Small lesions evaluation based on unsupervised cluster analysis of signal-intensity time courses in dynamic breast MRI.

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.

Analysis of dynamic susceptibility contrast MRI time series based on unsupervised clustering methods.

We compare five different unsupervised clustering techniques as tools for the analysis of dynamic susceptibility contrast MRI time series. The study included four subjects: two subjects with stroke and two subjects without focal neurological deficit. The goal was to determine the robustness and reliability of clustering methods in providing a self-organized segmentation of perfusion MRI data sharing common properties of signal dynamics. For this purpose, the relative signal reduction time series was computed for each pixel. Clustering of the resulting high-dimensional feature vectors was performed by minimal free-energy deterministic annealing, self-organizing maps, two variants of fuzzy c-means clustering (FVQ and FSM), and the neural gas algorithm. Clustering results were evaluated by visual assessment of cluster assignment maps and corresponding signal time curves as well as by quantitative comparison of cluster assignment maps with conventional pixel-specific perfusion parameter maps based on quantitative receiver operating characteristic (ROC) curve analysis. Clustering methods provided a functional segmentation with respect to vessel size, detected side asymmetries of contrast-agent first pass, and identified regions of perfusion deficits in subjects with stroke. As confirmed by quantitative ROC analysis, the clustering approach can detect regions of reduced brain perfusion with high accuracy when compared to conventional analysis by pixel-specific cerebral blood volume and mean transit time maps. We conclude that by unveiling differences of signal dynamics and amplitude, clustering is a useful tool to analyze and visualize regional properties of brain perfusion. Thus, it may contribute to the computer-aided diagnosis of cerebral circulation deficits by noninvasive neuroimaging.