Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.20214 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911228063907840 |
|---|---|
| author | Ilyas, Talha Nhu, Duong Thomas, Allison Levin, Arie Yap, Lim Wei Gong, Shu Anaya, David Vera Jiang, Yiwen Mehta, Deval Warty, Ritesh Smith, Vinayak Reddy, Maya Wallace, Euan Cheng, Wenlong Ge, Zongyuan Marzbanrad, Faezeh |
| author_facet | Ilyas, Talha Nhu, Duong Thomas, Allison Levin, Arie Yap, Lim Wei Gong, Shu Anaya, David Vera Jiang, Yiwen Mehta, Deval Warty, Ritesh Smith, Vinayak Reddy, Maya Wallace, Euan Cheng, Wenlong Ge, Zongyuan Marzbanrad, Faezeh |
| contents | Accurate fetal movement (FM) detection is essential for assessing prenatal health, as abnormal movement patterns can indicate underlying complications such as placental dysfunction or fetal distress. Traditional methods, including maternal perception and cardiotocography (CTG), suffer from subjectivity and limited accuracy. To address these challenges, we propose Contrastive Ultrasound Video Representation Learning (CURL), a novel self-supervised learning framework for FM detection from extended fetal ultrasound video recordings. Our approach leverages a dual-contrastive loss, incorporating both spatial and temporal contrastive learning, to learn robust motion representations. Additionally, we introduce a task-specific sampling strategy, ensuring the effective separation of movement and non-movement segments during self-supervised training, while enabling flexible inference on arbitrarily long ultrasound recordings through a probabilistic fine-tuning approach. Evaluated on an in-house dataset of 92 subjects, each with 30-minute ultrasound sessions, CURL achieves a sensitivity of 78.01% and an AUROC of 81.60%, demonstrating its potential for reliable and objective FM analysis. These results highlight the potential of self-supervised contrastive learning for fetal movement analysis, paving the way for improved prenatal monitoring and clinical decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20214 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Objective Obstetric Ultrasound Assessment: Contrastive Representation Learning for Fetal Movement Detection Ilyas, Talha Nhu, Duong Thomas, Allison Levin, Arie Yap, Lim Wei Gong, Shu Anaya, David Vera Jiang, Yiwen Mehta, Deval Warty, Ritesh Smith, Vinayak Reddy, Maya Wallace, Euan Cheng, Wenlong Ge, Zongyuan Marzbanrad, Faezeh Computer Vision and Pattern Recognition Accurate fetal movement (FM) detection is essential for assessing prenatal health, as abnormal movement patterns can indicate underlying complications such as placental dysfunction or fetal distress. Traditional methods, including maternal perception and cardiotocography (CTG), suffer from subjectivity and limited accuracy. To address these challenges, we propose Contrastive Ultrasound Video Representation Learning (CURL), a novel self-supervised learning framework for FM detection from extended fetal ultrasound video recordings. Our approach leverages a dual-contrastive loss, incorporating both spatial and temporal contrastive learning, to learn robust motion representations. Additionally, we introduce a task-specific sampling strategy, ensuring the effective separation of movement and non-movement segments during self-supervised training, while enabling flexible inference on arbitrarily long ultrasound recordings through a probabilistic fine-tuning approach. Evaluated on an in-house dataset of 92 subjects, each with 30-minute ultrasound sessions, CURL achieves a sensitivity of 78.01% and an AUROC of 81.60%, demonstrating its potential for reliable and objective FM analysis. These results highlight the potential of self-supervised contrastive learning for fetal movement analysis, paving the way for improved prenatal monitoring and clinical decision-making. |
| title | Towards Objective Obstetric Ultrasound Assessment: Contrastive Representation Learning for Fetal Movement Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.20214 |