(56 days)
HMD3C21S : The 3MP Color LCD Monitor HMD3C21S is indicated for use in displaying radiological images for review, and diagnosis by trained medical practitioners. The display is not intended for mammography.
HMD5G21S : The 5MP Monochrome LCD Monitor HMD5G21S is intended to be used in displaying and viewing medical images for diagnosis by trained medical practified personnel. It is intended to be used in digital mammography PACS, digital breast tomosynthesis and modalities including FFDM.
The LCD monitor employs high-luminance LCD panel, and is designed for medical image display.
This document describes the performance assessment of medical LCD monitors (HMD3C21S and HMD5G21S) for displaying radiological images. It is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices rather than proving clinical effectiveness of an AI algorithm. Therefore, many of the requested elements typically found in AI/ML medical device evaluations (like sample sizes for training/test sets, expert adjudication, MRMC studies, or specific performance metrics using AI) are not applicable or available in this submission.
The "acceptance criteria" here refers to the performance benchmarks for a medical display, ensuring it meets standards for diagnostic imaging. The "study that proves the device meets the acceptance criteria" refers to the bench testing performed on the monitors.
Here's the breakdown based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document lists various physical laboratory measurements performed on the monitors to ensure they meet the display requirements. The acceptance criteria are implicit in the tests performed, aiming for performance comparable to existing medical displays. The reported performance is generally "By reporting [method]" or "Measure the [property]", indicating that these measurements were taken rather than providing specific numerical results for each one. This type of submission focuses on demonstrating that the testing was done according to recognized standards.
Implicit Acceptance Criteria (based on tests performed): The monitors must demonstrate adequate performance across these parameters consistent with established medical display standards (e.g., AAPM-TG18, IEC).
| Measurements | HMD3C21S Performance | HMD5G21S Performance |
|---|---|---|
| a. Spatial resolution | By reporting modulation transfer function. | By reporting modulation transfer function. |
| b. Pixel defects (maximum counts, allowed defect types, and locations) | Maximum number allowed for each type. | Maximum number allowed for each type. |
| c. Artifacts | Crosstalk and Ghost. | Crosstalk and Ghost. |
| d. Temporal response | Measure the rise and fall time constants for 5 – 95% and 40 - 60% luminance transitions. | Measure the rise and fall time constants at several (e.g. every 15 levels) grayscale intervals between 0 and 255. |
| e. Luminance (maximum, minimum, achievable, and recommended) | Measure the maximum, minimum, achievable, and recommended luminance. | Measure the maximum, minimum, achievable, and recommended luminance. |
| f. Conformance to a gray scale-to-luminance function (for example, DICOM GSDF) | Luminance Response by AAPM-TG18. | Luminance Response by AAPM-TG18. |
| g. Luminance at 30° and 45°in diagonal horizontal, and vertical directions at center and four corners | NA | By AAPM TG18. |
| h. Luminance uniformity or Mura test | NA | Luminance uniformity and Chromaticity uniformity by AAPM TG18. |
| i. Stability of luminance and chromaticity response with temperature and time of operation or on-time | NA | By AAPM TG18. |
| j. Spatial noise | NA | By noise power spectrum. |
| k. Reflection coefficient | NA | By specular reflection coefficient and diffuse reflection coefficient. |
| I. Veiling glare or small-spot contrast | NA | By AAPM TG18. |
| m. Color tracking (primary colors and color gamut) | Measure the primary colors and color gamut. | NA, HMD5G21S employs gray scale LCD panel. |
| n. Gray tracking (gray shades and white points) | NA | Measure the maximum chromaticity variation by IEC. |
2. Sample size used for the test set and the data provenance
- Test Set Sample Size: Not explicitly stated as a "sample size" in the context of diagnostic performance testing with cases. This submission is for a medical monitor, not an AI diagnostic algorithm. The "testing" refers to the physical bench testing of the device itself.
- Data Provenance: No patient data or clinical images are referenced for the performance testing of the monitor. The testing relates to the physical characteristics and display capabilities of the monitor hardware.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not Applicable. This document is for a medical display device, not an AI algorithm that requires setting ground truth for image interpretation. The "ground truth" for a monitor's performance is established by objective physical measurements against industry standards (e.g., AAPM-TG18).
4. Adjudication method for the test set
- Not Applicable. As no diagnostic performance with images and human readers is being evaluated, no adjudication method is relevant.
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. This is a medical monitor, not an AI-powered diagnostic device. No MRMC studies were conducted as part of this submission.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not Applicable. This is a monitor, not an algorithm. Therefore, standalone performance (in the context of an algorithm's diagnostic output) is irrelevant.
7. The type of ground truth used
- Objective Physical Measurements against Industry Standards. The "ground truth" for a display device is its adherence to performance specifications and established industry standards (e.g., DICOM GSDF, AAPM-TG18), verified through physical and optical measurements using specialized equipment.
8. The sample size for the training set
- Not Applicable. This device is a medical monitor, not an AI/ML algorithm that requires a training set.
9. How the ground truth for the training set was established
- Not Applicable. As there is no training set for an AI algorithm, no ground truth needed to be established in that context.
§ 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).