(397 days)
ClearView is a CT reconstruction software. The end user can choose to apply either ClearView or the filter back-projection (FBP) to the acquired raw data.
Depending on the clinical task, patient size, anatomical location, and clinical practice, the use of ClearView can help to reduce radiation dose while maintaining Pixel noise, low contrast detectability and high contrast resolution. Phantom measurements showed that high contrast resolution and pixel noise are equivalent between full dose FBP images and reduced dose ClearView images. Additionally, ClearView can reduce body streak artifacts by using iterations between image space and raw data space.
A Model Observer evaluation showed that equivalent low contrast detectability can be achieved with less dose using ClearView at highest noise reduction level for thin (0.625 mm) reconstruction slices in MITA body and ACR head phantoms for low contrast objects with different contrasts.
ClearView are not intended to be used in CCT and Pilot.
ClearView reconstruction technology may enable reduction in pixel noise standard deviation and improvement in low contrast resolution. ClearView reconstruction algorithm may allow for reduced mAs in the acquisition of image, thereby it can reduce the dose required.
In clinical practice, the use of ClearView reconstruction may reduce CT patient dose depending on the clinical task, patient size, and clinical practice. A consultation with a radiologist and physicist should be made to determine the appropriate dose to obtain diagnostic image quality for the particular clinical task.
As a reconstruction option, ClearView can be selected before scanning or after scanning. There are 9 ClearView Levels from 10% to 90%. Users can select t.the level of ClearView that is appropriate for the clinical task being performed. According to the comparison based on the requirements of 21 CFR 807.87, we stated that ClearView reconstruction software is substantially equivalent to the FBP of NeuViz 64 Multi-Slice CT Scanner System.
ClearView is a moderate concern device.
Here's an analysis of the acceptance criteria and study information for the ClearView device as presented in the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document provides performance claims for ClearView, primarily in comparison to Filtered Back Projection (FBP) and related to dose reduction. It doesn't explicitly state "acceptance criteria" in a numerical table form, but rather describes how the device performs against certain metrics.
| Performance Metric | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Radiation Dose | Reduction in radiation dose while maintaining image quality | "can help to reduce radiation dose while maintaining Pixel noise, low contrast detectability and high contrast resolution." |
| Pixel Noise | Equivalence to full-dose FBP images at reduced dose | "Phantom measurements showed that... pixel noise are equivalent between full dose FBP images and reduced dose ClearView images." |
| Low Contrast Detectability | Equivalence to FBP at reduced dose | "A Model Observer evaluation showed that equivalent low contrast detectability can be achieved with less dose using ClearView at highest noise reduction level for thin (0.625 mm) reconstruction slices in MITA body and ACR head phantoms for low contrast objects with different contrasts." |
| High Contrast Resolution | Equivalence to full-dose FBP images at reduced dose | "Phantom measurements showed that high contrast resolution and pixel noise are equivalent between full dose FBP images and reduced dose ClearView images." |
| Artifact Reduction | Reduction of body streak artifacts | "ClearView can reduce body streak artifacts by using iterations between image space and raw data space." |
2. Sample Size Used for the Test Set and Data Provenance
The provided text does not contain information about the sample size used for a test set based on human patient data. The evaluations mentioned are based on:
- Phantom measurements: Performed on "MITA body and ACR head phantoms." No specific sample size (number of phantom scans) is provided.
- Data Provenance: The studies are described as "Phantom measurements" and "A Model Observer evaluation." This implies laboratory or simulated data, not retrospective or prospective human clinical data. The country of origin of the data is not specified beyond the manufacturer being in China.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
The document does not detail the use of human experts to establish ground truth for a test set. The evaluations primarily relied on phantom measurements and a model observer, which are objective, quantitative metrics. While "A consultation with a radiologist and physicist should be made to determine the appropriate dose to obtain diagnostic image quality for the particular clinical task," this refers to clinical practice guidance and not a component of the device's validation study itself as described.
4. Adjudication Method for the Test Set
Not applicable. The reported evaluations (phantom measurements, Model Observer) do not involve human adjudication for a test set's ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No. The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The evaluation focuses on standalone phantom performance and model observer results, not on how human readers' performance improves with or without the AI (ClearView) assistance.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes. The described studies are standalone evaluations of the ClearView reconstruction software's performance, primarily using phantom measurements and a "Model Observer evaluation." These do not involve a human in the loop for the performance assessment. The device itself is a reconstruction software.
7. Type of Ground Truth Used
The ground truth used in the described studies is:
- Physical Phantom Measurements: For pixel noise, high contrast resolution, and effectively for low contrast detectability (as measured by the Model Observer on phantoms). These are objective physical properties measured with specific phantoms and known targets.
- Model Observer Results: Used for low contrast detectability, which is a quantitative measure from a computational model mimicking human perception, applied to phantom data with known contrast objects.
8. Sample Size for the Training Set
The document does not provide any information about the sample size used for any training set. ClearView is described as CT reconstruction software, but details on its development or any machine learning training data are absent.
9. How the Ground Truth for the Training Set Was Established
The document does not provide any information on a training set or how its ground truth might have been established.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.