Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network

Üreten, Kemal; Erbay, Hasan; Maraş, Hadi Hakan

doi:10.1007/s10067-019-04487-4

Cited by 61 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Second, as part of an automated imaging pipeline, the model can be used to route images to more specialized networks for abnormality detection. For instance, the model can first identify a chest image so that it can then be analyzed by a network specialized for detecting anomalies in chest radiographs [9], abdominal radiographs [10], or musculoskeletal radiographs [11][12][13][14]. Again, our model did not achieve perfect accuracy for all classes.…”

Section: Discussionmentioning

confidence: 88%

Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network

et al. 2020

View full text Add to dashboard Cite

Objectives The goal of the present study was to classify the most common types of plain radiographs using a neural network and to validate the network’s performance on internal and external data. Such a network could help improve various radiological workflows. Methods All radiographs from the year 2017 (n = 71,274) acquired at our institution were retrieved from the PACS. The 30 largest categories (n = 58,219, 81.7% of all radiographs performed in 2017) were used to develop and validate a neural network (MobileNet v1.0) using transfer learning. Image categories were extracted from DICOM metadata (study and image description) and mapped to the WHO manual of diagnostic imaging. As an independent, external validation set, we used images from other institutions that had been stored in our PACS (n = 5324). Results In the internal validation, the overall accuracy of the model was 90.3% (95%CI: 89.2–91.3%), whereas, for the external validation set, the overall accuracy was 94.0% (95%CI: 93.3–94.6%). Conclusions Using data from one single institution, we were able to classify the most common categories of radiographs with a neural network. The network showed good generalizability on the external validation set and could be used to automatically organize a PACS, preselect radiographs so that they can be routed to more specialized networks for abnormality detection or help with other parts of the radiological workflow (e.g., automated hanging protocols; check if ordered image and performed image are the same). The final AI algorithm is publicly available for evaluation and extension. Key Points • Data from one single institution can be used to train a neural network for the correct detection of the 30 most common categories of plain radiographs. • The trained model achieved a high accuracy for the majority of categories and showed good generalizability to images from other institutions. • The neural network is made publicly available and can be used to automatically organize a PACS or to preselect radiographs so that they can be routed to more specialized neural networks for abnormality detection.

show abstract

Section: Discussionmentioning

confidence: 88%

Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms have been utilized in image processing to find patterns in images (so-called convolutional neural networks). This sort of neural network has been utilized to detect bone erosions ( 425 ) and differentiate RA patients from healthy participants from conventional hand radiographs ( 426 ). As discussed in the above subsection of multi-omics in precision medicine of RA, the combination of multi-omics and/or clinical data with machine learning could be used to predict response to DMARDs in RA patients ( 403 ).…”

Section: Bioinformatics and Biostatistics In Precision Medicine Of Ramentioning

confidence: 99%

Toward Overcoming Treatment Failure in Rheumatoid Arthritis

et al. 2021

View full text Add to dashboard Cite

Rheumatoid arthritis (RA) is an autoimmune disorder characterized by inflammation and bone erosion. The exact mechanism of RA is still unknown, but various immune cytokines, signaling pathways and effector cells are involved. Disease-modifying antirheumatic drugs (DMARDs) are commonly used in RA treatment and classified into different categories. Nevertheless, RA treatment is based on a “trial-and-error” approach, and a substantial proportion of patients show failed therapy for each DMARD. Over the past decades, great efforts have been made to overcome treatment failure, including identification of biomarkers, exploration of the reasons for loss of efficacy, development of sequential or combinational DMARDs strategies and approval of new DMARDs. Here, we summarize these efforts, which would provide valuable insights for accurate RA clinical medication. While gratifying, researchers realize that these efforts are still far from enough to recommend specific DMARDs for individual patients. Precision medicine is an emerging medical model that proposes a highly individualized and tailored approach for disease management. In this review, we also discuss the potential of precision medicine for overcoming RA treatment failure, with the introduction of various cutting-edge technologies and big data.

show abstract

“…Some researchers have devised models to solve the RA scoring challenge by learning to assess joint injuries directly from data. One approach uses various clinical data to determine whether a patient has RA and diagnose rheumatoid arthritis by training a convolutional neural network on a dataset of radiographs [15,16]. Another mainstream approach uses a two-step approach to detect finger joint destruction [17,18].…”

Section: Introductionmentioning

confidence: 99%

An Efficient CNN for Hand X‐Ray Overall Scoring of Rheumatoid Arthritis

Wang

Liu

et al. 2022

Complexity

View full text Add to dashboard Cite

Rheumatoid arthritis (RA) is a progressive systemic autoimmune disease characterized by inflammation of the joints and surrounding tissues, which seriously affects the life of patients. The Sharp/van der Heijde method has been widely used in clinical evaluation for the RA disease. However, this manual method is time-consuming and laborious. Even if two radiologists evaluate a specific location, their subjective evaluation may lead to low inter-rater reliability. Here, we developed an efficient model powered by deep convolutional neural networks to solve these problems and automated the overall scoring on hand X-rays. The depthwise separable (Dwise) convolution technique is used based on ResNet-50 due to the high resolution of hand X-rays. An inverted residual block is introduced to devise a ResNet-Dwise50 model to enhance the efficiency of the model. The model was trained and tested using bilateral posteroanterior (two-handed, side by side) images of 3818 patients. The experiment results show the ResNet-Dwise50 model achieved an MAE of 14.90 and RMSE of 22.01 while ensuring high efficiency. There was no statistical difference between the average scores given by two experienced radiologists and predicted scores from our model.

show abstract

Detection of rheumatoid arthritis from hand radiographs using a convolutional neural network

Cited by 61 publications

References 18 publications

Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network

Practical applications of deep learning: classifying the most common categories of plain radiographs in a PACS using a neural network

Toward Overcoming Treatment Failure in Rheumatoid Arthritis

An Efficient CNN for Hand X‐Ray Overall Scoring of Rheumatoid Arthritis

Contact Info

Product

Resources

About