Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study
Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study
Background
MRI scanning has revolutionized the clinical diagnosis of lumbar spinal stenosis (LSS). However, there is currently no consensus as to how best to classify MRI findings which has hampered the development of robust longitudinal epidemiological studies of the condition. We developed and tested an automated system for grading lumbar spine MRI scans for central LSS for use in epidemiological research.
Methods
Using MRI scans from the large population-based cohort study (the Wakayama Spine Study), all graded by a spinal surgeon, we trained an automated system to grade central LSS in four gradings of the bone and soft tissue margins: none, mild, moderate, severe. Subsequently, we tested the automated grading against the independent readings of our observer in a test set to investigate reliability and agreement.
Results
Complete axial views were available for 4855 lumbar intervertebral levels from 971 participants. The machine used 4365 axial views to learn (training set) and graded the remaining 490 axial views (testing set). The agreement rate for gradings was 65.7% (322/490) and the reliability (Lin’s correlation coefficient) was 0.73. In 2.2% of scans (11/490) there was a difference in classification of 2 and in only 0.2% (1/490) was there a difference of 3. When classified into 2 groups as ‘severe’ vs ‘no/mild/moderate’. The agreement rate was 94.1% (461/490) with a kappa of 0.75.
Conclusions
This study showed that an automated system can “learn” to grade central LSS with excellent performance against the reference standard. Thus SpineNet offers potential to grade LSS in large-scale epidemiological studies involving a high volume of MRI spine data with a high level of consistency and objectivity.
Automated grading, Lumbar spinal stenosis, MRI scans, Repeatability, Validation
Ishimoto, Yuyu
8c8108ca-80de-494e-8338-1783396b26eb
Jamalundin, Amir
498f9a48-52d2-4b50-8219-b6b2622395b9
Cooper, Cyrus
e05f5612-b493-4273-9b71-9e0ce32bdad6
Walker-Bone, Karen
ad7d1336-ed2c-4f39-ade5-da84eb412109
Yamanda, H.
23b64699-52f3-43c9-8702-bef6db780381
Hashizume, Hiroshi
12ff45ac-50ac-4032-98aa-f4ba3907341e
Tanaka, S.
a19b78ba-91e1-474d-a644-aaff05503a23
Yoshimura, Noriko
00436389-57b3-444c-b69d-0dc934d8e0d5
Yoshida, Misaki
268aedcc-e1d5-4585-943d-2808f076901b
Urban, Jill
d39c2d22-b0fd-4528-9670-d6262425bf01
Fairbank, Jeremy
bb1383b6-5ff3-40d6-9a23-66d733171c5e
12 March 2020
Ishimoto, Yuyu
8c8108ca-80de-494e-8338-1783396b26eb
Jamalundin, Amir
498f9a48-52d2-4b50-8219-b6b2622395b9
Cooper, Cyrus
e05f5612-b493-4273-9b71-9e0ce32bdad6
Walker-Bone, Karen
ad7d1336-ed2c-4f39-ade5-da84eb412109
Yamanda, H.
23b64699-52f3-43c9-8702-bef6db780381
Hashizume, Hiroshi
12ff45ac-50ac-4032-98aa-f4ba3907341e
Tanaka, S.
a19b78ba-91e1-474d-a644-aaff05503a23
Yoshimura, Noriko
00436389-57b3-444c-b69d-0dc934d8e0d5
Yoshida, Misaki
268aedcc-e1d5-4585-943d-2808f076901b
Urban, Jill
d39c2d22-b0fd-4528-9670-d6262425bf01
Fairbank, Jeremy
bb1383b6-5ff3-40d6-9a23-66d733171c5e
Ishimoto, Yuyu, Jamalundin, Amir, Cooper, Cyrus, Walker-Bone, Karen, Yamanda, H., Hashizume, Hiroshi, Tanaka, S., Yoshimura, Noriko, Yoshida, Misaki, Urban, Jill and Fairbank, Jeremy
(2020)
Could automated machine-learned MRI grading aid epidemiological studies of lumbar spinal stenosis? Validation within the Wakayama spine study.
BMC Musculoskeletal Disorders, 21 (1), [158].
(doi:10.1186/s12891-020-3164-1).
Abstract
Background
MRI scanning has revolutionized the clinical diagnosis of lumbar spinal stenosis (LSS). However, there is currently no consensus as to how best to classify MRI findings which has hampered the development of robust longitudinal epidemiological studies of the condition. We developed and tested an automated system for grading lumbar spine MRI scans for central LSS for use in epidemiological research.
Methods
Using MRI scans from the large population-based cohort study (the Wakayama Spine Study), all graded by a spinal surgeon, we trained an automated system to grade central LSS in four gradings of the bone and soft tissue margins: none, mild, moderate, severe. Subsequently, we tested the automated grading against the independent readings of our observer in a test set to investigate reliability and agreement.
Results
Complete axial views were available for 4855 lumbar intervertebral levels from 971 participants. The machine used 4365 axial views to learn (training set) and graded the remaining 490 axial views (testing set). The agreement rate for gradings was 65.7% (322/490) and the reliability (Lin’s correlation coefficient) was 0.73. In 2.2% of scans (11/490) there was a difference in classification of 2 and in only 0.2% (1/490) was there a difference of 3. When classified into 2 groups as ‘severe’ vs ‘no/mild/moderate’. The agreement rate was 94.1% (461/490) with a kappa of 0.75.
Conclusions
This study showed that an automated system can “learn” to grade central LSS with excellent performance against the reference standard. Thus SpineNet offers potential to grade LSS in large-scale epidemiological studies involving a high volume of MRI spine data with a high level of consistency and objectivity.
Text
Automated MRI reading
- Accepted Manuscript
Text
s12891-020-3164-1
- Version of Record
More information
Accepted/In Press date: 25 February 2020
e-pub ahead of print date: 12 March 2020
Published date: 12 March 2020
Additional Information:
Publisher Copyright:
© 2020 The Author(s).
Keywords:
Automated grading, Lumbar spinal stenosis, MRI scans, Repeatability, Validation
Identifiers
Local EPrints ID: 439248
URI: http://eprints.soton.ac.uk/id/eprint/439248
ISSN: 1471-2474
PURE UUID: 806e6107-fe82-4266-bf54-b1c7d9db7f20
Catalogue record
Date deposited: 07 Apr 2020 16:31
Last modified: 18 Mar 2024 02:51
Export record
Altmetrics
Contributors
Author:
Yuyu Ishimoto
Author:
Amir Jamalundin
Author:
H. Yamanda
Author:
Hiroshi Hashizume
Author:
S. Tanaka
Author:
Noriko Yoshimura
Author:
Misaki Yoshida
Author:
Jill Urban
Author:
Jeremy Fairbank
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
