Hard Sample Mining to Identify Challenging Samples for Breast Cancer Tumor Classification
Resumo
Deep learning has greatly advanced image classification in medical imaging, aiding the early detection of breast tumors. However, training deep learning models still presents challenges related to model efficiency and biases in data distribution. Breast tumor images highlight these challenges due to their complex tissue structures and overlapping cells. Hard Sample Mining (HSM) has emerged as a promising approach, focusing on selecting representative samples by ranking them based on loss or similarity. This work presents an experimental analysis of the effects of HSM on a binary breast tumor classification task using the BreakHis dataset. The results shows the method’s potential for sample ranking in training set pruning.
Palavras-chave:
Hard Sample Mining, Medical Imaging, Classification, Deep Learning
Referências
Chen, K., Sun, S., Zhao, J., Wang, F., and Zhang, Q. (2025). Multi-view representation for pathological image classification via contrastive learning. International Journal of Machine Learning and Cybernetics, 16(4):2285–2296.
Chengxiao, Y., Xiaoyang, Z., Ahmed, A., Tunio, M. H., and Shuhuan, F. (2023). Diffusion-enhanced magnified histopathological images for robust breast cancer classification. In 2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pages 1–7. IEEE.
Durgamahanthi, V., Anita Christaline, J., and Shirly Edward, A. (2021). Glcm and glrlm based texture analysis: Application to brain cancer diagnosis using histopathology images. In Dash, S. S., Das, S., and Panigrahi, B. K., editors, Intelligent Computing and Applications, page 691–706, Singapore. Springer.
Hesamian, M. H., Jia, W., He, X., and Kennedy, P. (2019). Deep learning techniques for medical image segmentation: Achievements and challenges. Journal of Digital Imaging, 32(4):582–596.
Kumar, T., Brennan, R., Mileo, A., and Bendechache, M. (2024). Image data augmentation approaches: A comprehensive survey and future directions. IEEE Access, 12:187536–187571.
Li, Y., Yu, Y., Zou, Y., Xiang, T., and Li, X. (2022). Online easy example mining for weakly-supervised gland segmentation from histology images. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 578–587. Springer.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). Focal loss for dense object detection. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2999–3007.
Liu, L., Liang, Y., Yan, X., Huangfu, L., Samtani, S., Yu, Z., Zhang, Y., and Zeng, D. D. (2025a). Hard sample mining: A new paradigm of efficient and robust model training. IEEE Transactions on Neural Networks and Learning Systems, page 1–21.
Liu, L., Zhang, P., Liang, Y., Liu, J., Morra, L., Guo, B., Yu, Z., Zhang, Y., and Zeng, D. D. (2025b). -Razor: Hardness-Aware Dataset Pruning for Efficient Neural Network Training. IEEE Transactions on Computational Social Systems, 12(3):957–971.
Peta, J. and Koppu, S. (2024). Explainable soft attentive efficientnet for breast cancer classification in histopathological images. Biomedical Signal Processing and Control, 90:105828.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016). A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 63(7):1455–1462.
Xue, C., Dou, Q., Shi, X., Chen, H., and Heng, P.-A. (2019). Robust learning at noisy labeled medical images: Applied to skin lesion classification. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), page 1280–1283.
Şaban Öztürk and Akdemir, B. (2018). Application of feature extraction and classification methods for histopathological image using glcm, lbp, lbglcm, glrlm and sfta. Procedia Computer Science, 132:40–46. International Conference on Computational Intelligence and Data Science.
Chengxiao, Y., Xiaoyang, Z., Ahmed, A., Tunio, M. H., and Shuhuan, F. (2023). Diffusion-enhanced magnified histopathological images for robust breast cancer classification. In 2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pages 1–7. IEEE.
Durgamahanthi, V., Anita Christaline, J., and Shirly Edward, A. (2021). Glcm and glrlm based texture analysis: Application to brain cancer diagnosis using histopathology images. In Dash, S. S., Das, S., and Panigrahi, B. K., editors, Intelligent Computing and Applications, page 691–706, Singapore. Springer.
Hesamian, M. H., Jia, W., He, X., and Kennedy, P. (2019). Deep learning techniques for medical image segmentation: Achievements and challenges. Journal of Digital Imaging, 32(4):582–596.
Kumar, T., Brennan, R., Mileo, A., and Bendechache, M. (2024). Image data augmentation approaches: A comprehensive survey and future directions. IEEE Access, 12:187536–187571.
Li, Y., Yu, Y., Zou, Y., Xiang, T., and Li, X. (2022). Online easy example mining for weakly-supervised gland segmentation from histology images. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 578–587. Springer.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). Focal loss for dense object detection. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2999–3007.
Liu, L., Liang, Y., Yan, X., Huangfu, L., Samtani, S., Yu, Z., Zhang, Y., and Zeng, D. D. (2025a). Hard sample mining: A new paradigm of efficient and robust model training. IEEE Transactions on Neural Networks and Learning Systems, page 1–21.
Liu, L., Zhang, P., Liang, Y., Liu, J., Morra, L., Guo, B., Yu, Z., Zhang, Y., and Zeng, D. D. (2025b). -Razor: Hardness-Aware Dataset Pruning for Efficient Neural Network Training. IEEE Transactions on Computational Social Systems, 12(3):957–971.
Peta, J. and Koppu, S. (2024). Explainable soft attentive efficientnet for breast cancer classification in histopathological images. Biomedical Signal Processing and Control, 90:105828.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision, pages 618–626.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., and Heutte, L. (2016). A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 63(7):1455–1462.
Xue, C., Dou, Q., Shi, X., Chen, H., and Heng, P.-A. (2019). Robust learning at noisy labeled medical images: Applied to skin lesion classification. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), page 1280–1283.
Şaban Öztürk and Akdemir, B. (2018). Application of feature extraction and classification methods for histopathological image using glcm, lbp, lbglcm, glrlm and sfta. Procedia Computer Science, 132:40–46. International Conference on Computational Intelligence and Data Science.
Publicado
08/09/2026
Como Citar
S. UCHIDA, Mariana Aya; S. LIMA, Afonso Matheus; SOUSA, Elaine P. M. de; TRAINA, Agma J. M..
Hard Sample Mining to Identify Challenging Samples for Breast Cancer Tumor Classification. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 41. , 2026, São Carlos/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 924-930.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2026.249481.
