LSW‐Net : Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation
Journal of Magnetic Resonance Imaging · 2023-12 · 58 (6) · 1762-1776
DOI: 10.1002/jmri.28735 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 29.04.2023. Verfasst von Siyuan He und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Intervertebral Disc Degeneration. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Jilin Provincial Scientific and Technological Development Program.
Abstract (Originalsprache)
Background
Segmenting spinal tissues from MR images is important for automatic image analysis. Deep neural network‐based segmentation methods are efficient, yet have high computational costs.
Purpose
To design a lightweight model based on small‐world properties (LSW‐Net) to segment spinal MR images, suitable for low‐computing‐power embedded devices. Study Type Retrospective. Population A total of 386 subjects (2948 images) from two independent sources. Dataset I: 214 subjects/779 images, all for disk degeneration screening, 147 had disk degeneration, 52 had herniated disc. Dataset II: 172 subjects/2169 images, 142 patients with vertebral degeneration, 163 patients with disc degeneration. 70% images in each dataset for training, 20% for validation, and 10% for testing. Field Strength/Sequence T1‐ and T2‐weighted turbo spin echo sequences at 3 T. Assessment Segmentation performance of LSW‐Net was compared with four mainstream (including U‐net and U‐net++) and five lightweight models using five radiologists' manual segmentations (vertebrae, disks, spinal fluid) as reference standard. LSW‐Net was also deployed on NVIDIA Jetson nano to compare the pixels number in segmented vertebrae and disks. Statistical Tests All models were evaluated with accuracy, precision, Dice similarity coefficient (DSC), and area under the receiver operating characteristic (AUC). Pixel numbers segmented by LSW‐Net on the embedded device were compared with manual segmentation using paired t ‐tests, with P < 0.05 indicating significance.
Results
LSW‐Net had 98.5% fewer parameters than U‐net but achieved similar accuracy in both datasets (dataset I: DSC 0.84 vs. 0.87, AUC 0.92 vs. 0.94; dataset II: DSC 0.82 vs. 0.82, AUC 0.88 vs. 0.88). LSW‐Net showed no significant differences in pixel numbers for vertebrae (dataset I: 5893.49 vs. 5752.61, P = 0.21; dataset II: 5073.42 vs. 5137.12, P = 0.56) and disks (dataset I: 1513.07 vs. 1535.69, P = 0.42; dataset II: 1049.74 vs. 1087.88, P = 0.24) segmentation on an embedded device compared to manual segmentation. Data Conclusion Proposed LSW‐Net achieves high accuracy with fewer parameters than U‐net and can be deployed on embedded device, facilitating wider application. Evidence Level 2. Technical Efficacy 1.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, China.
- Zhongshan Institute of Changchun University of Science and Technology, Zhongshan, China.
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, China.
ORCID-Profile: Qi Li
Förderung
- Jilin Provincial Scientific and Technological Development Program
Zitieren
APA
He, S., Li, Q., Li, X., & Zhang, M. (2023). LSW‐Net : Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation. Journal of Magnetic Resonance Imaging, 58(6), 1762-1776. https://doi.org/10.1002/jmri.28735
Vancouver
He S, Li Q, Li X, Zhang M. LSW‐Net : Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation. Journal of Magnetic Resonance Imaging. 2023;58(6):1762-1776. doi:10.1002/jmri.28735
BibTeX
@article{He2023,
author = {He, Siyuan and Li, Qi and Li, Xianda and Zhang, Mengchao},
title = {LSW‐Net : Lightweight Deep Neural Network Based on Small‐World properties for Spine MR Image Segmentation},
journal = {Journal of Magnetic Resonance Imaging},
year = {2023},
volume = {58},
number = {6},
pages = {1762--1776},
doi = {10.1002/jmri.28735}
}
EUVIMED