Deep Learning-Based Segmentation of the Ulnar Nerve in Ultrasound Images

<i>Background and Objectives</i>: We evaluate deep learning-based segmentation methods for detecting the ulnar nerve in ultrasound (US) images, leveraging the first-ever large US dataset of the ulnar nerve. We compare several widely used segmentation models, analyze their performance, and evaluate several common data augmentation techniques for the US. <i>Materials and Methods</i>: Our analysis is conducted on a large dataset of 4789 US images from 545 patients, with expert-annotated ground-truth segmentations of the ulnar nerve, and uses six segmentation models with several backbone architectures. Further, we analyze the statistical significance of five common data augmentation techniques on segmentation performance: flipping, rotation, shearing, contrast and brightness adjustments, and resizing. <i>Results</i>: In this study, the shear, rotate, and resize augmentations consistently improved segmentation performance across multiple runs, with <i>p</i>-values < 0.05 in a paired <i>t</i>-test relative to the no-augmentation baseline. Furthermore, we showed that newer architectures do not provide any metric improvements over traditional U-Net models, which achieved a Dice score of 0.88 and an IoU of 0.81. <i>Conclusions</i>: Through our systematic analysis of segmentation models and data augmentation strategies, we provide key insights into optimizing deep learning approaches for ulnar nerve segmentation and other US-based nerve segmentation tasks.