EL-nnU-Net: Early Learning para Segmentação 3D do Hipocampo em Ressonância Magnética
Resumo
A segmentação automática do hipocampo em exames de ressonância magnética é uma tarefa importante para o apoio ao diagnóstico de diversas doenças neurológicas. Este trabalho propõe a EL-nnU-Net, que utiliza estratégia de Early Learning baseada em autodestilação. O método explora mapas intermediários por meio do Early Decoder, permitindo a geração de máscaras auxiliares que auxiliam no refinamento do treinamento da rede. Os experimentos foram conduzidos com o conjunto de dados do Medical Segmentation Decathlon, composto por 260 volumes. A abordagem alcança desempenho competitivo, obtendo o melhor resultado para a classe Anterior e desempenho equivalente ao estado da arte para a classe Posterior.Referências
Albadawi, E. A. (2025). Structural and functional changes in the hippocampus induced by environmental exposures. Neurosciences Journal, 30(1):5–19.
Antonelli, M., Reinke, A., Bakas, S., Farahani, K., Kopp-Schneider, A., Landman, B. A., Litjens, G., Menze, B., Ronneberger, O., Summers, R. M., et al. (2022). The medical segmentation decathlon. Nature communications, 13(1):4128.
Arabi, H. and Zaidi, H. (2024). Single annotator versus multi-annotator: Challenge of segmenting two neighboring hippocampus head and body with high precision. Biomedical Signal Processing and Control, 97:106667.
Bonarota, S., Caruso, G., Di Domenico, C., Sperati, S., Tamigi, F. M., Giulietti, G., Giove, F., Caltagirone, C., and Serra, L. (2025). Integration of automatic mri segmentation techniques with neuropsychological assessments for early diagnosis and prognosis of alzheimer’s disease. a systematic review. Neuroimage, 314:121264.
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., and Ronneberger, O. (2016). 3d u-net: learning dense volumetric segmentation from sparse annotation. In International conference on medical image computing and computer-assisted intervention, pages 424–432. Springer.
dos Santos, P. V., dos Santos, P. R., Diniz, J. O., and de Carvalho Filho, A. O. (2025). U-net-el: A u-net and early learning-based method for histopathological breast image segmentation. In Brazilian Conference on Intelligent Systems, pages 593–606. Springer.
Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H. R., and Xu, D. (2021). Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI brainlesion workshop, pages 272–284. Springer.
Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H. R., and Xu, D. (2022). Unetr: Transformers for 3d medical image segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 574–584.
Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., and Maier-Hein, K. H. (2021). nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2):203–211.
Khan, H., Alutaibi, A. I., Tejani, G. G., Sharma, S. K., Khan, A. R., Ahmad, F., and Mousavirad, S. J. (2025). Mri based early temporal lobe epilepsy detection using dgwo based optimized haetn and fuzzy-aal segmentation framework (fasf). PLoS One, 20(7):e0325126.
Liu, W., Tian, T., Xu, W., Yang, H., Pan, X., Yan, S., and Wang, L. (2022). Phtrans: Parallelly aggregating global and local representations for medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 235–244. Springer.
Mansourian, A. M., Ahmadi, R., Ghafouri, M., Babaei, A. M., Golezani, E. B., yasamani ghamchi, Z., Ramezanian, V., Taherian, A., Dinashi, K., Miri, A., and Kasaei, S. (2025). A comprehensive survey on knowledge distillation. Transactions on Machine Learning Research.
Swathi, N. and Sankaran, K. S. (2025). Advances and clinical implications of neuroanatomical biomarkers in schizophrenia by optimizing brain tissue segmentation. Biomedical Signal Processing and Control, 102:107215.
Wang, W., Chen, C., Ding, M., Yu, H., Zha, S., and Li, J. (2021). Transbts: Multimodal brain tumor segmentation using transformer. In International conference on medical image computing and computer-assisted intervention, pages 109–119. Springer.
Xie, Y., Zhang, J., Shen, C., and Xia, Y. (2021). Cotr: Efficiently bridging cnn and transformer for 3d medical image segmentation. In International conference on medical image computing and computer-assisted intervention, pages 171–180. Springer.
Antonelli, M., Reinke, A., Bakas, S., Farahani, K., Kopp-Schneider, A., Landman, B. A., Litjens, G., Menze, B., Ronneberger, O., Summers, R. M., et al. (2022). The medical segmentation decathlon. Nature communications, 13(1):4128.
Arabi, H. and Zaidi, H. (2024). Single annotator versus multi-annotator: Challenge of segmenting two neighboring hippocampus head and body with high precision. Biomedical Signal Processing and Control, 97:106667.
Bonarota, S., Caruso, G., Di Domenico, C., Sperati, S., Tamigi, F. M., Giulietti, G., Giove, F., Caltagirone, C., and Serra, L. (2025). Integration of automatic mri segmentation techniques with neuropsychological assessments for early diagnosis and prognosis of alzheimer’s disease. a systematic review. Neuroimage, 314:121264.
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., and Ronneberger, O. (2016). 3d u-net: learning dense volumetric segmentation from sparse annotation. In International conference on medical image computing and computer-assisted intervention, pages 424–432. Springer.
dos Santos, P. V., dos Santos, P. R., Diniz, J. O., and de Carvalho Filho, A. O. (2025). U-net-el: A u-net and early learning-based method for histopathological breast image segmentation. In Brazilian Conference on Intelligent Systems, pages 593–606. Springer.
Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H. R., and Xu, D. (2021). Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI brainlesion workshop, pages 272–284. Springer.
Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H. R., and Xu, D. (2022). Unetr: Transformers for 3d medical image segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 574–584.
Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., and Maier-Hein, K. H. (2021). nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2):203–211.
Khan, H., Alutaibi, A. I., Tejani, G. G., Sharma, S. K., Khan, A. R., Ahmad, F., and Mousavirad, S. J. (2025). Mri based early temporal lobe epilepsy detection using dgwo based optimized haetn and fuzzy-aal segmentation framework (fasf). PLoS One, 20(7):e0325126.
Liu, W., Tian, T., Xu, W., Yang, H., Pan, X., Yan, S., and Wang, L. (2022). Phtrans: Parallelly aggregating global and local representations for medical image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 235–244. Springer.
Mansourian, A. M., Ahmadi, R., Ghafouri, M., Babaei, A. M., Golezani, E. B., yasamani ghamchi, Z., Ramezanian, V., Taherian, A., Dinashi, K., Miri, A., and Kasaei, S. (2025). A comprehensive survey on knowledge distillation. Transactions on Machine Learning Research.
Swathi, N. and Sankaran, K. S. (2025). Advances and clinical implications of neuroanatomical biomarkers in schizophrenia by optimizing brain tissue segmentation. Biomedical Signal Processing and Control, 102:107215.
Wang, W., Chen, C., Ding, M., Yu, H., Zha, S., and Li, J. (2021). Transbts: Multimodal brain tumor segmentation using transformer. In International conference on medical image computing and computer-assisted intervention, pages 109–119. Springer.
Xie, Y., Zhang, J., Shen, C., and Xia, Y. (2021). Cotr: Efficiently bridging cnn and transformer for 3d medical image segmentation. In International conference on medical image computing and computer-assisted intervention, pages 171–180. Springer.
Publicado
01/06/2026
Como Citar
SANTOS, Patrick Ryan Sales dos; ARAÚJO, José Denes Lima; CARVALHO FILHO, Antonio Oseas de.
EL-nnU-Net: Early Learning para Segmentação 3D do Hipocampo em Ressonância Magnética. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 812-823.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2026.21531.
