Sparse Anatomical Prompt Semi-Supervised Learning with Masked Image Modeling for CBCT Tooth Segmentation

2024-02-07

IEEE International Symposium on Biomedical Imaging

AI Summary

CBCT images exhibit high inter-tooth morphological similarity, dense spatial arrangement, and ill-defined boundaries, leading to heavy reliance on manual annotations and limited segmentation accuracy. To address this under extremely low labeling budgets (10% annotation rate), we propose a novel semi-supervised dental segmentation framework. First, we introduce Masked Autoencoders (MAE) for unsupervised representation pretraining—its first application in CBCT dental segmentation. Second, we design a sparse anatomical prompting mechanism based on Graph Attention Networks (GAT) to explicitly encode inter-tooth spatial topology and boundary structure. Third, we jointly optimize sparse prompt learning with consistency regularization to improve pseudo-label reliability. Experiments demonstrate a 5.2% Dice score improvement over state-of-the-art semi-supervised methods, approaching fully supervised performance while significantly reducing annotation effort and enhancing boundary delineation accuracy.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Accurate tooth identification and segmentation in Cone Beam Computed Tomography (CBCT) dental images can significantly enhance the efficiency and precesion of manual diagnoses performed by dentists. However, existing segmentation methods are mainly developed based on large data volumes training, on which their annotations are extremely time-consuming. Meanwhile, the teeth of each class in CBCT dental images being closely positioned, coupled with subtle inter-class differences, gives rise to the challenge of indistinct boundaries when training model with limited data. To address these challenges, this study aims to propose a task-oriented Masked Auto-Encoder paradigm to effectively utilize large amounts of unlabeled data to achieve accurate tooth segmentation with limited labeled data. Specifically, we first construct a self-supervised pre-training framework of masked auto encoder to efficiently utilize unlabeled data to enhance the network performance. Subsequently, we introduce a sparse masked prompt mechanism based on graph attention to incorporate boundary information of the teeth, aiding the network in learning the anatomical structural features of teeth. To the best of our knowledge, we are pioneering the integration of the mask pre-training paradigm into the CBCT tooth segmentation task. Extensive experiments demonstrate both the feasibility of our proposed method and the potential of the boundary prompt mechanism.

Problem

• CBCT image segmentation
• dental identification
• high similarity and close arrangement

Innovation

• Masked Autoencoder
• Anatomical Hints
• Semi-supervised Learning