(30 days)
Mars1417XF-CSI Wireless Digital Flat Panel Detector is indicated for digital imaging solution designed for providing general radiographic diagnosis of human anatomy. It is intended to replace radiographic film/screen systems in all general-purpose diagnostic procedures. This device is not intended for mammography or dental applications.
Mars1417XF-CSI Wireless Digital Flat Panel Detector is a kind of wireless digital flat panel detector. It supports the single frame mode, with the key component of TFT/PD image sensor flat panel of active area: 35.04cm×42.54cm.
The sensor plate of Mars1417XF-CSI Wireless Digital Flat Panel Detector is direct-deposited with CsI scintillator to achieve the conversion from X-ray to visible photon. The visible photons are transformed to electron signals by diode capacitor array within TFT panel, which are composed and processed by connecting to scanning and readout electronics, consequently to form a panel image by transmitting to PC through the user interface.
The major function of the Mars1417XF-CSI Wireless Digital Flat Panel Detector is to convert the X-ray to digital image, with the application of high resolution X-ray imaging. This detector is the key component of DR system, enables to complete the digitalization of the medical X-ray imaging with the DR system software.
The provided text describes a 510(k) submission for a Wireless Digital Flat Panel Detector (Mars1417XF-CSI). It focuses on establishing substantial equivalence to a predicate device rather than providing acceptance criteria and a detailed study proving the device meets them as a standalone AI/diagnostic device.
The document outlines performance characteristics of the detector itself (e.g., DQE, MTF, spatial resolution) and a "concurrence study" using phantom images, but this is not a clinical study to validate a diagnostic AI or to show human performance improvement.
Therefore, for AI/diagnostic device validation, much of the requested information (like specific acceptance criteria for diagnostic performance, details on test set ground truthing by experts, MRMC studies, or training set details) is not present in the provided text, as this device is a hardware component (a digital X-ray detector).
However, I can extract the relevant information regarding the device's technical specifications and the "concurrence study," and highlight what information isn't available for aspects typically associated with AI/diagnostic device validation.
Here's the breakdown based on the provided text:
Device: Wireless Digital Flat Panel Detector (Mars1417XF-CSI)
Device Type (as per 510(k)): Stationary x-ray system component (Product Code: MQB)
Purpose: Digital imaging solution for general radiographic diagnosis of human anatomy, replacing film/screen systems. Not an AI diagnostic device.
1. A table of acceptance criteria and the reported device performance
The document frames "acceptance criteria" through comparison with a predicate device and established technical parameters for X-ray detectors. It doesn't list explicit pass/fail criteria for clinical diagnostic performance but rather demonstrates comparability of technical specifications.
| Characteristic | Predicate Device (Mars1417V-PSI, K161730) Performance | Proposed Device (Mars1417XF-CSI) Performance | "Acceptance" (Substantial Equivalence Claim) |
|---|---|---|---|
| Technical Specifications | |||
| X-Ray Absorber | Gd2O2S | CsI | Different (but deemed equivalent) |
| Image Matrix Size | 2304 × 2800 pixels | 2336 × 2836 pixels | Different (but deemed equivalent) |
| ADC Digitization | 14 bit | 16 bit | Different (but deemed equivalent) |
| Effective Imaging Area | 355 mm × 434 mm | 350.4 mm × 425.4 mm | Similar |
| Spatial Resolution | Min. 3.4 lp/mm | Min. 3.3 lp/mm | Similar |
| Modulation Transfer Function (MTF) | 0.48 at 1 lp/mm (RQA5) | 0.5 at 1 lp/mm (RQA5) | Similar |
| Detective Quantum Efficiency (DQE) | 0.20 at 1 lp/mm (RQA5, 3.2µGy) | 0.37 at 1 lp/mm (RQA5, 2.5µGy) | Proposed device has higher DQE |
| Power Consumption | Max. 13W | Max. 19W | Different (but deemed acceptable) |
| Communications | Wired: Gigabit Ethernet, Wireless: IEEE 802.11a/b/g/n | Wireless: IEEE 802.11a/b/g/n | Similar (wired option removed) |
| Concurrence Study | |||
| Image Comparison | Baseline | Test images | "No significant difference between images" |
Notes: The "acceptance criteria" here are implicitly meeting the FDA 510(k) standard of substantial equivalence to a predicate device by demonstrating comparable technical performance and safety. The study is not a diagnostic performance study validating an AI algorithm.
2. Sample size used for the test set and the data provenance
- Test Set Size: 30 images
- Data Provenance: The images were described as "Phantom images." The origin (country, retrospective/prospective clinical data) is not specified, as this was a technical performance comparison using phantoms, not clinical data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- This information is not provided as the "concurrence study" used phantom images and focused on the technical image quality comparison, not diagnostic interpretation by human experts to establish ground truth for a diagnostic AI. The statement "No significant difference between the images" implies a qualitative assessment, but details on assessors (number or qualifications) are absent.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable / Not provided. Given it was a "concurrence study" of phantom images, detailed adjudication methods for human diagnostic interpretation are not relevant or described.
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
- No. An MRMC study was not performed. This device is a digital X-ray detector, not an AI-powered diagnostic tool, so a study comparing human reader performance with and without AI assistance is beyond the scope of this 510(k) submission for a hardware component.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. This submission is for an X-ray detector, not a diagnostic algorithm. Therefore, a standalone algorithm performance study was not conducted.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- The ground truth for the "concurrence study" was based on phantom images and comparison to the predicate device's image output, not clinical ground truth like pathology or patient outcomes. The study aimed to demonstrate technical equivalence in image generation.
8. The sample size for the training set
- Not applicable / Not provided. Given this is a hardware device (X-ray detector) and not an AI algorithm, there is no "training set" in the context of machine learning. The device's calibration and manufacturing processes would ensure its performance.
9. How the ground truth for the training set was established
- Not applicable / Not provided. As there is no AI training set, there is no ground truth establishment for such a set.
§ 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.