CT-Based Radiomics and Deep Learning for BRCA Mutation and Progression-Free Survival Prediction in Ovarian Cancer Using a Multicentric Dataset

SIMPLE SUMMARY: Ovarian cancer has a heterogeneous response to treatment, and relapse may vary considerably. Different studies investigated the role of radiomics in ovarian cancer. However, many of them were performed in a single center, and solid external validation of findings is still missing. We used a multicentric database of high-grade serous ovarian cancer to build predictive radiomic and deep-learning models for early relapse and BRCA mutation, validating them in a different set of cases coming from other institutions. 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 methods. This study highlights that to implement the radiomics approach in clinical routine, we still need standardization of acquisition protocols, validation of harmonization method and radiomic pipelines, other than robust, prospective, multicentric, external validations of findings. ABSTRACT: 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.