T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases
Abstract Low back pain is a very common symptom and the leading cause of disability throughout the world. Several degenerative imaging findings seen on magnetic resonance imaging are associated with low back pain but none of them is specific for the presence of low back pain as abnormal findings are...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
John Wiley & Sons
2021
|
Subjects: | |
Online Access: | http://urn.fi/urn:nbn:fi-fe2021111154700 |
id |
ftunivoulu:oai:oulu.fi:nbnfi-fe2021111154700 |
---|---|
record_format |
openpolar |
spelling |
ftunivoulu:oai:oulu.fi:nbnfi-fe2021111154700 2023-07-30T04:05:50+02:00 T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases Ketola, J. H. (Juuso H. J.) Inkinen, S. I. (Satu I.) Karppinen, J. (Jaro) Niinimäki, J. (Jaakko) Tervonen, O. (Osmo) Nieminen, M. T. (Miika T.) 2021 application/pdf http://urn.fi/urn:nbn:fi-fe2021111154700 eng eng John Wiley & Sons info:eu-repo/semantics/openAccess © 2020 The Authors. Journal of Orthopaedic Research® published by Wiley Periodicals LLC on behalf of Orthopaedic Research Society. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. https://creativecommons.org/licenses/by/4.0/ low back pain lumbar spine machine learning magnetic resonance imaging texture analysis info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion 2021 ftunivoulu 2023-07-08T19:58:32Z Abstract Low back pain is a very common symptom and the leading cause of disability throughout the world. Several degenerative imaging findings seen on magnetic resonance imaging are associated with low back pain but none of them is specific for the presence of low back pain as abnormal findings are prevalent among asymptomatic subjects as well. The purpose of this population-based study was to investigate if more specific magnetic resonance imaging predictors of low back pain could be found via texture analysis and machine learning. We used this methodology to classify T₂-weighted magnetic resonance images from the Northern Finland Birth Cohort 1966 data to symptomatic and asymptomatic groups. Lumbar spine magnetic resonance imaging was performed using a fast spin-echo sequence at 1.5 T. Texture analysis pipeline consisting of textural feature extraction, principal component analysis, and logistic regression classifier was applied to the data to classify them into symptomatic (clinically relevant pain with frequency ≥30 days and intensity ≥6/10) and asymptomatic (frequency ≤7 days, intensity ≤3/10, and no previous pain episodes in the follow-up period) groups. Best classification results were observed applying texture analysis to the two lowest intervertebral discs (L4-L5 and L5-S1), with accuracy of 83%, specificity of 83%, sensitivity of 82%, negative predictive value of 94%, precision of 56%, and receiver operating characteristic area-under-curve of 0.91. To conclude, textural features from T₂-weighted magnetic resonance images can be applied in low back pain classification. Article in Journal/Newspaper Northern Finland Jultika - University of Oulu repository |
institution |
Open Polar |
collection |
Jultika - University of Oulu repository |
op_collection_id |
ftunivoulu |
language |
English |
topic |
low back pain lumbar spine machine learning magnetic resonance imaging texture analysis |
spellingShingle |
low back pain lumbar spine machine learning magnetic resonance imaging texture analysis Ketola, J. H. (Juuso H. J.) Inkinen, S. I. (Satu I.) Karppinen, J. (Jaro) Niinimäki, J. (Jaakko) Tervonen, O. (Osmo) Nieminen, M. T. (Miika T.) T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
topic_facet |
low back pain lumbar spine machine learning magnetic resonance imaging texture analysis |
description |
Abstract Low back pain is a very common symptom and the leading cause of disability throughout the world. Several degenerative imaging findings seen on magnetic resonance imaging are associated with low back pain but none of them is specific for the presence of low back pain as abnormal findings are prevalent among asymptomatic subjects as well. The purpose of this population-based study was to investigate if more specific magnetic resonance imaging predictors of low back pain could be found via texture analysis and machine learning. We used this methodology to classify T₂-weighted magnetic resonance images from the Northern Finland Birth Cohort 1966 data to symptomatic and asymptomatic groups. Lumbar spine magnetic resonance imaging was performed using a fast spin-echo sequence at 1.5 T. Texture analysis pipeline consisting of textural feature extraction, principal component analysis, and logistic regression classifier was applied to the data to classify them into symptomatic (clinically relevant pain with frequency ≥30 days and intensity ≥6/10) and asymptomatic (frequency ≤7 days, intensity ≤3/10, and no previous pain episodes in the follow-up period) groups. Best classification results were observed applying texture analysis to the two lowest intervertebral discs (L4-L5 and L5-S1), with accuracy of 83%, specificity of 83%, sensitivity of 82%, negative predictive value of 94%, precision of 56%, and receiver operating characteristic area-under-curve of 0.91. To conclude, textural features from T₂-weighted magnetic resonance images can be applied in low back pain classification. |
format |
Article in Journal/Newspaper |
author |
Ketola, J. H. (Juuso H. J.) Inkinen, S. I. (Satu I.) Karppinen, J. (Jaro) Niinimäki, J. (Jaakko) Tervonen, O. (Osmo) Nieminen, M. T. (Miika T.) |
author_facet |
Ketola, J. H. (Juuso H. J.) Inkinen, S. I. (Satu I.) Karppinen, J. (Jaro) Niinimäki, J. (Jaakko) Tervonen, O. (Osmo) Nieminen, M. T. (Miika T.) |
author_sort |
Ketola, J. H. (Juuso H. J.) |
title |
T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
title_short |
T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
title_full |
T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
title_fullStr |
T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
title_full_unstemmed |
T₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
title_sort |
t₂-weighted magnetic resonance imaging texture as predictor of low back pain:a texture analysis-based classification pipeline to symptomatic and asymptomatic cases |
publisher |
John Wiley & Sons |
publishDate |
2021 |
url |
http://urn.fi/urn:nbn:fi-fe2021111154700 |
genre |
Northern Finland |
genre_facet |
Northern Finland |
op_rights |
info:eu-repo/semantics/openAccess © 2020 The Authors. Journal of Orthopaedic Research® published by Wiley Periodicals LLC on behalf of Orthopaedic Research Society. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. https://creativecommons.org/licenses/by/4.0/ |
_version_ |
1772818057917366272 |