A graph-based multi-kernel feature weight learning framework for detection and grading of prostate lesions using multi-parametric MR images

Prostate cancer is the third leading causes of death in men. However, the disease is curable if diagnosed early. During the past decades, multi-parametric magnetic resonance imaging (mpMRI) has been shown to be superior to trans-rectal ultrasound (TRUS) in detecting and localizing prostate cancer lesions to guide prostate biopsies and radiation therapies. The goal of this paper is to develop a simple and accurate graph-based regression framework for voxel-wise detection and grading of prostate cancer using mpMRIs. In the framework, groups of features were first extracted from the mpMRIs, and a graph-based multi-kernel model was proposed to learn the weights of the groups of features and the similarity matrix simultaneously. A Lapalacian regression model was then used to estimate the PIRADS score of each voxels which characterizes how likely a voxel is cancerous. Experimental results of detection and grading of prostate lesions evaluated by six metrics show that the proposed method yielded convincing results.