Small Lesions Evaluation Based on Unsupervised Cluster Analysis of Signal-Intensity Time Courses in Dynamic Breast MRI

A Meyer-Baese,O Lange,T Schlossbauer,A Wismueller

doi:10.1155/2009/326924

Abstract

An application of an unsupervised neural network-based computer-aided diagnosis (CAD) system is reported for the detection and characterization of small indeterminate breast lesions, average size 1.1 mm, in dynamic contrast-enhanced MRI. This system enables the extraction of spatial and temporal features of dynamic MRI data and additionally provides a segmentation with regard to identification and regional subclassification of pathological breast tissue lesions. Lesions with an initial contrast enhancement ≥50% were selected with semiautomatic segmentation. This conventional segmentation analysis is based on the mean initial signal increase and postinitial course of all voxels included in the lesion. In this paper, we compare the conventional segmentation analysis with unsupervised classification for the evaluation of signal intensity time courses for the differential diagnosis of enhancing lesions in breast MRI. The results suggest that the computerized analysis system based on unsupervised clustering has the potential to increase the diagnostic accuracy of MRI mammography for small lesions and can be used as a basis for computer-aided diagnosis of breast cancer with MR mammography.

Highlights

Breast cancer is one of the most common cancer among women
The results indicate that the enhancement kinetics, as represented by the time-signal intensity curves visualized in Figure 1, differ significantly for benign and malignant enhancing lesions and represent a basis for differential diagnosis
Clustering results were evaluated by (i) qualitative visual inspection of cluster assignment maps, that is, cluster membership maps according to a minimal distance criterion in the metric of the pixel-time course (PTC) feature space shown for the “neural-gas” network, (ii) qualitative visual inspection of corresponding cluster-specific time-signal intensity curves for the “neural-gas” network, (iii) optimal parameter combination, (iv) optimal number of clusters, (v) comparison between “neural-gas” network, minimal free energy vector quantization and conventional segmentation method, and (vi) receiver operating characteristic (ROC) analysis

Summary

Introduction

Breast cancer is one of the most common cancer among women. Dynamic magnetic resonance imaging (MRI) of the breast was reported to be a highly sensitive method for detection and further evaluation of clinically, mammographically, and sonographically occult cancers [1]. Two different approaches are mentioned in literature [2] aiming to improve the specificity: (1) single-breast imaging protocols with high spatial resolution offer a meticulous analysis of the lesion’s structure and internal architecture and are able to distinguish between benign and malignant lesions and (2) lesion differential diagnosis in dynamic protocols is based on the assumption that benign and malignant lesions exhibit different enhancement kinetics. In [2], it was shown that the shape of the time-signal intensity curve represents an important criterion in differentiating benign and malignant enhancing lesions in dynamic breast MR imaging. Progressive signal intensity time courses (type I) are exhibited by benign enhancing lesions. These enhancement kinetics are shared by benign tumors and by fibrocystic changes [2]

Methods

Results

Conclusion