ConvNeXt for Breast Cancer Classification in Infrared Images
Resumo
Breast cancer is a major public health concern, highlighting the need for accurate and accessible diagnostic tools. Infrared imaging offers a non-invasive alternative for detecting physiological abnormalities associated with tumor development. In this study, we evaluate the use of ConvNeXt architectures for breast cancer classification based on static infrared images. A patient-level stratified cross-validation protocol was adopted to ensure robust and unbiased assessment. Among the evaluated models, ConvNeXt-Large achieved the best performance, reaching an accuracy of 90.43% and an AUC of 98.29%. These results demonstrate the potential of modern deep learning architectures for supporting breast cancer detection using infrared imaging.
Referências
Aggarwal, A. K., Alphana, and Pandey, M. (2026). Ensemble classification of breast cancer using texture and color features. SN Computer Science, 7(3):221.
Alzahrani, R. M., Sikkandar, M. Y., Begum, S. S., Babetat, A. F. S., Alhashim, M., Alduraywish, A., Prakash, N., and Ng, E. Y. (2025). Early breast cancer detection via infrared thermography using a cnn enhanced with particle swarm optimization. Scientific Reports, 15(1):25290.
Baffa, M. d. F. O. and Conci, A. (2022). Radiomics for breast ir-imaging classification. In MICCAI Workshop on Medical Image Assisted Blomarkers’ Discovery, pages 10–19. Springer.
Cihan, M. and Ceylan, M. (2025). Multi-view thermal breast imaging for malignancy detection: Performance benchmarking of cnn, transformer, and involution architectures. In International Conference on Artificial Intelligence over Infrared Images for Medical Applications, pages 20–35. Springer.
D’Alessandro, G., Tavakolian, P., and Sfarra, S. (2024). A review of techniques and bioheat transfer models supporting infrared thermal imaging for diagnosis of malignancy. Applied Sciences, 14(4):1603.
Evans, A., Trimboli, R. M., Athanasiou, A., Balleyguier, C., Baltzer, P. A., Bick, U., Camps Herrero, J., Clauser, P., Colin, C., Cornford, E., et al. (2018). Breast ultrasound: recommendations for information to women and referring physicians by the european society of breast imaging. Insights into imaging, 9(4):449–461.
Hayat, A. (2023). Breast cancer detection system from thermal images using swin transformer. Journal Press India, 3(1).
Instituto Nacional do Câncer (2024). Controle do câncer de mama no Brasil: dados e números 2024. INCA, Rio de Janeiro. Available at: [link]. Accessed in 17 mar. 2026.
Koo, M. M., Von Wagner, C., Abel, G. A., McPhail, S., Rubin, G. P., and Lyratzopoulos, G. (2017). Typical and atypical presenting symptoms of breast cancer and their associations with diagnostic intervals: Evidence from a national audit of cancer diagnosis. Cancer epidemiology, 48:140–146.
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11976–11986.
Mashekova, A., Zhao, Y., Ng, E. Y. K., Zarikas, V., Fok, S. C., and Mukhmetov, O. (2022). Early detection of the breast cancer using infrared technology – a comprehensive review. Thermal Science and Engineering Progress.
National Health Service (2026). Symptoms of breast cancer in women. Available at: [link]. Accessed in 17 mar. 2026.
Nguyen Chi, T., Le Thi Thu, H., Doan Quang, T., and Taniar, D. (2025). A lightweight method for breast cancer detection using thermography images with optimized cnn feature and efficient classification. Journal of Imaging Informatics in Medicine, 38(3):1434–1451.
Pinto, G., León, J., Quintero, B., Villamizar, D., and Rueda-Chacón, H. (2025). Multimodal vision-language transformer for thermography breast cancer classification. In 2025 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI), pages 1–6. IEEE.
Rodd, B. (2026). Detecting vasodilation for early breast cancer using vit-based distribution embedding via extreme value theory on deep matrix approximation. Biomedical Signal Processing and Control, 119:109821.
Silva, L., Saade, D., Sequeiros, G., Silva, A., Paiva, A., Bravo, R., and Conci, A. (2014). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1):92–100.
