Deep learning in rheumatological image interpretation
- 8 February 2024
- journal article
- review article
- Published by Springer Nature in Nature Reviews Rheumatology
- Vol. 20 (3) , 182-195
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.Keywords
This publication has 86 references indexed in Scilit:
- Deep Learning Approach for Evaluating Knee MR Images: Achieving High Diagnostic Performance for Cartilage Lesion DetectionRadiology, 2018
- Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United StatesInsights into Imaging, 2018
- Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and MorphometryRadiology, 2018
- Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based ApproachScientific Reports, 2018
- Automatic identification of bone erosions in rheumatoid arthritis from hand radiographs based on deep convolutional neural networkMultimedia Tools and Applications, 2017
- Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methodsPLOS ONE, 2017
- Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imagingMagnetic Resonance in Medicine, 2017
- Using a reference when defining an abnormal MRI reduces false-positive MRI results—a longitudinal study in two cohorts at risk for rheumatoid arthritisRheumatology, 2017
- A preliminary examination of the diagnostic value of deep learning in hip osteoarthritisPLOS ONE, 2017
- Magnetic Resonance Imaging–Detected Features of Inflammation and Erosions in Symptom‐Free Persons From the General PopulationArthritis & Rheumatology, 2016