Radiomics to predict prostate cancer aggressiveness: a preliminary study

Radiomics is encouraging a paradigm shift in oncological diagnostics towards the symbiosis of radiology and Artificial Intelligence (AI) techniques. The aim is to exploit very accurate, robust image processing algorithms and provide quantitative information about the phenotypic differences of cancer traits. By exploring the association between this quantitative information and patients' prognosis, AI algorithms are boosting the power of radiomics in the perspective of precision oncology. However, the choice of the most suitable AI method can determine the success of a radiomic application. The current state-of-the art methods in radiomics aim at extracting statistical features from biomedical images and, then, process them with Machine Learning (ML) techniques. Many works have been reported in the literature presenting various combinations of radiomic features and ML methods. In this preliminary study, we aim to analyse the performance of a radiomic approach to predict prostate cancer (PCa) aggressiveness from multiarametric Magnetic Resonance Imaging (mp-MRI). Clinical mp-MRI data were collected from patients with histology-confirmed PCa and labelled by a team of expert radiologists. Such data were used to extract and select two sets of radiomic features; hence, the classification performances of five classifiers were assessed. This analysis is meant as a preliminary step towards the overall goal of investigating the potential of radiomic-based analyses.