Share this content in WeChat
Clinical Articles
Study on application value of proton density weighted imaging accelerated with artificial intelligence‐compressed sensing in assessing cartilage injury in osteoarthritis of the knee
PAN Ke  HUANG Xiaohua  LIU Nian  LEI Lixing  LIU Qianqian 

Cite this article as: Pan K, Huang XH, Liu N, et al. Study on application value of proton density weighted imaging accelerated with artificial intelligence‐compressed sensing in assessing cartilage injury in osteoarthritis of the knee[J]. Chin J Magn Reson Imaging, 2022, 13(10): 138-143, 156. DOI:10.12015/issn.1674-8034.2022.10.021.

[Abstract] Objective To explore the value of proton density weighted imaging (PDWI) accelerated with artificial intelligence-compressed sensing (ACS) for semiquantitatively assessing cartilage of the knee in osteoarthritis.Materials and Methods Seventy-four subjects were scanned with 3 T MRI scanner, undergoing three-plane PDWI accelerated with parallel imaging (PI), compressed sensing (CS) and ACS, respectively. The subjective image quality evaluation was performed by two radiologists using a 4‐point scale. The cartilage was divided into 14 regions. The two readers mentioned above graded cartilage abnormalities using an 8-point scale. In 15 of the subjects, the cartilages in 3 regions were graded twice at least a month apart. The Friedman test was used to analyze the differences of subjective image quality scores among PI, CS and ACS. Intra‐class correlation coefficient (ICC) was applied to assess consistency in grading cartilage abnormalities of CS‐PI and ACS‐PI. The specificity and sensitivity of CS and ACS in grading total articular cartilage injury were calculated. Cohen's Kappa was used to analyze intra‐reader agreement.Results Three‐plane PDWI accelerated with, PI, CS, ACS were acquired in 428 s, 375 s and 155 s, respectively. The subjective scores of the three-plane images were not different among the three groups (P=0.607, 0.174, 0.529, respectively). The agreement grading cartilage abnormalities in 14 regions of CS-PI, ACS‐PI were excellent (ICC ranging 0.969-0.995 and 0.951-0.987, respectively). Removing the regions with negative diagnosis in the three groups, the agreement in grading cartilage abnormalities of CS-PI, ACS-PI were still excellent (ICC ranging 0.868-0.939 and 0.842-0.948, respectively). The specificity of CS and ACS was 99.6% and 98.2%, respectively. The range of sensitivity of CS and ACS in grade 1-6 was 42.3%-100.0% and 17.3%-87.9%, respectively. Grading cartilage abnormalities showed perfect agreement (κ≥0.803) in 3 regions of 15 subjects for PI, CS and ACS.Conclusions ACS greatly accelerates multi‐plane MRI PDWI sequences while ensuring image quality, and achieve comparable diagnostic performance with sequences accelerated with parallel imaging in semi‐quantitative evaluation of multi‐region cartilage injury in knee osteoarthritis.
[Keywords] knee joint;osteoarthritis;articular cartilage;artificial intelligence-compressed sensing;proton density weighted imaging;magnetic resonance imaging

PAN Ke   HUANG Xiaohua   LIU Nian   LEI Lixing   LIU Qianqian*  

Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, China

Liu QQ, E-mail:

Conflicts of interest   None.

Received  2022-06-15
Accepted  2022-10-08
DOI: 10.12015/issn.1674-8034.2022.10.021
Cite this article as: Pan K, Huang XH, Liu N, et al. Study on application value of proton density weighted imaging accelerated with artificial intelligence‐compressed sensing in assessing cartilage injury in osteoarthritis of the knee[J]. Chin J Magn Reson Imaging, 2022, 13(10): 138-143, 156.DOI:10.12015/issn.1674-8034.2022.10.021

