DCS-NET: A multi-task model for detection of key anatomical structures and automatic staging of early endometrial cancer in MRI

Endometrial cancer (EC) is the most common gynecologic malignancy, with a steadily increasing incidence worldwide. Abnormal vaginal bleeding, a hallmark symptom, enables early diagnosis, which is critical for improving clinical outcomes. Pelvic magnetic resonance imaging (MRI) serves as the primary imaging modality for EC evaluation, offering detailed visualization of endometrial and myometrial invasion.This study proposes DCS-Net, a multi-task deep learning framework for the automated detection and staging of early-stage EC in MRI. The framework incorporates an advanced object detection module to accurately localize and crop the uterine region, followed by a convolutional neural network for staging classification.Experimental results show that the detection module achieves high localization performance, and the classification network reaches an accuracy of 90.8%. The region-focused approach improves staging accuracy by 5% compared to direct classification using unprocessed images.These results underscore the potential of DCS-Net to improve diagnostic efficiency and accuracy in alignment with clinical workflows. Future work will explore the integration of multi-parametric MRI data to further enhance diagnostic performance and address broader clinical needs.