Accurate segmentation of the fetal head and pubic symphysis in intrapartum ultrasound images and measurement of fetal angle of progression (AoP) are critical to both outcome prediction and complication prevention in delivery. However, due to the poor quality of perinatal ultrasound imaging with blurred target boundaries and the relatively small target of the public symphysis, fully automated and accurate segmentation remains challenging. In this paper, we propose a dual-path boundary-guided residual network (DBRN), which is a novel approach to tackle these challenges. The model contains a multi-scale weighted module (MWM) to gather global context information and enhance the feature response within the target region by weighting the feature map. The model also incorporates an enhanced boundary module (EBM) to obtain more precise boundary information. Furthermore, the model introduces a boundary-guided dual-attention residual module (BDRM) for residual learning. BDRM leverages boundary information as prior knowledge and employs spatial attention to simultaneously focus on background and foreground information in order to capture concealed details and improve segmentation accuracy. Extensive comparative experiments have been conducted on three datasets. The proposed method achieves an average Dice score of 0.908 ±0.05 and an average Hausdorff distance of 3.396 ±0.66 mm. Compared with state-of-the-art competitors, the proposed DBRN achieves better results. In addition, the average difference between the automatic measurement of AoPs based on this model and the manual measurement results is 6.157 °, which has good consistency and has broad application prospects in clinical practice.

The related challenges are the PSFHS challenge of MICCAI2023 (https://ps-fh-aop-2023.grand-challenge.org/) and the Intrapartum Ultrasound Grand Challenge (IUGC) 2024 of MICCAI 2024 (https://codalab.lisn.upsaclay.fr/competitions/18413).

Reference

Fernandez-Turienzo C, Sandall J. Delivering high-quality childbirth care. Nat Med. 2024;30(2):348-349. doi:10.1038/s41591-024-02812-2
Zhou M, Wang C, Lu Y, et al. The segmentation effect of style transfer on fetal head ultrasound image: a study of multi-source data. Med Biol Eng Comput. 2023;61(5):1017-1031. doi:10.1007/s11517-022-02747-1
Ou, Z., Bai, J., Chen, Z., Lu, Y., Wang, H., Long, S., Chen, G., RTSeg-Net: A Lightweight Network for Real-time Segmentation of Fetal Head and Pubic Symphysis from Intrapartum Ultrasound Images. Computers in biology and medicine, 2024; 108501. doi:10.1016/j.compbiomed.2024.108501
Qiu, R., Zhou M, Bai, J., Lu, Y., Wang, H. PSFHSP-Net: An Efficient Lightweight Network for Identifying Pubic Symphysis-Fetal Head Standard Plane from Intrapartum Ultrasound Images. Med Biol Eng Comput. 2024. https://doi.org/10.1007/s11517-024-03111-1
Chen, Z. Ou, Y. Lu, J. Bai, Direction-guided and multi-scale feature screening for fetal head–pubic symphysis segmentation and angle of progression calculation, Expert Systems with Applications, 245 (2024) 123096. doi:10.1016/j.eswa.2023.123096
Lu Y, Zhou M, Zhi D, et al. The JNU-IFM dataset for segmenting pubic symphysis-fetal head [published correction appears in Data Brief. 2022 Apr 01;42:108128]. Data Brief. 2022;41:107904. Published 2022 Feb 2. doi:10.1016/j.dib.2022.107904
Lu Y, Zhi D, Zhou M, et al. Multitask Deep Neural Network for the Fully Automatic Measurement of the Angle of Progression. Comput Math Methods Med. 2022;2022:5192338. Published 2022 Sep 2. doi:10.1155/2022/5192338
Bai J, Sun Z, Yu S, et al. A framework for computing angle of progression from transperineal ultrasound images for evaluating fetal head descent using a novel double branch network. Front Physiol. 2022;13:940150. Published 2022 Dec 2. doi:10.3389/fphys.2022.940150
Chen G, Bai J, Ou Z, Lu Y, Wang H. PSFHS: Intrapartum ultrasound image dataset for AI-based segmentation of pubic symphysis and fetal head. Scientific Data. 2024. doi:10.1038/s41597-024-03266-4
Chen, Y. Lu, S, Long, V, et al. Fetal Head and Pubic Symphysis Segmentation in Intrapartum Ultrasound Image Using a Dual-Path Boundary-Guided Residual Network.  IEEE Journal of Biomedical and Health Informatics. 2024