# AI system for fetal ultrasound in low-resource settings

arXiv: https://arxiv.org/abs/2203.10139 · HTML: https://mlsanity.com/paper/2203.10139/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 38 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 3 of 3)

- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Looking Fast and Slow: Memory-Guided Mobile Video Object Detection](https://mlsanity.com/paper/1903.10172/) (2019)
- [Automated interpretation of prenatal ultrasound using a predefined acquisition protocol in resource-limited countries](https://mlsanity.com/paper/1907.12314/) (2019)

## Built on by (most cited first, 2 of 2)

- [CRONOS: Continuous Time Reconstruction for 4D Medical Longitudinal Series](https://mlsanity.com/paper/2512.16577/) (2025)
- [Enabling faster and more reliable sonographic assessment of gestational age through machine learning](https://mlsanity.com/paper/2203.11903/) (2022)

## Abstract (arXiv)

Despite considerable progress in maternal healthcare, maternal and perinatal deaths remain high in low-to-middle income countries. Fetal ultrasound is an important component of antenatal care, but shortage of adequately trained healthcare workers has limited its adoption. We developed and validated an artificial intelligence (AI) system that uses novice-acquired "blind sweep" ultrasound videos to estimate gestational age (GA) and fetal malpresentation. We further addressed obstacles that may be encountered in low-resourced settings. Using a simplified sweep protocol with real-time AI feedback on sweep quality, we have demonstrated the generalization of model performance to minimally trained novice ultrasound operators using low cost ultrasound devices with on-device AI integration. The GA model was non-inferior to standard fetal biometry estimates with as few as two sweeps, and the fetal malpresentation model had high AUC-ROCs across operators and devices. Our AI models have the potential to assist in upleveling the capabilities of lightly trained ultrasound operators in low resource settings.