Statistical Textural Distinctiveness in Multi-Parametric Prostate MRI for Suspicious Region Detection

Prostate cancer is the most diagnosed form of cancer, but survival rates are relatively high with sufficiently early diagnosis. Current computer-aided image-based cancer detection methods face notable challenges include noise in MRI images, variability between different MRI modalities, weak contrast, and non-homogeneous texture patterns, making it difficult for diagnosticians to identify tumour candidates. We propose a novel saliency-based method for identifying suspicious regions in multi-parametric MR prostate images based on statistical texture distinctiveness. In this approach, a sparse texture model is learned via expectation maximization from features derived from multi-parametric MR prostate images, and the statistical texture distinctiveness-based saliency based on this model is used to identify suspicious regions. The proposed method was evaluated using real clinical prostate MRI data, and results demonstrate a clear improvement in suspicious region detection relative to the state-of-art method.