Enhanced Uncertainty Estimation in Ultrasound Image Segmentation with MSU-Net

TL;DR

This paper introduces MSU-Net, a multistage ensemble approach that significantly improves ultrasound image segmentation accuracy and uncertainty estimation, aiding autonomous needle insertion in critical care.

Contribution

MSU-Net is a novel multistage ensemble method that enhances segmentation accuracy and uncertainty estimation in ultrasound imaging, improving safety and reliability in autonomous medical procedures.

Findings

18.1% improvement over single Monte Carlo U-Net

Enhanced uncertainty evaluation and model transparency

Facilitates safe needle insertions in critical care

Abstract

Efficient intravascular access in trauma and critical care significantly impacts patient outcomes. However, the availability of skilled medical personnel in austere environments is often limited. Autonomous robotic ultrasound systems can aid in needle insertion for medication delivery and support non-experts in such tasks. Despite advances in autonomous needle insertion, inaccuracies in vessel segmentation predictions pose risks. Understanding the uncertainty of predictive models in ultrasound imaging is crucial for assessing their reliability. We introduce MSU-Net, a novel multistage approach for training an ensemble of U-Nets to yield accurate ultrasound image segmentation maps. We demonstrate substantial improvements, 18.1% over a single Monte Carlo U-Net, enhancing uncertainty evaluations, model transparency, and trustworthiness. By highlighting areas of model certainty, MSU-Net can guide safe needle insertions, empowering non-experts to accomplish such tasks.