Towards Objective Obstetric Ultrasound Assessment: Contrastive Representation Learning for Fetal Movement Detection
This addresses the need for objective prenatal health assessment by improving accuracy over subjective traditional methods, though it is incremental as it applies existing contrastive learning techniques to a specific domain.
The paper tackled the problem of fetal movement detection from ultrasound videos, proposing a self-supervised contrastive learning framework that achieved a sensitivity of 78.01% and an AUROC of 81.60% on an in-house dataset.
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.