Share：
Share this content in WeChat
X
[Chinese][PDF]2597
• Clinical Article •
Predicting the occurrence of knee osteoarthritis based on MRI meniscus 3D convolutional neural network model
JIANG Kexin  XIE Yuhan  LI Mianwen  ZHANG Zhiyong  CHEN Shaolong  QIU Changzhen  ZHANG Xiaodong 

Cite this article as: JIANG K X, XIE Y H, LI M W, et al. Predicting the occurrence of knee osteoarthritis based on MRI meniscus 3D convolutional neural network model[J]. Chin J Magn Reson Imaging, 2024, 15(2): 103-107, 121. DOI:10.12015/issn.1674-8034.2024.02.015.


[Abstract] Objective To explore the potential value of a 3D convolutional neural network (CNN) model based on automatically segmented meniscus MRI in predicting the occurrence of knee osteoarthritis (KOA).Materials and Methods This retrospective study used data from the Osteoarthritis Initiative (OAI), a publicly available database. A total of 130 baseline knee joint MRI images were randomly selected, and the meniscus regions of interest were manually delineated by trained musculoskeletal radiologists to train the meniscus MRI segmentation model. The meniscus segmentation was performed on the incident osteoarthritis cohort of OAI, and a 3D CNN model for KOA prediction was constructed. The incident osteoarthritis cohort included 710 knee joints with baseline Kellgren-Lawrence (KL) grading of ≤1, and no radiographic KOA at baseline. During a 48-month follow-up, cases with radiographic KOA (KL grade≥2) were considered as the case group, while those without radiographic KOA served as the control group, matched in a 1∶1 ratio. KOA prediction models were built using baseline and the time point one year before the occurrence of radiographic KOA (P-1) knee joint MRIs. The Dice coefficient was used to evaluate the performance of the meniscus MRI segmentation model. The predictive value of models based on meniscus MRI, clinical information, and MRI Osteoarthritis Knee Score (MOAKS) was assessed using the area under the curve (AUC) of the receiver operating characteristic curve.Results The meniscus segmentation model achieved a Dice coefficient of 90.32% on the test set. At baseline and P-1 time points, the 3D CNN KOA prediction model (baseline AUC: 0.60; P-1 AUC: 0.71) outperformed models based on clinical information (baseline AUC: 0.55; P-1 AUC: 0.63) and MOAKS (baseline AUC: 0.52-0.56; P-1 AUC: 0.51-0.64) in the test set, with statistically significant differences (P<0.05).Conclusions The 3D CNN KOA prediction model based on automatically segmented meniscus MRI demonstrates superior predictive capabilities for the occurrence of radiographic knee osteoarthritis compared to clinical information or semi-quantitative MRI scoring.
[Keywords] knee osteoarthritis；meniscus；magnetic resonance imaging；convolutional neural network；segmentation；prediction

JIANG Kexin1   XIE Yuhan2   LI Mianwen1   ZHANG Zhiyong2   CHEN Shaolong2   QIU Changzhen2*   ZHANG Xiaodong1*  

1 Department of Radiology, the Third Affiliated Hospital, Southern Medical University (Academy of Orthopedics, Guangzhou), Guangzhou 510630, China

2 School of Electronics and Communication Engineering, Sun Yat-sen University, Guangzhou 510275, China

Corresponding author: ZHANG X D, E-mail: ddautumn@126.com QIU C Z, E-mail: qiuchzh@mail.sysu.edu.cn#Co first author XIE Y H

Conflicts of interest   None.

Received  2023-09-09
Accepted  2024-01-20
DOI: 10.12015/issn.1674-8034.2024.02.015
Cite this article as: JIANG K X, XIE Y H, LI M W, et al. Predicting the occurrence of knee osteoarthritis based on MRI meniscus 3D convolutional neural network model[J]. Chin J Magn Reson Imaging, 2024, 15(2): 103-107, 121. DOI:10.12015/issn.1674-8034.2024.02.015.

