(25 days)
The Ziehm Vision FD is intended for use in providing medical imaging for general populations. The device provides pulsed and continuous fluoroscopic imaging of patients during diagnostic, interventional and surgical procedures. It is intended for use in visualizing complex anatomical structures and procedures such as vascular, cardiac, angiographic, cholangiography, endoscopic, urologic, orthopedic, neurologic, critical care, emergency room procedures, and where higher accuracy in Image geometry is required. This device does not support direct radiographic film exposures and is not intended for use in performing mammography.
The Ziehm Vision FD mobile fluoroscopy system is comprised of a mobile stand with a C-Profile shaped support with both a mono-block high voltage generator assembly and Flat Panel image receptor. These attach to either end of a C-Profile providing a fixed SID. The device performs 2D medical imaging using 4 axes of manual movement and one vertical axes of motorized movement. A user touch screen provides for concise user selectable anatomical programs and X-ray technique control. Integrated high-resolution flat panel display monitors directly mounted on the monitor cart providing the clinician with a precise angle for visualization of live fluoroscopic images of the patient's anatomy. This visualization helps to localize regions of pathology for surgical procedures. The mobile stand supports both a cable bound and optional wireless fluoroscopic footswitch. The Wireless footswitch operation allows for optimum positioning for the surgeon by removing the cable on the floor. The optional interface panel of the Ziehm Vision FD provides connection of peripheral devices such as external monitors, thermal video printers, and image storage devices (USB, DVD) and DICOM fixed wire and wireless network interfaces.
The provided document is a 510(k) Summary for the Ziehm Vision FD, a mobile fluoroscopic C-arm system. It focuses on demonstrating substantial equivalence to a predicate device (Ziehm Vision FD K061534) rather than presenting a standalone study with specific acceptance criteria and detailed performance metrics of a novel AI device. Therefore, much of the requested information, particularly regarding AI-specific performance, sample sizes for test and training sets, number and qualifications of experts for ground truth, adjudication methods, and MRMC studies, is not available in this document as it pertains to a traditional medical device modification and not an AI/ML-based diagnostic system.
However, I can extract the relevant information regarding the non-clinical testing and the comparison to the predicate device to address the core of your request as much as possible from the provided text.
Here's a breakdown of the available information:
1. A table of acceptance criteria and the reported device performance
Since this is a submission for substantial equivalence of a modified conventional X-ray device, the "acceptance criteria" are not explicit performance metrics in the way one might expect for an AI/ML device. Instead, the acceptance criteria are largely implied by demonstrating compliance with various regulatory standards and showing equivalent performance to the predicate device.
| Acceptance Criteria (Implied) | Reported Device Performance (Summary from Non-Clinical Tests) |
|---|---|
| Safety and Effectiveness: No new safety or effectiveness concerns compared to the predicate device. | The design was completed in accordance with Ziehm Imaging GmbH Quality Management System Design Controls, 21 CFR 820, and applicable standards. Verification and Validation testing were successfully conducted, ensuring the device performs to product specifications and intended use. |
| Electrical Safety: Compliance with IEC 60601-1 standards. | Testing regarding electrical safety according to ANSI/AAMI ES60601-1 was performed, and test results show compliance. |
| Electromagnetic Compatibility (EMC): Compliance with IEC 60601-1-2 standards. | Testing regarding electromagnetic compatibility according to IEC 60601-1-2 was performed, and test results show compliance. |
| Wireless & Interoperability Safety: No adverse effect on safety/effectiveness from wireless features and interoperable interfaces. | Testing according to Guidance's "Radio Frequency Wireless Technology in Medical Devices" and "Design Considerations and Premarket Submissions Recommendations for Interoperable Medical Devices" shows neither the wireless features nor the interoperable interfaces of the device affect safety and effectiveness. |
