![[2602.14365] Image-based Joint-level Detection for Inflammation in Rheumatoid Arthritis from Small and Imbalanced Data](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.14365] Image-based Joint-level Detection for Inflammation in Rheumatoid Arthritis from Small and Imbalanced Data
Summary
This paper presents a novel framework for detecting joint inflammation in rheumatoid arthritis using RGB images, addressing challenges like data imbalance and sample scarcity.
Why It Matters
Early detection of rheumatoid arthritis is crucial for effective management and prevention of irreversible damage. This research proposes a practical solution for at-home monitoring, potentially improving patient outcomes and accessibility to care.
Key Takeaways
- The study highlights the challenges of detecting joint inflammation in rheumatoid arthritis from RGB images.
- A dedicated dataset was constructed to demonstrate the difficulty of visual detection in this context.
- The proposed framework incorporates self-supervised pretraining and imbalance-aware training techniques.
- Results showed significant improvements in detection metrics, indicating the framework's effectiveness.
- This approach could facilitate easier at-home monitoring for patients with rheumatoid arthritis.
Computer Science > Computer Vision and Pattern Recognition arXiv:2602.14365 (cs) [Submitted on 16 Feb 2026] Title:Image-based Joint-level Detection for Inflammation in Rheumatoid Arthritis from Small and Imbalanced Data Authors:Shun Kato (Keio University, Japan), Yasushi Kondo (Keio University, Japan), Shuntaro Saito (Keio University, Japan), Yoshimitsu Aoki (Keio University, Japan), Mariko Isogawa (Keio University, Japan) View a PDF of the paper titled Image-based Joint-level Detection for Inflammation in Rheumatoid Arthritis from Small and Imbalanced Data, by Shun Kato (Keio University and 9 other authors View PDF HTML (experimental) Abstract:Rheumatoid arthritis (RA) is an autoimmune disease characterized by systemic joint inflammation. Early diagnosis and tight follow-up are essential to the management of RA, as ongoing inflammation can cause irreversible joint damage. The detection of arthritis is important for diagnosis and assessment of disease activity; however, it often takes a long time for patients to receive appropriate specialist care. Therefore, there is a strong need to develop systems that can detect joint inflammation easily using RGB images captured at home. Consequently, we tackle the task of RA inflammation detection from RGB hand images. This task is highly challenging due to general issues in medical imaging, such as the scarcity of positive samples, data imbalance, and the inherent difficulty of the task itself. However, to the best of our knowledge,...