Analysis of the paraspinal muscle morphology of the lumbar spine using a convolutional neural network (CNN)
Authors:
Open Access
- 11 December 2021
- journal article
- research article
- Published by Springer Nature in European Spine Journal
- Vol. 31 (3) , 774-782
Abstract
Purpose: This single-center study aimed to develop a convolutional neural network to segment multiple consecutive axial magnetic resonance imaging (MRI) slices of the lumbar spinal muscles of patients with lower back pain and automatically classify fatty muscle degeneration. Methods: We developed a fully connected deep convolutional neural network (CNN) with a pre-trained U-Net model trained on a dataset of 3,650 axial T2-weighted MRI images from 100 patients with lower back pain. We included all qualities of MRI; the exclusion criteria were fractures, tumors, infection, or spine implants. The training was performed using k-fold cross-validation (k = 10), and performance was evaluated using the dice similarity coefficient (DSC) and cross-sectional area error (CSA error). For clinical correlation, we used a simplified Goutallier classification (SGC) system with three classes. Results: The mean DSC was high for overall muscle (0.91) and muscle tissue segmentation (0.83) but showed deficiencies in fatty tissue segmentation (0.51). The CSA error was small for the overall muscle area of 8.42%, and fatty tissue segmentation showed a high mean CSA error of 40.74%. The SGC classification was correctly predicted in 75% of the patients. Conclusion: Our fully connected CNN segmented overall muscle and muscle tissue with high precision and recall, as well as good DSC values. The mean predicted SGC values of all available patient axial slices showed promising results. With an overall Error of 25%, further development is needed for clinical implementation. Larger datasets and training of other model architectures are required to segment fatty tissue more accurately.Keywords
Funding Information
- Forschungskuratorium Textil, Bundesministerium für Wirtschaft und Energie (01MK20003P)
- Universitätsklinikum Leipzig
This publication has 17 references indexed in Scilit:
- Development and Validation of a Deep Learning System for Segmentation of Abdominal Muscle and Fat on Computed TomographyKorean Journal of Radiology, 2020
- A Comparison of Peripheral Imaging Technologies for Bone and Muscle Quantification: A Review of Segmentation TechniquesJournal of Clinical Densitometry, 2020
- Machine Learning for Automatic Paraspinous Muscle Area and Attenuation Measures on Low-Dose Chest CT ScansAcademic Radiology, 2019
- Correlation between multifidus fatty atrophy and lumbar disc degeneration in low back painBMC Musculoskeletal Disorders, 2019
- Deep Learning Convolutional Neural Networks for the Automatic Quantification of Muscle Fat Infiltration Following Whiplash InjuryScientific Reports, 2019
- Focal Dice Loss and Image Dilation for Brain Tumor Segmentation2018
- Fine-Grain Segmentation of the Intervertebral Discs from MR Spine Images Using Deep Convolutional Neural Networks: BSU-NetApplied Sciences, 2018
- Interobserver and Intraobserver Reliability of the Goutallier Classification Using Magnetic Resonance ImagingThe American Journal of Sports Medicine, 2012
- Architectural Analysis and Intraoperative Measurements Demonstrate the Unique Design of the Multifidus Muscle for Lumbar Spine StabilityJournal of Bone and Joint Surgery, 2009
- Are MRI-defined fat infiltrations in the multifidus muscles associated with low back pain?BMC Medicine, 2007