(25 days)
This product is indicated for use in displaying radiological images (including full-field digital mammography and digital breast tomosynthesis) for review, analysis, and diagnosis by trained medical practitioners.
RadiForce RX1270 is a color LCD monitor for viewing medical images including those of mammography. The color panel employs in-plane switching (IPS) technology allowing wide viewing angles and the matrix size (or resolution) is 4.200 x 2.800 pixels (12MP) with a pixel pitch of 0.1554 mm. With the matrix size (or resolution) of 4.200 x 2.800 pixels (12MP), the RX1270 is an optimal replacement for traditional dual head 2,048 x 2,560 pixels (5MP) display installations. Since factory calibrated display modes, each of which is characterized by a specific tone curve (including DICOM GSDF), a specific luminance range and a specific color temperature, are stored in lookup tables within the monitor, the tone curve is e.g. DICOM compliant regardless of the display controller used. There are two model variations, RX1270 and RX1270-AR. The difference of the two variations is the surface treatment of the display screens; the surface treatment of the RX1270 is Anti-Glare (AG) treatment and that of the RX1270-AR is Anti-Reflection (AR) coating. RadiCS is application software to be installed in each workstation offering worry-free quality control of the diagnostic monitors including the RadiForce RX1270 based on the OC standards and guidelines and is capable of quantitative tests and visual tests defined by them. The RadiCS and its subset, RadiCS LE, are included in this 510(k) submission as an accessory to the RadiForce RX1270.
This document describes the EIZO RadiForce RX1270 and RX1270-AR diagnostic displays. It's a 510(k) submission to the FDA, demonstrating substantial equivalence to a predicate device, the RadiForce RX560. The document focuses on the technical specifications and bench testing of a medical display, not an AI-powered diagnostic device. Therefore, much of the requested information regarding AI study design (sample size for test/training sets, data provenance, expert ground truth, adjudication, MRMC studies, standalone performance) is not applicable or cannot be extracted from this document, as it pertains to AI/CADe systems, not display monitors.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't provide a specific table of acceptance criteria with numerical targets and direct performance outcomes for each criterion. Instead, it lists various bench tests performed and makes a general statement about meeting predetermined criteria and equivalence to the predicate device.
| Acceptance Criteria (Implied / General Statement) | Reported Device Performance |
|---|---|
| Spatial resolution (MTF) | Met pre-defined criteria; equivalent to predicate. |
| Pixel defects/faults (maximum number allowed) | Met pre-defined criteria; equivalent to predicate. |
| Absence of miscellaneous artifacts (TG18 guideline) | Met pre-defined criteria; equivalent to predicate. |
| Temporal response | Met pre-defined criteria; equivalent to predicate. |
| Luminance | Met pre-defined criteria; equivalent to predicate. |
| Conformance to DICOM GSDF (TG18 guideline) | Met pre-defined criteria; equivalent to predicate. |
| Angular dependency of luminance response | Met pre-defined criteria; equivalent to predicate. |
| Luminance non-uniformity (TG18 guideline) | Met pre-defined criteria; equivalent to predicate. |
| Chromaticity non-uniformity (TG18 guideline) | Met pre-defined criteria; equivalent to predicate. |
| Luminance stability | Met pre-defined criteria; equivalent to predicate. |
| Noise (NPS) | Met pre-defined criteria; equivalent to predicate. |
| Display reflections (specular, diffuse, haze) | Met pre-defined criteria; equivalent to predicate. |
| Small-spot contrast ratio | Met pre-defined criteria; equivalent to predicate. |
| Pixel aperture ratio | Met pre-defined criteria; equivalent to predicate. |
| Color tracking and Gray tracking | Met pre-defined criteria; equivalent to predicate. |
2. Sample size used for the test set and the data provenance
- Sample Size for Test Set: Not applicable. This document describes bench testing of a hardware device (display monitor), not a study involving patient data or images. The "test set" would refer to the physical display units tested.
- Data Provenance: Not applicable in the context of imaging data. The tests were performed according to "Guidance for Industry and FDA Staff: Display Devices for Diagnostic Radiology" and AAPM Task Group 18 (TG18 guideline).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. Ground truth, in this context, would relate to the accuracy of diagnostic interpretations by a human or AI system. This document concerns the performance characteristics of a display monitor as a tool, not its diagnostic output. Its performance is measured against established physical and photometric standards.
4. Adjudication method for the test set
Not applicable. Adjudication methods are relevant for resolving discrepancies in expert interpretations of medical images, which is not the subject of this document.
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 document does not mention any MRMC comparative effectiveness study, nor does it discuss AI assistance. The subject is a medical display monitor.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
No. This document does not describe any algorithm or AI system, standalone or otherwise.
7. The type of ground truth used
For the bench tests, the "ground truth" is established by physical standards and technical specifications for display performance, such as:
- TG18 guideline (AAPM Task Group 18)
- DICOM GSDF (Grayscale Standard Display Function)
- Manufacturer's internal specifications and design targets for parameters like resolution, luminance, contrast ratio, etc.
8. The sample size for the training set
Not applicable. This is not an AI/machine learning device; therefore, there is no "training set."
9. How the ground truth for the training set was established
Not applicable. As there is no training set for an AI model, there is no ground truth established for it.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).