Hepatocellular Carcinoma Immune Microenvironment Analysis: A Comprehensive Assessment with Computational and Classical Pathology.

Abstract

The spatial variability and clinical relevance of the tumour immune microenvironment (TIME) are still poorly understood for hepatocellular carcinoma (HCC). Here we aim to develop a deep learning (DL)-based image analysis model for the spatial analysis of immune cell biomarkers, and microscopically evaluate the distribution of immune infiltration. Ninety-two HCC surgical liver resections and 51 matched needle biopsies were histologically classified according to their immunophenotypes: inflamed, immune-excluded, and immune-desert. To characterise the TIME on immunohistochemistry (IHC)-stained slides, we designed a multi-stage DL algorithm, IHC-TIME, to automatically detect immune cells and their localisation in TIME in tumour-stromal, centre-border segments. Two models were trained to detect and localise the immune cells on IHC-stained slides. The framework models, i.e. immune cell detection models and tumour-stroma segmentation, reached 98% and 91% accuracy, respectively. Patients with inflamed tumours showed better recurrence-free survival than those with immune-excluded or immune desert tumours. Needle biopsies were found to be 75% accurate in representing the immunophenotypes of the main tumour. Finally, we developed an algorithm that defines immunophenotypes automatically based on the IHC-TIME analysis, achieving an accuracy of 80%. Our DL-based tool can accurately analyse and quantify immune cells on IHC-stained slides of HCC. The microscopical classification of the TIME can stratify HCCs according to the patient prognosis. Needle biopsies can provide valuable insights for TIME-related prognostic prediction, albeit with specific constraints. The computational pathology tool provides a new way to study the HCC TIME.