A Dual-Task Deep-Learning Model with Fused Ultrasound Images for Simultaneous Typing and Grading of Cystocele

The authors aimed to develop and evaluate a dual-task deep-learning model, FD-Net, that utilizes fused 2D and 3D ultrasound images to automate the typing and grading of cystocele. Their results demonstrated that FD-Net outperformed single-modal models in diagnostic accuracy and F1-scores, suggesting its potential for clinical application in cystocele assessment.