CT-Free Quantitative Thyroid Single-photon Emission Computed Tomography (SPECT) Based on Artificial Intelligence: A Prospective Multicenter Noninferiority Clinical Trial
Authors' conclusion
CT-free SPECT using AI demonstrated noninferior diagnostic performance for thyrotoxicosis compared with conventional hybrid imaging while reducing radiation exposure and analysis time.
Study context
- Population
- Patients with thyrotoxicosis from three tertiary referral hospitals; 84 GD, 45 indeterminate disease, 23 thyroiditis
- Participants
- 152 patients
- Comparison
- Computed tomography (CT)-free thyroid SPECT using artificial intelligence (AI) vs conventional SPECT/CT
- Outcome
- Diagnostic accuracy for GD
Methodological detailsprospective, multicenter, noninferiority clinical trial
- Prospective
- Multicenter
- Noninferiority clinical trial
Performance
As reported in the abstract
| Test or model | Accuracy |
|---|---|
| CT-free SPECT | 86.2% |
| SPECT/CT | 85.5% |
Accuracy
CT-free SPECT86.2%
SPECT/CT85.5%
- CT-free SPECT vs SPECT/CT: lower CI bound −3.0% — lower CI bound −3.0%
Secondary outcomes
Time to generate technetium thyroid uptake (TcTU) values
- CT-free SPECT automatically generated TcTU values more quickly than SPECT/CT (40 minutes vs. 4 minutes)
Safety
Radiation exposure
- Radiation exposure — Reduction of radiation exposure with omission of CT
- 33.5%
Original publication
CT-Free Quantitative Thyroid SPECT Based on Artificial Intelligence: A Prospective Multicenter Noninferiority Clinical Trial. Thyroid. Published 7 April 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →