MRI imaging texture features in prostate lesions classification

Abstract

Prostate cancer (PCa) is the most common diagnosed cancer and cause of cancer-related death among men. Computer Aided Diagnosis (CAD) systems are used to support radiologists in multiparametric Magnetic Resonance (mpMR) image-based analysis in order to avoid unnecessary biopsis and increase radiologist’s specificity. CAD systems have been reported in many papers for the last decade. The reported results have been obtained on small, private data sets and are impossible to reproduce or verify concluded remarks. PROSTATEx challenge organizers provided database that contains approximately 350 MRI cases, each from a distinct patient, allowing benchmarking of various CAD systems. This paper describes novel, deep learning based PCa CAD system that uses statistical central moments and Haralick features extracted from MR images, integrated with anamnestic data. Developed system has been trained on the dataset consisting of 330 lesions and evaluated on the challenge dataset using area under curve (AUC) related to estimated receiver operating characteristic (ROC). Two configurations of our method, based on statistical and Haralick features, scored 0.63 and 0.73 of AUC values. We draw conclusions from the challenge participation and discussed further improvements that could be made to the model to improve prostate classification.