High-accuracy prediction of mutations in nine genes in lung adenocarcinoma via two-stage multi-instance learning on large-scale whole-slide images

doi:10.1186/s13000-025-01663-w

	High-accuracy prediction of mutations in nine genes in lung adenocarcinoma via two-stage multi-instance learning on large-scale whole-slide images
	Zhao, Lingyu 1,2; Zhao, Na 3; Zhong, Ruiqi 2,4; Niu, Yiru 1,2; Chang, Ziyi 1; Su, Peng 5; Wang, Zhihui 1,2; Cui, Lifang 1; Wang, Bei 1; Chen, Huang 1; Wang, Xiaowen 3; Kong, Xiangbing 3; Du, Baolin 3; Ren, Fei 6; Zhong, Dingrong 1,2
	2025-06-02
发表期刊	DIAGNOSTIC PATHOLOGY
卷号	20 期号:1 页码:14
摘要	BackgroundLung cancer is widely recognized as a prevalent malignant neoplasm. Traditional genetic testing methods face limitations such as high costs and lengthy procedures. The prediction of clinically relevant genetic mutations via histopathological images could facilitate the expedited identification of genetic mutations in clinical settings.MethodsWe collected 2,221 slides from 1999 patients diagnosed with lung adenocarcinoma. The data include whole-slide images data as well as information on gene mutations in EGFR, KRAS, ALK, HER2, and other rare genes (ROS1, RET, BRAF, PIK3CA, NRAS), and related clinical information. The self-supervised model DINO and the two-stage multi-instance network GAMIL were employed to accurately identify mutation statuses in 9 genes linked to tumorigenesis and cancer progression. The comparison of model performance involves the utilization of various foundation model (UNI), classification models (CLAM and Inception v3), external datasets (TCGA and other medical institutions), and comparative analysis with human pathologists.ResultsOur approach outperforms the CLAM and inception v3 model, achieving AUC values ranging from 0.825 to 0.987 for predicting gene mutations. The AUC value on the external test data set is 0.516-0.843. Furthermore, when comparing EGFR gene mutation prediction between pathologists and the GAMIL model, GAMIL exhibited a significantly higher AUC value of 0.810, exceeding the average AUC value of 0.508 achieved by pathologists.ConclusionThe GAMIL models exhibit outstanding performance in delineating tumor regions in lung adenocarcinoma and in forecasting gene mutations. The utilization of these models presents substantial potential for markedly improving molecular testing efficiency and opening novel pathways for personalized treatment.Trial registrationNot applicable.
关键词	Artificial intelligence Lung adenocarcinoma Gene mutation Multiple instance learning Self-supervised
DOI	10.1186/s13000-025-01663-w
收录类别	SCI
语种	英语
资助项目	The National High Level Hospital Clinical Research Funding of China
WOS研究方向	Pathology
WOS类目	Pathology
WOS记录号	WOS:001500433600001
出版者	BMC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42334
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhong, Dingrong
作者单位	1.China Japan Friendship Hosp, Dept Pathol, Beijing 100029, Peoples R China 2.Chinese Acad Med Sci & Peking Union Med Coll, Beijing 100006, Peoples R China 3.Chongqing Zhijian Life Technol Co LTD, Chongqing 400039, Peoples R China 4.Chinese Acad Med Sci & Peking Union Med Coll, Natl Clin Res Ctr Canc, Natl Canc Ctr, Dept Med Oncol,Canc Hosp, Beijing, Peoples R China 5.Ordos Cent Hosp, Dept Pathol, Ordos 017000, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Lingyu,Zhao, Na,Zhong, Ruiqi,et al. High-accuracy prediction of mutations in nine genes in lung adenocarcinoma via two-stage multi-instance learning on large-scale whole-slide images[J]. DIAGNOSTIC PATHOLOGY,2025,20(1):14.
APA	Zhao, Lingyu.,Zhao, Na.,Zhong, Ruiqi.,Niu, Yiru.,Chang, Ziyi.,...&Zhong, Dingrong.(2025).High-accuracy prediction of mutations in nine genes in lung adenocarcinoma via two-stage multi-instance learning on large-scale whole-slide images.DIAGNOSTIC PATHOLOGY,20(1),14.
MLA	Zhao, Lingyu,et al."High-accuracy prediction of mutations in nine genes in lung adenocarcinoma via two-stage multi-instance learning on large-scale whole-slide images".DIAGNOSTIC PATHOLOGY 20.1(2025):14.