Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shun Kato, Yasushi Kondo, Shuntaro Saito, Yoshimitsu Aoki, Mariko Isogawa

TL;DR

This paper quantitatively demonstrates the difficulty of visually detecting inflammation by constructing a dedicated dataset, and proposes 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.

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.

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

TL;DR

This paper quantitatively demonstrates the difficulty of visually detecting inflammation by constructing a dedicated dataset, and proposes 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.

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.
Paper Structure (16 sections, 1 equation, 3 figures, 4 tables)

This paper contains 16 sections, 1 equation, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Detection for joint RA inflammation
  4. Machine Learning Methods for Small/Imbalanced Datasets
  5. Proposed Method
  6. Overview of the Proposed Framework
  7. Network Architecture
  8. Two-Stage Training Strategy
  9. Self-Supervised Pre-training
  10. Fine-tuning with Focal Loss
  11. Experiments
  12. Dataset
  13. Evaluation Metrics
  14. Implementation Details
  15. Experiments and Results
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Overview of the proposed framework. Joint regions are cropped from the input hand image and fed into the Local Encoder, while the whole hand image is input to the Global Encoder. The model estimates the presence of inflammation at the joint level by integrating global features from the whole hand with local features from the joints.
  • Figure 2: Number of positive cases at each finger joint. A 14-joint hand skeleton based on MCP/PIP/DIP joints.
  • Figure 3: Distributions of sex and age in the dataset. Blue line represents the mean value.