Pubic Symphysis-Fetal Head Segmentation Using Pure Transformer with Bi-level Routing Attention

TL;DR

The proposed BRAU-Net adopts a U-Net-like pure Transformer architecture with bi-level routing attention and skip connections, which effectively learns local-global semantic information.

Abstract

In this paper, we propose a method, named BRAU-Net, to solve the pubic symphysis-fetal head segmentation task. The method adopts a U-Net-like pure Transformer architecture with bi-level routing attention and skip connections, which effectively learns local-global semantic information. The proposed BRAU-Net was evaluated on transperineal Ultrasound images dataset from the pubic symphysis-fetal head segmentation and angle of progression (FH-PS-AOP) challenge. The results demonstrate that the proposed BRAU-Net achieves comparable a final score. The codes will be available at https://github.com/Caipengzhou/BRAU-Net.

Figures (3)

• Figure 1: The token-to-token attention.
• Figure 2: (a): The architecture of our BRAU-Net, which is constructed based on BiFormer block. (b): Details of a BiFormer Block.
• Figure 3: The some of visualization results on the validation set.