Clinical Research Directory
Browse clinical research sites, groups, and studies.
Clinical Application of a Low-Dose CBCT AI Model
Sponsor: Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
Summary
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.
Official title: Low-dose AI-reconstructed CBCT Versus Full-dose CBCT for Guidance of Interventional Procedures: a Multicenter Randomized Controlled Trial
Key Details
Gender
All
Age Range
18 Years - Any
Study Type
INTERVENTIONAL
Enrollment
1380
Start Date
2026-08-01
Completion Date
2026-12-31
Last Updated
2026-09-29
Healthy Volunteers
No
Conditions
Interventions
DeepPriorCBCT-V2
Compared with conventional CBCT-guided interventional procedures and previously reported low-dose CBCT studies, the intervention adopted in the present study has several distinct advantages. First, most existing low-dose CBCT protocols only reduce radiation for a single anatomical region, mainly the thorax, while our DeepPriorCBCT-V2 model achieves stable low-dose reconstruction for the brain, thorax, and abdomen simultaneously, with radiation reduced to 1/6 of the standard clinical level for the thorax and abdomen and 1/5 for the brain. Second, unlike general noise-reduction algorithms used in previous studies, our model embeds anatomical prior information through neural discrete representation learning, which ensures consistent and reliable image quality at extremely low radiation doses without sacrificing intraoperative guidance accuracy. Third, this study is the first prospective multicenter randomized controlled trial to systematically verify the clinical feasibility of multi-orga
Clinical standard protocol (Full-radiation-dose CBCT)
Interventional procedures were performed under the guidance of clinical standard protocol (Full-radiation-dose CBCT).
Locations (5)
The First Affiliated Hospital of University of Science and Technology of China
Hefei, Anhui, China
Wuhan Union Hospital
Wuhan, Hubei, China
Wuhan Union Jinyin Lake Hospital
Wuhan, Hubei, China
Wuhan Union West Hospital
Wuhan, Hubei, China
Zhongda Hospital, Medical School, Southeast University
Nanjing, Jiangsu, China