(113 days)
This device is a digital radiography/fluoroscopy system used in a diagnostic and interventional angiography configuration. The system is indicated for use in diagnostic and angiographic procedures for blood vessels in the heart, brain, abdomen and lower extremities.
INFX-8000V, V6.20, is an X-ray system that is capable of radiographic and fluoroscopic studies and is used in an interventional setting. The system consists of a C-arm, which is equipped with an X-ray tube, beam limiter and X-ray receptor, X-ray controller, computers with system and processing software, and a patient radiographic table. The device software is used to control the system, set X-ray conditions, acquire digital images from the X-ray detector, display images on the monitors, perform image processing and recording. This X-ray system has a wireless footswitch option. This X-ray system does not have wireless transmission of data.
This document describes a 510(k) premarket notification for the "INFX-8000V, V6.20" medical imaging system, which is a modification of a previously cleared device. The focus of the changes and the supporting study is on improvements to the Auto Pixel Shift (APS) algorithm, and the addition of Spot ROI Fluoroscopy and Clinical Mode.
1. Table of Acceptance Criteria and Reported Device Performance
| Feature/Algorithm | Acceptance Criteria (Implied) | Reported Device Performance | Notes |
|---|---|---|---|
| Auto Pixel Shift (APS) Algorithm | Correction accuracy should be at least equal to the current APS algorithm. | "the correction accuracy of the improved APS algorithm was confirmed to be equal to or greater than the correction accuracy of the current APS algorithm." | This indicates that the improved algorithm met or exceeded the performance of the predicate device's algorithm in terms of pixel shift correction. The specific metric for "correction accuracy" is not detailed in the provided text. |
| Spot ROI Fluoroscopy | The functionality should be available and integrate with the system. | "Available" | The document states it was added as a new feature. The acceptance criteria would likely involve successful implementation, appropriate display of peripheral regions outside the area of interest, and functional integration with the existing system. No specific quantitative performance metrics beyond availability are mentioned for this feature in terms of its "performance." |
| Clinical Mode | The functionality should be available and enhance user workflow. | "Available" | Similar to Spot ROI Fluoroscopy, this is a new feature. Acceptance criteria would involve successful implementation, providing preset 2D roadmap display settings, and demonstrating an enhancement in user workflow during common clinical cases. No specific quantitative performance metrics are provided for this feature beyond its availability and stated benefit. |
| Overall System Performance | Demonstrate that system modifications result in performance equal to or better than the predicate system. | "This submission contains test data that demonstrates that the system modifications result in performance that is equal to or better than the predicate system." | This is a high-level statement covering all modifications. It implies that no new safety issues were introduced and that the core imaging capabilities (image quality, dose, etc., where relevant to the changes) remained at least equivalent or improved. The detailed metrics are not presented in this summary. The testing was done "in accordance with the applicable standards published by the International Electrotechnical Commission (IEC) for Medical Devices and XR Systems." This suggests the use of standard phantom or test object measurements for image quality, radiation output, etc. |
2. Sample Size Used for the Test Set and Data Provenance
The provided summary does not explicitly state the sample size used for specific test sets or the data provenance (e.g., country of origin of data, retrospective or prospective).
It broadly states: "This submission contains test data..." and "Testing of the modified system was conducted in accordance with the applicable standards published by the International Electrotechnical Commission (IEC) for Medical Devices and XR Systems." This implies that standardized test procedures and potentially phantom-based studies were used, rather than human clinical data sets in the traditional sense of a clinical trial for software performance evaluation against a disease. For modifications to an existing imaging system, performance often refers to technical specifications, image quality metrics, and functional validation against a predicate device.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not specify the number of experts or their qualifications for establishing ground truth. Given the nature of a 510(k) for a modified imaging system, particularly an X-ray system, "ground truth" for technical performance often refers to objective physical measurements or established engineering benchmarks rather than clinical diagnostic ground truth from human experts. For example, the "correction accuracy" of the APS algorithm would likely be evaluated using phantoms with known shifts, where the "ground truth" is the precise, controlled shift introduced.
4. Adjudication Method for the Test Set
The document does not specify an adjudication method. This is typically not relevant for technical performance testing of an imaging system's components unless a specific clinical image quality assessment by multiple readers was performed, which is not described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not mentioned or described in this document. The device is an imaging system, not an AI-powered diagnostic algorithm applied to images for interpretation. The "improvements" are to existing algorithms of the imaging system itself (e.g., pixel shift correction) or new features that aid workflow (Spot ROI, Clinical Mode).
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
For the Auto Pixel Shift (APS) algorithm, a standalone evaluation was implicitly done to assess its "correction accuracy" against the previous version. The statement "the correction accuracy of the improved APS algorithm was confirmed to be equal to or greater than the correction accuracy of the current APS algorithm" directly refers to the algorithm's performance. This type of evaluation would typically be performed on a test set (e.g., images of phantoms) without human interaction.
For "Spot ROI Fluoroscopy" and "Clinical Mode," these are features that enhance visualization and workflow. Their standalone "performance" would be assessed in terms of their functionality and correct operation within the system, not as a diagnostic algorithm.
7. The Type of Ground Truth Used
The most likely type of ground truth used for the APS algorithm improvements would be based on objective physical measurements or engineered scenarios, particularly using phantoms or test objects with known, controlled parameters (e.g., known induced pixel shifts). For the new features (Spot ROI, Clinical Mode), the ground truth would be their functional performance as designed (e.g., does Spot ROI correctly visualize peripheral regions as intended; do Clinical Mode presets function as specified). There is no mention of expert consensus, pathology, or outcomes data as ground truth, which are typically used for diagnostic AI algorithms.
8. The Sample Size for the Training Set
The document does not mention a sample size for a training set. This is consistent with a device modification that primarily involves algorithmic refinement (like APS) or new user-interface features (Spot ROI, Clinical Mode) implemented within an existing imaging system based on traditional engineering and physics principles, rather than a deep learning AI model that requires large training datasets.
9. How the Ground Truth for the Training Set Was Established
Since a training set is not explicitly mentioned and the changes appear to be algorithmic/feature-based rather than related to deep learning, the concept of establishing ground truth for a training set as typically understood in AI/ML is not applicable or described in this document. Improvements to algorithms like Auto Pixel Shift are likely based on engineering analysis, simulation, and structured testing rather than iterative learning from a labeled training set.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. 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). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic 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. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.