Automated Quality Assessment of Blind Sweep Obstetric Ultrasound for Improved Diagnosis

2026-03-26

AI Summary

This study addresses the critical challenge of acquisition bias in low-resource settings where Blinded Screening Obstetric Ultrasound (BSOU) relies on non-expert operators, significantly compromising the reliability of downstream AI-based diagnostics. For the first time, this work systematically quantifies the impact of BSOU acquisition bias across multiple key AI tasks and proposes a deep learning–based automatic quality assessment model. The model evaluates essential quality indicators—including scan plane orientation, probe direction, and image completeness—and incorporates a simulated feedback mechanism to trigger rescanning when quality thresholds are unmet. Experimental results demonstrate that this closed-loop strategy substantially improves diagnostic accuracy for critical tasks such as fetal pose estimation and placental localization, thereby enhancing the robustness of AI systems in real-world clinical deployment.

Abstract

Blind Sweep Obstetric Ultrasound (BSOU) enables scalable fetal imaging in low-resource settings by allowing minimally trained operators to acquire standardized sweep videos for automated Artificial Intelligence(AI) interpretation. However, the reliability of such AI systems depends critically on the quality of the acquired sweeps, and little is known about how deviations from the intended protocol affect downstream predictions. In this work, we present a systematic evaluation of BSOU quality and its impact on three key AI tasks: sweep-tag classification, fetal presentation classification, and placenta-location classification. We simulate plausible acquisition deviations, including reversed sweep direction, probe inversion, and incomplete sweeps, to quantify model robustness, and we develop automated quality-assessment models capable of detecting these perturbations. To approximate real-world deployment, we simulate a feedback loop in which flagged sweeps are re-acquired, showing that such correction improves downstream task performance. Our findings highlight the sensitivity of BSOU-based AI models to acquisition variability and demonstrate that automated quality assessment can play a central role in building reliable, scalable AI-assisted prenatal ultrasound workflows, particularly in low-resource environments.

Problem

• Blind Sweep Obstetric Ultrasound
• ultrasound quality assessment
• AI robustness
• acquisition deviation
• low-resource settings

Innovation

• Blind Sweep Obstetric Ultrasound
• Automated Quality Assessment
• AI Robustness
• Acquisition Deviation Simulation
• Feedback-based Re-acquisition