Weighted knowledge distillation for semi-supervised segmentation of maxillary sinus in panoramic X-ray images

Accurate segmentation of maxillary sinus in panoramic X-ray images is essential for dental diagnosis and surgical planning; however, this task remains relatively underexplored in dental imaging research. Structural overlap, ambiguous anatomical boundaries inherent to two-dimensional panoramic projections, and the limited availability of large scale clinical datasets with reliable pixel-level annotations make the development and evaluation of segmentation models challenging. To address these challenges, we propose a semi-supervised segmentation framework that effectively leverages both labeled and unlabeled panoramic radiographs, where knowledge distillation is utilized to train a student model with reliable structural information distilled from a teacher model. Specifically, we introduce a weighted knowledge distillation loss to suppress unreliable distillation signals caused by structural discrepancies between teacher and student predictions. To further enhance the quality of pseudo labels generated by the teacher network, we introduce SinusCycle-GAN which is a refinement network based on unpaired image-to-image translation. This refinement process improves the precision of boundaries and reduces noise propagation when learning from unlabeled data during semi-supervised training. To evaluate the proposed method, we collected clinical panoramic X-ray images from 2,511 patients and assessed segmentation performance using Dice coefficient, recall, precision, and the 95th percentile Hausdorff distance (HD95). The proposed method achieved a Dice score of 96.35%, recall of 97.34%, precision of 95.90%, and the lowest HD95 among the compared models, outperforming state-of-the-art baselines. These results indicate that the framework yields robust and anatomically consistent segmentation under limited labeled data, supporting more reliable anatomical assessment for dental diagnosis and surgical planning.