English

Enhanced DeepLab Based Nerve Segmentation with Optimized Tuning

Image and Video Processing 2025-07-21 v1 Computer Vision and Pattern Recognition

Abstract

Nerve segmentation is crucial in medical imaging for precise identification of nerve structures. This study presents an optimized DeepLabV3-based segmentation pipeline that incorporates automated threshold fine-tuning to improve segmentation accuracy. By refining preprocessing steps and implementing parameter optimization, we achieved a Dice Score of 0.78, an IoU of 0.70, and a Pixel Accuracy of 0.95 on ultrasound nerve imaging. The results demonstrate significant improvements over baseline models and highlight the importance of tailored parameter selection in automated nerve detection.

Keywords

Cite

@article{arxiv.2507.13394,
  title  = {Enhanced DeepLab Based Nerve Segmentation with Optimized Tuning},
  author = {Akhil John Thomas and Christiaan Boerkamp},
  journal= {arXiv preprint arXiv:2507.13394},
  year   = {2025}
}
R2 v1 2026-07-01T04:06:42.437Z