Related Experiment Video
Updated: Jun 20, 2025
Author Spotlight: Insights into Visual Cortex Research Through Wide-View fMRI Mapping
Published on: December 8, 2023
Deep learning methods for diagnosis of graves' ophthalmopathy using magnetic resonance imaging
Zi-Chang Ma1, Jun-Yu Lin1, Shao-Kang Li2
1Department of Radiology, The Fifth Affiliated Hospital, Sun Yat-Sen University, Zhuhai, China.
Background:
The effect of diagnosing Graves' ophthalmopathy (GO) through traditional measurement and observation in medical imaging is not ideal. This study aimed to develop and validate deep learning (DL) models that could be applied to the diagnosis of GO based on magnetic resonance imaging (MRI) and compare them to traditional measurement and judgment of radiologists.
Methods:
A total of 199 clinically verified consecutive GO patients and 145 normal controls undergoing MRI were retrospectively recruited, of whom 240 were randomly assigned to the training group and 104 to the validation group. Areas of superior, inferior, medial, and lateral rectus muscles and all rectus muscles on coronal planes were calculated respectively. Logistic regression models based on areas of extraocular muscles were built to diagnose GO. The DL models named ResNet101 and Swin Transformer with T1-weighted MRI without contrast as input were used to diagnose GO and the results were compared to the radiologist's diagnosis only relying on MRI T1-weighted scans.
Results:
Areas on the coronal plane of each muscle in the GO group were significantly greater than those in the normal group. In the validation group, the areas under the curve (AUCs) of logistic regression models by superior, inferior, medial, and lateral rectus muscles and all muscles were 0.897 [95% confidence interval (CI): 0.833-0.949], 0.705 (95% CI: 0.598-0.804), 0.799 (95% CI: 0.712-0.876), 0.681 (95% CI: 0.567-0.776), and 0.905 (95% CI: 0.843-0.955). ResNet101 and Swin Transformer achieved AUCs of 0.986 (95% CI: 0.977-0.994) and 0.936 (95% CI: 0.912-0.957), respectively. The accuracy, sensitivity, and specificity of ResNet101 were 0.933, 0.979, and 0.869, respectively. The accuracy, sensitivity, and specificity of Swin Transformer were 0.851, 0.817, and 0.898, respectively. The ResNet101 model yielded higher AUC than models of all muscles and radiologists (0.986 vs. 0.905, 0.818; P<0.001).
Conclusions:
The DL models based on MRI T1-weighted scans could accurately diagnose GO, and the application of DL systems in MRI may improve radiologists' performance in diagnosing GO and early detection.
