Deep Learning Reconstruction Algorithms in Dual Low-dose CTA

Deep Learning Clinical Trial

Official title:

Evaluation of Deep Learning Reconstruction Algorithms in Dual Low-dose CT Vascular Imaging

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT06372756
• Other study ID #: 102122
• Status: Recruiting
• Start date: June 1, 2023
• Est. completion date: March 2026

Study information

• Verified date: April 2024
• Source: Tongji Hospital
• Contact: Youfa M Tang, Doctor
• Phone: 8613554101223
• Email: 1525573397[@]qq.com
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The goal of this observational study is to evaluate the impact of deep learning image reconstruction on the image quality and diagnostic performance of double low-dose CTA. The main question it aims to answer is to explore the feasibility of deep learning image reconstruction in double low-dose CTA.

Description:

1. The raw data from patients who underwent head and neck CTA, coronary CTA, and abdominal CTA in both standard dose and double low-dose groups were included.

2. Techniques such as filtered back projection, iterative reconstruction, and deep learning reconstruction were performed.

3. The feasibility of deep learning reconstruction in double low-dose CTA was evaluated based on image quality and diagnostic performance.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 1200
• Est. completion date: March 2026
• Est. primary completion date: December 2025
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 18 Years to 90 Years

Eligibility

Inclusion Criteria:

• Patients with head and neck CTA, coronary artery CTA, and abdominal CTA due to stroke, coronary heart disease and abdominal inflammatory disease, and abdominal tumors.

Exclusion Criteria:

• Age <18 years, pregnancy, allergic reaction to iodine contrast agent, renal insufficiency, and severe hyperthyroidism.

Related Conditions & MeSH terms

• Deep Learning

Intervention

Diagnostic Test:
• Deep learning image reconstruction
Deep learning image reconstruction (DLIR) is a newly developed artificial intelligence noise reduction algorithm in recent years. It trains massive high-quality FBP data sets to learn to distinguish noise and signal, so as to selectively reduce noise and reconstruct high-quality images with low-quality image data.

Locations

Country	Name	City	State
China	Tongji Hospital Affiliated to Tongji Medical College of Huazhong University of Science and Technology	Wuhan	Hubei

Sponsors (1)

Lead Sponsor	Collaborator
Hao Tang

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	The specificity and sensitivity calculated through the optimal cutoff value of the receiver operating characteristic curve.	The specificity and sensitivity were calculated separately for the standard dose group and the double low-dose group using the optimal cutoff value from the receiver operating characteristic curve, for the purpose of comparing diagnostic accuracy between the two groups.	2026.1
Secondary	The signal-to-noise ratio calculated from image CT values and noise	The signal-to-noise ratio was calculated separately for the standard dose group and the double low-dose group using image CT values and noise, to assess the image quality between the two groups.	2026.1