Lung Nodules
Conditions
Keywords
DeepPriorCBCT, Lung nodules, Low dose radiation, Cross-Over Observational Study, CBCT, Percutaneous thoracic biopsy
Brief summary
The goal of this clinical trial is to learn if the DeepPriorCBCT model ensure high-quality CBCT image while reducing CBCT radiation dose. The main questions it aims to answer are: * Can DeepPriorCBCT reduce CBCT radiation doses? * Is the image quality of DeepPriorCBCT reconstruction consistent with that of existing clinical reconstruction method? Researchers will compare CBCT images quality reconstruction with DeepPriorCBCT model to CBCT image quality reconstruction with existing clinical protocols to see if DeepPriorCBCT model can improve the CBCT image quality while reducing radiation dose. Participants will: * Receive a single low dose (1/6 of existing clinical protocols) CBCT scan * Receive a single conventional dose CBCT scan
Interventions
RADIATIONParticipants will receive a 1/6 views undersampling lung CBCT scan.
Participants will receive a 1/6 views undersampling lung CBCT scan. And the CBCT images will be reconstructed by DeepPriorCBCT model for further analysis.
Sponsors
Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
Study design
Allocation
NON_RANDOMIZED
Intervention model
CROSSOVER
Primary purpose
DIAGNOSTIC
Masking
DOUBLE (Investigator, Outcomes Assessor)
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
1. Participants will receive percutaneous thoracic puncture under the guidance of CBCT during the study period. 2. The participants' medical records containing basic information, medical history, etc are complete. 3. Participants can understand the study's purpose, procedures, potential risks, and benefits, and voluntarily signs a written informed consent form.
Exclusion criteria
1. Participants are under the age of 18. 2. Participants are suffering from severe mental illness or cognitive impairment, unable to understand the study and sign. 3. Participants are pregnant or breastfeeding women. 4. Participants are concurrent participating in other programs that affect the results of this study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| CBCT Images Quality Score | No more than 1 week | CBCT Images Quality Score was analyzed by 5 radiologists using 5-point Likert scale. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| The scores of lesion diagnosis from 5 radiologists | No more than 1 week | 5 radiologists from 5 medical centers will be invited to diagnosis the lesion of fully sampled machine-reconstructed CBCT images vs. undersampled model-reconstructed CBCT images. |
| The agreement scores given by the 25 interventionalists. | No more than 1 week. | 25 interventionalists from 5 medical centers will be invited to analyze fully sampled machine-reconstructed CBCT images vs. undersampled model-reconstructed CBCT images. The scores given by the 25 interventionalists will be used for agreement score analysis. |
| Radiation dose | No more than 1 day | Radiation dose is defined as the radiation dose received by patients when undergoing one conventional-dose CBCT scan and one undersampled CBCT scan. |
Other
| Measure | Time frame | Description |
|---|---|---|
| Objective indicators for reconstructed CBCT images | No more than 1 week. | Objective indicators for reconstructed CBCT images include peak signal to noise ratio (PSNR) and structure similarity (SSIM). PSNR is a ratio that represents the ratio between the maximum possible power of a signal and the destructive noise power that affects its representation accuracy. SSIM is a metric for measuring image similarity. |
Countries
China
Outcome results
None listed