(30 days)
Mars1417XF-GSI 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-GSI 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-GSI Wireless Digital Flat Panel Detector is direct-deposited with Gd2O2S 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-GSI 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 document is a 510(k) summary for a medical device called the "Wireless Digital Flat Panel Detector" (Model: Mars1417XF-GSI). This document primarily focuses on demonstrating substantial equivalence to a predicate device (Mars1417V-PSI, K161730) rather than presenting a detailed study with acceptance criteria for an AI/CAD algorithm.
The device itself is a digital X-ray detector, not an AI or CAD system that provides diagnostic assistance. Therefore, many of the requested criteria such as "effect size of how much human readers improve with AI vs without AI assistance" or "adjudication method" for establishing ground truth for an AI algorithm are not applicable to the information provided.
However, I can extract information related to the technical performance of the device, which can be seen as acceptance criteria for its physical characteristics and image quality, and how it was tested.
Here's a breakdown based on the information available:
1. A table of acceptance criteria and the reported device performance:
The document doesn't explicitly state "acceptance criteria" in a typical clinical study sense for an AI device. Instead, it compares the technical characteristics of the proposed device to its predicate device to demonstrate substantial equivalence. These technical characteristics can be considered as performance metrics that, when similar or improved, demonstrate "acceptance" in the context of a 510(k) submission.
| Characteristic | Predicate Device (Mars1417V-PSI) Performance | Proposed Device (Mars1417XF-GSI) Performance |
|---|---|---|
| Image Matrix Size | 2304 × 2800 pixels | 2336 × 2836 pixels |
| Pixel Pitch | 150μm | Same (150μm) |
| ADC Digitization | 14 bit | 16 bit |
| Effective Imaging Area | 355 mm × 434 mm | 350.4 mm × 425.4 mm |
| Spatial Resolution | Min. 3.4lp/mm | Min. 3.3lp/mm |
| Modulation Transfer Function (MTF) | 0.75 at 0.5lp/mm | 0.84 at 1 lp/mm |
| Detective Quantum Efficiency (DQE) | 0.27 at 0.5 lp/mm (RQA5, 3.2μGy) | 0.43 at 1 lp/mm (RQA5, 2.5μGy) |
| Power Consumption | Max. 13W | Max. 19W |
| Communications | Wired: Gigabit Ethernet, Wireless: IEEE 802.11a/b/g/n | Wireless: IEEE 802.11a/b/g/n |
| Dimensions | 384 mm × 460 mm × 15 mm | Same (384 mm × 460 mm × 15 mm) |
| Operating Temperature | +5 ~ +35°C | +5 ~ +30°C |
| Operating Humidity | 30 ~ 75% (Non-Condensing) | 10 ~ 80% (Non-Condensing) |
| Storage/Transportation Temperature | -20 ~ +55°C | -20 ~ +50°C |
| Storage/Transportation Humidity | 10 ~ 90% (Non-Condensing) | 10 ~ 90% (Non-Condensing) |
Note: The "acceptance criteria" for these are generally that the proposed device performs comparably or better, demonstrating that the changes do not negatively impact safety or effectiveness. For some parameters, like ADC Digitization, the proposed device shows an improvement (16 bit vs 14 bit).
2. Sample size used for the test set and the data provenance:
The document describes non-clinical studies focused on the physical and performance attributes of the detector itself, not on analyzing patient data with an algorithm. Therefore, there isn't a "test set" of patient images in the context of an AI algorithm evaluation.
The non-clinical studies performed include:
- Electrical Safety and EMC testing (IEC/ES 60601-1, IEC 60601-1-2)
- Biological Evaluation (ISO 10993-1)
- Evaluation of detector characteristics: Detective quantum efficiency (DQE), Quantum limited performance, Modulation transfer function (MTF), Effects of aliasing, Sensitivity linearity, Lag, Change in detection sensitivity, Dose requirement and reciprocity changes, Stability of device characteristics with time, Uniformity of device characteristic, Noise power spectrum (NPS), Spatial resolution, Image Acquisition time, and Black level.
The "sample size" for these technical tests would refer to the number of devices or components tested, which is not specified but is typically a small number for device verification. The data provenance would be laboratory testing data, not patient data from specific countries.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable, as this is not an AI/CAD device being evaluated on clinical images by human experts. The "ground truth" for the technical performance metrics (e.g., DQE, MTF) is established through standardized physical measurements and calculations.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable, as there is no clinical test set requiring expert adjudication.
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:
Not applicable. The device is a digital X-ray detector, not an AI or CAD system designed to assist human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Not applicable. The device itself is the "standalone" component in the sense that it converts X-rays to digital images without an AI algorithm for diagnostic interpretation. The document explicitly states that the device is a "key component of DR system, enables to complete the digitalization of the medical X-ray imaging with the DR system software."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
For the evaluation of the detector's image quality and physical performance, the "ground truth" is established through physical measurements and calculations using standardized methods (e.g., for DQE, MTF, spatial resolution). These are objective technical metrics, not clinical ground truth like pathology or expert consensus.
8. The sample size for the training set:
Not applicable. This device is an X-ray detector, not a machine learning model that requires a training set. The "software" mentioned (iRay DR and iRay SDK) are for device control, image acquisition, and processing, not for AI-based interpretation.
9. How the ground truth for the training set was established:
Not applicable (see point 8).
§ 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.