[1]
HUNTER D J, BIERMA-ZEINSTRA S. Osteoarthritis[J]. Lancet, 2019, 393(10182): 1745-1759. DOI: 10.1016/S0140-6736(19)30417-9.
[2]
JIN Z Y, WANG D D, ZHANG H Y, et al. Incidence trend of five common musculoskeletal disorders from 1990 to 2017 at the global, regional and national level: results from the global burden of disease study 2017[J]. Ann Rheum Dis, 2020, 79(8): 1014-1022. DOI: 10.1136/annrheumdis-2020-217050.
[3]
THOMAS A C, HUBBARD-TURNER T, WIKSTROM E A, et al. Epidemiology of posttraumatic osteoarthritis[J]. J Athl Train, 2017, 52(6): 491-496. DOI: 10.4085/1062-6050-51.5.08.
[4]
SCOTT D, KOWALCZYK A. Osteoarthritis of the knee[J]. BMJ Clin Evid, 2007, 2007: 1121.
[5]
GIORGINO R, ALBANO D, FUSCO S, et al. Knee osteoarthritis: epidemiology, pathogenesis, and mesenchymal stem cells: what else is new? an update[J/OL]. Int J Mol Sci, 2023, 24(7): 6405 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/37047377/. DOI: 10.3390/ijms24076405.
[6]
OZEKI N, KOGA H, SEKIYA I. Degenerative Meniscus in knee osteoarthritis: from pathology to treatment[J/OL]. Life, 2022, 12(4): 603 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/35455094/. DOI: 10.3390/life12040603.
[7]
MARKES A R, HODAX J D, MA C B. Meniscus form and function[J]. Clin Sports Med, 2020, 39(1): 1-12. DOI: 10.1016/j.csm.2019.08.007.
[8]
MAKRIS E A, HADIDI P, ATHANASIOU K A. The knee meniscus: structure-function, pathophysiology, current repair techniques, and prospects for regeneration[J]. Biomaterials, 2011, 32(30): 7411-7431. DOI: 10.1016/j.biomaterials.2011.06.037.
[9]
BADLANI J T, BORRERO C, GOLLA S, et al. The effects of meniscus injury on the development of knee osteoarthritis: data from the Osteoarthritis Initiative[J]. Am J Sports Med, 2013, 41(6): 1238-1244. DOI: 10.1177/0363546513490276.
[10]
EVERHART J S, MAGNUSSEN R A, ABOULJOUD M M, et al. Meniscus tears accelerate joint space loss and lateral meniscal extrusion increases risk of knee arthroplasty in middle-aged adults[J]. J Orthop Res, 2020, 38(11): 2495-2504. DOI: 10.1002/jor.24672.
[11]
ROSAS H G. Magnetic resonance imaging of the meniscus[J]. Magn Reson Imaging Clin N Am, 2014, 22(4): 493-516. DOI: 10.1016/j.mric.2014.07.002.
[12]
STENSBY J D, PRINGLE L C, CRIM J. MRI of the Meniscus[J]. Clin Sports Med, 2021, 40(4): 641-655. DOI: 10.1016/j.csm.2021.05.004.
[13]
HUNTER D J, GUERMAZI A, LO G H, et al. Evolution of semi-quantitative whole joint assessment of knee OA: MOAKS (MRI Osteoarthritis Knee Score)[J]. Osteoarthritis Cartilage, 2011, 19(8): 990-1002. DOI: 10.1016/j.joca.2011.05.004.
[14]
WANG M Y. Research status and development prospect of magnetic resonance imaging artificial intelligence[J]. Chin J Magn Reson Imag, 2023, 14(3): 1-5. DOI: 10.12015/issn.1674-8034.2023.03.001.
[15]
CHEN X X, WANG X M, ZHANG K, et al. Recent advances and clinical applications of deep learning in medical image analysis[J/OL]. Med Image Anal, 2022, 79: 102444 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/35472844/. DOI: 10.1016/j.media.2022.102444.
[16]
YAQUB M, JINCHAO J C, ARSHID K, et al. Deep learning-based image reconstruction for different medical imaging modalities[J/OL]. Comput Math Methods Med, 2022, 2022: 8750648 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/35756423/. DOI: 10.1155/2022/8750648.
[17]
JEON U, KIM H, HONG H, et al. Automatic Meniscus segmentation using adversarial learning-based segmentation network with object-aware map in knee MR images[J/OL]. Diagnostics, 2021, 11(9): 1612 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/34573953/. DOI: 10.3390/diagnostics11091612.
[18]
GAJ S, YANG M R, NAKAMURA K, et al. Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks[J]. Magn Reson Med, 2020, 84(1): 437-449. DOI: 10.1002/mrm.28111.
[19]
NORMAN B, PEDOIA V, MAJUMDAR S. Use of 2D U-net convolutional neural networks for automated cartilage and Meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry[J]. Radiology, 2018, 288(1): 177-185. DOI: 10.1148/radiol.2018172322.
[20]
KOHN M D, SASSOON A A, FERNANDO N D. Classifications in brief: kellgren-lawrence classification of osteoarthritis[J]. Clin Orthop Relat Res, 2016, 474(8): 1886-1893. DOI: 10.1007/s11999-016-4732-4.
[21]
GUAN B, LIU F, HAJ-MIRZAIAN A, et al. Deep learning risk assessment models for predicting progression of radiographic medial joint space loss over a 48-MONTH follow-up period[J]. Osteoarthritis Cartilage, 2020, 28(4): 428-437. DOI: 10.1016/j.joca.2020.01.010.
[22]
