Computerized tertiary lymphoid structures density on H&E-images is a prognostic biomarker in resectable lung adenocarcinoma

• DOI: 10.1016/j.isci.2023.107635
• Publication Date: 2023-08-16T06:02:36Z
• Authors: Yumeng Wang; Huan Lin; Ningning Yao; Xiaobo Chen; Bingjiang Qiu; Yanfen Cui; Yu Liu; Bingbing Li; Chu Han; Zhenhui Li; Wei Zhao; Zimin Wang; Xipeng Pan; Cheng Lu; Jun Liu; Zhenbing Liu; Zaiyi Liu
• Keywords: Health informatics; Science; Q; cancer; computational bioinformatics; Article

The increased amount of tertiary lymphoid structures (TLSs) is associated with a favorable prognosis in patients lung adenocarcinoma (LUAD). However, evaluating TLSs manually an experience-dependent and time-consuming process, which limits its clinical application. In this multi-center study, we developed automated computational workflow for quantifying the TLS density tumor region routine hematoxylin eosin (H&E)-stained whole-slide images (WSIs). association between computerized disease-free survival (DFS) was further explored 802 resectable LUAD three cohorts. Additionally, Cox proportional hazard regression model, incorporating clinicopathological variables density, established to assess prognostic ability. independent biomarker LUAD. integration could support individualized decision-making by improving stratification.