Background Rheumatoid arthritis (RA) is a chronic inflammatory disease associated with significant functional impairment and disability, linked to inflammatory and structural articular and peri-articular damage [1]. Synovitis is a characteristic feature of RA, and is considered an important factor in disease activity and the best predictive marker of joint damage [2]. Therefore, accurate quantification of synovitis can play an important role in clinical evaluation and treatment serving as a biomarker. Pixel-by-pixel time–intensity curve (TIC) shape analysis is a dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique to help visualize differently shaped TICs [3]. Pixels having TIC shape type 4, which is characterized as early enhancement followed by washout phase, were regarded as synovitis pixel [4]. A deep residual network called ResNet-50 model, a convolutional neural network (CNN) that is 50 layers deep, might effectively classify TIC shapes.

Objectives This study aimed to develop software that can automatically demonstrate the distribution of enhancing synovial pannus of patients with inflammatory arthritis on DCE-MRI.

Methods Modified ResNet-50 was used on MATLAB. Two investigators drew regions of interest (ROIs) of muscle, bone, and synovitis under expert guidance and obtained TICs for each tissue on DCE-MRI of ten rheumatoid patients. Through cross-validation and batch evaluation, we verified the confusion matrices for the performance of the classifier. Then we identified the pixels of enhancing synovial pannus by image classification from the obtained pixel-by-pixel TIC shape and displayed them in color. The software performance was evaluated using a visual assessment on seven hand joints of one patient.

Results 150 ROIs for muscles, 150 ROIs for bones, and 59 ROIs for synovitis on DCE-MRI of the hand joints were drawn in ten patients and obtained 4049, 3825, and 1041 TIC shape images, respectively. The classifier’s accuracy, precision, sensitivity, and specificity were 99.6%, 99.3%, 98.4%, and 99.7%, respectively. Out of seven joints, four were assessed as good, two as fair, and one as fail.

• Download figure
• Open in new tab
• Download powerpoint

Figure 1.

Software performance on contrast enhanced dynamic MRI of the wrist

Conclusion Our classifier showed high accuracy, precision, sensitivity, and specificity. And through the comparison between manual outlining and the result of software, our software had relatively good performance. This automatic software developed using deep learning with CNN might accurately display the enhancing synovial pannus in RA.

References [1]Micu MC, Fodor D. Concepts in monitoring the treatment in rheumatoid arthritis- the role of musculoskeletal ultrasound. Part I: synovitis. Med Ultrason. 2015;17(3):367-76.

[2]Carotti M, Galeazzi V, Catucci F, Zappia M, Arrigoni F, Barile A, et al. Clinical utility of eco-color-power Doppler ultrasonography and contrast enhanced magnetic resonance imaging for interpretation and quantification of joint synovitis: a review. Acta Biomed. 2018;89(1-s):48-77.

[3]Sakashita T, Kamishima T, Kobayashi Y, Sugimori H, Tang M, Sutherland K, et al. Accurate quantitative assessment of synovitis in rheumatoid arthritis using pixel-by-pixel, time-intensity curve shape analysis. Br J Radiol. 2016;89(1061):20151000.

[4]Kobayashi Y, Kamishima T, Sugimori H, Ichikawa S, Noguchi A, Kono M, et al. Quantification of hand synovitis in rheumatoid arthritis: Arterial mask subtraction reinforced with mutual information can improve accuracy of pixel-by-pixel time-intensity curve shape analysis in dynamic MRI. J Magn Reson Imaging. 2018.

Disclosure of Interests None declared