T2‐Weighted MR Imaging‐Derived Radiomics for Pretreatment Determination of Therapeutic Response to Glucocorticoid in Patients With Thyroid‐Associated Ophthalmopathy: Comparison With Semiquantitative Evaluation

Background MR imaging has been applied to determine therapeutic response to glucocorticoid (GC) before treatment in thyroid‐associated ophthalmopathy (TAO), while the performance was still poor. Purpose To investigate the value of T 2 ‐weighted imaging (T 2 WI)‐derived radiomics for pretreatment determination of therapeutic response to GC in TAO patients, and compare its diagnostic performance with that of semiquantitative parameters. Study Type Retrospective. Population A total of 110 patients (49 ± 12 years; male/female, n = 48/62; responsive/unresponsive, n = 62/48), divided into training (n = 78) and validation (n = 32) cohorts. Field Strength/Sequence 3.0 T, T 2 ‐weighted fast spin echo. Assessment W.C. and H.H. (6 and 10 years of experience, respectively) performed the measurements. Maximum, mean, and minimum signal intensity ratios (SIRs) of extraocular muscle (EOM) bellies were collected to construct a semiquantitative imaging model. Radiomics features from volumes of interest covering EOM bellies were extracted and three machine learning‐based (logistic regression [LR]; decision tree [DT]; support vector machine [SVM]) models were built. Statistical Tests The diagnostic performances of models were evaluated using receiver operating characteristic curve analyses, and compared using DeLong test. Two‐sided P < 0.05 was considered statistically significant. Results The responsive group showed higher minimum signal intensity ratio (SIR min ) of EOMs than the unresponsive group (training: 1.46 ± 0.34 vs. 1.18 ± 0.39; validation: 1.44 ± 0.33 vs. 1.19 ± 0.20). In both cohorts, LR‐based radiomics model demonstrated good diagnostic performance (area under the curve [AUC] = 0.968, 0.916), followed by DT‐based (AUC = 0.933, 0.857) and SVM‐based models (AUC = 0.919, 0.855). All three radiomics models outperformed semiquantitative imaging model (SIR min : AUC = 0.805) in training cohort. In validation cohort, only LR‐based radiomics model outperformed that of SIR min (AUC = 0.745). The nomogram integrating LR‐based radiomics signature and disease duration further elevated the diagnostic performance in validation cohort (AUC: 0.952 vs. 0.916, P = 0.063). Data Conclusion T 2 WI‐derived radiomics of EOMs, together with disease duration, provides a promising noninvasive approach for determining therapeutic response before GC administration in TAO patients. Level of Evidence 3 Technical Efficacy Stage 4