Automated detection and segmentation of non-mass enhancing breast tumors with dynamic contrast-enhanced magnetic resonance imaging

TL;DR

This paper introduces a novel CAD system for detecting and segmenting non-mass enhancing breast tumors in DCE-MRI by leveraging ICA for feature extraction and SVM for classification, improving accuracy over previous methods.

Contribution

The study presents a new ICA-based feature extraction method combined with SVM classification for NME detection, addressing false positives more effectively than prior approaches.

Findings

ICA effectively captures dynamic lesion features

SVM classification improves detection accuracy

Controlled hyperplane reduces false positives

Abstract

Non-mass enhancing lesions (NME) constitute a diagnostic challenge in dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer Aided Diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from DCE-MRI dataset of breast patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.