Simple Summary: Clinical responses to the initial treatment of high grade serous ovarian cancer (HGSOC) vary greatly. Widespread intra-site and inter-site genomic heterogeneity presents significant challenges for the development of predictive biomarkers based on pre-treatment sampling of select individual tumors. Non-invasive stratification of patients with HGSOC by risk of outcome could facilitate a higher level of intervention for those with the highest risk of a poor outcome. We developed and validated a machine learning-based integrated marker of HGSOC outcomes to standard chemotherapy that combines a previously developed intra-site and inter-site CT radiomics measure called cluster dissimilarity (cluDiss) with clinical and genomic measures using two retrospective cohorts of internal and external institution datasets. Our approach was more accurate than conventional clinical and average radiomics measures for prognosticating progression-free survival and platinum resistance. Abstract: Purpose: Develop an integrated intra-site and inter-site radiomics-clinical-genomic marker of high grade serous ovarian cancer (HGSOC) outcomes and explore the biological basis of radiomics with respect to molecular signaling pathways and the tumor microenvironment (TME). Method: Seventy-five stage III-IVHGSOCpatients frominternal (N = 40) and external factors via the Cancer Imaging Archive (TCGA) (N = 35) with pre-operative contrast enhanced CT, attempted primary cytoreduction, at least two disease sites, and molecular analysis performed within TCGA were retrospectively analyzed. An intra-site and inter-site radiomics (cluDiss) measure was combined with clinical-genomic variables (iRCG) and compared against conventional (volume and number of sites) and average radiomics (N = 75) for prognosticating progression-free survival (PFS) and platinum resistance. Correlation with molecular signaling and TME derived using a single sample gene set enrichment that was measured. Results: The iRCG model had the best platinum resistance classification accuracy (AUROC of 0.78 [95% CI 0.77 to 0.80]). CluDiss was associated with PFS (HR 1.03 [95% CI: 1.01 to 1.05], p = 0.002), negatively correlated with Wnt signaling, and positively to immune TME. Conclusions: CluDiss and the iRCG prognosticated HGSOC outcomes better than conventional and average radiomic measures and could better stratify patient outcomes if validated on larger multi-center trials.
- Chemotherapy response prognostication
- Computed tomography
- High grade serous ovarian cancer
- Intra-site and inter-site radiomic heterogeneity
- Machine learning
ASJC Scopus subject areas
- Cancer Research