GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation

TL;DR

This paper introduces GT U-Net, a novel end-to-end network combining group Transformers and convolutional structures for accurate tooth root segmentation in X-ray images, achieving state-of-the-art results.

Contribution

The paper presents a U-Net like architecture with group Transformers replacing encoders and decoders, reducing computational cost and enabling shape-aware segmentation without pre-training.

Findings

Achieves state-of-the-art performance on tooth root segmentation dataset.

Effectively utilizes a shape-sensitive Fourier Descriptor loss.

Demonstrates robustness on public retina dataset DRIVE.

Abstract

To achieve an accurate assessment of root canal therapy, a fundamental step is to perform tooth root segmentation on oral X-ray images, in that the position of tooth root boundary is significant anatomy information in root canal therapy evaluation. However, the fuzzy boundary makes the tooth root segmentation very challenging. In this paper, we propose a novel end-to-end U-Net like Group Transformer Network (GT U-Net) for the tooth root segmentation. The proposed network retains the essential structure of U-Net but each of the encoders and decoders is replaced by a group Transformer, which significantly reduces the computational cost of traditional Transformer architectures by using the grouping structure and the bottleneck structure. In addition, the proposed GT U-Net is composed of a hybrid structure of convolution and Transformer, which makes it independent of pre-training weights. For optimization, we also propose a shape-sensitive Fourier Descriptor (FD) loss function to make use of shape prior knowledge. Experimental results show that our proposed network achieves the state-of-the-art performance on our collected tooth root segmentation dataset and the public retina dataset DRIVE. Code has been released at https://github.com/Kent0n-Li/GT-U-Net.