FUGC: Benchmarking Semi-Supervised Learning Methods for Cervical Segmentation

2026-01-22

AI Summary

This study addresses the challenge of limited annotated data hindering cervical structure segmentation in transvaginal ultrasound images by introducing FUGC, the first publicly available semi-supervised learning benchmark for this task, comprising 890 clinical images. The authors propose a comprehensive evaluation metric that integrates the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and inference time with respective weights of 0.4, 0.4, and 0.2, and systematically assess various semi-supervised approaches. The best-performing model achieves a mean DSC of 90.26%, a mean HD of 38.88 mm, and an inference time of 32.85 ms on the test set, demonstrating the efficacy of semi-supervised strategies under annotation scarcity. This work establishes a new benchmark and provides a viable pathway toward the clinical deployment of AI-based cervical segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

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.

Problem

• cervical segmentation
• semi-supervised learning
• transvaginal ultrasound
• spontaneous preterm birth
• limited labeled data

Innovation

• semi-supervised learning
• cervical segmentation
• transvaginal ultrasound
• benchmark
• preterm birth risk assessment