Actively Recruiting
Application of Deep Learning in CT Imaging of Elective Thoracic Surgery Patients: Assessing Preoperative Abnormal Pulmonary Function
Led by The First Affiliated Hospital of Guangzhou Medical University · Updated on 2024-06-27
2000
Participants Needed
1
Research Sites
13 weeks
Total Duration
On this page
Sponsors
T
The First Affiliated Hospital of Guangzhou Medical University
Lead Sponsor
G
GE Healthcare
Collaborating Sponsor
AI-Summary
What this Trial Is About
Researchers are evaluating the use of deep learning technology combined with computed tomography (CT) images to precisely predict pulmonary function indicators in patients scheduled for elective thoracic surgery. This observational study addresses the challenges of traditional pulmonary function tests, such as long duration, patient cooperation difficulties, false negatives, and contraindications. The study aims to optimize a model that supports more convenient and personalized preoperative pulmonary function assessments. The study involves two groups of patients: one undergoing single inspiratory phase CT scans and the other undergoing respiratory dual-phase CT scans, both combined with pulmonary function tests before surgery. The model was refined using data from 1500 single inspiratory phase CTs and 500 dual-phase respiratory CTs, enhancing its ability to predict pulmonary function accurately in real-world settings. Participants will have preoperative chest CT scans and pulmonary function tests within one month of each other, ensuring complete and artifact-free imaging. Researchers will measure the accuracy of pulmonary function predictions using the mean absolute error and concordance correlation coefficient over two years. The study will monitor participant cooperation, image quality, and pulmonary function report quality throughout the observation period.
CONDITIONS
Brief Title
Deep Learning for Preoperative Pulmonary Assessment in Thoracic CT
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Signing of the informed consent form
- Male or female, aged 18 to 75 years
- Undergoing elective thoracic surgery
- Good cooperation with preoperative pulmonary function testing and complete reporting
- Preoperative chest single or dual phase CT scans without significant artefacts and with complete imaging
- Interval between preoperative pulmonary function and CT scans does not exceed one month
You will not qualify if you...
- Poor cooperation with preoperative pulmonary function testing or missing reports
- Preoperative chest single or dual phase CT scans with significant artefacts or image omission
- Interval between preoperative pulmonary function and CT scans exceeds one month
- Severe respiratory disorders such as lung transplantation, pneumothorax, or giant bullae
- Other severe functional impairments
- Obstructive lesions like airway or esophageal stenosis
- Height below predicted equation range (Female < 1.45m; Male < 1.55m)
- Medication use before pulmonary function testing that does not meet cessation guidelines
- Pulmonary function report quality graded D-F
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Up to 1 month
Participants undergo preoperative pulmonary function testing and chest CT scans to assess lung function before elective thoracic surgery.
1 to 2 visits depending on cohort assignment
Duration - 2 years
Participants are monitored over time to evaluate pulmonary function prediction accuracy using deep learning on CT images.
Follow-up visits as scheduled during the 2-year period
Trial Site Locations
Total: 1 location
1
Department of Cardiothoracic Surgery, the First Affiliated Hospital of Guangzhou Medical College
Guangzhou, Guangdong, China, 510120
Actively Recruiting
Research Team
J
Jianxing He, MD
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
2
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here