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