Ovarian cancer is challenging due to late diagnosis and diverse subtypes. This study uses CNN-based models (MobileNet, DenseNet) for histopathological image classification and applies machine learning (Logistic Regression, Random Forest, XGBoost) for PCOS outlier detection. The system is supported by a Python backend and an intuitive web interface to assist clinicians. This integrated approach improves diagnostic accuracy and contributes to better patient outcomes.