Cargando…

Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model

BACKGROUND: We aimed to develop and evaluate a deep learning-based method for fully automatic segmentation of knee joint MR imaging and quantitative computation of knee osteoarthritis (OA)-related imaging biomarkers. MATERIAL/METHODS: This retrospective study included 843 volumes of proton density-w...

Descripción completa

Detalles Bibliográficos
Autores principales: Tang, Xiongfeng, Guo, Deming, Liu, Aie, Wu, Dijia, Liu, Jianhua, Xu, Nannan, Qin, Yanguo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: International Scientific Literature, Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9206408/
https://www.ncbi.nlm.nih.gov/pubmed/35698440
http://dx.doi.org/10.12659/MSM.936733
_version_ 1784729331362168832
author Tang, Xiongfeng
Guo, Deming
Liu, Aie
Wu, Dijia
Liu, Jianhua
Xu, Nannan
Qin, Yanguo
author_facet Tang, Xiongfeng
Guo, Deming
Liu, Aie
Wu, Dijia
Liu, Jianhua
Xu, Nannan
Qin, Yanguo
author_sort Tang, Xiongfeng
collection PubMed
description BACKGROUND: We aimed to develop and evaluate a deep learning-based method for fully automatic segmentation of knee joint MR imaging and quantitative computation of knee osteoarthritis (OA)-related imaging biomarkers. MATERIAL/METHODS: This retrospective study included 843 volumes of proton density-weighted fat suppression MR imaging. A convolutional neural network segmentation method with multiclass gradient harmonized Dice loss was trained and evaluated on 500 and 137 volumes, respectively. To assess potential morphologic biomarkers for OA, the volumes and thickness of cartilage and meniscus, and minimal joint space width (mJSW) were automatically computed and compared between 128 OA and 162 control data. RESULTS: The CNN segmentation model produced reasonably high Dice coefficients, ranging from 0.948 to 0.974 for knee bone compartments, 0.717 to 0.809 for cartilage, and 0.846 for both lateral and medial menisci. The OA-related biomarkers computed from automatic knee segmentation achieved strong correlation with those from manual segmentation: average intraclass correlations of 0.916, 0.899, and 0.876 for volume and thickness of cartilage, meniscus, and mJSW, respectively. Volume and thickness measurements of cartilage and mJSW were strongly correlated with knee OA progression. CONCLUSIONS: We present a fully automatic CNN-based knee segmentation system for fast and accurate evaluation of knee joint images, and OA-related biomarkers such as cartilage thickness and mJSW were reliably computed and visualized in 3D. The results show that the CNN model can serve as an assistant tool for radiologists and orthopedic surgeons in clinical practice and basic research.
format Online
Article
Text
id pubmed-9206408
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher International Scientific Literature, Inc.
record_format MEDLINE/PubMed
spelling pubmed-92064082022-06-27 Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model Tang, Xiongfeng Guo, Deming Liu, Aie Wu, Dijia Liu, Jianhua Xu, Nannan Qin, Yanguo Med Sci Monit Clinical Research BACKGROUND: We aimed to develop and evaluate a deep learning-based method for fully automatic segmentation of knee joint MR imaging and quantitative computation of knee osteoarthritis (OA)-related imaging biomarkers. MATERIAL/METHODS: This retrospective study included 843 volumes of proton density-weighted fat suppression MR imaging. A convolutional neural network segmentation method with multiclass gradient harmonized Dice loss was trained and evaluated on 500 and 137 volumes, respectively. To assess potential morphologic biomarkers for OA, the volumes and thickness of cartilage and meniscus, and minimal joint space width (mJSW) were automatically computed and compared between 128 OA and 162 control data. RESULTS: The CNN segmentation model produced reasonably high Dice coefficients, ranging from 0.948 to 0.974 for knee bone compartments, 0.717 to 0.809 for cartilage, and 0.846 for both lateral and medial menisci. The OA-related biomarkers computed from automatic knee segmentation achieved strong correlation with those from manual segmentation: average intraclass correlations of 0.916, 0.899, and 0.876 for volume and thickness of cartilage, meniscus, and mJSW, respectively. Volume and thickness measurements of cartilage and mJSW were strongly correlated with knee OA progression. CONCLUSIONS: We present a fully automatic CNN-based knee segmentation system for fast and accurate evaluation of knee joint images, and OA-related biomarkers such as cartilage thickness and mJSW were reliably computed and visualized in 3D. The results show that the CNN model can serve as an assistant tool for radiologists and orthopedic surgeons in clinical practice and basic research. International Scientific Literature, Inc. 2022-06-14 /pmc/articles/PMC9206408/ /pubmed/35698440 http://dx.doi.org/10.12659/MSM.936733 Text en © Med Sci Monit, 2022 https://creativecommons.org/licenses/by-nc-nd/4.0/This work is licensed under Creative Common Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0 (https://creativecommons.org/licenses/by-nc-nd/4.0/) )
spellingShingle Clinical Research
Tang, Xiongfeng
Guo, Deming
Liu, Aie
Wu, Dijia
Liu, Jianhua
Xu, Nannan
Qin, Yanguo
Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title_full Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title_fullStr Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title_full_unstemmed Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title_short Fully Automatic Knee Joint Segmentation and Quantitative Analysis for Osteoarthritis from Magnetic Resonance (MR) Images Using a Deep Learning Model
title_sort fully automatic knee joint segmentation and quantitative analysis for osteoarthritis from magnetic resonance (mr) images using a deep learning model
topic Clinical Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9206408/
https://www.ncbi.nlm.nih.gov/pubmed/35698440
http://dx.doi.org/10.12659/MSM.936733
work_keys_str_mv AT tangxiongfeng fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT guodeming fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT liuaie fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT wudijia fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT liujianhua fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT xunannan fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel
AT qinyanguo fullyautomatickneejointsegmentationandquantitativeanalysisforosteoarthritisfrommagneticresonancemrimagesusingadeeplearningmodel