Evaluating Deep Learning-Based Nerve Segmentation in Brachial Plexus Ultrasound Under Realistic Data Constraints

TL;DR

This study evaluates deep learning methods for nerve segmentation in brachial plexus ultrasound images, highlighting how dataset diversity, annotation strategies, and nerve size affect segmentation performance in realistic clinical scenarios.

Contribution

It systematically assesses the impact of multi-source training, multi-class supervision, and nerve size on deep learning-based nerve segmentation performance.

Findings

Multi-source training offers regularization benefits but doesn't outperform single-source training on target data.

Multi-class supervision decreases nerve segmentation accuracy due to class imbalance and boundary ambiguity.

Smaller nerves are more challenging to segment, with a moderate correlation between nerve size and accuracy.

Abstract

Accurate nerve localization is critical for the success of ultrasound-guided regional anesthesia, yet manual identification remains challenging due to low image contrast, speckle noise, and inter-patient anatomical variability. This study evaluates deep learning-based nerve segmentation in ultrasound images of the brachial plexus using a U-Net architecture, with a focus on how dataset composition and annotation strategy influence segmentation performance. We find that training on combined data from multiple ultrasound machines (SIEMENS ACUSON NX3 Elite and Philips EPIQ5) provides regularization benefits for lower-performing acquisition sources, though it does not surpass single-source training when matched to the target domain. Extending the task from binary nerve segmentation to multi-class supervision (artery, vein, nerve, muscle) results in decreased nerve-specific Dice scores, with performance drops ranging from 9% to 61% depending on dataset, likely due to class imbalance and boundary ambiguity. Additionally, we observe a moderate positive correlation between nerve size and segmentation accuracy (Pearson r=0.587, p<0.001), indicating that smaller nerves remain a primary challenge. These findings provide methodological guidance for developing robust ultrasound nerve segmentation systems under realistic clinical data constraints.