» Articles » PMID: 38456001

Automatic Segmentation of Skeletal Muscles from MR Images Using Modified U-Net and a Novel Data Augmentation Approach

Overview
Date 2024 Mar 8
PMID 38456001
Authors
Affiliations
Soon will be listed here.
Abstract

Rapid and accurate muscle segmentation is essential for the diagnosis and monitoring of many musculoskeletal diseases. As gold standard, manual annotation suffers from intensive labor and high inter-operator reproducibility errors. In this study, deep learning (DL) based automatic muscle segmentation from MR scans is investigated for post-menopausal women, who normally experience a decline in muscle volume. The performance of four Deep Learning (DL) models was evaluated: U-Net and UNet++ and two modified U-Net networks, which combined feature fusion and attention mechanisms (Feature-Fusion-UNet, FFU, and Attention-Feature-Fusion-UNet, AFFU). The models were tested for automatic segmentation of 16-lower limb muscles from MRI scans of two cohorts of post-menopausal women (11 subjects in PMW-1, 8 subjects in PMW-2; from two different studies so considered independent datasets) and 10 obese post-menopausal women (PMW-OB). Furthermore, a novel data augmentation approach is proposed to enlarge the training dataset. The results were assessed and compared by using the Dice similarity coefficient (DSC), relative volume error (RVE), and Hausdorff distance (HD). The best performance among all four DL models was achieved by AFFU (PMW-1: DSC 0.828 ± 0.079, 1-RVE 0.859 ± 0.122, HD 29.9 mm ± 26.5 mm; PMW-2: DSC 0.833 ± 0.065, 1-RVE 0.873 ± 0.105, HD 25.9 mm ± 27.9 mm; PMW-OB: DSC 0.862 ± 0.048, 1-RVE 0.919 ± 0.076, HD 34.8 mm ± 46.8 mm). Furthermore, the augmentation of data significantly improved the DSC scores of U-Net and AFFU for all 16 tested muscles (between 0.23% and 2.17% (DSC), 1.6%-1.93% (1-RVE), and 9.6%-19.8% (HD) improvement). These findings highlight the feasibility of utilizing DL models for automatic segmentation of muscles in post-menopausal women and indicate that the proposed augmentation method can enhance the performance of models trained on small datasets.

Citing Articles

A novel mean shape based post-processing method for enhancing deep learning lower-limb muscle segmentation accuracy.

Lin Z, DallAra E, Guo L PLoS One. 2024; 19(10):e0308664.

PMID: 39365764 PMC: 11452003. DOI: 10.1371/journal.pone.0308664.


AI driven analysis of MRI to measure health and disease progression in FSHD.

Riem L, DuCharme O, Cousins M, Feng X, Kenney A, Morris J Sci Rep. 2024; 14(1):15462.

PMID: 38965267 PMC: 11224366. DOI: 10.1038/s41598-024-65802-x.

References
1.
Davico G, Bottin F, Di Martino A, Castafaro V, Baruffaldi F, Faldini C . Intra-operator Repeatability of Manual Segmentations of the Hip Muscles on Clinical Magnetic Resonance Images. J Digit Imaging. 2022; 36(1):143-152. PMC: 9984589. DOI: 10.1007/s10278-022-00700-0. View

2.
Graffy P, Liu J, Pickhardt P, Burns J, Yao J, Summers R . Deep learning-based muscle segmentation and quantification at abdominal CT: application to a longitudinal adult screening cohort for sarcopenia assessment. Br J Radiol. 2019; 92(1100):20190327. PMC: 6724622. DOI: 10.1259/bjr.20190327. View

3.
Ibtehaz N, Sohel Rahman M . MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 2019; 121:74-87. DOI: 10.1016/j.neunet.2019.08.025. View

4.
Zhu J, Bolsterlee B, Chow B, Cai C, Herbert R, Song Y . Deep learning methods for automatic segmentation of lower leg muscles and bones from MRI scans of children with and without cerebral palsy. NMR Biomed. 2021; 34(12):e4609. DOI: 10.1002/nbm.4609. View

5.
Henson W, Li X, Lin Z, Guo L, Mazza C, DallAra E . Automatic segmentation of lower limb muscles from MR images of post-menopausal women based on deep learning and data augmentation. PLoS One. 2024; 19(4):e0299099. PMC: 10986986. DOI: 10.1371/journal.pone.0299099. View