(235 days)
The 3MP Color LCD Display UMD3-21B01) is indicated for use in displaying radiological images for review, analysis, and diagnosis by trained medical practitioners. The display is not intended for mammography.
UMD3-21B01 (MD3-21B01) is a 3 mega pixels 21.3" color LCD display for viewing medical images, not including mammography. The resolution of the display is 1,536 x 2,048 pixels (3MP) with a pixel pitch of 0.2115 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 MD-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 Mange is a PC application for managing a group of displays.
The provided text describes a 510(k) submission for a medical display device, the 21.3" 3MP Color LCD Display UMD3-21B01 (MD3-21B01). This document focuses on demonstrating substantial equivalence to a predicate device, rather than proving that an AI/ML algorithm meets acceptance criteria through a specific study design (e.g., MRMC).
The document is about a display device, not an AI/ML algorithm. Therefore, many of the requested criteria (e.g., sample size for test/training sets, number of experts for ground truth, adjudication method, MRMC study, standalone algorithm performance) are not applicable to the type of device described.
However, I can extract information related to the performance data and the "acceptance criteria" as they apply to a display device being cleared for diagnostic imaging.
Here's an interpretation of the performance data that can be framed as "acceptance criteria" for a medical display device, based on the provided text:
Acceptance Criteria and Reported Device Performance for a Medical Display Device
Since the device is a medical display, the acceptance criteria relate to its image quality and conformance to standards relevant for medical imaging. The performance data section describes tests performed to ensure the display meets these expectations.
1. A table of acceptance criteria and the reported device performance
The document doesn't explicitly list "acceptance criteria" as pass/fail thresholds for each test, but rather describes the measurements taken and implies that the device performed adequately to demonstrate substantial equivalence. The predicate device's specifications act as an implicit benchmark for many of these performance characteristics.
| Acceptance Criterion (Test Performed) | Reported Device Performance (UMD3-21B01) | Comparison/Context (Predicate Device) |
|---|---|---|
| Measurement of spatial resolution (MTF) | Performed as per "Guidance for Industry..." | Not explicitly stated for predicate in comparison table, but general expectation for diagnostic displays. |
| Measurement of pixel aperture ratio | Performed as per "Guidance for Industry..." | Not explicitly stated for predicate. |
| Maximum number allowed for each type of pixel defects/faults | Addressed as per "Guidance for Industry..." | Not explicitly stated for predicate. |
| Visual check of miscellaneous artifacts (TG18 guideline) | Assessed as per AAPM TG18 guideline | Not explicitly stated for predicate. |
| Measurement of temporal response | Performance data provided by Innolux (LCD panel vender) | Predicate device's response time is 25ms (On/Off), proposed device is also 25ms (On/Off). |
| Measurements of maximum and minimum luminance | Performed as per "Guidance for Industry..." | Predicate device's brightness (typical) is 1,000cd/m2, recommended brightness for is 500cd/m2. Proposed device matches these specifications. |
| Verification of DICOM GSDF conformance (TG18) | Verified as specified in TG18; tone curve is DICOM compliant. | Not explicitly stated for predicate in comparison table, but implicit for a medical display. "AcuCal-Pro" (firmware) on proposed device ensures DICOM conformance, |
| predicate uses "Beacon Monitor Manage". Both achieve appropriate calibration for medical image viewing. | ||
| Measurement of angular dependency of luminance response | Performed in horizontal, vertical, and diagonal directions | Predicate device's viewing angle is Horizontal: Typ.178, Vertical: Typ.178. Proposed device matches this. |
| Measurement of chromaticity non-uniformity (TG18) | Performed as specified in TG18 guideline | Display type is Color (IPS) for both, so uniformity is expected. |
| Contrast Ratio (typical) | 1500:1 | Predicate device also 1500:1. |
| Display Colors | 10-bit (DisplayPort): 1.073 billion (1024 from a palette of 16,384 tones), 8-bit (DVI): 16.77 million (256 from a palette of 16,384 tones) | Predicate device has identical display color capabilities. |
| Quality-control Software | AcuCal (AcuCal-Pro firmware, AcuCal Manage PC app) performs luminance calibration and quality control (DICOM conformance). | Predicate device uses "Beacon Monitor Manage". Both serve similar quality control functions, "different design scheme" but no impact on safety/effectiveness. |
| Sensors | Backlight sensor, Integrated front sensor, Ambient light sensor | Predicate device has identical sensors. |
| Luminance calibration tools | Integrated optical sensor, External optical sensor, Calibration software: AcuCal-Pro | Predicate device has Integrated optical sensor, External optical sensor, Calibration software: Beacon Monitor Manage. "Different design scheme" but no impact on safety/effectiveness. |
2. Sample size used for the test set and the data provenance
The document does not detail a "test set" in the context of an AI/ML algorithm. Instead, it describes performance tests conducted on the physical display device itself. The provenance of this performance "data" would be the manufacturing site (Taiwan, where ACULA Technology Corp. is located) and the testing procedures applied to the specific model (UMD3-21B01/MD3-21B01). It is device performance testing, not clinical data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This is not applicable as the submission is for a medical display, not an AI/ML diagnostic tool that requires ground truth established by experts. The "ground truth" for a display is its physical performance characteristics measured against industry standards (e.g., DICOM GSDF, AAPM TG18).
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. This is for an AI/ML algorithm's performance on a dataset, not a display's physical performance verification.
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 not an AI/ML device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. This is not an AI/ML device.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
The "ground truth" for the display's performance is established by physical measurement standards and industry guidelines, such as the DICOM GSDF (Grayscale Standard Display Function) and AAPM Task Group 18 (TG18) guidelines. These are objective, quantifiable standards for display performance in medical imaging.
8. The sample size for the training set
Not applicable. The device is a display, not an AI/ML algorithm that requires a training set.
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).