KCA
Search
- Page Path
- HOME > Search
Original Article
- Breast cancer
- Molecular Classification of Breast Cancer Using Weakly Supervised Learning
- Wooyoung Jang, Jonghyun Lee, Kyong Hwa Park, Aeree Kim, Sung Hak Lee, Sangjeong Ahn
- Cancer Res Treat. 2025;57(1):116-125. Published online June 25, 2024
- DOI: https://doi.org/10.4143/crt.2024.113
-
Abstract
PDF
Supplementary Material
PubReader
ePub - Purpose
The molecular classification of breast cancer is crucial for effective treatment. The emergence of digital pathology has ushered in a new era in which weakly supervised learning leveraging whole-slide images has gained prominence in developing deep learning models because this approach alleviates the need for extensive manual annotation. Weakly supervised learning was employed to classify the molecular subtypes of breast cancer.
Materials and Methods
Our approach capitalizes on two whole-slide image datasets: one consisting of breast cancer cases from the Korea University Guro Hospital (KG) and the other originating from The Cancer Genomic Atlas dataset (TCGA). Furthermore, we visualized the inferred results using an attention-based heat map and reviewed the histomorphological features of the most attentive patches.
Results
The KG+TCGA-trained model achieved an area under the receiver operating characteristics value of 0.749. An inherent challenge lies in the imbalance among subtypes. Additionally, discrepancies between the two datasets resulted in different molecular subtype proportions. To mitigate this imbalance, we merged the two datasets, and the resulting model exhibited improved performance. The attentive patches correlated well with widely recognized histomorphologic features. The triple-negative subtype has a high incidence of high-grade nuclei, tumor necrosis, and intratumoral tumor-infiltrating lymphocytes. The luminal A subtype showed a high incidence of collagen fibers.
Conclusion
The artificial intelligence (AI) model based on weakly supervised learning showed promising performance. A review of the most attentive patches provided insights into the predictions of the AI model. AI models can become invaluable screening tools that reduce costs and workloads in practice. -
Citations
Citations to this article as recorded by
- Computational Methods for Breast Cancer Molecular Profiling using Routine Histopathology: A Review
Suchithra Kunhoth, Somaya Al-maadeed, Younes Akbari, Rafif Mahmood Al Saady
Archives of Computational Methods in Engineering.2025;[Epub] CrossRef - Development and validation of an artificial intelligence system for triple-negative breast cancer identification and prognosis prediction: a multicentre retrospective study
Xiu-Ming Zhang, Hua-Jun Zhou, Qing Chen, Xi Wang, Yu-Juan Fu, Cheng Jin, Feng-Tao Zhou, Jing-Ping Wang, Qiu-Yu Cai, Ji-Li Wang, Bo Luo, Mao-Tong Hu, Cai-Yun Yao, Xia Yang, Ya-Li Xu, Jing Zhang, Hao Chen
eClinicalMedicine.2025; 89: 103557. CrossRef - An interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging
Tengfei Ren, Vijay Govindarajan, Sami Bourouis, Xiangkun Wang, Shanbao Ke
Scientific Reports.2025;[Epub] CrossRef
- Computational Methods for Breast Cancer Molecular Profiling using Routine Histopathology: A Review
- 4,714 View
- 257 Download
- 3 Web of Science
- 3 Crossref
First
Prev
