CoChat
Sign Up
Cited by 22Radiomics and Machine Learning in Medical ImagingOsteoarthritis Treatment and MechanismsArtificial Intelligence in Healthcare and Education

Automatic grading of knee osteoarthritis with a plain radiograph radiomics model: combining anteroposterior and lateral images

Open access
Li, Wei, Liu, Jin, Xiao, Zhongli, Zhu, Dantian, Liao, Jianwei, Yu, Wenjun, Feng, Jiaxin, Qian, Baoxin +2 more·2024·Insights into Imaging
DOI 10.1186/s13244-024-01719-3PMC PMC11169124
Open this paper in CoChat — free account

Abstract

Objectives: To establish a radiomics-based automatic grading model for knee osteoarthritis (OA) and evaluate the influence of different body positions on the model’s effectiveness. Materials and methods: Plain radiographs of a total of 473 pairs of knee joints from 473 patients (May 2020 to July 2021) were retrospectively analyzed. Each knee joint included anteroposterior (AP) and lateral (LAT) images which were randomly assigned to the training cohort and the testing cohort at a ratio of 7:3. First, an assessment of knee OA severity was done by two independent radiologists with Kallgren–Lawrence grading scale. Then, another two radiologists independently delineated the region of interest for radiomic feature extraction and selection. The radiomic classification features were dimensionally reduced and a machine model was conducted using logistic regression (LR). Finally, the classification efficiency of the model was evaluated using receiver operating characteristic curves and the area under the curve (AUC). Results: The AUC (macro/micro) of the model using a combination of AP and LAT (AP&LAT) images were 0.772/0.778, 0.818/0.799, and 0.864/0.879, respectively. The radiomic features from the combined images achieved better classification performance than the individual position image (p < 0.05). The overall accuracy of the radiomic model with AP&LAT images was 0.727 compared to 0.712 and 0.417 for radiologists with 4 years and 2 years of musculoskeletal diagnostic experience. Conclusions: A radiomic model constructed by combining the AP&LAT images of the knee joint can better grade knee OA and assist clinicians in accurate diagnosis and treatment. Critical relevance statement: A radiomic model based on plain radiographs accurately grades knee OA severity. By utilizing the LR classifier and combining AP&LAT images, it improves accuracy and consistency in grading, aiding clinical decision-making, and treatment planning. Key Points: Radiomic model performed more accurately in K/L grading of knee OA than junior radiologists. Radiomic features from the combined images achieved better classification performance than the individual position image. A radiomic model can improve the grading of knee OA and assist in diagnosis and treatment. Graphical Abstract:

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s13244-024-01719-3

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Molecular imaging techniques such as PET, SPECT, optical imaging, and contrast-enhanced MRI are revolutionizing degenerative joint disease assessment by visualizing specific biological processes at molecular and cellular levels, surpassing traditional anatomical imaging.

    “Molecular imaging techniques, such as positron emission tomography (PET), single-photon emission computed tomography (SPECT), optical imaging, and contrast-enhanced MRI, are revolutionizing degenerative joint disease assessment by visualizing specific biological processes at molecular and cellular levels, surpassing traditional anatomical imaging [163,164,165].”

    From Biomarker-Guided Imaging and AI-Augmented Diagnosis of Degenerative Joint Disease (2025) · cites this paper as [165]

    Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 33 · Cited by 22

Research works printed but not linked: 33

  1. [1]Katz JN, Arant KR, Loeser RF (2021) Diagnosis and treatment of hip and knee osteoarthritis: a review. JAMA 325:568–578. 10.1001/jama.2020.22171 33560326 10.1001/jama.2020.22171 PMC8225295 · DOI
  2. [2]Cui A, Li H, Wang D, et al (2020) Global, regional prevalence, incidence and risk factors of knee osteoarthritis in population-based studies. EClinicalMedicine 29–30:100587. 10.1016/j.eclinm.2020.100587 PMC7704420 34505846 · DOI
  3. [3]Sharma L (2021) Osteoarthritis of the knee. N Engl J Med 384:51–59. 10.1056/NEJMcp1903768 33406330 10.1056/NEJMcp1903768 · DOI
  4. [4]Long H, Zeng X, Liu Q et al (2020) Burden of osteoarthritis in China, 1990–2017: findings from the Global Burden of Disease Study 2017. Lancet Rheumatol 2:e164–e172. 10.1016/S2665-9913(19)30145-6 38263654 10.1016/S2665-9913(19)30145-6 · DOI
  5. [5]Lee LS, Chan PK, Fung WC et al (2021) Imaging of knee osteoarthritis: a review of current evidence and clinical guidelines. Musculoskelet Care 19:363–374. 10.1002/msc.1536 10.1002/msc.1536 33387447 · DOI
  6. [6]Kellgren JH, Lawrence JS (1957) Radiological assessment of osteo-arthrosis. Ann Rheum Dis 16:494–502 13498604 10.1136/ard.16.4.494 PMC1006995 · DOI
  7. [7]Saini D, Chand T, Chouhan DK, Prakash M (2021) A comparative analysis of automatic classification and grading methods for knee osteoarthritis focussing on X-ray images. Biocybern Biomed Eng 41:419–444. 10.1016/j.bbe.2021.03.002 10.1016/j.bbe.2021.03.002 · DOI
  8. [8]Mayerhoefer ME, Materka A, Langs G et al (2020) Introduction to radiomics. J Nucl Med 61:488–495. 10.2967/jnumed.118.222893 32060219 10.2967/jnumed.118.222893 PMC9374044 · DOI · Paper page
  9. [9]Avanzo M, Wei L, Stancanello J et al (2020) Machine and deep learning methods for radiomics. Med Phys 47:e185–e202. 10.1002/mp.13678 32418336 10.1002/mp.13678 PMC8965689 · DOI
  10. [10]Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. 10.1148/radiol.2015151169 26579733 10.1148/radiol.2015151169 PMC4734157 · DOI · Paper page
  11. [11]Ji G-W, Zhang Y-D, Zhang H et al (2019) Biliary tract cancer at CT: a radiomics-based model to predict lymph node metastasis and survival outcomes. Radiology 290:90–98. 10.1148/radiol.2018181408 30325283 10.1148/radiol.2018181408 · DOI
  12. [12]Kniep HC, Madesta F, Schneider T et al (2019) Radiomics of brain MRI: utility in prediction of metastatic tumor type. Radiology 290:479–487. 10.1148/radiol.2018180946 30526358 10.1148/radiol.2018180946 · DOI
  13. [13]Suarez-Ibarrola R, Basulto-Martinez M, Heinze A et al (2020) Radiomics applications in renal tumor assessment: a comprehensive review of the literature. Cancers 12:1387. 10.3390/cancers12061387 32481542 10.3390/cancers12061387 PMC7352711 · DOI
  14. [14]Zhou M, Scott J, Chaudhury B et al (2018) Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches. AJNR Am J Neuroradiol 39:208–216. 10.3174/ajnr.A5391 28982791 10.3174/ajnr.A5391 PMC5812810 · DOI
  15. [15]Yin P, Mao N, Zhao C et al (2019) A triple-classification radiomics model for the differentiation of primary chordoma, giant cell tumor, and metastatic tumor of sacrum based on t2-weighted and contrast-enhanced T1-weighted MRI. J Magn Reson Imaging 49:752–759. 10.1002/jmri.26238 30430686 10.1002/jmri.26238 · DOI
  16. [16]Li W, Feng J, Zhu D et al (2023) Nomogram model based on radiomics signatures and age to assist in the diagnosis of knee osteoarthritis. Exp Gerontol 171:112031. 10.1016/j.exger.2022.112031 36402414 10.1016/j.exger.2022.112031 · DOI
  17. [17]Lambin P, Leijenaar RT, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749–762 28975929 10.1038/nrclinonc.2017.141 · DOI · Paper page
  18. [18]Brahim A, Jennane R, Riad R et al (2019) A decision support tool for early detection of knee osteoarthritis using X-ray imaging and machine learning: data from the OsteoArthritis Initiative. Comput Med Imaging Graph 73:11–18. 10.1016/j.compmedimag.2019.01.007 30784984 10.1016/j.compmedimag.2019.01.007 · DOI
  19. [19]Saleem M, Farid MS, Saleem S, Khan MH (2020) X-ray image analysis for automated knee osteoarthritis detection. SIViP 14:1079–1087. 10.1007/s11760-020-01645-z 10.1007/s11760-020-01645-z · DOI
