Ovarian cancer poses a significant healthcare burden, characterized by late-stage diagnosis and poor prognosis. Current diagnostic modalities, including ultrasound, CT, and MRI, exhibit limited sensitivity and specificity, leading to diagnostic uncertainties and invasive diagnostic procedures. This study aims to address these challenges by using Computer-Aided Diagnostics (CADx) on CT- and MRI-scans for enhanced ovarian cancer detection. Leveraging both retrospective datasets and prospective data collection, this research seeks to evaluate CADx's predictive ability for distinguishing malignant from benign ovarian tumors. By using advanced imaging techniques and machine learning algorithms, we aim to develop strong diagnostic models capable of accurately identifying ovarian cancer, ultimately improving early detection rates and patient outcomes. The outcomes of this study hold promise for revolutionizing ovarian cancer diagnosis and improved survival rates for ovarian cancer patients.