Clinical Application of a Low-Dose CBCT AI Model
Low-dose AI-reconstructed CBCT Versus Full-dose CBCT for Guidance of Interventional Procedures: a Multicenter Randomized Controlled Trial
- Cerebrovascular Diseases
- Lung
- Liver
At a glance
- Phase
- Phase not stated
- Study type
- Interventional
- Sponsor
- Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
- Enrolment target
- 1,380
- Started
- 1 August 2026
- Main results due
- 30 November 2026
- Study sites
- 5
- Registry updated
- 29 September 2026
Can you take part?
- Aged 18 years and over.
- Open to any sex.
- You need the condition being studied — healthy volunteers are not accepted.
These are the headline rules only. Every study has a longer list, and whether you are eligible is decided by the research team at the site — never by this page.
Read the full eligibility criteria
Inclusion Criteria:
* Age ≥18 years.
* Requires CBCT-guided interventional treatment or surgery (e.g., cerebral angiography, lung puncture biopsy, hepatic artery chemoembolization, or percutaneous liver biopsy) and meets operational indications.
* Can understand the study's purpose, procedures, potential risks, and benefits, and voluntarily signs a written informed consent form.
Exclusion Criteria:
* History of high-dose radiation exams or treatments.
* Known allergies or severe adverse reactions to iodine contrast agents or other relevant medications.
* Pregnant or breastfeeding women.
* Severe comorbidities or chronic diseases (e.g., severe diabetes, renal insufficiency).
* Severe mental illness or cognitive impairment preventing understanding of the study procedures or providing informed consent.
⑥ Participants are not suitable for the trial per investigator's opinion.What this study is about
In the sponsor’s own words, from the registry.
Cone Beam CT (CBCT) is an imaging modality used in interventional digital subtraction angiography (DSA). It produces three-dimensional images via cone-beam X-ray scanning and computer reconstruction. Clinically, CBCT guides puncture for pulmonary and hepatic lesions and evaluates post-intervention outcomes in liver cancer and cerebrovascular diseases. However, CBCT-guided interventions carry high patient radiation exposure; dose reduction often degrades image quality and impairs procedural results. Studies report that each 100 mGy radiation increment elevates cancer risk by 1.96-fold.
Artificial intelligence enables low-dose CBCT. Our prior DeepPriorCBCT model embedded anatomical priors using neural discrete representation learning, reducing thoracic CBCT dose to one-sixth of routine protocols while preserving image quality. We further developed DeepPriorCBCT-V2 using 55 000 pre-reconstruction CBCT datasets covering brain, thorax and abdomen. This multi-organ model maintains image quality at one-sixth standard radiation dose. Nevertheless, its real-world clinical performance remains unvalidated. We therefore designed this prospective multicenter randomized controlled trial to evaluate the clinical applicability of DeepPriorCBCT-V2.
Study sites(5)
The First Affiliated Hospital of University of Science and Technology of China
Hefei, Anhui, China
Recruiting
Wuhan Union Hospital
Wuhan, Hubei, China
Recruiting
Wuhan Union Jinyin Lake Hospital
Wuhan, Hubei, China
Recruiting
Wuhan Union West Hospital
Wuhan, Hubei, China
Recruiting
Zhongda Hospital, Medical School, Southeast University
Nanjing, Jiangsu, China
Recruiting
Showing 5 of 5 sites. 5 of the 5 sites on this study are recruiting right now — a site can stop enrolling while the study as a whole is still open.
Source: ClinicalTrials.gov record NCT07845929. Trialion does not run this study, is not paid to refer anyone to it, and cannot enrol you. Eligibility is always decided by the research team at the site.
Not the right study?
Answer three questions and see the studies recruiting near you, in plain language.
Find a study for me