Magnetic resonance imaging (MRI) is an important non-invasive examination in the early diagnosis of juvenile dermatomyositis (JDM). We aimed to evaluate the feasibility of radiomics to establish a quantitative analysis of MRI images. Radiomics and machine learning were used to retrospectively analyze MRI T2 fat suppression sequences and relevant clinical data. The model associated with radiomics features was established using a cohort of patients who underwent thigh MRI at the children's hospital from June 2014 to September 2021. In total, 75 patients with JDM and 75 control children were included in the training cohort (n = 102) and validation cohort (n = 48). The independent factors including lower muscle strength (OR, 0.75; 95% CI, 0.59-0.90), higher creatine kinase (CK) level (OR, 1.65; 95% CI, 1.20-2.38), and higher radiomics score (OR, 2.30; 95% CI, 1.63-3.62) were associated with a clinical diagnosis of JDM. The combined model achieved good discrimination performance compared the radiomics score model under linear discriminant analyses in the training cohort (AUC, 0.949; 95% CI, 0.912-0.986 vs. AUC, 0.912; 95% CI, 0.858-0.967; p = 0.02) and in the validation cohort (AUC, 0.945; 95% CI, 0.878-1 vs. AUC, 0.905; 95% CI, 0.812-0.998; p = 0.03). The combined model showed the diagnostic value was not weaker than the biopsy (AUC, 0.950; 95% CI, 0.919-0.981, n = 150 vs. AUC, 0.952; 95% CI, 0.889-1, n = 72; p = 0.95) and electromyogram (EMG) (AUC, 0.950; 95% CI, 0.919-0.981 vs. AUC, 0.900; 95% CI, 0.852-0.948; p = 0.10) among all the patients. The combination of radiomics features extracted from the MRI and non-invasive clinical characteristics obtained a pronounced discriminative performance to assist in discriminating JDM.
Keywords: MRI; diagnosis; juvenile dermatomyositis; nomogram; radiomics.