Hawker GA, King LK. The burden of osteoarthritis in older adults[J]. Clin Geriatr Med, 2022, 38(2): 181-192. DOI: 10.1016/j.cger.2021.11.005.
Xue QY, Wang KZ, Pei FX, et al. The survey of the prevalence of primary osteoarthritis in the population aged 40 years and over in China[J]. Chin J Orthop, 2015, 35(12): 1206-1212. DOI: 10.3760/cma.j.issn.0253-2352.2015.12.005.
Wang K, Dong X, Lin JH. The fees of patients with knee osteoarthritis[J]. Natl Med J China, 2017, 97(1): 29-32. DOI: 10.3760/cma.j.issn.0376-2491.2017.01.008.
Liu D, Cai ZJ, Yang YT, et al. Mitochondrial quality control in cartilage damage and osteoarthritis: new insights and potential therapeutic targets[J]. Osteoarthr Cartil, 2022, 30(3): 395-405. DOI: 10.1016/j.joca.2021.10.009.
Eckstein F, Collins JE, Nevitt MC, et al. Brief report: cartilage thickness change as an imaging biomarker of knee osteoarthritis progression: data from the foundation for the national institutes of health osteoarthritis biomarkers consortium[J]. Arthritis Rheumatol, 2015, 67(12): 3184-3189. DOI: 10.1002/art.39324.
Stefanik JJ, Gross KD, Guermazi A, et al. The relation of MRI-detected structural damage in the medial and lateral patellofemoral joint to knee pain: the Multicenter and Framingham Osteoarthritis Studies[J]. Osteoarthritis Cartilage, 2015, 23(4): 565-570. DOI: 10.1016/j.joca.2014.12.023.
Mahmoudian A, Lohmander LS, Mobasheri A, et al. Early-stage symptomatic osteoarthritis of the knee—time for action[J]. Nat Rev Rheumatol, 2021, 17(10): 621-632. DOI: 10.1038/s41584-021-00673-4.
Block JA, Cherny D. Management of knee osteoarthritis: what internists need to know[J]. Rheum Dis Clin North Am, 2022, 48(2): 549-567. DOI: 10.1016/j.rdc.2022.02.011.
Sakellariou G, Conaghan PG, Zhang WY, et al. EULAR recommendations for the use of imaging in the clinical management of peripheral joint osteoarthritis[J]. Ann Rheum Dis, 2017, 76(9): 1484-1494. DOI: 10.1136/annrheumdis-2016-210815.
Deshmane A, Gulani V, Griswold MA, et al. Parallel MR imaging[J]. J Magn Reson Imaging, 2012, 36(1): 55-72. DOI: 10.1002/jmri.23639.
Lustig M, Donoho D, Pauly JM. Sparse MRI: the application of compressed sensing for rapid MR imaging[J]. Magn Reson Med, 2007, 58(6): 1182-1195. DOI: 10.1002/mrm.21391.
Delattre BMA, Boudabbous S, Hansen C, et al. Compressed sensing MRI of different organs: ready for clinical daily practice?[J]. Eur Radiol, 2020, 30(1): 308-319. DOI: 10.1007/s00330-019-06319-0.
Honda M, Kataoka M, Onishi N, et al. New parameters of ultrafast dynamic contrast-enhanced breast MRI using compressed sensing[J]. J Magn Reson Imaging, 2020, 51(1): 164-174. DOI: 10.1002/jmri.26838.
Johnson PM, Recht MP, Knoll F. Improving the speed of MRI with artificial intelligence[J]. Semin Musculoskelet Radiol, 2020, 24(1): 12-20. DOI: 10.1055/s-0039-3400265.
Kakigi T, Sakamoto R, Tagawa H, et al. Diagnostic advantage of thin slice 2D MRI and multiplanar reconstruction of the knee joint using deep learning based denoising approach[J/OL]. Sci Rep, 2022, 12(1) [2022-09-27]. DOI: 10.1038/s41598-022-14190-1.
Almansour H, Gassenmaier S, Nickel D, et al. Deep learning-based superresolution reconstruction for upper abdominal magnetic resonance imaging: an analysis of image quality, diagnostic confidence, and lesion conspicuity[J]. Invest Radiol, 2021, 56(8): 509-516. DOI: 10.1097/RLI.0000000000000769.
Naganawa S, Nakamichi R, Ichikawa K, et al. MR imaging of endolymphatic Hydrops: utility of iHYDROPS-Mi2 combined with deep learning reconstruction denoising[J]. Magn Reson Med Sci, 2021, 20(3): 272-279. DOI: 10.2463/
Recht MP, Zbontar J, Sodickson DK, et al. Using deep learning to accelerate knee MRI at 3 T: results of an interchangeability study[J]. AJR Am J Roentgenol, 2020, 215(6): 1421-1429. DOI: 10.2214/AJR.20.23313.
