3D-U-SAM Network For Few-shot Tooth Segmentation in CBCT Images

TL;DR

This paper introduces a novel 3D-U-SAM network leveraging a pretrained SAM and convolution approximation for effective few-shot 3D tooth segmentation in CBCT images, addressing data scarcity issues.

Contribution

It proposes a new 3D segmentation network that adapts 2D pretrained weights for 3D data using convolution approximation and skip connections inspired by U-Net.

Findings

Demonstrates improved segmentation accuracy in ablation studies.

Shows effectiveness with small sample sizes.

Outperforms existing methods in comparison experiments.

Abstract

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.