Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Mar;53(3):799-806.
doi: 10.1002/jmri.27400. Epub 2020 Oct 23.

Automated Grading of Lumbar Disc Degeneration Using a Push-Pull Regularization Network Based on MRI

Fei Gao  1 , Shui Liu  2 , Xiaodong Zhang  2 , Xiaoying Wang  2   3 , Jue Zhang  1   3
Affiliations

Automated Grading of Lumbar Disc Degeneration Using a Push-Pull Regularization Network Based on MRI

Fei Gao et al. J Magn Reson Imaging. 2021 Mar.

Abstract

Background: Lower back pain is one of the most widely experienced health problems and is strongly associated with intervertebral disc (IVD) degeneration. The quantification of the degeneration is valuable for estimation of the material properties of the IVDs and then to perform biomechanical simulation of the spinal conditions and treatments. The MR image characteristics of relatively high intraclass variability and small interclass differences pose challenges for the classification algorithm to perform automatic grading of degenerated IVD.

Purpose: To assess the feasibility and improvement of a computer-assisted IVD degeneration grading method based on proposed push-pull regularization (PPR) strategy.

Study type: Retrospective.

Population: In total, 500 subjects (350 for training, 70 for validation, and 80 for test in a 10-time 10-fold cross validation setting) with varied lumbar disorders were included.

Field strength/sequence: 3.0T; T2 -weighted spin echo sequence.

Assessment: IVD degeneration grading was taken as a classification task of five classes according to the Pfirrmann grading system in this study. The classification results of deep-learning models with and without PPR were compared with the classifications made by three experienced spinal radiologists.

Statistical tests: Paired t-tests.

Results: The classification results show that in four classical CNN models of VGG-M, VGG-16, GoogleNet, and ResNet-34, by embedding a PPR strategy, the accuracies of grade II and III IVD classification were improved by more than 10% (P < 0.05), and that the overall accuracy (grades I to V) was improved by over 8% (P < 0.05).

Data conclusion: The embedded PPR significantly improved the classification performance, which enhanced CNN representation capability for IVD degeneration grading.

Level of evidence: 3 TECHNICAL EFFICACY STAGE: 1.

Keywords: Pfirrmann grading; deep convolutional neural networks; intervertebral disc degeneration; lumbar; push-pull regularization.

PubMed Disclaimer

References

REFERENCES

    1. Clarke TC, Nahin R, Barnes P, Stussman B. Use of complementary health approaches for musculoskeletal pain disorders among adults: United States, 2012. Natl Health Stat Report 2016;98:1-12.
    1. Mahato NK, Sybert D, Law T, Clark B. Effects of spine loading in a patient with post-decompression lumbar disc herniation: Observations using an open weight-bearing MRI. Eur Spine J 2017;26(1):17-23.
    1. Malandrino A, Pozo JM, Castro-Mateos I, et al. On the relative relevance of subject-specific geometries and degeneration-specific mechanical properties for the study of cell death in human intervertebral disk models. Front Bioeng Biotechnol 2015;3:5.
    1. An HS, Anderson PA, Haughton VM, et al. Introduction: Disc degeneration: Summary. Spine 2004;29(23):2677-2678.
    1. Thompson J, Pearce R, Schechter M, Adams M, Tsang I, Bishop P. Preliminary evaluation of a scheme for grading the gross morphology of the human intervertebral disc. Spine 1990;15(5):411-415.

LinkOut - more resources