Fayad LM, Parekh VS, de Castro Luna R, et al. A deep learning system for synthetic knee magnetic resonance imaging: is artificial intelligence-based fat-suppressed imaging feasible?[J]. Invest Radiol, 2021, 56(6): 357-368. DOI: 10.1097/RLI.0000000000000751.
Khoury NJ, Mahfoud Z, Masrouha KZ, et al. Value of sagittal fat-suppressed proton-density fast-spin-echo of the knee joint as a limited protocol in evaluating internal knee derangements[J]. J Comput Assist Tomogr, 2011, 35(5): 653-661. DOI: 10.1097/RCT.0b013e3182251016.
Wang X, Oo WM, Linklater J. What is the role of imaging in the clinical diagnosis of osteoarthritis and disease management?[J]. Rheumatology, 2018, 57: iv51-iv60. DOI: 10.1093/rheumatology/kex501.
Peterfy CG, 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.
Pan K, Liu QQ, Tang LL, et al. Study on acceleration efficiency and image quality of artificial intelligence compressed sensing and compressed sensing in knee MRI[J]. Chin J Magn Reson Imaging, 2022, 13(5): 94-98. DOI: 10.12015/issn.1674-8034.2022.05.017.
Verschueren J, Eijgenraam SM, Klein S, et al. T2 mapping of healthy knee cartilage: multicenter multivendor reproducibility[J]. Quant Imaging Med Surg, 2021, 11(4): 1247-1255. DOI: 10.21037/qims-20-674.
Panfilov E, Tiulpin A, Nieminen MT, et al. Deep learning-based segmentation of knee MRI for fully automatic subregional morphological assessment of cartilage tissues: data from the Osteoarthritis Initiative[J]. J Orthop Res, 2022, 40(5): 1113-1124. DOI: 10.1002/jor.25150.
Kobayashi S, Peduto A, Simic M, et al. Can we have an overall osteoarthritis severity score for the patellofemoral joint using magnetic resonance imaging? Reliability and validity[J]. Clin Rheumatol, 2018, 37(4): 1091-1098. DOI: 10.1007/s10067-017-3888-y.
Riddle DL, Vossen JA, Hoover KB. Magnetic resonance imaging of patellofemoral osteoarthritis: intertester reliability and associations with knee pain and function[J]. Clin Rheumatol, 2019, 38(5): 1469-1476. DOI: 10.1007/s10067-018-04414-z.
Iuga AI, Abdullayev N, Weiss K, et al. Accelerated MRI of the knee. Quality and efficiency of compressed sensing[J/OL]. Eur J Radiol, 2020, 132 [2022-09-27]. DOI: 10.1016/j.ejrad.2020.109273.
Herrmann J, Gassenmaier S, Nickel D, et al. Diagnostic confidence and feasibility of a deep learning accelerated HASTE sequence of the abdomen in a single breath-hold[J]. Invest Radiol, 2021, 56(5): 313-319. DOI: 10.1097/RLI.0000000000000743.
Qiu JX, Liu J, Bi ZX, et al. An investigation of 2D spine magnetic resonance imaging (MRI) with compressed sensing (CS)[J]. Skeletal Radiol, 2022, 51(6): 1273-1283. DOI: 10.1007/s00256-021-03954-x.
Gao TY, Lu Z, Wang FZ, et al. Using the compressed sensing technique for lumbar vertebrae imaging: comparison with conventional parallel imaging[J]. Curr Med Imaging, 2021, 17(8): 1010-1017. DOI: 10.2174/1573405617666210126155814.
Chaudhari AS, Grissom MJ, Fang ZN, et al. Diagnostic accuracy of quantitative multicontrast 5-minute knee MRI using prospective artificial intelligence image quality enhancement[J]. AJR Am J Roentgenol, 2021, 216(6): 1614-1625. DOI: 10.2214/AJR.20.24172.
Wang XZ, Ma JF, Bhosale P, et al. Novel deep learning-based noise reduction technique for prostate magnetic resonance imaging[J]. Abdom Radiol (NY), 2021, 46(7): 3378-3386. DOI: 10.1007/s00261-021-02964-6.

PREV Value of preoperative prediction of Ki-67 expression in breast cancer based on DCE-MRI intratumoral combined with peritumoral radiomics model
NEXT Comparative study on resting functional connection of amygdala between recurrent and first-episode depression

Tel & Fax: +8610-67113815    E-mail: