This master’s project focuses on improving personalized treatments for high-grade serous ovarian cancer (HGSOC), the most common subtype of ovarian cancer, by addressing its significant heterogeneity. Currently, personalized approaches are limited, creating an urgent need for biomarkers that can capture tumor diversity. The project explores the integration of radiomics, which extracts tumor-specific data from medical images (e.g., CT, MRI), with multiomics data (genomics, transcriptomics, etc.). Combining these datasets allows a holistic view of the tumor, bridging microscopic and macroscopic scales and offering spatio-temporal insights critical for individualized therapies. The project is part of the ERC-funded MROMICS initiative and investigates the use of AI and machine learning for multimodal data integration. It aims to develop pipelines for predictive modeling and survival analysis while ensuring the robustness and reproducibility of radiomics features. Tasks include feature selection using advanced methods, training state-of-the-art machine learning models (e.g., logistic regression, random forests), and designing multimodal fusion pipelines that can handle diverse clinical data types. The ultimate goal is to advance understanding of tumor heterogeneity and optimize treatment strategies. The position, supervised by Pr. Stéphanie Nougaret, is based in the PINKCC lab at the Montpellier Cancer Institute and supported by Montpellier SIRIC. The trainee will join a multidisciplinary team focused on AI-driven virtual biopsies and innovative biomedical imaging. They will also collaborate with the microimaging platform and the Montpellier Cancer Research Institute. This six-month Master 2 project offers a hands-on opportunity to contribute to cutting-edge research, with flexibility to explore individual interests within the broader goals of the initiative.