Search Results

This product is intended to be used in displaying and viewing digital images, including standard and multi-frame digital mammography, for review, and diagnosis by trained medical practitioners. It is specially designed for breast tomosynthesis applications.

RadiForce GX540 is a monochrome LCD monitor for viewing medical images including those of mammography. The monochrome panel employs in-plane switching (IPS) technology allowing wide viewing angles and the matrix size (or resolution) is 2,048 x 2,560 pixels (5MP) with a pixel pitch of 0.165 mm.

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, GX540-CL and GX540-CLAR (GX540 without any suffix does not exist). The difference of the two variations is the surface treatment of the display screens; the surface treatment of the GX540-CL is Anti-Glare (AG) treatment and that of the GX540-CLAR is Anti-Reflection (AR) coating. The suffix common to the both variations, " - CL", means that the tint of the backlight is Clear Base (vs. Blue Base, another popular tint slightly bluish).

RadiCS is application software to be installed in each workstation offering worry-free quality control of the diagnostic monitors including the RadiForce GX540 based on the OC standards and guidelines and is capable of quantitative tests and visual tests defined by them. The RadiCS is included in this 510(k) submission as an accessory to the RadiForce GX540.

The provided document is a 510(k) premarket notification for the EIZO RadiForce GX540 5MP Monochrome LCD Monitor. This document is a submission to the FDA for a medical display device, not an AI/ML-driven diagnostic device. Therefore, many of the requested criteria often associated with AI/ML device studies (such as sample sizes for test/training sets, number/qualifications of experts, adjudication methods, MRMC studies, standalone performance, and ground truth types) are not applicable or typically reported in this type of submission for a display monitor.

However, I can extract and present the available information related to acceptance criteria and performance testing for this device.

Acceptance Criteria and Reported Device Performance

Device: EIZO RadiForce GX540 5MP Monochrome LCD Monitor

Study Proving Acceptance Criteria:

The device's performance was evaluated through Bench Testing and Clinical Testing.

The bench tests were performed following instructions in the "Guidance for Industry and FDA Staff: Display Accessories for Full-Field Digital Mammography Systems-Premarket Notification (510(k)) Submissions" and the AAPM Task Group 18 (TG18 guideline) for assessing display performance.

The clinical testing aimed to assess the image quality of tomosynthesis images on the proposed device compared to the predicate device.

Additional Requested Information:

1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

   • Bench Testing: No sample size is explicitly stated for images or data sets. The tests are focused on the physical characteristics and performance of the monitor itself (e.g., luminance, contrast, resolution, temporal response).
   • Clinical Testing: The document states the goal was to "assess the image quality of tomosynthesis images," but it does not specify the number of images or cases used for this assessment. The data provenance (country of origin, retrospective/prospective) is also not provided.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Bench Testing: Ground truth is not applicable in the traditional sense for these technical display measurements. The "pre-defined criteria" for bench tests are based on established guidelines (FDA Guidance, TG18).
   • Clinical Testing: The document states the clinical testing evaluated "viewing tomosynthesis images, especially lesions like masses, microcalcifications and architectural distortions within the images." This implies evaluation by medical practitioners, but the number or qualifications of these "trained medical practitioners" who assessed the images are not mentioned.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • Not specified or applicable for either the bench or clinical testing described.

4. 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:

   • An MRMC study was done in the sense that medical practitioners evaluated images on the proposed device versus the predicate device. However, this study was not an AI-assisted study. It was a comparison of display monitors. The document states: "The results of the testing indicated that the proposed device is at least equivalent to the predicate device for viewing tomosynthesis images, especially lesions like masses, microcalcifications and architectural distortions within the images." No effect size related to AI assistance is applicable or reported.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • Not applicable, as this is a medical display monitor for human viewing, not an algorithm.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

   • Bench Testing: The ground truth is the physical measurement against set technical standards (e.g., DICOM GSDF, TG18 guidelines).
   • Clinical Testing: The "ground truth" implicitly relies on the subjective assessment of image quality by "trained medical practitioners" for identifying lesions. No objective ground truth like pathology or outcomes data is mentioned as being used to validate these visual assessments in the clinical test.

7. The sample size for the training set:

   • Not applicable. This is a display monitor, not an AI/ML device that requires a training set.

8. How the ground truth for the training set was established:

   • Not applicable.

Ask a specific question about this device

This product is intended to be used in displaying digital images including those of digital mammography for review and analysis by trained medical practitioners.

RadiForce GX540 is a monochrome LCD monitor for viewing medical images including those of mammography. The monochrome panel employs in-plane switching (IPS) technology allowing wide viewing angles and the matrix size (or resolution) is 2,048 x 2,560 pixels (5MP) with a pixel pitch of 0.165 mm. 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. Model variations with cosmetic differences are distinguished by characters attached to the name of the base model "GX540" such as "GX540-CLAR", a model whose backlight is Clear Base with an Anti-Reflective coating on the screen surface although the hardware design, components and labeling remain unchanged. RadiCS is application software to be installed in each workstation offering worry-free quality control of the diagnostic monitors including the RadiForce GX540 based on the QC standards and guidelines and is capable of quantitative tests and visual tests defined by them. The RadiCS is included in this 510(k) submission as an accessory to the RadiForce GX540.

The provided text describes a 510(k) premarket notification for a medical display monitor, the Eizo RadiForce GX540. It focuses on demonstrating substantial equivalence to a predicate device (RadiForce GX530) rather than providing extensive details about acceptance criteria and a study proving the device meets those criteria, which would typically be found in a clinical or performance study report for an AI/software device.

However, based on the performance testing section, we can infer some details and present them in the requested format, acknowledging where information is not explicitly provided.

Here's an analysis of the provided text in relation to your questions:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly state "acceptance criteria" but rather lists "performance testing" conducted to verify the device's characteristics, especially where it differs from the predicate device (backlighting). The performance details are presented as verification of conformance to established guidelines and measurements.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

This information is not provided in the document. The tests were bench tests on the device itself, not image data.

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)

This information is not applicable/not provided as the tests were technical measurements of display performance characteristics, not an assessment of medical images by experts. The "visual check" of artifacts likely refers to technical personnel inspecting the display, guided by the TG18 guideline, rather than medical experts establishing a "ground truth" for patient diagnosis.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

This information is not applicable/not provided. The tests involved objective measurements against established technical standards (like DICOM GSDF and AAPM TG18 guidelines), not expert adjudication of diagnostic findings.

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 comparative effectiveness study was not done. This device is a medical display monitor, not an AI or CAD system designed to assist human readers in image interpretation. The study focused on the display's technical performance characteristics.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

No, this is not applicable. The device is a display monitor, not an algorithm. The "standalone" performance here would refer to the monitor's technical specifications and performance, which were indeed tested.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

The "ground truth" in this context refers to established technical standards and industry guidelines. Specifically:

• DICOM GSDF (Grayscale Standard Display Function): A standardized luminance response curve essential for consistent medical image display.
• AAPM Task Group 18 (TG18) guideline: A comprehensive set of recommendations and test patterns for assessing the performance of medical displays.

These are objective, measurable technical standards, not clinical "ground truth" derived from patient data.

8. The sample size for the training set

This information is not applicable/not provided. This is a hardware device (display monitor), not a machine learning algorithm that requires a training set.

9. How the ground truth for the training set was established

This information is not applicable/not provided. As above, there is no training set for a display monitor.

Ask a specific question about this device