(16 days)
UMD5-21B01 is indicated for use in displaying radiological images (including full-field digital breast tomosynthesis) for review, analysis, and diagnosis by trained medical practitioners.
UMD5-21B01 is a 5 mega pixels 21.3" color LCD display for viewing medical images including mammography and digital breast tomosynthesis. The resolution of the display is 2,048 x 2,560 pixels (5MP) with a pixel pitch of 0.165 mm and wide angle LCD technology (IPS) support Dual-link DVI and Displayport signals from workstation or personal computer.
Since factory calibrated 3 display modes, each of which is characterized by a specific curve (including DICOM GSDF), a specific luminance range and a pre-defined color temperature, are stored in Lookup Table (LUT) within the display, the tone curve is e.g. DICOM compliant regardless of the display controller used.
AcuCal, a general name for the calibration and quality control functions of UMD-series product, includes corresponding firmware (AcuCal-Pro) and management application of PC (AcuCal Manage). AcuCal-Pro is the controlling firmware of this LCD display. AcuCal-Pro can perform the luminance calibration without PC or workstation and also includes the quality control scheme to make sure display quality, especially DICOM conformance. AcuCal Manage is a PC application for managing a group of displays.
The provided text is a 510(k) summary for a medical display device (ACULA Technology Corp.'s UMD5-21B01). This document describes the device, its intended use, and compares it to a predicate device to establish substantial equivalence.
However, the nature of this document (a 510(k) summary for a display device) means that it does not include the type of detailed clinical study information typically associated with AI/ML-based medical devices or devices that generate diagnostic assessments needing complex acceptance criteria and ground truth establishment.
Instead, the performance data section focuses on bench tests related to the display's technical characteristics, such as spatial resolution, luminance, contrast, and DICOM conformance. These tests are conducted to ensure the display accurately presents medical images as per industry standards (like TG18 guidelines), which is a different kind of "acceptance criteria" than what would be applied to an AI algorithm predicting disease.
Therefore, many of the specific questions you asked (e.g., sample size for test set, number of experts for ground truth, MRMC studies, standalone performance of an algorithm, training set size) are not applicable to this device and the information provided in this 510(k) summary.
I will fill in the table and address the relevant points based on the provided text, indicating "Not Applicable" or "Not Provided" where the information does not exist for this type of device and submission.
Acceptance Criteria and Study Details for UMD5-21B01 Display Device
1. Table of Acceptance Criteria and Reported Device Performance
As this is a display device, the acceptance criteria relate to its imaging performance characteristics rather than diagnostic accuracy measures (like sensitivity/specificity for an AI algorithm). The document refers to "bench tests" and conformance to "TG18 guideline" and "DICOM GSDF." The table below summarizes the types of measurements performed, which serve as the "acceptance criteria" and the reported "performance" is that the device meets these standards (implicitly, as it gained clearance).
| Acceptance Criteria (Bench Test Type) | Reported Device Performance (Implicitly Met for Clearance) |
|---|---|
| Measurement of spatial resolution (MTF) | Performed; Conforms to standards (e.g., TG18) |
| Measurement of pixel aperture ratio | Performed; Conforms to standards (e.g., TG18) |
| Maximum allowed number for each type of pixel defects/faults | Performed; Conforms to standards (e.g., TG18) |
| Visual check of presence or absence of miscellaneous artifacts | Performed; Conforms to standards (e.g., TG18) |
| Measurement of temporal response | Performed; Data provided by Innolux |
| Measurements of maximum and minimum luminance | Performed; Achievable values verified |
| Verification of DICOM GSDF conformance | Performed; Conforms to DICOM GSDF (TG18 guideline) |
| Measurement of angular dependency of luminance response | Performed; Conforms to standards (e.g., TG18) |
| Measurement of noise (NPS) | Performed; Conforms to standards (e.g., TG18) |
| Measurement of display reflections (specular, diffuse, glare) | Performed; Conforms to standards (e.g., TG18) |
| Measurement of small-spot contrast ratio | Performed; Conforms to standards (e.g., TG18) |
| Measurement of chromaticity non-uniformity characteristics | Performed; Conforms to standards (e.g., TG18) |
| Measurement of luminance non-uniformity characteristics | Performed; Conforms to standards (e.g., TG18) |
2. Sample size used for the test set and the data provenance
- Sample Size: Not applicable in the context of image data for diagnostic performance. The "test set" here refers to the device itself undergoing various physical and photometric measurements. Typically, a single production unit or a small number of units are tested to confirm design specifications.
- Data Provenance: Not applicable. The tests are bench tests of the display hardware and its performance, not studies on image data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable. Ground truth as typically defined for AI algorithms (e.g., disease presence) is not established for a display device. The "ground truth" for these tests are objective physical measurements against established industry standards (like TG18 guidelines).
4. Adjudication method for the test set
- Not applicable. As no human interpretation of images for ground truth labeling is involved, there is no need for 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. This is a display device, not an AI-assisted diagnostic tool. No MRMC study was performed or needed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. This is a display device, not a standalone algorithm. The "performance" is its ability to accurately display images, which is assessed through bench testing.
7. The type of ground truth used
- Not applicable in the sense of clinical ground truth (e.g., pathology, outcomes). The "ground truth" for the device's technical performance is defined by established industry standards, measurement protocols (e.g., AAPM TG18), and physical metrology.
8. The sample size for the training set
- Not applicable. This is a display device, not an AI system that undergoes training.
9. How the ground truth for the training set was established
- Not applicable.
§ 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).