A novel and automatic pectoral muscle identification algorithm for mediolateral oblique (MLO) view mammograms using ImageJ

TL;DR

This paper introduces an automatic algorithm for identifying pectoral muscles in MLO view mammograms, improving accuracy over traditional methods by handling curved boundaries, and is implemented using ImageJ for both digital and scanned images.

Contribution

The paper presents a novel, fully automatic pectoral muscle identification method suitable for various mammogram types, implemented in ImageJ, and validated with real-world data.

Findings

The algorithm accurately identifies pectoral muscles in diverse mammogram images.

It outperforms manual and straight line fitting methods in boundary detection.

Validation shows promising results on real-world datasets.

Abstract

Pectoral muscle identification is often required for breast cancer risk analysis, such as estimating breast density. Traditional methods are overwhelmingly based on manual visual assessment or straight line fitting for the pectoral muscle boundary, which are inefficient and inaccurate since pectoral muscle in mammograms can have curved boundaries. This paper proposes a novel and automatic pectoral muscle identification algorithm for MLO view mammograms. It is suitable for both scanned film and full field digital mammograms. This algorithm is demonstrated using a public domain software ImageJ. A validation of this algorithm has been performed using real-world data and it shows promising result.