Radiomics and Artificial Intelligence for Outcome Prediction in Multiple Myeloma Patients

The significant clinical heterogeneity of Multiple Myeloma (MM) patients implies that a set of consolidated biomarkers is currently missing. Radiomics is an advanced, quantitative feature-based methodology for image analysis. We assess the feasibility of an AI-based approach for the automatic stratification of MM patients from CT data, and for the automatic identification of radiological biomarkers with a possible prognostic value. A retrospective analysis of n = 33 transplanted MM with focal lesion were performed via an open-source toolbox that extracted 109 radiomics features. The redundancy reduction was realized via correlation and principal component analysis. The highest sensitivity and critical success index (CSI) were obtained representing each patient, with 17 focal features selected via correlation with the 24 features describing the overall skeletal asset. The Mann– Whitney U-test showed that three among the 17 imaging descriptors passed the null hypothesis. This computational approach to the interpretation of radiomics features shows the potential for the stratification of relapsed and non-relapsed MM patients, and could represent a prognostic image-based procedure for determining the disease follow-up and therapy.