Literature DB >> 34657211

Learning-based fully automated prediction of lumbar disc degeneration progression with specified clinical parameters and preliminary validation.

Jason Pui Yin Cheung1, Xihe Kuang2, Marcus Kin Long Lai2, Kenneth Man-Chee Cheung2, Jaro Karppinen3,4, Dino Samartzis5,6, Honghan Wu7, Fengdong Zhao8, Zhaomin Zheng9, Teng Zhang2.   

Abstract

BACKGROUND: Lumbar disc degeneration (LDD) may be related to aging, biomechanical and genetic factors. Despite the extensive work on understanding its etiology, there is currently no automated tool for accurate prediction of its progression.
PURPOSE: We aim to establish a novel deep learning-based pipeline to predict the progression of LDD-related findings using lumbar MRIs.
MATERIALS AND METHODS: We utilized our dataset with MRIs acquired from 1,343 individual participants (taken at the baseline and the 5-year follow-up timepoint), and progression assessments (the Schneiderman score, disc bulging, and Pfirrmann grading) that were labelled by spine specialists with over ten years clinical experience. Our new pipeline was realized by integrating the MRI-SegFlow and the Visual Geometry Group-Medium (VGG-M) for automated disc region detection and LDD progression prediction correspondingly. The LDD progression was quantified by comparing the Schneiderman score, disc bulging and Pfirrmann grading at the baseline and at follow-up. A fivefold cross-validation was conducted to assess the predictive performance of the new pipeline.
RESULTS: Our pipeline achieved very good performances on the LDD progression prediction, with high progression prediction accuracy of the Schneiderman score (Accuracy: 90.2 ± 0.9%), disc bulging (Accuracy: 90.4% ± 1.1%), and Pfirrmann grading (Accuracy: 89.9% ± 2.1%).
CONCLUSION: This is the first attempt of using deep learning to predict LDD progression on a large dataset with 5-year follow-up. Requiring no human interference, our pipeline can potentially achieve similar predictive performances in new settings with minimal efforts.
© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Entities:  

Keywords:  Convolutional neural network; Disease progression prediction; Lumbar disc degeneration; Magnetic resonance imaging

Mesh:

Year:  2021        PMID: 34657211     DOI: 10.1007/s00586-021-07020-x

Source DB:  PubMed          Journal:  Eur Spine J        ISSN: 0940-6719            Impact factor:   2.721


  11 in total

1.  Prognosis of cervical myelopathy based on diffusion tensor imaging with artificial intelligence methods.

Authors:  Richu Jin; Keith Dk Luk; Jason Pui Yin Cheung; Yong Hu
Journal:  NMR Biomed       Date:  2019-05-27       Impact factor: 4.044

2.  The association of lumbar intervertebral disc degeneration on magnetic resonance imaging with body mass index in overweight and obese adults: a population-based study.

Authors:  Dino Samartzis; Jaro Karppinen; Danny Chan; Keith D K Luk; Kenneth M C Cheung
Journal:  Arthritis Rheum       Date:  2012-05

Review 3.  Incidence of Spontaneous Resorption of Lumbar Disc Herniation: A Meta-Analysis.

Authors:  Ming Zhong; Jin-Tao Liu; Hong Jiang; Wen Mo; Peng-Fei Yu; Xiao-Chun Li; Rui Rui Xue
Journal:  Pain Physician       Date:  2017 Jan-Feb       Impact factor: 4.965

4.  SpineNet: Automated classification and evidence visualization in spinal MRIs.

Authors:  Amir Jamaludin; Timor Kadir; Andrew Zisserman
Journal:  Med Image Anal       Date:  2017-07-21       Impact factor: 8.545

5.  Spine-GAN: Semantic segmentation of multiple spinal structures.

Authors:  Zhongyi Han; Benzheng Wei; Ashley Mercado; Stephanie Leung; Shuo Li
Journal:  Med Image Anal       Date:  2018-08-25       Impact factor: 8.545

6.  Progression of lumbar disc degeneration over a decade: a heritability study.

Authors:  Frances M K Williams; Maria Popham; Philip N Sambrook; Annette F Jones; Tim D Spector; Alex J MacGregor
Journal:  Ann Rheum Dis       Date:  2011-03-13       Impact factor: 19.103

7.  Spinal cord gray matter segmentation using deep dilated convolutions.

Authors:  Christian S Perone; Evan Calabrese; Julien Cohen-Adad
Journal:  Sci Rep       Date:  2018-04-13       Impact factor: 4.379

8.  Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network.

Authors:  Ming-Huwi Horng; Chan-Pang Kuok; Min-Jun Fu; Chii-Jen Lin; Yung-Nien Sun
Journal:  Comput Math Methods Med       Date:  2019-02-19       Impact factor: 2.238

9.  Progression of lumbar disc herniations over an eight-year period in a group of adult Danes from the general population--a longitudinal MRI study using quantitative measures.

Authors:  Per Kjaer; Andreas Tunset; Eleanor Boyle; Tue Secher Jensen
Journal:  BMC Musculoskelet Disord       Date:  2016-01-15       Impact factor: 2.362

10.  Spinopelvic alignment predicts disc calcification, displacement, and Modic changes: Evidence of an evolutionary etiology for clinically-relevant spinal phenotypes.

Authors:  Uruj Zehra; Jason P Y Cheung; Cora Bow; Rebecca J Crawford; Keith D K Luk; William Lu; Dino Samartzis
Journal:  JOR Spine       Date:  2020-02-19
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.