A Computational Tumor-Infiltrating Lymphocyte Assessment Method Comparable with Visual Reporting Guidelines for Triple-Negative Breast Cancer
Peng Sun,
Jiehua He,
Xue Chao,
Keming Chen,
Yuanyuan Xu,
Qitao Huang,
Jingping Yun,
Mei Li,
Rongzhen Luo,
Jinbo Kuang,
Huajia Wang,
Haosen Li,
Hui Hui,
Shuoyu Xu
Affiliations
Peng Sun
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China; Corresponding authors: Dr. Peng Sun, Department of Pathology, Sun Yat-sen University Cancer Center, 651 Dongfeng East Road, 510060, Guangzhou, P. R. China
Jiehua He
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Xue Chao
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Keming Chen
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Yuanyuan Xu
Department of Physiology, Zhongshan school of Medicine, Sun Yat-Sen University, Guangzhou, P. R. China
Qitao Huang
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Jingping Yun
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Mei Li
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Rongzhen Luo
State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, P. R. China; Department of Pathology, Sun Yat-sen University Cancer Center, Guangzhou, P. R. China
Jinbo Kuang
Bio-totem Pte Ltd, Foshan, P. R. China
Huajia Wang
Bio-totem Pte Ltd, Foshan, P. R. China
Haosen Li
Bio-totem Pte Ltd, Foshan, P. R. China
Hui Hui
Bio-totem Pte Ltd, Foshan, P. R. China
Shuoyu Xu
Bio-totem Pte Ltd, Foshan, P. R. China; Department of General Surgery, Nanfang Hospital, Southern Medical University, Guangzhou, P. R. China; Co-coresponding author: Dr. Shuoyu Xu: Bio-totem Pte Ltd, 321 State Road, 528231, Foshan, P.R.China; Department of General Surgery Nanfang Hospital, Southern Medical University, 1838 Guangzhou Avenue North, 510515, Guangzhou, P.R.China.; 1838 Guangzhou Avenue North, 510515, Guangzhou, P. R. China
Background: Tumor-infiltrating lymphocytes (TILs) are clinically significant in triple-negative breast cancer (TNBC). Although a standardized methodology for visual TILs assessment (VTA) exists, it has several inherent limitations. We established a deep learning-based computational TIL assessment (CTA) method broadly following VTA guideline and compared it with VTA for TNBC to determine the prognostic value of the CTA and a reasonable CTA workflow for clinical practice. Methods: We trained three deep neural networks for nuclei segmentation, nuclei classification and necrosis classification to establish a CTA workflow. The automatic TIL (aTIL) score generated was compared with manual TIL (mTIL) scores provided by three pathologists in an Asian (n = 184) and a Caucasian (n = 117) TNBC cohort to evaluate scoring concordance and prognostic value. Findings: The intraclass correlations (ICCs) between aTILs and mTILs varied from 0.40 to 0.70 in two cohorts. Multivariate Cox proportional hazards analysis revealed that the aTIL score was associated with disease free survival (DFS) in both cohorts, as either a continuous [hazard ratio (HR)=0.96, 95% CI 0.94–0.99] or dichotomous variable (HR=0.29, 95% CI 0.12–0.72). A higher C-index was observed in a composite mTIL/aTIL three-tier stratification model than in the dichotomous model, using either mTILs or aTILs alone. Interpretation: The current study provides a useful tool for stromal TIL assessment and prognosis evaluation for patients with TNBC. A workflow integrating both VTA and CTA may aid pathologists in performing risk management and decision-making tasks.