Table of Contents Author Guidelines Submit a Manuscript
Contrast Media & Molecular Imaging
Volume 2018, Article ID 5308517, 11 pages
Research Article

Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging

1Signal Theory and Communications Department, Universidad de Granada, Granada, Spain
2Department of Radiology, Memorial Sloan-Kettering Cancer Center, NewYork, USA
3Department of Biomedical Imaging and Image-Guided Therapy, Division of Molecular and Gender Imaging, Medical University Vienna/AKH Wien, Wien, Austria
4Scientific Computer Department, Florida State University, Tallahassee, FL 32306, USA

Correspondence should be addressed to Ignacio Alvarez Illan; se.rgu@nalli

Katja Pinker and Anke Meyer-Baese contributed equally to this work.

Received 31 July 2018; Accepted 16 September 2018; Published 24 October 2018

Academic Editor: Orazio Schillaci

Copyright © 2018 Ignacio Alvarez Illan et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Nonmass-enhancing (NME) lesions 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 lesion 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 the DCE-MRI dataset of breast cancer 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.