Feature Extraction Of Tumor Infiltrating Lymphocytes Based On Neural Network And Its Clinical Application

Tumor-infiltrating lymphocytes(TILs)have a significant prognostic value in cancers.However,very few automated,deep learning-based TIL scoring algorithms have been developed for colorectal cancer(CRC)and breast cancer(BRCA).In this research,an automated,multiscale LinkNet workflow was developed for quantifying TILs at the cellular level in CRC tumors using H&E-stained images from the Lizard dataset with annotations of lymphocytes.The predictive performance of the automatic TIL scores for disease progression and overall survival was evaluated using three international datasets,including 554 CRC patients from The Cancer Genome Atlas(TCGA),926 BRCA patients from TCGA and 1130 CRC patients from Molecular and Cellular Oncology(MCO).The LinkNet model provided outstanding precision(0.9508),recall(0.9185),and overall F1 score(0.9347).Clear continuous TILs-hazard relationships were observed between and the risk of disease progression or death in both TCGA and MCO cohorts.Both univariate and multivariate Cox regression analyses for the TCGA-CRC data demonstrated that patients with high TIL abundance had a significant(approximately 75%)reduction in risk for disease progression.Also,Both univariate and multivariate Cox regression analyses for the TCGA-BRCA data demonstrated that patients with high TIL abundance had a significant(approximately 50%)reduction in risk for disease progression.In both the MCO and TCGA-CRC cohorts,the TIL-high group was significantly associated with improved overall survival in univariate analysis(30%and 54%reduction in risk,respectively).The favorable effects of high TIL levels were consistently observed in different subgroups(classified according to known risk factors).The proposed deep-learning workflow for automatic TIL quantification based on LinkNet can be a useful tool for CRC and BRCA.TIL score is likely an independent risk factor for disease progression and carries predictive information of disease progression beyond the current clinical risk factors and biomarkers.The prognostic significance of TIL score for overall survival is also evident.