Caner Ercan,Salvatore Lorenzo Renne,Luca Di Tommaso,Charlotte K Y Ng,Salvatore Piscuoglio,Luigi M Terracciano
{"title":"Hepatocellular Carcinoma Immune Microenvironment Analysis: A Comprehensive Assessment with Computational and Classical Pathology.","authors":"Caner Ercan,Salvatore Lorenzo Renne,Luca Di Tommaso,Charlotte K Y Ng,Salvatore Piscuoglio,Luigi M Terracciano","doi":"10.1158/1078-0432.ccr-24-0960","DOIUrl":null,"url":null,"abstract":"PURPOSE\r\nThe 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.\r\n\r\nEXPERIMENTAL DESIGN\r\nNinety-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.\r\n\r\nRESULTS\r\nTwo 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%.\r\n\r\nCONCLUSIONS\r\nOur 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.","PeriodicalId":10279,"journal":{"name":"Clinical Cancer Research","volume":null,"pages":null},"PeriodicalIF":10.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Cancer Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1158/1078-0432.ccr-24-0960","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
PURPOSE
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.
EXPERIMENTAL DESIGN
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.
RESULTS
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%.
CONCLUSIONS
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.
期刊介绍:
Clinical Cancer Research is a journal focusing on groundbreaking research in cancer, specifically in the areas where the laboratory and the clinic intersect. Our primary interest lies in clinical trials that investigate novel treatments, accompanied by research on pharmacology, molecular alterations, and biomarkers that can predict response or resistance to these treatments. Furthermore, we prioritize laboratory and animal studies that explore new drugs and targeted agents with the potential to advance to clinical trials. We also encourage research on targetable mechanisms of cancer development, progression, and metastasis.