AI-based Low Dose CBCT Reconstruction for Clinical Application

NCT06831617 | Not Yet Recruiting DMC

• 1 other identifier: AI guidance-Lung 001
• Study Type: interventional
• Target: 400
• Locations: 1 country
• Sites: 3

Brief Summary

The goal of this clinical trial is to learn if AI-based low dose CBCT reconstructed images can guide lung puncture effectively. The main questions it aims to answer are:

1. 1.Does the AI-based low dose CBCT reconstruction model reconstruct high quality images?
2. 2.Is it possible that low-dose CBCT reconstructed images can guide lung puncture procedures without compromising the efficiency of the procedure? Researchers will compare AI-based low dose CBCT reconstructed images to a placebo (conventional CBCT images) to see if AI-based low dose CBCT reconstructed image can guide lung puncture procedures without compromising the efficiency of the procedure.
3. 3.Undergo lung puncture under AI-based low dose CBCT reconstructed images guidance or under conventional CBCT images
4. 4.Be followed up for 1 week postoperative to obtain patient complications

Conditions

Lung Nodule

Keywords

Artificial Intelligence; Lung Nodule; Cone Beam CT; Lung Puncture; Images Reconstruction

Outcome Measures

Primary Outcomes (1)

• Number of puncture needles of participants undergoing percutaneous lung puncture procedures.

  The number of punctures was defined as the number of punctures performed throughout the percutaneous lung puncture procedure.

  From enrollment to the end of the lung puncture procedure.

Secondary Outcomes (2)

• Radiation Dose

  From enrollment to the end of the lung puncture procedure.

• Intraoperative and postoperative complications of participants undergoing lung puncture procedures

  From enrollment to the end of the lung puncture procedure at 1 week.

Other Outcomes (2)

• Algorithmic performance (peak signal-to-noise ratio)

  Through study completion, an average of 9 months.

• Algorithmic performance (structural similarity)

  Through study completion, an average of 9 months.

Study Arms (2)

AI based CBCT reconstructed images guided lung puncture

EXPERIMENTAL

Participants in the experimental group undergo AI-based low dose (radiation dose is 1/6th of the dose used in the clinic) CBCT reconstructed images guided lung puncture procedures.

Other: AI-based low dose CBCT reconstructed images system

Conventional CBCT images guided lung puncture

PLACEBO COMPARATOR

Participants in the experimental group undergo conventional CBCT images guided lung puncture procedures.

Other: Conventional CBCT images system

Interventions

AI-based low dose CBCT reconstructed images system OTHER

Participants in the experimental group undergo AI-based low dose (radiation dose is 1/6th of the dose used in the clinic) CBCT reconstructed images guided lung puncture procedures.

AI based CBCT reconstructed images guided lung puncture

Conventional CBCT images system OTHER

Participants in the experimental group undergo conventional CBCT images guided lung puncture procedures.

Conventional CBCT images guided lung puncture

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Participants who require CBCT-guided precutaneous lung puncture (PLP) and meet the clinical indications for the procedure.
• Participants whose physical condition is suitable for PLP.
• Participants are willing to sign informed consent.

You may not qualify if:

• Participants have metallic implants in the body, which severely affects the image quality.
• Participants are pregnant or breastfeeding.
• Participants are unwilling or unable to sign informed consent.

Sponsors & Collaborators

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

Study Sites (3)

Wuhan Union Hospital

Wuhan, Hubei, 430022, China

Location

Wuhan Union Jinyinhu Hospital

Wuhan, Hubei, 430022, China

Location

Wuhan Union West Hospital

Wuhan, Hubei, 430022, China

Location

Related Publications (1)

• Zhao H, Xu Z, Chen L, Wu L, Cui Z, Ma J, Sun T, Lei Y, Wang N, Hu H, Tan Y, Lu W, Yang W, Liao K, Teng G, Liang X, Li Y, Feng C, Nie T, Han X, Xiang D, Majoie CBLM, van Zwam WH, van der Lugt A, van der Sluijs PM, van Walsum T, Feng Y, Liu G, Huang Y, Liu W, Kan X, Su R, Zhang W, Wang X, Zheng C. Large-scale pretrained frame generative model enables real-time low-dose DSA imaging: An AI system development and multi-center validation study. Med. 2025 Jan 10;6(1):100497. doi: 10.1016/j.medj.2024.07.025. Epub 2024 Aug 19.

  PMID: 39163857 RESULT

Central Study Contacts

Huangxuan Zhao, PhD

CONTACT

+8618971676985; zhao_huangxuan@sina.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: TRIPLE
• Who Masked: PARTICIPANT, INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: PREVENTION
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: February 12, 2025
• First Posted: February 18, 2025
• Study Start: March 1, 2025
• Primary Completion: October 31, 2025
• Study Completion: November 30, 2025
• Last Updated: February 18, 2025

Record last verified: 2025-02

Data Sharing

• IPD Sharing: Will not share

Locations

CN (3)