摘要：SummaryLess than 35% of advanced patients with high-grade serous ovarian cancer (HGSOC) survive for 5 years after diagnosis. Here, we developed radiomics-based models to predict HGSOC clinical outcomes using preoperative contrast-enhanced computed tomography (CECT) images. 891 radiomics features were extracted between primary, metastatic, or lymphatic lesions from preoperative venous phase CECT images of 217 patients with HGSOC. A heuristic method,FrequencyAppearance inMultipleUnivariate preScreening (FAMUS), was proposed to identify stable and task-relevant radiomic features. Using FAMUS, we constructed predictive models of overall survival and disease-free survival in patients with HGSOC based on these stable radiomic features. According to their CT images, patients with HGSOC can be accurately stratified into high-risk or low-risk groups for cancer-related death within 2-6 years or for likely recurrence within 1-5 years. These radiomic models provide convincing and reliable non-invasive markers for individualized prognostic evaluation and clinical decision-making for patients with HGSOC.Graphical abstractDisplay OmittedHighlights•FrequencyAppearance inMultipleUnivariate preScreening (FAMUS) identifies stable and task-relevant radiomic features from computed tomography (CT) images•Radiomics-based signatures are highly predictive of the clinical outcome of high-grade serous ovarian cancer (HGSOC)•FAMUS improves the prognostic performance of radiomics-based prediction models•Developed radiomic models can help clinicians tailor treatment plans for HGSOCRadiology; Medical imaging; Cancer
