A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis

Abstract

Pathology image analysis is an essential procedure for clinical diagnosis of many diseases. To boost the accuracy and objectivity of detection, nowadays, an increasing number of computer-aided diagnosis (CAD) system is proposed. Among these methods, random field models play an indispensable role in improving the analysis performance. In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models. Firstly, we introduce the background of two random fields and pathology images. Secondly, we summarize the basic mathematical knowledge of MRFs and CRFs from modelling to optimization. Then, a thorough review of the recent research on the MRFs and CRFs of pathology images analysis is presented. Finally, we investigate the popular methodologies in the related works and discuss the method migration among CAD field.

A Hierarchical Conditional Random Field-based Attention Mechanism Approach for Gastric Histopathology Image Classification

“…Furthermore, we combine the AM with the HCRF model and apply them in classification tasks, obtaining preliminary research results in [45]. For more information, please refer to our previous survey paper [46]. The spatial dependencies on patches are usually neglected in previous GHIC tasks, and the inference is only based on the appearance of individual patches.…”

“…The AM module is integrated to assist the CNN classifier with extracting key characteristics of the abnormal images and reducing redundant information mean-while. The HCRF, which is the improvement of CRF [47], have excellent attention area detection performance, because it can characterize the spatial relationship of images [46]. The fundamental definition of CRFs will be introduced first.…”