AUTHOR=Qu Wei-Feng , Tian Meng-Xin , Qiu Jing-Tao , Guo Yu-Cheng , Tao Chen-Yang , Liu Wei-Ren , Tang Zheng , Qian Kun , Wang Zhi-Xun , Li Xiao-Yu , Hu Wei-An , Zhou Jian , Fan Jia , Zou Hao , Hou Ying-Yong , Shi Ying-Hong TITLE=Exploring pathological signatures for predicting the recurrence of early-stage hepatocellular carcinoma based on deep learning JOURNAL=Frontiers in Oncology VOLUME=12 YEAR=2022 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.968202 DOI=10.3389/fonc.2022.968202 ISSN=2234-943X ABSTRACT=Background

Postoperative recurrence impedes the curability of early-stage hepatocellular carcinoma (E-HCC). We aimed to establish a novel recurrence-related pathological prognosticator with artificial intelligence, and investigate the relationship between pathological features and the local immunological microenvironment.

Methods

A total of 576 whole-slide images (WSIs) were collected from 547 patients with E-HCC in the Zhongshan cohort, which was randomly divided into a training cohort and a validation cohort. The external validation cohort comprised 147 Tumor Node Metastasis (TNM) stage I patients from The Cancer Genome Atlas (TCGA) database. Six types of HCC tissues were identified by a weakly supervised convolutional neural network. A recurrence-related histological score (HS) was constructed and validated. The correlation between immune microenvironment and HS was evaluated through extensive immunohistochemical data.

Results

The overall classification accuracy of HCC tissues was 94.17%. The C-indexes of HS in the training, validation and TCGA cohorts were 0.804, 0.739 and 0.708, respectively. Multivariate analysis showed that the HS (HR= 4.05, 95% CI: 3.40-4.84) was an independent predictor for recurrence-free survival. Patients in HS high-risk group had elevated preoperative alpha-fetoprotein levels, poorer tumor differentiation and a higher proportion of microvascular invasion. The immunohistochemistry data linked the HS to local immune cell infiltration. HS was positively correlated with the expression level of peritumoral CD14+ cells (p= 0.013), and negatively with the intratumoral CD8+ cells (p< 0.001).

Conclusions

The study established a novel histological score that predicted short-term and long-term recurrence for E-HCCs using deep learning, which could facilitate clinical decision making in recurrence prediction and management.