A deep learning classification of metacarpophalangeal joints synovial proliferation in rheumatoid arthritis by ultrasound images

Objective To evaluate if an automatic classification of rheumatoid arthritis (RA) metacarpophalangeal joint conditions in ultrasound images is feasible by deep learning (DL) method, to provide a more objective, automated, and fast way of RA diagnosis in clinical setting. Materials and Methods DenseNet-based DL model was used and both training and testing are implemented in TensorFlow 1.13.1 with Keras DL libraries. The area under curve (AUC), accuracy, sensitivity, and specificity values with 95% CIs were reported. The statistical analysis was performed by using scikit-learn libraries in Python 3.7. Results A total of 1337 RA ultrasound images were acquired from 208 patients, the number of images is 313, 657, 178, and 189 in OESS Grade L0, L1, L2, and L3, respectively. In Classification Scenario 1 SP-no versus SP-yes, three experiments with region of interest of size 192 x 448 (Group 1), 96 x 224 (Group 2), and 96 x 224 stacked with pre-segmented annotated mask of SP area (Group 3) as input achieve an AUC of 0.863 (95% CI: 0.809, 0.917), 0.861 (95% CI: 0.805, 0.916), and 0.886 (95% CI: 0.836, 0.936), respectively. In Classification Scenario 2 Healthy versus Diseased, experiments in Group 1, Group 2 and Group 3 achieve an AUC of 0.848 (95% CI: 0.799, 0.896), 0.864 (95% CI: 0.819, 0.909), and 0.916 (95% CI: 0.883, 0.952), respectively. Conclusion We combined DenseNet model with ultrasound images for RA condition assessment. The feasibility of using DL to create an automatic RA condition classification system was also demonstrated. The proposed method can be an alternative to the initial screening of RA patients.

Automated summary

The objective of this study was to evaluate the feasibility of using a deep learning method to automatically classify metacarpophalangeal joint conditions in rheumatoid arthritis (RA) ultrasound images, providing a more objective, automated, and fast way of diagnosing RA in clinical settings. The results demonstrated that combining the DenseNet model with ultrasound images achieved effective assessment of RA conditions and demonstrated the potential of creating an automatic RA condition classification system.