MRICondyleNet

##########

MRICondyleNet is a comprehensive medical image segmentation platform designed specifically to precisely localize and delineate the condyle region. Automated segmentation of Temporomandibular Joint (TMJJ) anatomical structures in MRI scans is crucial for efficient clinical diagnosis, alleviating the time-consuming nature of manual delineation and reducing inter-observer variability. Operating as an end-to-end, pure deep learning pipeline, strictly avoiding hybrid architectures, the project scope encompasses the evaluation and integration of state-of-the-art instance segmentation models, including Mask R-CNN, Cascade Mask R-CNN, Hybrid Task Cascade (HTC), and Mask2Former with a Swin-T backbone. To ensure high reliability, these models are rigorously evaluated using standard computer vision metrics. The project transitions these advanced architectures from theoretical evaluation on a curated MRI dataset directly into a practical clinical tool. Ultimately, the MRICondyleNet segmentation platform is deployed as an interactive, user-friendly web application, facilitating real-time prediction visualization and delivering a scalable, deployment-ready diagnostic solution to support modern pathology workflows.

---