The five-year survival rate of epithelial ovarian cancer (EOC) is approximately 35–40% despite maximal treatment efforts, highlighting a need for stratification biomarkers for personalized treatment. Here we extract 657 quantitative mathematical descriptors from the preoperative CT images of 364 EOC patients at their initial presentation. Using machine learning, we derive a non-invasive summary-statistic of the primary ovarian tumor based on 4 descriptors, which we name “Radiomic Prognostic Vector” (RPV). RPV reliably identifies the 5% of patients with median overall survival less than 2 years, significantly improves established prognostic methods, and is validated in two independent, multi-center cohorts. Furthermore, genetic, transcriptomic and proteomic analysis from two independent datasets elucidate that stromal phenotype and DNA damage response pathways are activated in RPV-stratified tumors. RPV and its associated analysis platform could be exploited to guide personalized therapy of EOC and is potentially transferrable to other cancer types.

Purpose: Build predictive radiomic models for early relapse and BRCA mutation based on a multicentric database of high-grade serous ovarian cancer (HGSOC) and validate them in a test set coming from different institutions. Methods: Preoperative CTs of patients with HGSOC treated at four referral centers were retrospectively acquired and manually segmented. Hand-crafted features and deep radiomics features were extracted respectively by dedicated software (MODDICOM) and a dedicated convolutional neural network (CNN). Features were selected with and without prior harmonization (ComBat harmonization), and models were built using different machine learning algorithms, including clinical variables. Results: We included 218 patients. Radiomic models showed low performance in predicting both BRCA mutation (AUC in test set between 0.46 and 0.59) and 1-year relapse (AUC in test set between 0.46 and 0.56); deep learning models demonstrated similar results (AUC in the test of 0.48 for BRCA and 0.50 for relapse). The inclusion of clinical variables improved the performance of the radiomic models to predict BRCA mutation (AUC in the test set of 0.74). Conclusions: In our multicentric dataset, representative of a real-life clinical scenario, we could not find a good radiomic predicting model for PFS and BRCA mutational status, with both traditional radiomics and deep learning, but the combination of clinical and radiomic models improved model performance for the prediction of BRCA mutation. These findings highlight the need for standardization through the whole radiomic pipelines and robust multicentric external validations of results.

No abstract

The ovarian cancer recurrence occurs in 75% of patients with advanced FIGO stage, and its treatment is a challenge for the oncologist in gynecology. The standard treatment of recurrent ovarian cancer (ROC) usually includes intravenous chemotherapy according to platinum sensitivity. Furthermore, maintenance treatment with target therapies [e.g., anti-angiogenic drug or PARP inhibitors (PARPi)], should be provided if not precedently administrated. In this scenario, secondary cytoreductive surgery (SCS) remains a practical but controversial option for platinum-sensitive ROC (PSROC). So far, several retrospective series and a Cochrane meta-analysis had concluded that SCS could determine better survival outcomes in ROC with favorable prognostic characteristics, such as the presence of a single anatomical site of recurrence, or when patients are accurately selected for surgery based on complete resection's predictive models. Recently, three randomized clinical trials (RCTs) investigated the role of SCS in PSROC patients selected with different criteria. All the three RCTs showed a significant statistical advantage in progression-free survival (PFS) in the SCS group, with an even more significant difference in patients with complete cytoreduction (about 7-month PFS increased). Data on overall survival (OS) are different in the two completed trials. The GOG213 study has documented a longer OS of PSROC patients who received chemotherapy alone compared to surgery plus chemotherapy. Contrarily, the DESKTOP III trial showed 7.7 months of increased OS in the surgery group vs. chemotherapy alone, with a more difference in the complete tumor cytoreduction (CTC) group (12 months). These RCTs thereby suggest that undergoing complete cytoreduction may not be the only key and that the disease biology may also matter. Few recent retrospective series investigated the role of SCS according to BRCA mutation status and the effect of SCS in patients receiving emerging PARPi. A consequence of the developments in SCS and knowledge of different molecular pathways influencing the recurrent disease is that the future research objective should be to individualize and personalize the surgical approach.