Cargando…
Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis
OBJECTIVE: Knee osteoarthritis (KOA) is a prevalent disease with a high economic and social cost. Magnetic resonance imaging (MRI) can be used to visualize many KOA-related structures including bone marrow lesions (BMLs), which are associated with OA pain. Several semi-automated software methods hav...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9718203/ https://www.ncbi.nlm.nih.gov/pubmed/36474467 http://dx.doi.org/10.1016/j.ocarto.2022.100234 |
_version_ | 1784843039998476288 |
---|---|
author | Preiswerk, Frank Sury, Meera S. Wortman, Jeremy R. Neumann, Gesa Wells, William Duryea, Jeffrey |
author_facet | Preiswerk, Frank Sury, Meera S. Wortman, Jeremy R. Neumann, Gesa Wells, William Duryea, Jeffrey |
author_sort | Preiswerk, Frank |
collection | PubMed |
description | OBJECTIVE: Knee osteoarthritis (KOA) is a prevalent disease with a high economic and social cost. Magnetic resonance imaging (MRI) can be used to visualize many KOA-related structures including bone marrow lesions (BMLs), which are associated with OA pain. Several semi-automated software methods have been developed to segment BMLs, using manual, labor-intensive methods, which can be costly for large clinical trials and other studies of KOA. The goal of our study was to develop and validate a more efficient method to quantify BML volume on knee MRI scans. MATERIALS AND METHODS: We have applied a deep learning approach using a patch-based convolutional neural network (CNN) which was trained using 673 MRI data sets and the segmented BML masks obtained from a trained reader. Given the location of a BML provided by the reader, the network performed a fully automated segmentation of the BML, removing the need for tedious manual delineation. Accuracy was quantified using the Pearson's correlation coefficient, by a comparison to a second expert reader, and using the Dice Similarity Score (DSC). RESULTS: The Pearson's R(2) value was 0.94 and we found similar agreement when comparing two readers (R(2) = 0.85) and each reader versus the DL model (R(2) = 0.95 and R(2) = 0.81). The average DSC was 0.70. CONCLUSIONS: We developed and validated a deep learning-based method to segment BMLs on knee MRI data sets. This has the potential to be a valuable tool for future large studies of KOA. |
format | Online Article Text |
id | pubmed-9718203 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-97182032022-12-05 Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis Preiswerk, Frank Sury, Meera S. Wortman, Jeremy R. Neumann, Gesa Wells, William Duryea, Jeffrey Osteoarthr Cartil Open ORIGINAL PAPER OBJECTIVE: Knee osteoarthritis (KOA) is a prevalent disease with a high economic and social cost. Magnetic resonance imaging (MRI) can be used to visualize many KOA-related structures including bone marrow lesions (BMLs), which are associated with OA pain. Several semi-automated software methods have been developed to segment BMLs, using manual, labor-intensive methods, which can be costly for large clinical trials and other studies of KOA. The goal of our study was to develop and validate a more efficient method to quantify BML volume on knee MRI scans. MATERIALS AND METHODS: We have applied a deep learning approach using a patch-based convolutional neural network (CNN) which was trained using 673 MRI data sets and the segmented BML masks obtained from a trained reader. Given the location of a BML provided by the reader, the network performed a fully automated segmentation of the BML, removing the need for tedious manual delineation. Accuracy was quantified using the Pearson's correlation coefficient, by a comparison to a second expert reader, and using the Dice Similarity Score (DSC). RESULTS: The Pearson's R(2) value was 0.94 and we found similar agreement when comparing two readers (R(2) = 0.85) and each reader versus the DL model (R(2) = 0.95 and R(2) = 0.81). The average DSC was 0.70. CONCLUSIONS: We developed and validated a deep learning-based method to segment BMLs on knee MRI data sets. This has the potential to be a valuable tool for future large studies of KOA. Elsevier 2022-01-10 /pmc/articles/PMC9718203/ /pubmed/36474467 http://dx.doi.org/10.1016/j.ocarto.2022.100234 Text en © 2022 Published by Elsevier Ltd on behalf of Osteoarthritis Research Society International (OARSI). https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | ORIGINAL PAPER Preiswerk, Frank Sury, Meera S. Wortman, Jeremy R. Neumann, Gesa Wells, William Duryea, Jeffrey Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title | Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title_full | Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title_fullStr | Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title_full_unstemmed | Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title_short | Fast quantitative bone marrow lesion measurement on knee MRI for the assessment of osteoarthritis |
title_sort | fast quantitative bone marrow lesion measurement on knee mri for the assessment of osteoarthritis |
topic | ORIGINAL PAPER |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9718203/ https://www.ncbi.nlm.nih.gov/pubmed/36474467 http://dx.doi.org/10.1016/j.ocarto.2022.100234 |
work_keys_str_mv | AT preiswerkfrank fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis AT surymeeras fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis AT wortmanjeremyr fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis AT neumanngesa fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis AT wellswilliam fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis AT duryeajeffrey fastquantitativebonemarrowlesionmeasurementonkneemrifortheassessmentofosteoarthritis |