Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images

2026-04-22

AI Summary

This study addresses the challenges of segmenting maxillary sinuses in panoramic radiographs, where structural overlap, ambiguous boundaries, and scarce annotations hinder model training. To overcome these limitations, the authors propose a semi-supervised segmentation framework that integrates knowledge distillation with unlabeled data to train a student model. A key innovation is the introduction of a weighted distillation loss designed to suppress unreliable signals arising from inconsistencies between teacher and student predictions. Furthermore, the work presents SinusCycle-GAN—a novel unpaired image translation approach—to refine pseudo-label boundary quality. Evaluated on 2,511 clinical images, the method achieves a Dice score of 96.35%, significantly outperforming existing approaches and demonstrating high accuracy, anatomical consistency, and robustness under limited annotation conditions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

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 experimental results demonstrate that the proposed method outperforms state-of-the-art segmentation models, achieving the Dice score of 96.35\% while reducing boundary error. The results indicate that the proposed semi-supervised framework provides robust and anatomically consistent segmentation performance under limited labeled data conditions, highlighting its potential for broader dental image analysis applications.

Problem

• maxillary sinus segmentation
• panoramic X-ray
• semi-supervised learning
• anatomical boundary ambiguity
• limited labeled data

Innovation

• Weighted Knowledge Distillation
• Semi-Supervised Segmentation
• SinusCycle-GAN
• Pseudo-label Refinement
• Maxillary Sinus Segmentation