Pubic Symphysis-Fetal Head Segmentation Network Using BiFormer Attention Mechanism and Multipath Dilated Convolution

TL;DR

This paper introduces BRAU-Net, a novel segmentation network with dynamic attention and dilated convolutions, significantly improving pubic symphysis-fetal head segmentation accuracy in ultrasound images.

Contribution

The paper presents a new BRAU-Net architecture with query-aware sparse attention and IBPE modules, enhancing segmentation performance over existing methods.

Findings

Achieved superior segmentation accuracy on FH-PS-AoP and HC18 datasets.

Demonstrated robustness of the proposed method across different datasets.

Provided open-source code for reproducibility.

Abstract

Pubic symphysis-fetal head segmentation in transperineal ultrasound images plays a critical role for the assessment of fetal head descent and progression. Existing transformer segmentation methods based on sparse attention mechanism use handcrafted static patterns, which leads to great differences in terms of segmentation performance on specific datasets. To address this issue, we introduce a dynamic, query-aware sparse attention mechanism for ultrasound image segmentation. Specifically, we propose a novel method, named BRAU-Net to solve the pubic symphysis-fetal head segmentation task in this paper. The method adopts a U-Net-like encoder-decoder architecture with bi-level routing attention and skip connections, which effectively learns local-global semantic information. In addition, we propose an inverted bottleneck patch expanding (IBPE) module to reduce information loss while performing up-sampling operations. The proposed BRAU-Net is evaluated on FH-PS-AoP and HC18 datasets. The results demonstrate that our method could achieve excellent segmentation results. The code is available on GitHub.