Evaluating Cancer-Related Biomarkers Based on Pathological Images: A Systematic Review.

Xiaoliang Xie,Yuebin Liang,Geng Tian,Yan Wu,Xin Sun,Li Li,Binsheng He,Pingping Bing,Xiaoli Shi,Xulin Wang,Jingya Yang

doi:10.3389/fonc.2021.763527

Abstract

Many diseases are accompanied by changes in certain biochemical indicators called biomarkers in cells or tissues. A variety of biomarkers, including proteins, nucleic acids, antibodies, and peptides, have been identified. Tumor biomarkers have been widely used in cancer risk assessment, early screening, diagnosis, prognosis, treatment, and progression monitoring. For example, the number of circulating tumor cell (CTC) is a prognostic indicator of breast cancer overall survival, and tumor mutation burden (TMB) can be used to predict the efficacy of immune checkpoint inhibitors. Currently, clinical methods such as polymerase chain reaction (PCR) and next generation sequencing (NGS) are mainly adopted to evaluate these biomarkers, which are time-consuming and expansive. Pathological image analysis is an essential tool in medical research, disease diagnosis and treatment, functioning by extracting important physiological and pathological information or knowledge from medical images. Recently, deep learning-based analysis on pathological images and morphology to predict tumor biomarkers has attracted great attention from both medical image and machine learning communities, as this combination not only reduces the burden on pathologists but also saves high costs and time. Therefore, it is necessary to summarize the current process of processing pathological images and key steps and methods used in each process, including: (1) pre-processing of pathological images, (2) image segmentation, (3) feature extraction, and (4) feature model construction. This will help people choose better and more appropriate medical image processing methods when predicting tumor biomarkers.

Highlights

Biomarkers are critical in cancer diagnosis, treatment, and prognosis
Kather et al developed a deep residual learning method that can predict Microsatellite instability (MSI) status directly from hematoxylin and eosin (H&E) stained histology slides [17]. These findings suggest that inferring genomic features from histopathological images is possible and analyzing histopathological images is important for studying cancer treatments, mutated gene expression status, cancer prognosis and risk of recurrence
Based on the above problems, this paper summarizes the whole process and key steps of current pathological image processing, including image preprocessing, image segmentation, feature extraction and model construction, to help researchers choose more suitable medical image processing methods and predict biomarkers more accurately

Summary

Introduction

Biomarkers are critical in cancer diagnosis, treatment, and prognosis. They can be used for patient’s evaluation in a variety of clinical settings, such as risk assessment, early diagnosis, drug effect evaluation, and prognosis prediction [1,2,3]. Yu [12] for the first time constructed the recurrence risk prediction model of LUAD and LUSC by automatically extracting morphological features from the full-scan histopathological images of lung cancer to provide prognostic information for patients.

Results

Conclusion