(30 days)
Mars 17 17XF-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.
Mars1717XF-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 (Thin Film Transistor)/PD (Photo Diode) image sensor flat panel of active area: 42.48cm×42.54cm. The sensor plate of Mars1717XF-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 Mars1717XF-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 the iRay Technology Taicang Ltd. "Wireless Digital Flat Panel Detector" (Mars1717XF-CSI) and its substantial equivalence to a predicate device (Mars1417XF-CSI, K182551). The document is a 510(k) summary, which focuses on demonstrating that a new device is "substantially equivalent" to a legally marketed predicate device, rather than proving independent effectiveness through extensive clinical studies.
Therefore, the study supporting the device's acceptance criteria primarily relies on non-clinical tests demonstrating substantial equivalence to a predicate device, not a standalone clinical effectiveness study with human readers or AI performance metrics.
Here's a breakdown based on your request, with the understanding that the "study" referred to is a substantial equivalence comparison:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly list "acceptance criteria" in the traditional sense of performance targets for an AI algorithm. Instead, it compares the proposed device's characteristics and performance metrics to its predicate device to demonstrate substantial equivalence.
| Acceptance Criteria (Proxy: Predicate Device Performance) | Proposed Device Performance (Mars1717XF-CSI) |
|---|---|
| Intended Use: Digital imaging solution for general radiographic diagnosis of human anatomy, replacing film/screen systems in general-purpose diagnostic procedures (excluding mammography or dental). | Same, additionally excludes pediatric, pregnant women, and fluoroscopy. Applicable to usual body parts for adults. |
| X-Ray Absorber (Scintillator): CsI | Same (CsI) |
| Installation Type: Wireless, Portable | Same (Wireless, Portable) |
| Readout Mechanism: Thin Film Transistor | Same (Thin Film Transistor) |
| Image Matrix Size: 2336 × 2836 pixels | 2832 × 2836 pixels (Slight difference due to panel dimension change, considered equivalent) |
| Pixel Pitch: 150μm | Same (150μm) |
| ADC Digitization: 16 bit | Same (16 bit) |
| Effective Imaging Area: 350.4 mm × 425.4 mm | 424.8 mm × 425.4 mm (Larger, but considered equivalent as the change is in panel dimension) |
| Spatial Resolution: Min. 3.3 lp/mm | Same (Min. 3.3 lp/mm) |
| Modulation Transfer Function (MTF) (0.5 at 1 lp/mm): 0.5 at 1 lp/mm | 0.49 at 1 lp/mm (Very close, considered equivalent) |
| Detective Quantum Efficiency (DQE) (RQA5, 2.5µGy): 0.37 at 1 lp/mm | 0.40 at 1 lp/mm (Slightly better, considered equivalent) |
| Power Consumption: Max. 19W | Max. 20W (Very close, considered equivalent) |
| Communications (Wireless functionality): IEEE 802.11a/b/g/n (2.4 GHz / 5 GHz) | Same (IEEE 802.11a/b/g/n) |
| Imaging protect Plate: Carbon Fiber Plate | Same (Carbon Fiber Plate) |
| Cooling: Air cooling | Same (Air cooling) |
| Dimensions: 384 mm × 460 mm × 15 mm | 460 mm × 460 mm × 15 mm (Larger, but considered a dimension change) |
| Operation Temperature: +5 ~ +30°C | Same (+5 ~ +30°C) |
| Operation Humidity: 10 ~ 80% (Non-Condensing) | Same (10 ~ 80% (Non-Condensing)) |
| Operation Atmospheric pressure: 70 ~ 106 kPa | Same (70 ~ 106 kPa) |
| Operation Altitude: Max. 3000 meters | Same (Max. 3000 meters) |
| Storage & Transportation Temperature: -20 ~ +50°C | Same (-20 ~ +50°C) |
| Storage & Transportation Humidity: 10 ~ 90% (Non-Condensing) | Same (10 ~ 90% (Non-Condensing)) |
| Storage & Transportation Atmospheric pressure: 70 ~ 106 kPa | Same (70 ~ 106 kPa) |
| Software: iRay SDK (include iDetector) supplies API interface for DR system manufacturers. | Same |
| Electrical Safety and EMC: Compliance with IEC/ES 60601-1 and IEC/EN 60601-1-2. | All test results meet standard requirements. |
| Biological Evaluation: Materials contacting operators' skin evaluated with ISO 10993-1. | Evaluation results and test results assured safety same as the predicate device. |
| Image Quality (non-clinical): No significant difference in images between devices. | No significant difference reported from non-clinical studies. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not detail specific "test sets" of data as in an AI performance study comparing to a ground truth. Instead, the "test" primarily involved non-clinical performance testing of the device itself (electrical, mechanical, environmental, biological, and technical specifications) and a comparison to the predicate device's established performance.
- Sample Size: Not specified for image evaluation, as it's not a clinical study on a patient cohort. The "non-clinical studies" refer to technical performance evaluations.
- Data Provenance: Not applicable in the context of patient data provenance, as this is a device performance evaluation, not a clinical study on images. The studies were non-clinical tests performed by the manufacturer (iRay Technology Taicang Ltd. in China).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Not applicable. The ground truth here is the technical specifications and performance of the predicate device, against which the proposed device was compared. There was no "ground truth" derived from human experts interpreting images for diagnostic accuracy in this submission for the purpose of a clinical evaluation of the device's diagnostic performance. The submission claims that "There was no significant difference between the images of the Mars1717XF-CSI and those of the predicate device," but this is a statement summarizing non-clinical evaluation findings rather than a detailed expert-driven image review.
4. Adjudication Method for the Test Set
Not applicable, as there was no expert review of images for diagnostic purposes described as a "test set" with adjudication. The evaluation focused on technical specifications and substantial equivalence.
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. This submission is for a conventional digital X-ray flat panel detector, not an AI-powered diagnostic algorithm. Therefore, an MRMC study comparing human readers with and without AI assistance was not conducted or mentioned.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
No. This is a hardware device (flat panel detector), not a standalone AI algorithm.
7. The Type of Ground Truth Used
The "ground truth" for this substantial equivalence submission is primarily the technical and performance characteristics of the legally marketed predicate device (Mars1417XF-CSI, K182551), as well as established international standards for medical electrical equipment (e.g., IEC/ES 60601-1, IEC/EN 60601-1-2, ISO 10993-1). The new device's specifications and test results were compared to these benchmarks.
8. The Sample Size for the Training Set
Not applicable. This is a hardware device; there is no "training set" in the context of machine learning.
9. How the Ground Truth for the Training Set Was Established
Not applicable. There is no training set for this device.
§ 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.