World Health Organization (2024). Breast cancer. Available at: [link]. Accessed in 17 mar. 2026.
Alzahrani, R. M., Sikkandar, M. Y., Begum, S. S., Babetat, A. F. S., Alhashim, M., Alduraywish, A., Prakash, N., and Ng, E. Y. (2025). Early breast cancer detection via infrared thermography using a cnn enhanced with particle swarm optimization. Scientific Reports, 15(1):25290.
Baffa, M. d. F. O. and Conci, A. (2022). Radiomics for breast ir-imaging classification. In MICCAI Workshop on Medical Image Assisted Blomarkers’ Discovery, pages 10–19. Springer.
Cihan, M. and Ceylan, M. (2025). Multi-view thermal breast imaging for malignancy detection: Performance benchmarking of cnn, transformer, and involution architectures. In International Conference on Artificial Intelligence over Infrared Images for Medical Applications, pages 20–35. Springer.
D’Alessandro, G., Tavakolian, P., and Sfarra, S. (2024). A review of techniques and bioheat transfer models supporting infrared thermal imaging for diagnosis of malignancy. Applied Sciences, 14(4):1603.
Evans, A., Trimboli, R. M., Athanasiou, A., Balleyguier, C., Baltzer, P. A., Bick, U., Camps Herrero, J., Clauser, P., Colin, C., Cornford, E., et al. (2018). Breast ultrasound: recommendations for information to women and referring physicians by the european society of breast imaging. Insights into imaging, 9(4):449–461.
Hayat, A. (2023). Breast cancer detection system from thermal images using swin transformer. Journal Press India, 3(1).
Instituto Nacional do Câncer (2024). Controle do câncer de mama no Brasil: dados e números 2024. INCA, Rio de Janeiro. Available at: [link]. Accessed in 17 mar. 2026.
Koo, M. M., Von Wagner, C., Abel, G. A., McPhail, S., Rubin, G. P., and Lyratzopoulos, G. (2017). Typical and atypical presenting symptoms of breast cancer and their associations with diagnostic intervals: Evidence from a national audit of cancer diagnosis. Cancer epidemiology, 48:140–146.
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022). A convnet for the 2020s. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11976–11986.
Mashekova, A., Zhao, Y., Ng, E. Y. K., Zarikas, V., Fok, S. C., and Mukhmetov, O. (2022). Early detection of the breast cancer using infrared technology – a comprehensive review. Thermal Science and Engineering Progress.
National Health Service (2026). Symptoms of breast cancer in women. Available at: [link]. Accessed in 17 mar. 2026.
Nguyen Chi, T., Le Thi Thu, H., Doan Quang, T., and Taniar, D. (2025). A lightweight method for breast cancer detection using thermography images with optimized cnn feature and efficient classification. Journal of Imaging Informatics in Medicine, 38(3):1434–1451.
Pinto, G., León, J., Quintero, B., Villamizar, D., and Rueda-Chacón, H. (2025). Multimodal vision-language transformer for thermography breast cancer classification. In 2025 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI), pages 1–6. IEEE.
Rodd, B. (2026). Detecting vasodilation for early breast cancer using vit-based distribution embedding via extreme value theory on deep matrix approximation. Biomedical Signal Processing and Control, 119:109821.
Silva, L., Saade, D., Sequeiros, G., Silva, A., Paiva, A., Bravo, R., and Conci, A. (2014). A new database for breast research with infrared image. Journal of Medical Imaging and Health Informatics, 4(1):92–100.
World Health Organization (2024). Breast cancer. Available at: [link]. Accessed in 17 mar. 2026.
Publicado
01/06/2026
Como Citar
LOUZADA, Víctor Emmanuel Olmi; BAFFA, Matheus de Freitas Oliveira.
ConvNeXt for Breast Cancer Classification in Infrared Images. In: WORKSHOP DE TERMOGRAFIA COMPUTACIONAL E IA PARA APLICAÇÕES MÉDICAS - SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 479-489.
ISSN 2763-8987.
DOI: https://doi.org/10.5753/sbcas_estendido.2026.25278.
