Related Experiment Video
Updated: Jun 25, 2026
07:15
In vivo Macrophage Imaging Using MR Targeted Contrast Agent for Longitudinal Evaluation of Septic Arthritis
Published on: October 20, 2013
9.3K
Artificial Intelligence Quantification of Enhanced Synovium Throughout the Entire Hand in Rheumatoid Arthritis on
Yijun Mao1, Kiko Imahori1, Wanxuan Fang1
1Graduate School of Health Sciences, Hokkaido University, Sapporo, Hokkaido, Japan.
Journal of Magnetic Resonance Imaging : JMRI
|May 29, 2024
Summary
An artificial intelligence (AI) model effectively quantifies inflammation in rheumatoid arthritis (RA) using dynamic contrast-enhanced MRI. Optimal results require at least 15 phases, reducing scan time while accurately assessing disease activity.
Area of Science:
- Radiology
- Artificial Intelligence
- Medical Imaging
Background:
- Challenges exist in automatically and efficiently quantifying inflammation in rheumatoid arthritis (RA) patients using dynamic contrast-enhanced (DCE) MRI.
- Current methods may lack the precision and speed required for effective disease monitoring.
Purpose of the Study:
- To develop and validate an automated artificial intelligence (AI) approach for quantifying RA disease activity in the whole hand.
- To optimize the dynamic MRI protocol, specifically the number of phases, to exclude arterial pixels and improve quantification accuracy.
Main Methods:
- A retrospective study utilizing DCE-MRI data from 35 RA patients.
- An AI model was trained using DCE-MRI with 27 phases and tested on images with varying numbers of phases.
- Performance was evaluated using metrics such as Area Under the Curve (AUC), Dice score, and Spearman's rank correlation coefficient, comparing AI segmentation to manual outlining and RAMRIS scores.
Main Results:
- A minimum of 15 MRI phases (approximately 2.5 minutes acquisition time) was determined to be necessary for optimal performance.
- The AI model demonstrated high accuracy, with AUC ranging from 0.941 to 0.965.
- Strong correlations were observed between AI segmentation and ground truth (Spearman's coefficients 0.884-0.927 for joint ROIs, 0.736-0.831 for whole hands).
Conclusions:
- The developed AI-based classification model accurately identifies synovitis pixels while effectively excluding arterial signals.
- An optimized protocol with at least 15 phases enables quantitative assessment of RA inflammatory activity with minimized acquisition time.
- This AI approach offers a promising solution for efficient and accurate disease monitoring in rheumatoid arthritis.
Related Concept Videos
01:11Genome-wide Association Studies-GWAS
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
01:07Development of the Limb Synovial Joints
Joints form during embryonic development in conjunction with the formation and growth of the associated bones. The embryonic tissue that gives rise to all bones, cartilage, and connective tissues of the body is called mesenchyme.
The mesenchymal stem cells differentiate into chondrocytes that form the hyaline cartilage, and later the cartilaginous model of the bone. This model further transforms into a bone. This process is known as endochondral ossification.
During development, the limbs...
The mesenchymal stem cells differentiate into chondrocytes that form the hyaline cartilage, and later the cartilaginous model of the bone. This model further transforms into a bone. This process is known as endochondral ossification.
During development, the limbs...