Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May;35(5):2457-2469.
doi: 10.1007/s00330-024-11105-8. Epub 2024 Oct 18.

MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review

Keiley Mead  1 , Tom Cross  2 , Greg Roger  3   4 , Rohan Sabharwal  5 , Sahaj Singh  5 , Nicola Giannotti  6
Affiliations

MRI deep learning models for assisted diagnosis of knee pathologies: a systematic review

Keiley Mead et al. Eur Radiol. 2025 May.

Abstract

Objectives: Despite showing encouraging outcomes, the precision of deep learning (DL) models using different convolutional neural networks (CNNs) for diagnosis remains under investigation. This systematic review aims to summarise the status of DL MRI models developed for assisting the diagnosis of a variety of knee abnormalities.

Materials and methods: Five databases were systematically searched, employing predefined terms such as 'Knee AND 3D AND MRI AND DL'. Selected inclusion criteria were used to screen publications by title, abstract, and full text. The synthesis of results was performed by two independent reviewers.

Results: Fifty-four articles were included. The studies focused on anterior cruciate ligament injuries (n = 19, 36%), osteoarthritis (n = 9, 17%), meniscal injuries (n = 13, 24%), abnormal knee appearance (n = 11, 20%), and other (n = 2, 4%). The DL models in this review primarily used the following CNNs: ResNet (n = 11, 21%), VGG (n = 6, 11%), DenseNet (n = 4, 8%), and DarkNet (n = 3, 6%). DL models showed high-performance metrics compared to ground truth. DL models for the detection of a specific injury outperformed those by up to 4.5% for general abnormality detection.

Conclusion: Despite the varied study designs used among the reviewed articles, DL models showed promising outcomes in the assisted detection of selected knee pathologies by MRI. This review underscores the importance of validating these models with larger MRI datasets to close the existing gap between current DL model performance and clinical requirements.

Key points: Question What is the status of DL model availability for knee pathology detection in MRI and their clinical potential? Findings Pathology-specific DL models reported higher accuracy compared to DL models for the detection of general abnormalities of the knee. DL model performance was mainly influenced by the quantity and diversity of data available for model training. Clinical relevance These findings should encourage future developments to improve patient care, support personalised diagnosis and treatment, optimise costs, and advance artificial intelligence-based medical imaging practices.

Keywords: Artificial intelligence; Deep learning; Knee; Magnetic resonance imaging; Three-dimensional.

PubMed Disclaimer

Conflict of interest statement

Compliance with ethical standards. Guarantor: The scientific guarantor of this publication is Nicola Giannotti. Conflict of interest: The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article. Statistics and biometry: No complex statistical methods were necessary for this paper. Informed consent: Written informed consent was waived by the Research Integrity and Ethics Committee at the University of Sydney. Ethical approval: Ethics approval was deemed unnecessary by the Research Integrity and Ethics Committee at the University of Sydney. Study subjects or cohorts overlap: Not applicable as this is a systematic review of previously published, original research. Methodology: Retrospective Systematic review Performed at one institution—The University of Sydney

Figures

Fig. 1
Fig. 1
PRISMA flow diagram showcasing the selection of evidence for the systematic review ‘DL models available for assisted detection of knee pathologies in MRI’
Fig. 2
Fig. 2
Graphical depiction of the occurrence of various ground truth or reference standards representative of the articles analysed in the review
See this image and copyright information in PMC

References

    1. Maniar N, Verhagen E, Bryant AL, Opar DA (2022) Trends in Australian knee injury rates: an epidemiological analysis of 228,344 knee injuries over 20 years. Lancet Reg Health West Pac. 10.1016/j.lanwpc.2022.100409 - PMC - PubMed
    1. Ridley U, Ridley L (2020) Imaging of the knee: common acute presentations to general practice. Aust J Gen Pract. 10.31128/AJGP-10-19-5120 - PubMed
    1. Nacey NC, Geeslin MG, Miller GW, Pierce JL (2017) Magnetic resonance imaging of the knee: an overview and update of conventional and state of the art imaging. J Magn Reson Imaging. 10.1002/jmri.25620 - PubMed
    1. El-Liethy NE, Rashwan AS, Kamal H (2020) Single isotropic 3D fast spin echo sequence compared with conventional 2D sequences for detecting meniscal and cruciate ligament tears in the knee. Egypt J Radiol Nucl Med. 10.1186/s43055-020-00362-4
    1. Kijowski R, Davis KW, Woods MA et al (2009) Knee joint: comprehensive assessment with 3D isotropic resolution fast spin-echo MR Imaging—diagnostic performance compared with that of conventional MR imaging at 3.0 T. Radiology. 10.1148/radiol.2523090028 - PMC - PubMed

Publication types

MeSH terms

LinkOut - more resources