Receiver operating characteristic analysis using a novel combined thermal and ultrasound imaging for assessment of disease activity in rheumatoid arthritis

Thermography at the Elbow Among Patients with Rheumatoid Arthritis: A Comparison with Ultrasound-Detected Joint Inflammation Findings

INTRODUCTION

There is a lack of data on the use of thermography for elbow joint inflammation assessment among patients with rheumatoid arthritis (RA). Hence, we aimed to compare thermography with ultrasonography (a more established imaging modality for joint inflammation assessment) in the assessment of inflammation in the elbows of patients with RA.

METHODS

Standardised minimum (Tmin), maximum (Tmax) and average (Tavg) temperatures at each elbow (medial, lateral, posterior and anterior aspects) were summed to obtain the thermographic parameters MIN, MAX and AVG, respectively. Ultrasound parameters of elbow joint inflammation included total greyscale (TGS) and total power Doppler (TPD) scores. Pearson's correlation coefficient was utilized for correlation analysis between parameters. The relationship between parameters was characterized using simple linear regression.

RESULTS

Sixty elbows were evaluated from 30 patients with RA in this cross-sectional study. Thermographic parameters (MIN, MAX and AVG) showed significant correlation (P < 0.05) with (1) TPD scores at both elbows (correlation coefficient ranging 0.40 to 0.55) and (2) TGS scores at the right elbow (correlation coefficient ranging 0.39 to 0.42). A statistically significant relationship (P values ranging from 0.002 to 0.033) between parameters was demonstrable as follows: (1) MIN, MAX and AVG versus TPD scores (bilateral elbows) and (2) MIN, MAX and AVG versus TGS scores (right elbow).

CONCLUSION

Thermographic temperatures have been demonstrated to correlate with ultrasound-detected joint inflammation at the elbow in patients with RA. The association is more consistently observed with ultrasound PD joint inflammation than its GS counterpart.

RANet: a custom CNN model and quanvolutional neural network for the automated detection of rheumatoid arthritis in hand thermal images

Rheumatoid arthritis is an autoimmune disease which affects the small joints. Early prediction of RA is necessary for the treatment and management of the disease. The current work presents a deep learning and quantum computing-based automated diagnostic approach for RA in hand thermal imaging. The study's goals are (i) to develop a custom RANet model and compare its performance with the pretrained models and quanvolutional neural network (QNN) to distinguish between the healthy subjects and RA patients, (ii) To validate the performance of the custom model using feature selection method and classification using machine learning (ML) classifiers. The present study developed a custom RANet model and employed pre-trained models such as ResNet101V2, InceptionResNetV2, and DenseNet201 to classify the RA patients and normal subjects. The deep features extracted from the RA Net model are fed into the ML classifiers after the feature selection process. The RANet model, RA Net+ SVM, and QNN model produced an accuracy of 95%, 97% and 93.33% respectively in the classification of healthy groups and RA patients. The developed RANet and QNN models based on thermal imaging could be employed as an accurate automated diagnostic tool to differentiate between the RA and control groups.