LFNS-Net: a lightweight partial convolution and attention network for femoral nerve segmentation in ultrasound images
Physica Scripta · 06.02.2026 · 101 (5) · 056002
DOI: 10.1088/1402-4896/ae3c69 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 03.02.2026. Verfasst von Jialin Hong und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.
Abstract (Originalsprache)
Femoral nerve block is a commonly used technique in lower limb anesthesia, relying on precise identification of nerve structures in ultrasound images. However, significant variations in the size of the femoral nerve across individuals, combined with complex backgrounds and blurred tissue boundaries in ultrasound images, pose challenges for automatic segmentation. Existing deep learning models often struggle with capturing long-range dependencies and have high computational complexity, which makes them unsuitable for real-time surgery, especially on portable devices with limited computational power. To address these challenges, we propose a lightweight deep learning network, LFNS-Net. In the encoder stage, we introduce the Axial Part Convolutional Block (APCB) to effectively capture long-range spatial information while maintaining low computational cost. In the decoder, we build the Dilated Channel Attention (DCA) module to guide the model’s focus on key femoral nerve regions while suppressing background noise interference. Additionally, we incorporate a Grouped Attention Gate (GAG) in the skip connections to optimize multi-scale feature fusion. We constructed a dataset of 3684 images for femoral nerve segmentation and conducted experiments. The results show that LFNS-Net outperforms existing methods with a Dice Similarity Coefficient (DSC) of 82.61%, mean Intersection over Union (mIoU) of 84.76%, and sensitivity of 83.93%. Moreover, LFNS-Net requires only 1.51 M parameters and 3.32 G FLOPs, reducing the parameter count by 22 times compared to U-Net, while maintaining a real-time processing speed of 67 FPS. These results demonstrate LFNS-Net’s potential for providing decision support to anesthesiologists, enhancing the segmentation quality and efficiency of ultrasound-guided femoral nerve block procedures.
Förderung
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
Zitieren
APA
Hong, J., Ge, Y., Long, Q., Hou, C., Huo, D., Yang, Z., Yin, P., & Luo, X. (2026). LFNS-Net: a lightweight partial convolution and attention network for femoral nerve segmentation in ultrasound images. Physica Scripta, 101(5), 056002. https://doi.org/10.1088/1402-4896/ae3c69
Vancouver
Hong J, Ge Y, Long Q, Hou C, Huo D, Yang Z, et al. LFNS-Net: a lightweight partial convolution and attention network for femoral nerve segmentation in ultrasound images. Physica Scripta. 2026;101(5):056002. doi:10.1088/1402-4896/ae3c69
BibTeX
@article{Hong2026,
author = {Hong, Jialin and Ge, Yongxin and Long, Qin and Hou, Changjun and Huo, Danqun and Yang, Zhihao and Yin, Peng and Luo, Xiaogang},
title = {LFNS-Net: a lightweight partial convolution and attention network for femoral nerve segmentation in ultrasound images},
journal = {Physica Scripta},
year = {2026},
volume = {101},
number = {5},
pages = {056002},
doi = {10.1088/1402-4896/ae3c69}
}
EUVIMED