Screening, Classification, and Outcome Prediction Ensemble Using Orbital MRI for Thyroid Eye Disease: The TED SCOPE National Multicenter Registry Study (TED-SCOPE-MR)

Construction and Optimization of a Multimodal Orbital MRI-AI Model and Its Application in Thyroid Eye Disease: A National Multicenter Registry Study

The goal of this observational study is to prospectively validate the efficacy of an AI multimodal model constructed based on multi - sequence orbital MRI in the diagnosis, activity and severity assessment, and prognosis prediction of thyroid - associated ophthalmopathy (TAO) in real - world clinical scenarios. The main questions it aims to answer are:

Can AI models accurately assess the presence, activity, and severity of Thyroid-Associated Orbitopathy (TAO)? Can AI models predict the prognosis of TAO? Researchers will compare the diagnostic accuracy of the AI model for TAO patients and healthy subjects to evaluate its diagnostic performance.

Participants will undergo a standardized, study - specific multimodal orbital MRI scan (sequences include T1WI, T2WI, STIR, and research sequences such as Magic, IDEAL - IQ, DWI, ASL, CEST). And will systematically acquire ocular ultrasound images from TED patients (active and inactive stages), non-TED ophthalmic disease controls, and healthy volunteers. AI-driven deep learning techniques (convolutional neural networks) will be applied to achieve automatic segmentation of key structures (extraocular muscles, optic nerve, lacrimal gland, and retrobulbar soft tissue). High-throughput radiomic features encompassing morphological parameters and gray-level texture patterns will be extracted. Machine learning algorithms will then be employed to construct objective prediction models for TED screening and activity staging, with MRI findings and CAS scores serving as the reference standards for external validation.

Study Overview

• Status: Recruiting
• Conditions: Graves Ophthalmopathy; Graves Disease; Thyroid Associated Ophthalmopathies
• Intervention / Treatment: Diagnostic test: MRI scan，ocular ultrasound

• Study Type: Observational
• Enrollment (Estimated): 1200

Contacts and Locations

• Study Contact: Name: Tuo Li, Vice Professor; Phone Number: +86-13918507887; Email: zoe_leeto@hotmail.com

Study Locations

• China
  • Huangpu District
    • Shanghai, Huangpu District, China, 200003
      • Recruiting
      • Shanghai Changzheng Hospital
      • Principal Investigator: Tuo Li, MD
      • Principal Investigator: Yongquan Shi, MD
      • Contact: Tuo Li, MD; Phone Number: +86-13918507887; Email: zoe_leeto@hotmail.com
      • Contact: Wei-yi Zhou, MD; Phone Number: +86-18689756502; Email: weiyizhou@smmu.edu.cn
      • Sub-Investigator: Jian Zhou, MD
      • Sub-Investigator: Weiyi Zhou, MD
      • Sub-Investigator: Jingmin Feng, MD
      • Sub-Investigator: Xiaoyun Feng, MD
      • Sub-Investigator: Lianqun Wu, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Before initiating the corresponding procedures for the study, all subjects must personally sign the informed consent form approved by the Independent Ethics Committee (IEC)/Institutional Review Board (IRB) and indicate the date.

Description

Inclusion Criteria:

• TAO patient group

  • Age between 18 and 75 years old, regardless of gender.

    • Patients with thyroid eye disease who meet the disease staging and grading criteria specified in diagnostic guidelines such as those of Bartley, CAS, and EUGOGO.

      • The patient has planned or received thyroid-related treatment, and the condition is relatively stable.

        • Voluntarily participate in this study and sign the informed consent form.

Control group:

① Healthy volunteers matched with the TAO group in terms of age and gender.

② Voluntarily participate in this study and sign the informed consent form.

Exclusion Criteria:

• TAO patient group:

  • Pregnant or lactating women.

    • Patients with other orbital lesions.

      ③ Having contraindications for MRI examination (such as non - compatible metal implants in the body, claustrophobia, etc.).

      ④ The patient has previously received orbital radiotherapy or orbital surgery (except for patients who need to collect tissue specimens).

      ⑤ Comorbid with other severe systemic diseases (such as uncontrolled heart failure, liver and kidney failure) or mental illnesses, and unable to cooperate to complete the study.

      ⑥ Participated in other clinical trials that may interfere with the results of this study within 3 months.

Control group:

Same as the exclusion criteria 1 - 6 for the TAO patient group

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
TAO; Participants with Thyroid Associated Ophthalmopathy	Diagnostic test: MRI scan，ocular ultrasound; Participants will undergo a standardized, study - specific multimodal orbital MRI scan (sequences include T1WI, T2WI, STIR, and research sequences such as Magic, IDEAL - IQ, DWI, ASL, CEST).
Normal; healthy individuals without thyroid-associated ophthalmopathy	Diagnostic test: MRI scan，ocular ultrasound; Participants will undergo a standardized, study - specific multimodal orbital MRI scan (sequences include T1WI, T2WI, STIR, and research sequences such as Magic, IDEAL - IQ, DWI, ASL, CEST).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy (AUC) of the AI model for TED	using comprehensive clinical diagnosis (Bartley criteria) as the gold standard.	From enrollment to the end of follow-up at 18 months
Classification accuracy of the AI model for distinguishing active versus inactive TED		From enrollment to the end of follow-up at 18 months
Classification accuracy of the AI model for distinguishing mild versus moderate to severe TED		From enrollment to the end of follow-up at 18 months

Secondary Outcome Measures

Outcome Measure	Time Frame
Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the AI model.	From enrollment to the end of follow-up at 18 months
Inter-observer agreement (Kappa coefficient) between the AI model and clinical experts.	From enrollment to the end of follow-up at 18 months
Correlation (Pearson/Spearman correlation) between imaging features and pathological indicators .	From enrollment to the end of follow-up at 18 months
Predictive performance of the AI model for treatment response, assessed by comparing baseline and follow-up ultrasound data.	From enrollment to the end of follow-up at 18 months

Collaborators and Investigators

• Sponsor: Shanghai Changzheng Hospital

Study record dates

Study Major Dates

• Study Start (Actual): January 1, 2026
• Primary Completion (Estimated): December 31, 2028
• Study Completion (Estimated): December 31, 2028

Study Registration Dates

• First Submitted: May 23, 2026
• First Submitted That Met QC Criteria: July 20, 2026
• First Posted (Actual): July 21, 2026

Study Record Updates

• Last Update Posted (Actual): July 21, 2026
• Last Update Submitted That Met QC Criteria: July 20, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: TED
• Additional Relevant MeSH Terms: Endocrine System Diseases; Genetic Diseases, Inborn; Autoimmune Diseases; Immune System Diseases; Eye Diseases; Eye Diseases, Hereditary; Exophthalmos; Orbital Diseases; Goiter; Hyperthyroidism; Thyroid Diseases; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Graves Ophthalmopathy; Graves Disease
• Other Study ID Numbers: TED-SCOPE-MR

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No