Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 86 of the 86 references it cites were found in a registry or an index.

Deep learning in rheumatological image interpretation

Open access
Stoel, Berend C., Staring, Marius, Reijnierse, Monique, van der Helm-van Mil, Annette H. M. · 2024 · Nature Reviews Rheumatology

Abstract

Artificial intelligence techniques, specifically deep learning, have already affected daily life in a wide range of areas. Likewise, initial applications have been explored in rheumatology. Deep learning might not easily surpass the accuracy of classic techniques when performing classification or regression on low-dimensional numerical data. With images as input, however, deep learning has become so successful that it has already outperformed the majority of conventional image-processing techniques developed during the past 50 years. As with any new imaging technology, rheumatologists and radiologists need to consider adapting their arsenal of diagnostic, prognostic and monitoring tools, and even their clinical role and collaborations. This adaptation requires a basic understanding of the technical background of deep learning, to efficiently utilize its benefits but also to recognize its drawbacks and pitfalls, as blindly relying on deep learning might be at odds with its capabilities. To facilitate such an understanding, it is necessary to provide an overview of deep-learning techniques for automatic image analysis in detecting, quantifying, predicting and monitoring rheumatic diseases, and of currently published deep-learning applications in radiological imaging for rheumatology, with critical assessment of possible limitations, errors and confounders, and conceivable consequences for rheumatologists and radiologists in clinical practice. Deep learning is a powerful technique with great potential for the analysis and interpretation of rheumatological images. To successfully use deep learning, rheumatologists should understand the tasks involved in image processing and the potential confounders and limitations that can affect the analysis of clinical data.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1038/s41584-023-01074-5

Cites

86 of 86 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY · From the PDF
Fig. 3 Example of convolution, as a core building block in deep learning in image analysis. a , Zooming in on this MRI scan of the wrist shows the individual pixels, which can be represented as a matrix of intensity values. Convolutional neural networks (CNNs) rely on learning to quantify local features in the image by multiplying the intensity values in an area (for example, a three-by-three grid) surrounding each pixel with the contents of a so-called convolution kernel, containing weights. The output image then contains the sum of these
Fig. 3 Example of convolution, as a core building block in deep learning in image analysis. a , Zooming in on this MRI scan of the wrist shows the individual pixels, which can be represented as a matrix of intensity values. Convolutional neural networks (CNNs) rely on learning to quantify local features in the image by multiplying the intensity values in an area (for example, a three-by-three grid) surrounding each pixel with the contents of a so-called convolution kernel, containing weights. The output image then contains the sum of theseCC-BY · From the PDF
Fig. 4 Categorization of published studies on deep learning in rheumatological imaging. a , The number of publications per month on deep learning in imaging in rheumatology. b , Disease domains represented in the published research, together with the use of imaging modalities in the studies within each domain. c , The use of deep-learning models in studies within each disease domain. d , The distribution of studies of deep-learning models in relation to particular anatomical sites in osteoarthritis (OA) research, along with the use of imaging modalities. e , The distribution of studies of deep-learning models
Fig. 4 Categorization of published studies on deep learning in rheumatological imaging. a , The number of publications per month on deep learning in imaging in rheumatology. b , Disease domains represented in the published research, together with the use of imaging modalities in the studies within each domain. c , The use of deep-learning models in studies within each disease domain. d , The distribution of studies of deep-learning models in relation to particular anatomical sites in osteoarthritis (OA) research, along with the use of imaging modalities. e , The distribution of studies of deep-learning modelsCC-BY · From the PDF
Fig. 5 AI-based comparison between baseline and follow-up MRI of the wrist, without prior knowledge. In this example, the neural network has learned without supervision to neglect changes that are common in the population (for example, common artefacts or gradual changes in the MRI scanner) and to only show intensity changes that cannot be predicted 87 . a , The follow-up image is predicted from the baseline image, and vice versa. Two so-called U-nets are trained jointly with a common loss function, in which the input image at one time point is encoded followed by decoding into the predicted image at the opposite
Fig. 5 AI-based comparison between baseline and follow-up MRI of the wrist, without prior knowledge. In this example, the neural network has learned without supervision to neglect changes that are common in the population (for example, common artefacts or gradual changes in the MRI scanner) and to only show intensity changes that cannot be predicted 87 . a , The follow-up image is predicted from the baseline image, and vice versa. Two so-called U-nets are trained jointly with a common loss function, in which the input image at one time point is encoded followed by decoding into the predicted image at the oppositeCC-BY · From the PDF

Verification

Claims the paper makes

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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?

Self-check

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

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

Citations

Cites

Show all 86 references

Research works printed but not linked: 5

  1. Banerjee, S., Bhunia, S. & Schaefer, G. Osteophyte detection for hand osteoarthritis identification in X-ray images using CNNs. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011, 6196–6199 (2011).
  2. Ras, G., Xie, N., Gerven, M. V. & Doran, D. Explainable deep learning: a field guide for the uninitiated. J. Artif. Int. Res. 73, 68 (2022).
  3. Tiulpin, A., Thevenot, J., Rahtu, E., Lehenkari, P. & Saarakkala, S. Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci. Rep. 8, 1727 (2018). · DOI
  4. Shamonin, D. P. et al. POS0920 quantification of tenosynovitis from wrist MRIs, based on deep learning. Ann. Rheum. Dis. 82, 770–771 (2023).
  5. Hassanzadeh, T. et al. A deep learning model to locate inflammatory changes in rheumatoid arthritis. Ann. Rheum. Dis. 82, 298–299 (2023).

Cited by

See all 25

Metadata

Authors
Stoel, B. C., Staring, M., Reijnierse, M., & van der Helm-van Mil, A. H. M.
Affiliations
Leiden University Medical Center (NL)
Corresponding author
Stoel, Berend C.
Venue
Nature Reviews Rheumatology
Published
2024-02-08
Volume
20
Issue
3
Pages
182-195
ISSN
  • 1759-4790 (ISSN-L)
  • 1759-4804
OpenAlex
W4391642764
Cited by
25
References
86
Citations by year
2026: 7 · 2025: 14 · 2024: 4
FWCI
0.57
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Reviews Rheumatology (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Leiden Repository (Leiden University) (submittedVersion, cc-by)
Funders
Nederlandse Organisatie voor Wetenschappelijk Onderzoek (17970)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
  • Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
Keywords
deep learning, radiological imaging, rheumatic diseases, automatic image analysis, disease detection, disease quantification, disease surveillance, clinical decision support
MeSH terms
Deep Learning, Artificial Intelligence, Diagnostic Imaging, Humans, Rheumatic Diseases, Rheumatology

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Deep learning in rheumatological image interpretation. https://app.cochat.ai/papers/10.1038/s41584-023-01074-5
The paper
Stoel, B. C., Staring, M., Reijnierse, M., & van der Helm-van Mil, A. H. M. (2024). Deep learning in rheumatological image interpretation. Nature Reviews Rheumatology. https://doi.org/10.1038/s41584-023-01074-5

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.