此页面是自动翻译的，不保证翻译的准确性。请参阅 英文版 对于源文本。

Clinical Application of a Low-Dose CBCT AI Model

2026年9月27日 更新者：Union Hospital, Tongji Medical College, Huazhong University of Science and Technology

Low-dose AI-reconstructed CBCT Versus Full-dose CBCT for Guidance of Interventional Procedures: a Multicenter Randomized Controlled Trial

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.

研究概览

地位

招聘中

条件

干预/治疗

研究类型

介入性

注册 (估计的)

1380

阶段

  • 不适用

联系人和位置

本节提供了进行研究的人员的详细联系信息，以及有关进行该研究的地点的信息。

学习联系方式

学习地点

  • 中国
    • Anhui
      • Hefei、Anhui、中国
        • 招聘中
        • The First Affiliated Hospital of University of Science and Technology of China
        • 接触：
    • Hubei
      • Wuhan、Hubei、中国、430022
        • 招聘中
        • Wuhan Union Hospital
        • 接触：
      • Wuhan、Hubei、中国、430022
        • 招聘中
        • Wuhan Union West Hospital
        • 接触：
      • Wuhan、Hubei、中国、430022
        • 招聘中
        • Wuhan Union Jinyin Lake Hospital
        • 接触：
    • Jiangsu
      • Nanjing、Jiangsu、中国
        • 招聘中
        • Zhongda Hospital, Medical School, Southeast University
        • 接触：

参与标准

研究人员寻找符合特定描述的人，称为资格标准。这些标准的一些例子是一个人的一般健康状况或先前的治疗。

资格标准

适合学习的年龄

18年 及以上 (成人、年长者)

接受健康志愿者

不

有资格学习的性别

全部

描述

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.

学习计划

本节提供研究计划的详细信息，包括研究的设计方式和研究的衡量标准。

研究是如何设计的？

设计细节

  • 主要用途：预防
  • 分配：随机化
  • 介入模型：并行分配
  • 屏蔽：三倍

武器和干预

参与者组/臂
干预/治疗
实验性的：Participants will receive interventional procedures guided by DeepPriorCBCT-V2.

Patients underwent interventional procedures guided by CBCT images reconstructed via the DeepPriorCBCT-V2 model from low-radiation-dose scans (1/6 of the conventional dose for the thorax and abdomen, and 1/5 for the brain).
其他：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
安慰剂比较：Participants will receive interventional procedures guided by clinical standard protocol.

Patients underwent interventional procedures guided by CBCT images reconstructed via clinical standard protocol (full-radiation-dose).
设备：Clinical standard protocol (Full-radiation-dose CBCT)

Interventional procedures were performed under the guidance of clinical standard protocol (Full-radiation-dose CBCT).

研究衡量的是什么？

主要结果指标

结果测量
措施说明
大体时间
Radiation dose
大体时间：Through study completion, an average of 5 months.

Air Kerma (AK) refers to the sum of the initial kinetic energies transferred from uncharged ionizing radiation (such as X-ray photons) to charged particles in air, divided by the mass of air at that location.
Through study completion, an average of 5 months.

次要结果测量

结果测量
措施说明
大体时间
Operation time
大体时间：Through study completion, an average of 5 months.

The time from the initiation to the completion of the interventional procedure.
Through study completion, an average of 5 months.
Intraoperative complications.
大体时间：Through study completion, an average of 5 months.

Procedure-related intraprocedural complications.
Through study completion, an average of 5 months.
Post operative complications
大体时间：Through study completion, an average of 5 months.

Procedure-related complications within 7 days after the interventional procedure.
Through study completion, an average of 5 months.

其他结果措施

结果测量
措施说明
大体时间
Subjective scoring
大体时间：Through study completion, an average of 5 months.

Scoring of reconstructed CBCT images was performed by radiologists and interventional physicians using a 5-point Likert scale. The scale was defined as: 1 = very poor image quality; lesions cannot be assessed and the procedure cannot be guided; 2 = poor image quality; lesion assessment and procedure guidance are difficult; 3 = moderate image quality; lesion assessment is relatively difficult, but procedure guidance is feasible; 4 = good image quality; lesions can be assessed and procedure guidance is achievable; 5 = excellent image quality; lesion assessment is not compromised at all and procedure guidance is fully supported.
Through study completion, an average of 5 months.

合作者和调查者

在这里您可以找到参与这项研究的人员和组织。

赞助

Union Hospital, Tongji Medical College, Huazhong University of Science and Technology

研究记录日期

这些日期跟踪向 ClinicalTrials.gov 提交研究记录和摘要结果的进度。研究记录和报告的结果由国家医学图书馆 (NLM) 审查，以确保它们在发布到公共网站之前符合特定的质量控制标准。

研究主要日期

学习开始 (实际的)

2026年8月1日

初级完成 (估计的)

2026年11月30日

研究完成 (估计的)

2026年12月31日

研究注册日期

首次提交

2026年9月21日

首先提交符合 QC 标准的

2026年9月27日

首次发布 (实际的)

2026年9月29日

研究记录更新

最后更新发布 (实际的)

2026年9月29日

上次提交的符合 QC 标准的更新

2026年9月27日

最后验证

2026年9月1日

更多信息

与本研究相关的术语

其他相关的 MeSH 术语

其他研究编号

  • DeepPriorCBCT-V2

计划个人参与者数据 (IPD)

计划共享个人参与者数据 (IPD)？

不

药物和器械信息、研究文件

研究美国 FDA 监管的药品

不

研究美国 FDA 监管的设备产品

不

此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.

订阅