An Automatic Patch-based Approach for HER-2 Scoring in Immunohistochemical Breast Cancer Images Using Color Features

TL;DR

This paper presents an automated, color feature-based method for HER-2 scoring in breast cancer images, achieving over 90% concordance with pathologists and reducing variability in diagnosis.

Contribution

It introduces a fully-automated, segmentation-free approach for HER-2 scoring using color features, improving consistency and accuracy in breast cancer diagnosis.

Findings

Achieved over 90% concordance with pathologist scores

Avoided segmentation to simplify the process

Demonstrated high reliability in HER-2 scoring

Abstract

Breast cancer (BC) is the most common cancer among women world-wide, approximately 20-25% of BCs are HER-2 positive. Analysis of HER-2 is fundamental to defining the appropriate therapy for patients with breast cancer. Inter-pathologist variability in the test results can affect diagnostic accuracy. The present study intends to propose an automatic scoring HER-2 algorithm. Based on color features, the technique is fully-automated and avoids segmentation, showing a concordance higher than 90% with a pathologist in the experiments realized.