Skip to main content

Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI.

Publication ,  Journal Article
Coppock, JA; Zimmer, NE; Spritzer, CE; Goode, AP; DeFrate, LE
Published in: Osteoarthr Cartil Open
September 2023

OBJECTIVE: The measurement of in vivo intervertebral disc (IVD) mechanics may be used to understand the etiology of IVD degeneration and low back pain (LBP). To this end, our lab has developed methods to measure IVD morphology and uniaxial compressive deformation (% change in IVD height) resulting from dynamic activity, in vivo, using magnetic resonance images (MRI). However, due to the time-intensive nature of manual image segmentation, we sought to validate an image segmentation algorithm that could accurately and reliably reproduce models of in vivo tissue mechanics. DESIGN: Therefore, we developed and evaluated two commonly employed deep learning architectures (2D and 3D U-Net) for the segmentation of IVDs from MRI. The performance of these models was evaluated for morphological accuracy by comparing predicted IVD segmentations (Dice similarity coefficient, mDSC; average surface distance, ASD) to manual (ground truth) measures. Likewise, functional reliability and precision were assessed by evaluating the intraclass correlation coefficient (ICC) and standard error of measurement (SEm) of predicted and manually derived deformation measures. RESULTS: Peak model performance was obtained using the 3D U-net architecture, yielding a maximum mDSC ​= ​0.9824 and component-wise ASDx ​= ​0.0683 ​mm; ASDy ​= ​0.0335 ​mm; ASDz ​= ​0.0329 ​mm. Functional model performance demonstrated excellent reliability ICC ​= ​0.926 and precision SEm ​= ​0.42%. CONCLUSIONS: This study demonstrated that a deep learning framework can precisely and reliably automate measures of IVD function, drastically improving the throughput of these time-intensive methods.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Osteoarthr Cartil Open

DOI

EISSN

2665-9131

Publication Date

September 2023

Volume

5

Issue

3

Start / End Page

100378

Location

England

Related Subject Headings

  • 3202 Clinical sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Coppock, J. A., Zimmer, N. E., Spritzer, C. E., Goode, A. P., & DeFrate, L. E. (2023). Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI. Osteoarthr Cartil Open, 5(3), 100378. https://doi.org/10.1016/j.ocarto.2023.100378
Coppock, James A., Nicole E. Zimmer, Charles E. Spritzer, Adam P. Goode, and Louis E. DeFrate. “Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI.Osteoarthr Cartil Open 5, no. 3 (September 2023): 100378. https://doi.org/10.1016/j.ocarto.2023.100378.
Coppock JA, Zimmer NE, Spritzer CE, Goode AP, DeFrate LE. Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI. Osteoarthr Cartil Open. 2023 Sep;5(3):100378.
Coppock, James A., et al. “Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI.Osteoarthr Cartil Open, vol. 5, no. 3, Sept. 2023, p. 100378. Pubmed, doi:10.1016/j.ocarto.2023.100378.
Coppock JA, Zimmer NE, Spritzer CE, Goode AP, DeFrate LE. Automated segmentation and prediction of intervertebral disc morphology and uniaxial deformations from MRI. Osteoarthr Cartil Open. 2023 Sep;5(3):100378.

Published In

Osteoarthr Cartil Open

DOI

EISSN

2665-9131

Publication Date

September 2023

Volume

5

Issue

3

Start / End Page

100378

Location

England

Related Subject Headings

  • 3202 Clinical sciences