基于 AI 的 TIL（肿瘤浸润淋巴细胞）评分系统评估肝切除患者 HCC 预后

We conducted a retrospective multicenter study on patients undergoing liver resection across three cohorts (N = 514). We trained a deep neural network and a random forest model to segment tumor regions and locate CD8+ TILs in H&E and CD8-stained whole-slide images. We quantified CD8+ TIL density and established an Automated CD8+ Tumor-infiltrating Lymphocyte Scoring (ATLS-8) system to assess its prognostic value.

In the discovery cohort, the 5-year overall survival (OS) rates were 34.05% for ATLS-8 low-score and 65.03% for ATLS-8 high-score groups (hazard ratio [HR] 2.40; 95% CI, 1.37-4.19; p = 0.015). These findings were confirmed in validation cohort 1, which had 5-year OS rates of 28.57% and 68.73% (HR 3.38; 95% CI, 1.27-9.02; p = 0.0098), and validation cohort 2, which had 59.26% and 81.48% (HR 2.74; 95% CI, 1.05-7.15; p = 0.031). ATLS-8 improved the prognostic model based on clinical variables (C-index 0.770 vs. 0.757; 0.769 vs. 0.727; 0.712 vs. 0.642 in three cohorts).

We developed an automated system using CD8-stained whole-slide images to assess immune infiltration (ATLS-8). In patients with HCC undergoing resection, higher CD8+ TIL density correlates with better OS, as per ATLS-8 assessment. This system is a promising tool for advancing clinical immune microenvironment assessment and outcome prediction. IMPACT AND IMPLICATIONS: CD8+ tumor-infiltrating lymphocytes (TILs) have been identified as a prognostic factor associated with many cancers. In this study, CD8+ TILs were identified as an independent prognostic factor for overall survival in patients with hepatocellular carcinoma who undergoing liver resection. Therefore, ATLS-8, a novel digital biomarker based on whole-slide image-level CD8+ TILs, could play an important role in the prognostic assessment of patients with HCC and could be integrated into clinicopathological models to participate in the decision-making and prognostic assessment of patients. The scoring system combined with artificial intelligence is essential for automated, quantitative, whole-slide image-level assessment of TILs, which can be widely applied to quantify the immune profile of multi-cancer disease types with the discussion of subsequent immunotherapy.