Jieyun Bai's Challenge Paper"FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation”

💡 This paper presents the Fetal Ultrasound Grand Challenge (FUGC) hosted at ISBI 2025, the 1st benchmark dedicated to semi-supervised cervical ultrasound segmentation, enabling robust learning from limited labeled and abundant unlabeled data.

ℹ️ Accurate cervical segmentation in transvaginal ultrasound (TVS) is critical for early preterm birth (PTB) risk assessment.
⚠️ Yet progress is constrained by scarce labeled data and the lack of standardized semi-supervised benchmarks for reliable evaluation.
💡 This paper presents the Fetal Ultrasound Grand Challenge (FUGC) hosted at ISBI 2025, the 1st benchmark dedicated to semi-supervised cervical ultrasound segmentation, enabling robust learning from limited labeled and abundant unlabeled data.
🩺 890 TVS images
🤝 10 teams, 82 participants
🔥 Key findings: the FUGC demonstrates how foundation model–driven semi-supervised frameworks can deliver high-accuracy cervical segmentation and support AI-assisted early PTB risk assessment and clinical decision-making.
➡️ especially integrating UniMatch-V2, DINO-based encoders, and human-in-the-loop refinement!


Read the paper: 🔗 https://lnkd.in/eSr48pRJ
📦Dataset: https://lnkd.in/em53UGEf
💻 Code: https://lnkd.in/e-h_Y3PT
🌐 Project page: https://lnkd.in/e9rTYuNY

Authors: Jieyun Bai, Yitong Tang, Zihao Zhou, Mahdi Islam, Musarrat Tabassum, Enrique Almar-Munoz, Hongyu Liu, Hui Meng, Nianjiang Lv, Bo Deng, Yu Chen, Zilun Peng, Yusong Xiao, Li Xiao, Nam-Khanh Tran, Dac-Phu Phan-Le, Hai-Dang Nguyen, Xiao Liu, Jiale Hu, Mingxu Huang, Jitao Liang, Chaolu Feng, Xuezhi Zhang, Lyuyang Tong, Bo Du, Ha-Hieu Pham, Thanh-Huy Nguyen, Min Xu, Juntao Jiang, Jiangning Zhang, Yong Liu, Md Kamrul Hasan, Jie Gan, Zhuonan Liang, Weidong (Tom) Cai, Yuxin Huang, Gongning Luo, Mohammad Yaqub, Karim Lekadir