Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study

Xiangyang Zhang; Yang Chen; Changjing Cai; Yifeng Wang; Jun Tan; Zijie Fang; Le Wei; Zhuchen Shao; Liwen Wang; Tiezheng Qi; Yihan Liu; Zhaohui Jiang; Yin Li; Ying Han; Tibera Kagemulo Rugambwa; Shan Zeng; Haoqian Wang; Hong Shen; Yongbing Zhang

doi:10.1097/JS9.0000000000002220

Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study

Xiangyang Zhang
, Yang Chen
, Changjing Cai
, Yifeng Wang
, Jun Tan
, Zijie Fang
, Le Wei
, Zhuchen Shao
, Liwen Wang
, Tiezheng Qi
, Yihan Liu
, Zhaohui Jiang
, Yin Li
, Ying Han
, Tibera Kagemulo Rugambwa
, Shan Zeng
, Haoqian Wang
, Hong Shen
, Yongbing Zhang

Central South University
City University of Hong Kong
Tsinghua University
Harbin Institute of Technology
Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

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.

Original language	English
Pages (from-to)	3109-3114
Number of pages	6
Journal	International Journal of Surgery
Volume	111
Issue number	4
DOIs	https://doi.org/10.1097/JS9.0000000000002220
State	Published - 1 Apr 2025
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

breast cancer
deep learning
digital pathology

Access to Document

10.1097/JS9.0000000000002220

Cite this

Zhang, X., Chen, Y., Cai, C., Wang, Y., Tan, J., Fang, Z., Wei, L., Shao, Z., Wang, L., Qi, T., Liu, Y., Jiang, Z., Li, Y., Han, Y., Rugambwa, T. K., Zeng, S., Wang, H., Shen, H., & Zhang, Y. (2025). Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study. International Journal of Surgery, 111(4), 3109-3114. https://doi.org/10.1097/JS9.0000000000002220

@article{d5209c9130154fedb7b1424552ea3143,

title = "Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study",

abstract = "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.",

keywords = "breast cancer, deep learning, digital pathology",

author = "Xiangyang Zhang and Yang Chen and Changjing Cai and Yifeng Wang and Jun Tan and Zijie Fang and Le Wei and Zhuchen Shao and Liwen Wang and Tiezheng Qi and Yihan Liu and Zhaohui Jiang and Yin Li and Ying Han and Rugambwa, \{Tibera Kagemulo\} and Shan Zeng and Haoqian Wang and Hong Shen and Yongbing Zhang",

note = "Publisher Copyright: Copyright {\textcopyright} 2025 The Author(s). Published by Wolters Kluwer Health, Inc.",

year = "2025",

month = apr,

day = "1",

doi = "10.1097/JS9.0000000000002220",

language = "英语",

volume = "111",

pages = "3109--3114",

journal = "International Journal of Surgery",

issn = "1743-9191",

publisher = "Wolters Kluwer Health Inc",

number = "4",

}

Zhang, X, Chen, Y, Cai, C, Wang, Y, Tan, J, Fang, Z, Wei, L, Shao, Z, Wang, L, Qi, T, Liu, Y, Jiang, Z, Li, Y, Han, Y, Rugambwa, TK, Zeng, S, Wang, H, Shen, H & Zhang, Y 2025, 'Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study', International Journal of Surgery, vol. 111, no. 4, pp. 3109-3114. https://doi.org/10.1097/JS9.0000000000002220

TY - JOUR

T1 - Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology

T2 - a multicenter retrospective study

AU - Zhang, Xiangyang

AU - Chen, Yang

AU - Cai, Changjing

AU - Wang, Yifeng

AU - Tan, Jun

AU - Fang, Zijie

AU - Wei, Le

AU - Shao, Zhuchen

AU - Wang, Liwen

AU - Qi, Tiezheng

AU - Liu, Yihan

AU - Jiang, Zhaohui

AU - Li, Yin

AU - Han, Ying

AU - Rugambwa, Tibera Kagemulo

AU - Zeng, Shan

AU - Wang, Haoqian

AU - Shen, Hong

AU - Zhang, Yongbing

PY - 2025/4/1

Y1 - 2025/4/1

N2 - 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.

AB - 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.

KW - breast cancer

KW - deep learning

KW - digital pathology

UR - https://www.scopus.com/pages/publications/105003705088

U2 - 10.1097/JS9.0000000000002220

DO - 10.1097/JS9.0000000000002220

M3 - 文章

C2 - 39764584

AN - SCOPUS:105003705088

SN - 1743-9191

VL - 111

SP - 3109

EP - 3114

JO - International Journal of Surgery

JF - International Journal of Surgery

IS - 4

ER -

Artificial intelligence predicts multiclass molecular signatures and subtypes directly from breast cancer histology: a multicenter retrospective study

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this