AI-based MRI and ultrasound for thyroid-related eye disease
Official title: Construction and Optimization of a Multimodal Orbital MRI-AI Model and Its Application in Thyroid Eye Disease: A National Multicenter Registry Study
Run by Shanghai Changzheng Hospital · NCT07716397 · Data updated 2026-11-12
This study tests an AI model using orbital MRI and eye ultrasound to help diagnose activity and severity of thyroid-associated ophthalmopathy and predict its course in adults.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 75 Years |
| Sex | All |
| Enrollment | 1200 (estimated) |
| Sponsor | Shanghai Changzheng Hospital Academic / other |
| Locations | 1 site (Shanghai, Huangpu District) |
| Status | Recruiting |
| Started | January 1, 2026 |
| Main results expected | December 31, 2028 |
| Study ends | December 31, 2028 |
| Registry record updated | July 21, 2026 |
| Trial ID | NCT07716397 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults aged 18 to 75 with thyroid-associated ophthalmopathy, at various stages, and healthy volunteers matched by age and gender.
✕Probably not a fit
Patients with contraindications to MRI, prior orbital surgery or radiotherapy (except some allowed cases), or other orbital lesions may not benefit from this approach.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a multicenter observational study that prospectively validates an AI multimodal model built from orbital MRI sequences and ocular ultrasound for TAO. The study compares AI-driven assessments of presence, activity, severity, and prognosis between TAO patients and controls. Participants undergo standardized MRI scans including multiple sequences and receive ocular ultrasound, with data collected in real-world clinical settings. The goal is to determine how accurately the AI model can classify TAO status and forecast disease trajectory. Real-world applicability and diagnostic performance across diverse patients are central to the approach.
Why it matters
Potential benefit: If successful, the AI model could improve accuracy and speed of TAO diagnosis and prognosis, supporting more personalized management.
How similar studies have gone: Previous studies show promise for AI in imaging-based TAO assessment, but this specific multimodal MRI-plus-ultrasound approach in a real-world registry is relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
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
Where it's running
-
Shanghai Changzheng Hospital
Shanghai, Huangpu District, China Recruiting
Study contacts
- Study coordinator: Tuo Li, Vice Professor
- Email: zoe_leeto@hotmail.com
- Phone: +86-13918507887
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
ETHY-001 safety and activity in Thyroid Eye Disease (TED)
This study tests ETHY-001 versus placebo to see if it is safe, tolerable, and shows activity in people with thyroid eye disease.
-
Efgartigimod for Graves' Disease in adults
We are testing if efgartigimod given under the skin can help adults with Graves' disease by improving thyroid function and whether it is safe and tolerable.
-
Links between inflammation, thyroid antibodies, and retinal changes in Graves disease
This study will see if blood markers of inflammation and thyroid antibodies are linked to retinal measurements from OCT in adults with Graves disease and in healthy adults.
-
Teprotumumab for treating thyroid eye disease and thyroid dysfunction
This study is testing how well teprotumumab can help people with thyroid eye disease who have serious symptoms like bulging eyes, pain, and double vision.
-
Early risk stratification of thyroid eye disease in newly diagnosed Graves' disease
This study tests whether early eye-related signs, blood and tear biomarkers, or eye surface features can predict who with Graves’ disease will develop thyroid eye disease within a year.
-
Felzartamab for Graves’ Disease: See if it helps control thyroids and reduce need for ATDs
This study tests felzartamab vs placebo in adults with Graves’ disease to see if it can normalize thyroid hormones and let people stop anti-thyroid drugs.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.