Image-based Joint-level Detection for Inflammation in Rheumatoid Arthritis from Small and Imbalanced Data

2026-02-16

AI Summary

This study addresses the challenge of timely professional assessment for rheumatoid arthritis (RA) patients amid constrained healthcare resources by proposing a home-based joint inflammation detection method using RGB hand images. To tackle key obstacles in medical imaging—namely extreme class imbalance, scarcity of positive samples, and subtle visual manifestations—the authors construct the first dedicated dataset to quantify the difficulty of inflammation detection and introduce a novel global–local joint encoder framework. This framework leverages self-supervised pretraining on large-scale healthy hand images and incorporates an imbalance-aware training strategy. Experimental results demonstrate that the proposed approach significantly outperforms baseline models under few-shot and highly imbalanced conditions, achieving a 0.2 improvement in F1-score and a 0.25 gain in G-mean, thereby offering the first effective solution to data scarcity and imbalance in RA inflammation detection from RGB images.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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, no existing work has explicitly addressed these challenges in RGB-based RA inflammation detection. This paper quantitatively demonstrates the difficulty of visually detecting inflammation by constructing a dedicated dataset, and we propose a inflammation detection framework with global local encoder that combines self-supervised pretraining on large-scale healthy hand images with imbalance-aware training to detect RA-related joint inflammation from RGB hand images. Our experiments demonstrated that the proposed approach improves F1-score by 0.2 points and Gmean by 0.25 points compared with the baseline model.

Problem

• rheumatoid arthritis
• joint inflammation detection
• small data
• imbalanced data
• RGB image

Innovation

• self-supervised pretraining
• imbalanced data
• joint-level inflammation detection
• global-local encoder
• RGB-based RA diagnosis