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

Abstract

Advanced image analysis, including radiomics, has recently acquired recognition as a source of biomarkers, although there are some technical and methodological challenges to face for its application in the clinic. Among others, proper phenotyping of metastatic or systemic disease where multiple lesions coexist is an issue, since each lesion contributes to characterization of the disease. Therefore, the radiomic profile of each lesion should be modeled into a more complex architecture able to reproduce each “unit” (lesion) as a part of the “entire” (patient). This work aimed to characterize intra-tumor heterogeneity underpinning metastatic prostate cancer using an exhaustive innovative approach which consist of a i) feature transformation method to build an agnostic (i.e., irrespective of pre-existence knowledge, experience, and expertise) radiomic profile of lesions extracted from [18F]FMCH PET/CT, ii) qualitative assessment of intra-tumor heterogeneity of patients, iii) quantitative representation of the intra-tumor heterogeneity of patients in terms of the relationship between their lesions’ profiles, to be associated with prognostic factors. We confirmed that metastatic prostate cancer patients encompassed 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.

Radiomic-Based Prediction of Lesion-Specific Systemic Treatment Response in Metastatic Disease

“…Most published radiomic studies extract radiomic features from only one lesion, even in multi metastatic patients. While analyzing a single lesion may be less time-consuming and involve simpler mathematical models, it may also lead to misevaluation of the cancer inter-lesion heterogeneity [7], [17], [40], [41]. This is especially consequential in the context of predicting patient-specific outcomes such as overall treatment response or patient survival; hence, we sought only to predict tumor response at a lesion level.…”

“…Patients who relapse with a single metastatic lesion can occasionally be cured by surgery or radiotherapy, but single metastases are the exception rather than the rule [5], [6]. Unfortunately, metastatic sites develop unique phenotypes and genotypes [7], [8]. As such, eradicating a subset of metastatic lesions in a patient is not likely to provide adequate long-term disease control.…”