3D-U-SAM Network For Few-shot Tooth Segmentation in CBCT Images
This work addresses the challenge of limited labeled 3D dental datasets for tooth segmentation, which is crucial for accurate treatment planning in dentistry, but it is incremental as it builds on existing SAM and U-Net methods.
The authors tackled the problem of few-shot 3D tooth segmentation in CBCT images by proposing a 3D-U-SAM network, which adapts a pretrained SAM to 3D data using convolution approximation and skip connections, achieving effectiveness as demonstrated in ablation, comparison, and sample size experiments.
Accurate representation of tooth position is extremely important in treatment. 3D dental image segmentation is a widely used method, however labelled 3D dental datasets are a scarce resource, leading to the problem of small samples that this task faces in many cases. To this end, we address this problem with a pretrained SAM and propose a novel 3D-U-SAM network for 3D dental image segmentation. Specifically, in order to solve the problem of using 2D pre-trained weights on 3D datasets, we adopted a convolution approximation method; in order to retain more details, we designed skip connections to fuse features at all levels with reference to U-Net. The effectiveness of the proposed method is demonstrated in ablation experiments, comparison experiments, and sample size experiments.