LI J, FU S, GONG Z, et al. MRI-based texture analysis of infrapatellar fat pad to predict knee osteoarthritis incidence[J]. Radiology, 2022, 304(3): 611-621. DOI: 10.1148/radiol.212009.
[23]
YU K Y, YING J, ZHAO T Y, et al. Prediction model for knee osteoarthritis using magnetic resonance-based radiomic features from the infrapatellar fat pad: data from the Osteoarthritis Initiative[J]. Quant Imaging Med Surg, 2023, 13(1): 352-369. DOI: 10.21037/qims-22-368.
[24]
ATUKORALA I, KWOH C K, GUERMAZI A, et al. Synovitis in knee osteoarthritis: a precursor of disease?[J]. Ann Rheum Dis, 2016, 75(2): 390-395. DOI: 10.1136/annrheumdis-2014-205894.
[25]
ROEMER F W, KWOH C K, HANNON M J, et al. What comes first? Multitissue involvement leading to radiographic osteoarthritis: magnetic resonance imaging-based trajectory analysis over four years in the Osteoarthritis Initiative[J]. Arthritis Rheumatol, 2015, 67(8): 2085-2096. DOI: 10.1002/art.39176.
[26]
DEMEHRI S, KASAEIAN A, ROEMER F W, et al. Osteoarthritis year in review 2022: imaging[J]. Osteoarthritis Cartilage, 2023, 31(8): 1003-1011. DOI: 10.1016/j.joca.2023.03.005.
[27]
SALAFFI F, LEARDINI G, CANESI B, et al. Reliability and validity of the Western Ontario and McMaster Universities (WOMAC) Osteoarthritis Index in Italian patients with osteoarthritis of the knee[J]. Osteoarthritis Cartilage, 2003, 11(8): 551-560. DOI: 10.1016/s1063-4584(03)00089-x.
[28]
ZHOU Z Y, ZHAO G Y, KIJOWSKI R, et al. Deep convolutional neural network for segmentation of knee joint anatomy[J]. Magn Reson Med, 2018, 80(6): 2759-2770. DOI: 10.1002/mrm.27229.
[29]
GUAN S, KHAN A A, SIKDAR S, et al. Fully dense UNet for 2-D sparse photoacoustic tomography artifact removal[J]. IEEE J Biomed Health Inform, 2020, 24(2): 568-576. DOI: 10.1109/JBHI.2019.2912935.
[30]
CAO H, WANG Y Y, CHEN J, et al. Swin-unet: unet-like pure transformer for medical image segmentation[C]//KARLINSKY L, MICHAELI T, NISHINO K. European Conference on Computer Vision. Cham: Springer, 2023: 205-218.10.1007/978-3-031-25066-8_9
[31]
CHEN J N, LU Y Y, YU Q H, et al. TransUNet: transformers make strong encoders for medical image segmentation[EB/OL]. ArXiv, 2021: 2102.04306 [2023-01-16]. http://arxiv.org/abs/2102.04306.pdf
[32]
KHAN T, ALVAND A, PRIETO-ALHAMBRA D, et al. ACL and meniscal injuries increase the risk of primary total knee replacement for osteoarthritis: a matched case-control study using the Clinical Practice Research Datalink (CPRD)[J]. Br J Sports Med, 2019, 53(15): 965-968. DOI: 10.1136/bjsports-2017-097762.
[33]
PETERFY C G, GUERMAZI A, ZAIM S, et al. Whole-Organ Magnetic Resonance Imaging Score (WORMS) of the knee in osteoarthritis[J]. Osteoarthritis Cartilage, 2004, 12(3): 177-190. DOI: 10.1016/j.joca.2003.11.003.
[34]
HUNTER D J, LO G H, GALE D, et al. The reliability of a new scoring system for knee osteoarthritis MRI and the validity of bone marrow lesion assessment: BLOKS (Boston Leeds Osteoarthritis Knee Score)[J]. Ann Rheum Dis, 2008, 67(2): 206-211. DOI: 10.1136/ard.2006.066183.
[35]
KIJOWSKI R, FRITZ J, DENIZ C M. Deep learning applications in osteoarthritis imaging[J]. Skeletal Radiol, 2023, 52(11): 2225-2238. DOI: 10.1007/s00256-023-04296-6.
[36]
OLSSON S, AKBARIAN E, LIND A, et al. Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population[J/OL]. BMC Musculoskelet Disord, 2021, 22(1): 844 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/34600505/. DOI: 10.1186/s12891-021-04722-7.
[37]
JOSEPH G B, MCCULLOCH C E, NEVITT M C, et al. Machine learning to predict incident radiographic knee osteoarthritis over 8Years using combined MR imaging features, demographics, and clinical factors: data from the Osteoarthritis Initiative[J]. Osteoarthritis Cartilage, 2022, 30(2): 270-279. DOI: 10.1016/j.joca.2021.11.007.
[38]
TIULPIN A, KLEIN S, BIERMA-ZEINSTRA S M A, et al. Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data[J/OL]. Sci Rep, 2019, 9(1): 20038 [2023-01-16]. https://pubmed.ncbi.nlm.nih.gov/31882803/. DOI: 10.1038/s41598-019-56527-3.
[39]
LEUNG K, ZHANG B F, TAN J M, et al. Prediction of total knee replacement and diagnosis of osteoarthritis by using deep learning on knee radiographs: data from the Osteoarthritis Initiative[J]. Radiology, 2020, 296(3): 584-593. DOI: 10.1148/radiol.2020192091.

PREV Evaluation of the value of DWI combined with T2 mapping sequences to identify prostate cancer and benign prostatic hyperplasia
NEXT Research on the recognition of brain functional connections in flight students based on multivariate pattern analysis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn