ABSTRACT
Background and Aims: Joint pain is the main symptom of acute attacks in patients with gout, which if not managed properly, can develop into chronic gout. The aim of this study was to investigate the correlation between ultrasound (US) features of gouty arthritis (GA) and its clinical manifestations to provide a basis for diagnosing and evaluating the disease. Methods: We retrospectively analyzed 182 sites in 139 patients with GA diagnosed by the Rheumatology and Immunology Department. Degree of pain was evaluated using the visual analog scale (VAS). Patients with GA were divided into active and inactive arthritis groups. Statistical differences between the two groups and the correlation between US features and clinical manifestations of the affected joints in patients with GA were analyzed. Results: The groups had statistical significance in joint effusion, power Doppler ultrasonography (PDS), double contour sign, and bone erosion (p = 0.02, 0.001, 0.04, 0.04, respectively). Correlation analysis in this study showed that joint effusion and PDS were positively correlated with degree of pain (r s = 0.275, 0.269; p < 0.001, <0.001, respectively). Additionally, PDS was positively correlated with synovitis, joint effusion, bone erosion, and aggregates (r s = 0.271, 0.281, 0.222, 0.281; p < 0.001, <0.001, 0.003, <0.001, respectively). Conclusions: Pathological US features, such as joint effusion, synovitis, PDS and bone erosion were more likely to be detected in GA with clinical signs and symptoms. PDS was positively correlated with joint effusion and synovitis, pain was closely related to PDS and joint effusion, which suggested that the clinical symptoms of GA were related to inflammation, reflecting the patient's condition to some extent. Therefore, musculoskeletal US is a useful clinical tool for managing patients with GA and can provide a reliable reference for diagnosing and treating GA.
ABSTRACT
OBJECTIVES: Accurate detection of carotid plaque using ultrasound (US) is essential for preventing stroke. However, the diagnostic performance of junior radiologists (with approximately 1 year of experience in carotid US evaluation) is relatively poor. We thus aim to develop a deep learning (DL) model based on US videos to improve junior radiologists' performance in plaque detection. METHODS: This multicenter prospective study was conducted at five hospitals. CaroNet-Dynamic automatically detected carotid plaque from carotid transverse US videos allowing clinical detection. Model performance was evaluated using expert annotations (with more than 10 years of experience in carotid US evaluation) as the ground truth. Model robustness was investigated on different plaque characteristics and US scanning systems. Furthermore, its clinical applicability was evaluated by comparing the junior radiologists' diagnoses with and without DL-model assistance. RESULTS: A total of 1647 videos from 825 patients were evaluated. The DL model yielded high performance with sensitivities of 87.03% and 94.17%, specificities of 82.07% and 74.04%, and areas under the receiver operating characteristic curve of 0.845 and 0.841 on the internal and multicenter external test sets, respectively. Moreover, no significant difference in performance was noted among different plaque characteristics and scanning systems. Using the DL model, the performance of the junior radiologists improved significantly, especially in terms of sensitivity (largest increase from 46.3 to 94.44%). CONCLUSIONS: The DL model based on US videos corresponding to real examinations showed robust performance for plaque detection and significantly improved the diagnostic performance of junior radiologists. KEY POINTS: ⢠The deep learning model based on US videos conforming to real examinations showed robust performance for plaque detection. ⢠Computer-aided diagnosis can significantly improve the diagnostic performance of junior radiologists in clinical practice.
