NOVEL PHANTOMS FOR ROBUST MRI-BASED RADIOMICS IN ONCOLOGY

Radiomics is the process of converting medical images into minable high-dimensional data to support clinical decision. A dedicated software is exploited to extract many synthetic biomarkers, called radiomic features, which can be correlated with specific clinical outcomes and may uncover disease characteristics that failed to be appreciated by visual inspection of the images. In pelvic and breast cancer, MRI-based radiomics has been investigated for its potential to describe the tumour heterogeneity, thus improving diagnosis, prognosis and early therapy assessment, and it has shown promising results. However, the process lacks standardisation and harmonisation of the methods employed, from the image processing to the building of predictive models. Parts of these challenges can be investigated with phantom studies, which offer the possibility of repeated acquisition in controlled experimental setup. In this thesis, a pelvic phantom dedicated to MRI-based radiomics has been designed, developed and validated for the first time. A research has been conducted to identify the materials and geometry of the phantom in such a way that it could mimic the MR signal and texture of a tumour and its surrounding tissues, as seen in a set of representative patients. The phantom has been used for a multicentric evaluation of the repeatability and reproducibility of the radiomic features extracted from images acquired on three MR scanners of two vendors and two magnetic field strengths. This study allowed to identify a set of robust radiomic features to support studies on clinical datasets of patients with pelvic cancer. In addition, three radiomic software products for feature extraction have been tested to assess the impact of the choice of a specific tool on the value of the features. A prototype of a radiomic breast phantom has been assembled in the last part of the thesis work, including a 3D-printed insert to mimic a real tumour.