• Corpus ID: 239016496

Rheumatoid Arthritis: Automated Scoring of Radiographic Joint Damage

  title={Rheumatoid Arthritis: Automated Scoring of Radiographic Joint Damage},
  author={Yan Ming Tan and Raphael Quek Hao Chong and Carol Anne Hargreaves},
Rheumatoid arthritis is an autoimmune disease that causes joint damage due to inflammation in the soft tissue lining the joints known as the synovium. It is vital to identify joint damage as soon as possible to provide necessary treatment early and prevent further damage to the bone structures. Radiographs are often used to assess the extent of the joint damage. Currently, the scoring of joint damage from the radiograph takes expertise, effort, and time. Joint damage associated with rheumatoid… 

Figures and Tables from this paper


Bone erosion scoring for rheumatoid arthritis with deep convolutional neural networks
It is demonstrated that deep convolutional neural networks can be leveraged for a fully automated, fast, and reproducible scoring of X-ray images of patients with rheumatoid arthritis.
Automatic joint detection in rheumatoid arthritis hand radiographs
This paper focuses on both joint location and joint margin detection in hand x-ray images of patients suffering from Rheumatoid Arthritis and uses five hand radiographs from RA patients, in which the joints have been manually delineated.
Radiographic progression on radiographs of hands and feet during the first 3 years of rheumatoid arthritis measured according to Sharp's method (van der Heijde modification).
It was found that 70% of the patients showed radiographic damage after 3 years and this group could already be selected after 1 year, indicating a flattening of the curve of radiographic progression.
Hand Radiograph Analysis and Joint Space Location Improvement for Image Interpretation
An improvement of a method used to quantify the minimal JSW in hand radiographs, proposed by the author in his previous works, is considered and has an impact on initial pre-processing and joint space location.
Radiographic severity of Rheumatoid Arthritis in African Americans: Results from a multicenter observational study
To describe radiographic changes in African Americans with rheumatoid arthritis (RA) from the Consortium for the Longitudinal Evaluations of African Americans with Early Rheumatoid Arthritis (CLEAR)
A Lightweight U-Net Architecture Multi-Scale Convolutional Network for Pediatric Hand Bone Segmentation in X-Ray Image
This study proposes a lightweight U-Net architecture multi-scale convolutional network for pediatric hand bone segmentation in the X-ray image and results indicate promising performance in hand bones segmenting, especially for small bones of the hand.
Dense Genotyping of Immune-Related Regions Identifies Loci for Rheumatoid Arthritis Risk and Damage in African Americans
The dense genotyping of the iChip array and the unique LD structure of African Americans are used to validate known risk loci for RA susceptibility and radiographic severity, and to better characterize the associations of AFF3, ETS1 and IL2RA.
Deep learning with convolutional neural network in radiology
Basic technical knowledge regarding deep learning with CNNs along the actual course is illustrated (collecting data, implementing CNNs, and training and testing phases).
X-Ray Chest Image Classification by A Small-Sized Convolutional Neural Network
  • Ege Kesim, Z. Dokur, T. Olmez
  • Computer Science
    2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT)
  • 2019
New network structures and the size of the input image are investigated and it is observed that chest images are assigned to twelve classes with approximately 86% success rate by using the proposed network, and the training is carried out in a short time due to the small network structure.
Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification
A powerful network architecture in detail, which considers transfer learning with and without fine-tuning as well as the training of a dedicated X-ray network from scratch is investigated: the ResNet-50.