Ovarian Cancer Identification on CT Using Deep Learning

Ovarian cancer remains the deadliest gynecologic malignancy, with poor survival rates largely due to late-stage diagnosis. Early detection is crucial, yet no universally accepted screening method exists. Current imaging techniques and biomarkers, such as CA-125, have limitations in specificity and sensitivity. This study aims to develop and evaluate a deep learning-based computer-aided diagnosis tool (CAT-OV), for ovarian cancer detection using CT imaging. The system integrates a Body Part Regression (BPR) model for pelvic localization and a Multiple Instance Learning (MIL) ensemble classifier for cancer prediction. The model was trained and validated using retrospective datasets from Taiwan, the United States, and a nationwide real-world cohort. Stringent preprocessing and quality control measures were implemented to enhance model accuracy. Results highlight the potential of AI-driven CT screening in improving early detection, though further validation is needed for clinical adoption.

Inclusion Criteria: 1. Age ≥ 20 years old. 2. Female 3. undergone a CT scan 4. undergone a CT scan within 180 days prior to ovarian surgery for histopathological evaluation. Exclusion Criteria: 1. Age \< 20 years old. 2. Non-female 3. Non-CT imaging 4. Incorrect image orientation 5. Number of slices \< 10 6. Slice thickness \>10 mm or \< 1 mm 7. Unsuccessful DICM-to-NIfTI 8. Pelvic subvolume extraction failed 9. Non-contrast CT scans 10. Metallic artifacts 11. Inconclusive cases