Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| Cedars-Sinai Medical Center | OTHER |
Not provided
Not provided
Not provided
This study will compare the quality of CT images acquired with very low-dose radiation and processed with commercially available software vs. PixelShine processed images. It would potentially allow imaging facilities to acquire CT scans using lower doses of radiation without sacrificing clarity of CT images. Acquiring high quality CT images with low-dose radiation has the potential to enhance patient safety and has significant implications in imaging practices.
Patients receiving CT scans as part of their standard treatment will be asked to consent to an additional 5 minutes of imaging using very low-dose radiation prior to the conventional-dose CT scan. The prospective review will be performed in two cohorts: Chest CT scans and abdominal CT scans.
Anonymized images will be processed by conventional CT software and compared to the same images processed with machine-learning-based PixelShine. A board-certified radiologist will assess the noise and visual quality of the imaging data.
Study patients will receive approximately 10% more dose than a standard CT scan by participating in the study. There are no known short-term safety issues associated with this study. The study-related very low dose radiation is at a level far below that used for conventional x-ray imaging. The study has been approved by the Radiation Safety Committee as part of the review process.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Chest CT | Active Comparator | Conventional processing vs. PixelShine processing |
|
| Abdominal CT | Active Comparator | Conventional processing vs. PixelShine processing |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| PixelShine | Device | Machine learning algorithm |
| |
| Measure | Description | Time Frame |
|---|---|---|
| Visual Image Quality as Assessed by Image Noise Reduction | Comparison of image noise | Through study completion, an average of 1 month |
| Measure | Description | Time Frame |
|---|---|---|
| Image Resolution as Assessed by Size of Detected Lesions | Determine smallest size of detectable objects | Through study completion, an average of 1 month |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D008175 | Lung Neoplasms |
| D006528 | Carcinoma, Hepatocellular |
| ID | Term |
|---|---|
| D012142 | Respiratory Tract Neoplasms |
| D013899 | Thoracic Neoplasms |
| D009371 | Neoplasms by Site |
| D009369 | Neoplasms |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Conventional processing |
| Device |
Iterative reconstruction software |
|
| D008171 |
| Lung Diseases |
| D012140 | Respiratory Tract Diseases |
| D000230 | Adenocarcinoma |
| D002277 | Carcinoma |
| D009375 | Neoplasms, Glandular and Epithelial |
| D009370 | Neoplasms by Histologic Type |
| D008113 | Liver Neoplasms |
| D004067 | Digestive System Neoplasms |
| D004066 | Digestive System Diseases |
| D008107 | Liver Diseases |