Radiomics-Based Inter-Lesion Relation Network to Describe [18F]FMCH PET/CT Imaging Phenotypes in Prostate Cancer

Advanced image analysis, specifically radiomics, has been recognized as a potential source of biomarkers for cancers. However, there are challenges to its application in the clinic, such as proper description of diseases where multiple lesions coexist. In this study, we aimed to characterize the intra-tumor heterogeneity of metastatic prostate cancer using an innovative approach. This approach consisted of a transformation method to build a radiomic profile of lesions extracted from [18F]FMCH PET/CT images, a qualitative assessment of intra-tumor heterogeneity of patients, and a quantitative representation of the intra-tumor heterogeneity of patients in terms of the relationship between their lesions’ profiles. We found that metastatic prostate cancer patients had lesions with different radiomic profiles that exhibited intra-tumor radiomic heterogeneity and that the presence of many radiomic profiles within the same patient impacted the outcome.