Artificial Intelligence For Histopathological Breast Cancer Diagnosis: A Comprehensive Survey
DOI:
https://doi.org/10.29284/9qtmg634Keywords:
Artificial intelligence, breast cancer, histopathology, digital pathology, whole-slide imaging, deep learning, convolutional neural networks, multiple-instance learning, Vision Transformers, computational pathology.Abstract
Traditional histopathology and digital pathology and computational image analysis are now part of breast cancer diagnosis. Hematoxylin and eosin (H&E) staining remains the most important method for diagnosis and subsequent classification and grading, and immunohistochemistry and molecular assays offer additional data when used in conjunction with H&E staining that is important for treatment planning. With the advent of digitization of slides into whole-slide images (WSI), there is a new opportunity to utilize Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) to solve problems such as tissue and tumour segmentation, cancer detection, histologic classification, cancer grading, detection of lymph-node metastases, quantification of biomarkers, prediction of molecular subtypes and modelling of outcomes. This survey summarizes the technical pipeline from slide preparation and scanning to preprocessing, patch extraction, representation learning and aggregation and clinical decision support. Special attention is paid to convolutional neural networks (CNNs), transfer learning, multiple-instance learning (MIL), attention mechanisms and Vision Transformers, explainability, uncertainty estimation and domain adaptation. Public data sets including BACH, CAMELYON16/17, TUPAC16 and associated data repositories are discussed as well as their advantages and disadvantages. The survey also investigates dataset biases, staining and scanner variation, label noise, class imbalance, leakage, and external validation as well as the discrepancy between retrospective benchmark performance and the usefulness of these labels in the clinical setting. Recent reviews suggest significant potential, but widespread adoption will need multicenter testing, consistent reporting, integration into workflows, regulatory monitoring, and evaluation from a human-centered perspective. The paper concludes with directions on research that include foundation models, weakly supervised learning, multimodal pathology, federated learning and resource-aware inference.
References
[1] Baxi V, Edwards R, Montalto M, Saha S. Artificial intelligence in breast cancer histopathology. Histopathology. 2023;82:198–211. doi:10.1111/his.14820.
[2] Soliman A, Li Z, Parwani AV. Artificial intelligence’s impact on breast cancer pathology: a literature review. Diagnostic Pathology. 2024;19:38. doi:10.1186/s13000-024-01453-w.
[3] Current status and prospects of artificial intelligence in breast cancer pathology: convolutional neural networks to prospective Vision Transformers. Review literature, 2024.
[4] Artificial intelligence in breast pathology: Overview and recent updates. Human Pathology. 2025. doi:10.1016/j.humpath.2025.105819.
[5] Lu MY, Williamson DFK, Chen TY, et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature Biomedical Engineering. 2021;5:555–570.
[6] Ilse M, Tomczak JM, Welling M. Attention-based deep multiple instance learning. Proceedings of ICML. 2018.
[7] Komura D, Ishikawa S. Machine learning methods for histopathological image analysis. Computational and Structural Biotechnology Journal. 2018;16:34–42.
[8] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of CVPR. 2016.
[9] Tan M, Le Q. EfficientNet: rethinking model scaling for convolutional neural networks. Proceedings of ICML. 2019.
[10] Dosovitskiy A, et al. An image is worth 16×16 words: transformers for image recognition at scale. ICLR. 2021.
[11] Komura D, Ochi M, Ishikawa S. Machine learning methods for histopathological image analysis: Updates in 2024. Computational and Structural Biotechnology Journal. 2024;27:383–400.
[12] Williams DKA Jr, et al. Digital pathology, deep learning, and cancer: a narrative review. Translational Cancer Research. 2024;13:2544–2560.
[13] Deep learning approaches for breast cancer detection in histopathology images: a review. Cancer Biomarkers. 2024;40:1–25. doi:10.3233/CBM-230251.
[14] McCaffrey C, Jahangir C, Murphy C, et al. Artificial intelligence in digital histopathology for predicting patient prognosis and treatment efficacy in breast cancer. Expert Review of Molecular Diagnostics. 2024;24:363–377.
[15] Mandair D, Reis-Filho JS, Ashworth A. Biological insights and novel biomarker discovery through deep learning approaches in breast cancer histopathology. npj Breast Cancer. 2023;9:21.
[16] Deep-learning-based breast cancer stage prediction from H&E-stained whole-slide images in resource-constrained settings. 2026.
[17] A Multi-Stage Approach to Breast Cancer Classification Using Histopathology Images. Dataset description based on ICIAR 2018 BACH; 2022.
[18] Ehteshami Bejnordi B, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318:2199–2210.
[19] Campanella G, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nature Medicine. 2019;25:1301–1309.
[20] Bandi P, Geessink O, Manson Q, et al. From detection of individual metastases to classification of breast cancer lymph nodes: the CAMELYON17 challenge. IEEE Transactions on Medical Imaging. 2018;39:340–350.
[21] Machine Learning Methods for Computer-Aided Breast Cancer Diagnosis Using Histopathology: A Narrative Review. 2019.
[22] Tafavvoghi M, Sildnes A, Rakaee M, et al. Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images. Journal of Pathology Informatics. 2025;16:100410.
[23] Couture HD, et al. A deep learning image-based intrinsic molecular subtype classifier of breast tumors reveals tumor heterogeneity that may affect survival. Scientific Reports. 2018/2020 literature record.
[24] Wetstein SC, de Jong VMT, Stathonikos N, et al. Deep learning-based breast cancer grading and survival analysis on whole-slide histopathology images. Scientific Reports. 2022;12:15102.
[25] Ki-67 Quantification in Breast Cancer by Digital Imaging AI Software and its Concordance with Manual Method. 2023.
[26] Artificial intelligence-powered optimization of Ki-67 assessment in breast cancer: enhancing precision and workflow efficiency. Literature review. 2024.
[27] Artificial intelligence in digital pathology diagnosis and analysis: technologies, challenges, and future prospects. Review literature, 2025/2026.
[28] Breast Cancer Molecular Subtype Prediction on Pathological Images with Discriminative Patch Selection and Multi-Instance Learning. 2022.
[29] Progress on deep learning in digital pathology of breast cancer: a narrative review. Gland Surgery. 2022;11.
[30] Artificial intelligence applied to breast pathology. Review literature. 2021.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
