Resumen
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.