  20. [20]Minciullo L, Cootes T (2016) Fully automated shape analysis for detection of Osteoarthritis from lateral knee radiographs. In 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp. 3787–3791. 10.1109/ICPR.2016.7900224 · DOI
  21. [21]Olsson S, Akbarian E, Lind A et al (2021) Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population. BMC Musculoskelet Disord 22:844. 10.1186/s12891-021-04722-7 34600505 10.1186/s12891-021-04722-7 PMC8487469 · DOI
  22. [22]Swiecicki A, Li N, O’Donnell J et al (2021) Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists. Comput Biol Med 133:104334. 10.1016/j.compbiomed.2021.104334 33823398 10.1016/j.compbiomed.2021.104334 · DOI
  23. [23]Oka H, Muraki S, Akune T et al (2008) Fully automatic quantification of knee osteoarthritis severity on plain radiographs. Osteoarthritis Cartilage 16:1300–1306. 10.1016/j.joca.2008.03.011 18424107 10.1016/j.joca.2008.03.011 · DOI
  24. [24]Norman B, Pedoia V, Noworolski A et al (2019) Applying densely connected convolutional neural networks for staging osteoarthritis severity from plain radiographs. J Digit Imaging 32:471–477. 10.1007/s10278-018-0098-3 30306418 10.1007/s10278-018-0098-3 PMC6499841 · DOI
  25. [25]Tiulpin A, Saarakkala S (2020) Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. Diagnostics 10:932. 10.3390/diagnostics10110932 33182830 10.3390/diagnostics10110932 PMC7697270 · DOI
  26. [26]Thomas, Kidziński KA, Halilaj E et al (2020) Automated classification of radiographic knee osteoarthritis severity using deep neural networks. Radiol Artif Intell 2:e190065. 10.1148/ryai.2020190065 32280948 10.1148/ryai.2020190065 PMC7104788 · DOI
  27. [27]Li W, Xiao Z, Liu J, et al (2023) Deep learning-assisted knee osteoarthritis automatic grading on plain radiographs: the value of multiview X-ray images and prior knowledge. Quant Imaging Med Surg 0:0–0. 10.21037/qims-22-1250 PMC10239991 37284121 · DOI
  28. [28]Lee J-G, Jun S, Cho Y-W et al (2017) Deep learning in medical imaging: general overview. Korean J Radiol 18:570. 10.3348/kjr.2017.18.4.570 28670152 10.3348/kjr.2017.18.4.570 PMC5447633 · DOI
  29. [29]van Ooijen PMA, Nagaraj Y, Olthof A (2020) Medical imaging informatics, more than ‘just’ deep learning. Eur Radiol 30:5507–5509. 10.1007/s00330-020-06939-x 32430677 10.1007/s00330-020-06939-x · DOI
  30. [30]Abdullah SS, Rajasekaran MP (2022) Automatic detection and classification of knee osteoarthritis using deep learning approach. Radiol Med 127:398–406. 10.1007/s11547-022-01476-7 35262842 10.1007/s11547-022-01476-7 · DOI
  31. [31]Kızılgöz V, Sivrioğlu AK, Ulusoy GR et al (2019) Posterior tibial slope measurement on lateral knee radiographs as a risk factor of anterior cruciate ligament injury: A cross-sectional study. Radiography 25:33–38. 10.1016/j.radi.2018.07.007 30599827 10.1016/j.radi.2018.07.007 · DOI
  32. [32]Kong AP, Robbins RM, Stensby JD, Wissman RD (2022) The lateral knee radiograph: a detailed review. J Knee Surg 35:482–490. 10.1055/s-0041-1741391 35062040 10.1055/s-0041-1741391 · DOI
  33. [33]Tai AW, Alparslan HL, Townsend BA et al (2009) Accuracy of cross-table lateral knee radiography for evaluation of joint effusions. AJR Am J Roentgenol 193:W339–W344. 10.2214/AJR.09.2562 19770305 10.2214/AJR.09.2562 · DOI

Authors
Li, W., Liu, J., Xiao, Z., Zhu, D., Liao, J., Yu, W., Feng, J., Qian, B., Fang, Y., & Li, S.
Affiliations
Fifth Affiliated Hospital of Sun Yat-sen University (CN)
Corresponding author
Li, Shaolin
ORCID
Venue
Insights into Imaging
Publisher
Springer Science and Business Media LLC
Published
2024-06-13
Volume
15
Issue
1
Pages
143-143
ISSN
1869-4101 (ISSN-L)
DOI
10.1186/s13244-024-01719-3
PMC
PMC11169124
OpenAlex
W4399655654
Cited by
22
References
33
Citations by year
2026: 9 · 2025: 11 · 2024: 2
FWCI
5.60
Type
journal article
Language
en
Update notices
correction (2024-08-01)
Open access
Licence
Locations
  • Insights into Imaging (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Zhuhai Science and Technology Planning Project in the Social Development Field (2320004000144)
  • National Natural Science Foundation of China (82172053)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Health Sciences › Medicine › Rheumatology › Osteoarthritis Treatment and Mechanisms
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
Keywords
knee osteoarthritis, radiomics, automated grading, plain radiographs, knee joint

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review