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

Ignacio Alvarez Illan,Pascal Baltzer,Thomas Helbich,Maria Adele Marino,J M Gorriz,Javier Ramirez,Katja Pinker,Anke Meyer-Baese,Daly Avendano

doi:10.1155/2018/5308517

Abstract

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.

Highlights

Accurate methods for early diagnosis of breast cancer are pivotal and contribute to an improved prognosis and survival outcomes in breast cancer patients. ere is a consensus that dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is the most sensitive test for breast cancer detection and the backbone of any MRI protocol, enabling simultaneous assessment of tumor morphology and enhancement kinetics that evaluate neoangiogenesis as a tumorspeci c feature
We examined the relationship between the false-positive rate of computer-aided diagnosis (CAD) systems for breast cancer diagnosis and lesion segmentation on DCE-MRI
Results e scores de ned in Equation (1) are depicted in two di erent spaces: the 3DDCE-MRI space coregistered with the original data (Figure 3) and the E subspace spanned by the rst two temporal sources a1 and a2 (Figure 4), sorted according to the mean squared error (MSE)-de ned criteria. e representation in the 3DDCE-MRI space shows that similar score values are grouped together around tissues that have a similar enhancement

Summary

Research Article

Ignacio Alvarez Illan ,1 Javier Ramirez ,1 J. Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. 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 di erent 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 classi ed 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

Introduction

Methods

Benign Malignant SVs

False positive rate

Validation DSC