Quantifying Cancer Likeness: A Statistical Approach for Pathological Image Diagnosis

TL;DR

This paper introduces a statistical method for automatically identifying cancer regions in pathological images, achieving high accuracy without needing precise boundary delineation, thus aiding pathologists.

Contribution

A novel statistical approach based on information theory for cancer region detection that simplifies the diagnostic process and improves efficiency.

Findings

Achieved AUCs of 0.95+ in cancer classification

Does not require precise boundary demarcation

Reduces pathologists' workload

Abstract

In this paper, we present a new statistical approach to automatically identify cancer regions in pathological images. The proposed method is built from statistical theory in line with evidence-based medicine. The two core technologies are the classification information of image features, which was introduced based on information theory and which cancer features take positive values, normal features take negative values, and the calculation technique for determining their spatial distribution. This method then estimates areas where the classification information content shows a positive value as cancer areas in the pathological image. The method achieves AUCs of 0.95 or higher in cancer classification tasks. In addition, the proposed method has the practical advantage of not requiring a precise demarcation line between cancer and normal. This frees pathologists from the monotonous and tedious work of building consensus with other pathologists.