| X-Ray System Performance: Compliance with FDA requirements for diagnostic X-ray systems (e.g., leakage radiation, kV, mA, exposure rates, beam-limiting alignment) and 21 CFR 1020.30-32. Also, relevant safety standards like IEC 60601-1-3, IEC 60601-2-43, IEC 60601-2-54. | Documentation demonstrated compliance of the modified device to FDA requirements stated in "A Guide for the Submission of Initial Reports on Diagnostic X-Ray Systems and Their Major Components." This includes, but is not limited to, leakage radiation, peak tube potential (kV), tube current (mA), fluoroscopic entrance exposure rates, and beam-limiting alignment. Performance testing confirmed compliance with 21 CFR 1020.30-32 and relevant safety standards (IEC 60601-1-3, IEC 60601-2-43, IEC 60601-2-54). |
| Image Quality: Equivalence regarding image quality to the predicate device, while potentially providing reduced dose. | Non-clinical image comparison with sets of images from the modified device and the predicate shows equivalence regarding image quality. Assessment of the low dose functionality shows the ability to reduce dose for certain applications. An image comparison study using anthropomorphic phantoms concluded that the image quality combined with reduced patient dosage will result in comparable patient care to the predicate. A Radiologist assessed individual image sets from anthropomorphic phantoms, concluding comparable image quality and fulfilling intended use requirements. |
| Software Safety: Compliance with guidance for software in medical devices and cybersecurity. | Software testing was performed as required by "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" and "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices." |
| Risk Management: Potential radiation, mechanical, and electrical hazards identified, analyzed, and controlled. | Hazards were identified and analyzed as part of risk management and controlled by meeting applicable CDRH 21CFR subchapter J performance requirements, recognized and general consensus standards, designing and manufacturing under Ziehm Imaging GmbH Quality System, and system verification and validation testing. Adherence to regulations and certifications provides assurance of safety and effectiveness. This included Risk Analysis, Required reviews, Design reviews, Component testing, Integration testing, Performance testing, Safety testing, and Product use testing. |
2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)
- Test Set Sample Size: Not specified. The document mentions "sets of images" and "anthropomorphic phantoms" but does not give a number of images or cases.
- Data Provenance: The images were generated using "anthropomorphic (PMMA material) phantoms and anatomical simulation phantoms." This indicates that the data is synthetic/phantom-based rather than from human patients. Therefore, information on country of origin, retrospective, or prospective is not applicable in the traditional sense.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)
- Number of Experts: "A board-certified Radiologist." Implies one expert.
- Qualifications: "board-certified Radiologist." No specific years of experience are mentioned.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
- Adjudication Method: "Evaluation of the individual images arranged in image sets was conducted by a board-certified Radiologist." This indicates a single reader assessment rather than an adjudication process involving multiple readers. Therefore, methods like 2+1 or 3+1 are not applicable.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- MRMC Study: No, an MRMC comparative effectiveness study was not done. The submission explicitely states: "The modified Ziehm Vision FD mobile fluoroscopic C-arm system did not require live human clinical studies to support substantial equivalence." The evaluation was a comparison of image quality between the modified device and the predicate device, performed by a single radiologist using phantom images.
- Effect Size with AI: Not applicable, as this is a traditional medical imaging device modification, not an AI-based system.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- This is not an AI/ML algorithm; it is a fluoroscopic X-ray system. Therefore, the concept of "standalone algorithm performance" is not applicable. The device itself is the "standalone" system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: For the image quality comparison, the "ground truth" was implicitly the assessment and conclusion of a single "board-certified Radiologist" based on images derived from "anthropomorphic (PMMA material) phantoms and anatomical simulation phantoms." This isn't pathology or outcomes data, but rather an expert's qualitative judgment of image quality and its suitability for patient care.
8. The sample size for the training set
- Training Set Sample Size: Not applicable. This is not an AI/ML device that requires a training set in that sense. The device's modifications are based on engineering design and validation processes, not machine learning model training.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable, as there is no AI/ML training set mentioned in the document.
§ 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.