An Efficient CNN for Hand X-Ray Classification of Rheumatoid Arthritis

Mate, Gitanjali; Kureshi, A. K.; Singh, Bhupesh Kumar

doi:10.1155/2021/6712785

Cited by 14 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the metrical analysis demonstrated a clear change in the joint diameter/finger line ratio after successful therapy and resolution of inflammation. To our knowledge, this is the first application of CNNs to real-world images in the setting of RA or osteoarthritis, whilst in previous studies, CNNs were applied to radiographs and ultrasound images [11, 12]. Such a patient-controlled biomarker could complement patient reported outcomes and wearables and thus empower patients in monitoring their disease.…”

Section: Discussionmentioning

confidence: 99%

Dorsal Finger Fold Recognition by Convolutional Neural Networks for the Detection and Monitoring of Joint Swelling in Patients with Rheumatoid Arthritis

Hügle

Caratsch

Caorsi³

et al. 2022

Digit Biomark

View full text Add to dashboard Cite

Digital biomarkers such as wearables are of increasing interest in monitoring rheumatic diseases, but they usually lack disease specificity. In this study, we apply convolutional neural networks (CNN) to real-world hand photographs in order to automatically detect, extract, and analyse dorsal finger fold lines as a correlate of proximal interphalangeal (PIP) joint swelling in patients with rheumatoid arthritis (RA). Hand photographs of RA patients were taken by a smartphone camera in a standardized manner. Overall, 190 PIP joints were categorized as either swollen or not swollen based on clinical judgement and ultrasound. Images were automatically preprocessed by cropping PIP joints and extracting dorsal finger folds. Subsequently, metrical analysis of dorsal finger folds was performed, and a CNN was trained to classify the dorsal finger lines into swollen versus non-swollen joints. Representative horizontal finger folds were also quantified in a subset of patients before and after resolution of PIP swelling and in patients with disease flares. In swollen joints, the number of automatically extracted deep skinfold imprints was significantly reduced compared to non-swollen joints (1.3, SD 0.8 vs. 3.3, SD 0.49, <i>p</i> < 0.01). The joint diameter/deep skinfold length ratio was significantly higher in swollen (4.1, SD 1.4) versus non-swollen joints (2.1, SD 0.6, <i>p</i> < 0.01). The CNN model successfully differentiated swollen from non-swollen joints based on finger fold patterns with a validation accuracy of 0.84, a sensitivity of 88%, and a specificity of 75%. A heatmap of the original images obtained by an extraction algorithm confirmed finger folds as the region of interest for correct classification. After significant response to disease-modifying antirheumatic drug ± corticosteroid therapy, longitudinal metrical analysis of eight representative deep finger folds showed a decrease in the mean diameter/finger fold length (finger fold index, FFI) from 3.03 (SD 0.68) to 2.08 (SD 0.57). Conversely, the FFI increased in patients with disease flares. In conclusion, automated preprocessing and the application of CNN algorithms in combination with longitudinal metrical analysis of dorsal finger fold patterns extracted from real-world hand photos might serve as a digital biomarker in RA.

show abstract

Section: Discussionmentioning

confidence: 99%

Dorsal Finger Fold Recognition by Convolutional Neural Networks for the Detection and Monitoring of Joint Swelling in Patients with Rheumatoid Arthritis

Hügle

Caratsch

Caorsi³

et al. 2022

Digit Biomark

View full text Add to dashboard Cite

show abstract

“…This automation of the bone erosion scoring process reduces the time and effort required for manual analysis by medical professionals, although it heavily depends on the quality and diversity of the training data. Additionally, a CNN architecture efficient for image classification tasks is proposed in Refs., 30,31 aiming to automate the classification process and assist radiologists in quickly identifying potential cases of RA from x-ray images. However, it is crucial to address imbalances in the dataset, as they can affect the model's performance and introduce biases toward the majority class.…”

Section: Related Workmentioning

confidence: 99%

Identification of rheumatoid arthritis using bone image features with radial basis function neural networks

Bose,

Srinivasan,

Surenderanath

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Rheumatoid arthritis (RA) leads to the destruction, deformation, and loss of function and causes joint damages to 85% of patients. The detection of bone mineral density from traditional x‐ray images consumes more time and it is observer dependent which decreases the evaluation performance when RA is in its early stage. Therefore, it is necessary to develop an observer‐independent computer‐aided automatic analysis system for evaluating JS narrowing. An efficient RA detection system based on feed‐forward neural network is proposed in this article. Initially the dataset is preprocessed to remove blur, redundant data and nonlinearities in RA images using wiener filter in less computation time. The edge boundaries are detected using nonlinear partial differential equation as the texture features of bones has great impact on the system accuracy. The detection strategy is implemented by optimized gray‐level co‐occurrence matrix based on bone image features. The selected features are optimized by genetic algorithm to improve the classification performance. The images are then classified as inflamed and noninflamed by radial basis function neural network. The effectiveness of the proposed classification approach is verified in terms of accuracy, sensitivity, and specificity and compared with the conventional convolutional neural network, artificial neural network, and support vector machine classifiers. Among the several existing techniques, our method found to be much effective with a maximum accuracy of 98.5% as some novel approaches are proposed and also tends to possess more compatible than the present system. Our computerized rheumatoid arteries detection approach will give more precise and flawless consistency rate.

show abstract

“…A study found that building accurate models to forecast complex disease outcomes using electronic health record data is possible [15]. More recently, convolutional neural networks have become the dominant method for medical image classification [16,17], medical image segmentation [18]. An efficient CNN architecture (GRNN) achieves high accuracy for hand X-ray classification [19].…”

Section: Our Contributions To Wrist-joint X-ray Image Detectionmentioning

confidence: 99%

"Automated Computer Vision Technology Algorithm for Wrist Joint Detection for Rheumatoid Arthritis"

Hargreaves

2023

BJSTR

View full text Add to dashboard Cite

The application of artificial intelligence (AI), including Deep Learning (DL) algorithms, is an emerging ground in the healthcare industry. Rheumatoid arthritis (RA) is a disease that is at the forefront of digital healthcare. The traditional manual approach is time consuming, tedious, and highly subjective. Multiple research paper has demonstrated promising results for the classification of rheumatoid arthritis using the fingers and toes, but little research has shown progress at classifying rheumatoid arthritis using the wrist X-Ray images. The objective of this paper is to develop an algorithm for automatically detecting the wrist joints of rheumatoid arthritis patients using X-Ray images and computer vision technology. In this study, >95% accuracy is obtained for the wrist joint detection. This paper serves as a proof of concept for wrist joint identification. Our initial experiments in wrist joint detection have shown significant improvements to this area of research, bringing automatic wrist joint detection closer than ever before towards a clinical support system. Our automated algorithm also provides the foundation for the classification of RA using wrist joint X-Ray images.

show abstract

An Efficient CNN for Hand X-Ray Classification of Rheumatoid Arthritis

Cited by 14 publications

References 33 publications

Dorsal Finger Fold Recognition by Convolutional Neural Networks for the Detection and Monitoring of Joint Swelling in Patients with Rheumatoid Arthritis

Dorsal Finger Fold Recognition by Convolutional Neural Networks for the Detection and Monitoring of Joint Swelling in Patients with Rheumatoid Arthritis

Identification of rheumatoid arthritis using bone image features with radial basis function neural networks

"Automated Computer Vision Technology Algorithm for Wrist Joint Detection for Rheumatoid Arthritis"

Contact Info

Product

Resources

About