Neural Network Analysis of Dynamic Contrast-Enhanced MRI Mammography

Abstract

We present a neural network clustering approach to the analysis of dynamic contrast-enhanced magnetic resonance imaging (MRI) mammography time-series. In contrast to conventional extraction of a few voxel-based perfusion parameters, neural network clustering does not discard information contained in the complete signal dynamics time-series data. We performed exploratory data analysis in patients with breast lesions classified as indeterminate from clinical findings and conventional X-ray mammography. Minimal free energy vector quantization provided a self-organized segmentation of voxels w.r.t. fine-grained differences of signal amplitude and dynamics, thus identifying the lesions from surrounding tissue and enabling a subclassification within the lesions with regard to regions characterized by different MRI signal time-courses. We conclude that neural network clustering can provide a useful extension to the conventional visual inspection of interactively defined regions-of-interest. Thus, it can contribute to the diagnosis of indeterminate breast lesions by non-invasive imaging.