Zhang Xiangyang, Chen Yang, Cai Changjing, Wang Yifeng, Tan Jun, Fang Zijie, Wei Le, Shao Zhuchen, Wang Liwen, Qi Tiezheng, Liu Yihan, Jiang Zhaohui, Li Yin, Han Ying, Rugambwa Tibera Kagemulo, Zeng Shan, Wang Haoqian, Shen Hong, Zhang Yongbing
Department of Oncology, Xiangya Hospital, Central South University, Changsha, Hunan, China.
Department of Biomedical Sciences, City University of Hong Kong, Hong Kong, China.
Int J Surg. 2025 Apr 1;111(4):3109-3114. doi: 10.1097/JS9.0000000000002220.
Detection of biomarkers of breast cancer incurs additional costs and tissue burden. We propose a deep learning-based algorithm (BBMIL) to predict classical biomarkers, immunotherapy-associated gene signatures, and prognosis-associated subtypes directly from hematoxylin and eosin stained histopathology images. BBMIL showed the best performance among comparative algorithms on the prediction of classical biomarkers, immunotherapy related gene signatures, and subtypes.
乳腺癌生物标志物的检测会带来额外的成本和组织负担。我们提出了一种基于深度学习的算法（BBMIL），可直接从苏木精和伊红染色的组织病理学图像中预测经典生物标志物、免疫治疗相关基因特征以及预后相关亚型。在比较算法中，BBMIL在预测经典生物标志物、免疫治疗相关基因特征和亚型方面表现最佳。
