(30 days)
SmartGrid feature is a software option that provides, upon request by user, a diagnostic radiograph image with a reduction in visible x-ray scatter similar to the effect of an anti-scatter grid.
The SmartGrid II software is designed to improve contrast and reduce the appearance of scatter in radiographic images that have been acquired without a physical grid. SmartGrid II encapsulates an algorithm for estimating and removing scatter from radiographic images.
The SmartGrid II software feature is accessible through the DirectView application software. Users will be able to select SmartGrid II processing before an image is acquired, or to change whether SmartGrid II processing is applied to a previously acquired image.
The Carestream SmartGrid II is a software option designed to reduce visible x-ray scatter in diagnostic radiograph images, similar to the effect of an anti-scatter grid. It is an improvement to the original SmartGrid software.
Here's a breakdown of the acceptance criteria and the study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Successful installation of the SmartGrid II software component. | Installation testing was performed and verified successful installation of the SmartGrid II software. |
| Consistent production of diagnostic quality images by SmartGrid II processing. | Specific test cases were implemented and verified that SmartGrid II image processing consistently produces a diagnostic quality image. |
| Sufficient reduction of image noise and sufficient image contrast/brightness for clinical diagnosis. | Specific test cases were implemented and verified that image noise was sufficiently reduced and image contrast/brightness were sufficient for clinical diagnosis. |
| Proper performance of the SmartGrid II software feature when integrated into the Carestream application software. | Integration tests were performed and ensured proper performance of the SmartGrid II software feature when integrated into the Carestream application software. |
| No unexpected negative effects (clinical evaluation with respect to diagnostic image quality). | A reader study demonstrated that images processed with SmartGrid II were equivalent in diagnostic quality to images processed with the predicate device (original SmartGrid). Also, error handling was observed for proper function through monitoring of event logs, and Ad Hoc testing was performed to help ensure no unexpected negative effects. |
| Conformance of the device to its specifications. | Non-clinical test results demonstrated the intrinsic workflow, related performance, overall function, verification and validation of requirements for intended use, and reliability of the software. Predefined acceptance criteria were met and demonstrated that the device is as safe, as effective, and performs as well as or better than the predicate device. |
| Substantial equivalence to the legally marketed predicate device (SmartGrid, K163157) in terms of safety and effectiveness. | Performance testing results support a substantial equivalence determination. The differences between SmartGrid II and the predicate device do not affect the intended use or alter the fundamental scientific technology. Both devices use scatter factor estimation, scatter correction, noise reduction, and image rendering. The improved algorithms in SmartGrid II for scatter estimation and correction (based on the full detector field versus collimated subregion) lead to improvements in diagnostic quality. |
2. Sample Size and Data Provenance:
- Test Set Sample Size: The document does not explicitly state the numerical sample size of images used for the clinical reader study. It mentions "existing clinical research images" were evaluated.
- Data Provenance: The document does not specify the country of origin. It indicates the study used "existing clinical research images," implying a retrospective nature where stored images were processed and then evaluated.
3. Number of Experts and Qualifications:
- Number of Experts: One board-certified radiologist was used for the clinical evaluation.
- Qualifications: Board-certified radiologist. No specific number of years of experience is provided.
4. Adjudication Method for the Test Set:
- The document describes a reader study where a single board-certified radiologist evaluated images processed with both the original SmartGrid and SmartGrid II. There is no mention of an adjudication method as only one reader was used.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, a multi-reader, multi-case comparative effectiveness study was not explicitly described. The clinical evaluation involved a single radiologist. Therefore, there is no reported effect size of human readers improving with AI vs. without AI assistance from an MRMC study in this document.
6. Standalone Performance Study (Algorithm only):
- Yes, a standalone performance evaluation of the algorithm was conducted as part of the non-clinical (bench) testing. This included verifying consistent diagnostic quality image production, sufficient noise reduction, and appropriate contrast/brightness for clinical diagnosis.
7. Type of Ground Truth Used:
- For the clinical evaluation, the ground truth was essentially based on the expert opinion/consensus (or lack thereof, since only one expert) on diagnostic image quality comparison between the two software versions (SmartGrid II vs. predicate SmartGrid). The study aimed to confirm "no unexpected negative effects with respect to diagnostic image quality" and that SmartGrid II images were "equivalent in diagnostic quality" to predicate images.
- For the non-clinical bench testing, the ground truth would be represented by the predefined specifications and requirements for image quality metrics (noise, contrast, brightness) and system functionality.
8. Sample Size for the Training Set:
- The document does not provide information regarding the sample size of the training set used for developing the SmartGrid II algorithm. It primarily focuses on the validation of the updated algorithm.
9. How the Ground Truth for the Training Set was Established:
- The document does not provide information on how the ground truth for the training set was established for the SmartGrid II algorithm. It mentions that "the SmartGrid and SmartGrid II algorithms differ slightly to further improve the scatter estimation and correction," suggesting an iterative development process that would have involved some form of ground truth or reference data, but details are not included.
§ 892.1680 Stationary x-ray system.
(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.