Accurate segmentation of cervical structures in transvaginal ultrasound (TVS) is critical for assessing the risk of spontaneous preterm birth (PTB), yet the scarcity of labeled data limits the performance of supervised learning approaches. This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation, hosted at ISBI 2025. FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images. Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2. The challenge attracted 10 teams with 82 participants submitting innovative solutions. The best-performing methods for each individual metric achieved 90.26\% mDSC, 38.88 mHD, and 32.85 ms RT, respectively. FUGC establishes a standardized benchmark for cervical segmentation, demonstrates the efficacy of semi-supervised methods with limited labeled data, and provides a foundation for AI-assisted clinical PTB risk assessment.
@article{arxiv.2601.15572,
title = {FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation},
author = {Jieyun Bai and Yitong Tang and Zihao Zhou and Mahdi Islam and Musarrat Tabassum and Enrique Almar-Munoz and Hongyu Liu and Hui Meng and Nianjiang Lv and Bo Deng and Yu Chen and Zilun Peng and Yusong Xiao and Li Xiao and Nam-Khanh Tran and Dac-Phu Phan-Le and Hai-Dang Nguyen and Xiao Liu and Jiale Hu and Mingxu Huang and Jitao Liang and Chaolu Feng and Xuezhi Zhang and Lyuyang Tong and Bo Du and Ha-Hieu Pham and Thanh-Huy Nguyen and Min Xu and Juntao Jiang and Jiangning Zhang and Yong Liu and Md. Kamrul Hasan and Jie Gan and Zhuonan Liang and Weidong Cai and Yuxin Huang and Gongning Luo and Mohammad Yaqub and Karim Lekadir},
journal= {arXiv preprint arXiv:2601.15572},
year = {2026}
}