Author: Bai Jieyun

Publisher: College of Information Science and Technology  

Date: September 27, 2024  

A research team led by Professor Lu Yaosheng from the College of Information Science and Technology at Jinan University has made significant strides in the field of delivery monitoring, publishing their groundbreaking findings in the renowned journal Medical Image Analysis. The paper is titled PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Images.

(Screenshot of the paper)

Professor Lu, who serves as the chief scientist at the Guangdong Province Intelligent Maternal and Child Diagnosis and Treatment Equipment and Information System Engineering Technology Research Center, spearheaded this innovative research. The co-first authors of the study include Jinan University's own Bai Jieyun, Zhou Zihao, and Qu Zhanhong, while Professor Lu and Bai Jieyun are identified as corresponding authors.

The research introduces a novel childbirth monitoring strategy utilizing artificial intelligence, backed by the creation of the world's first multi-center dataset of intrapartum ultrasound images, comprising 5,101 images. The team successfully conducted an intrapartum ultrasound image analysis challenge at the prestigious MICCAI conference, attracting participation from 193 teams globally. By evaluating the algorithm performance of these participants, the team proposed a benchmark model for segmenting fetal and maternal structures, laying a critical foundation for intelligent prenatal monitoring.

This achievement is poised to enhance obstetric monitoring by improving efficiency, accuracy, and the overall quality of patient care, thereby promoting further advancements in obstetric diagnosis and treatment.

The research was supported by several funding sources, including the National Key Research and Development Program, the National Natural Science Foundation of China, the China Scholarship Council, the Guangdong Basic and Applied Basic Research Fund, and the Guangzhou Science and Technology Plan Project.

For further details, the full paper can be accessed here:

 (https://doi.org/10.1016/j.media.2024.103353).