Rheumatoid Arthritis: Automated Scoring of Radiographic Joint Damage

Rheumatoid arthritis is an autoimmune disease that causes joint damage due to inflammation in the soft tissue lining joints known as synovium. It vital identify soon possible provide necessary treatment early and prevent further bone structures. Radiographs are often used assess extent of damage. Currently, scoring from radiograph takes expertise, effort, time. Joint associated with rheumatoid also not quantitated clinical practice subjective descriptors used. In this work, a description pipeline deep learning models automatically score arthritic radiographic image provided. An automatic tool was built produce scores extremely high balanced accuracy within couple minutes utilizing would remove subjectivity between human reviewers. Using segmentation approach training prediction ordinal class encoding, under-sampling, transfer learning, wised ±1 accuracies ranging 91.51% 97.30% were achieved. The 4 showed great potential achieving industry-standard reliability.