMS58004.2023.00288. Disponível em: http://repositorio.ipen.br/handle/123456789/34444. Acesso em: 30 Dec 2025.
Esta referência é gerada automaticamente de acordo com as normas do estilo IPEN/SP (ABNT NBR 6023) e recomenda-se uma verificação final e ajustes caso necessário.