(89 days)
The use of SplitScreen is indicated whenever two images are required to be shown together side-by-side in a single image/display, and a high-line rate (e.g., 1049 lines @ 30 frames/sec or 1249 lines @ 25 fps) video signal is required. . . Examples include conversion / combining of X-ray (stationary, C-arm, angiography, etc.), nuclear medicine, magnetic resonance, and/or ultrasound images either directly from their source, or from an intermediate storage device (like a video tape or video disk), for use on display monitors, optical, tape, disk, or other apparatus requiring a high-line rate video signal.
SplitScreen is a digital image processing systems that can display 2 pictures side-by-side on a single video monitor. Additionally, SplitScreen has provisions for video scan rate conversion. SplitScreen accepts two input signals at various scan rates, and it outputs video at high-line rate. Both images share the full video frame by splitting them with a vertical boundary. The position of the boundary can be adjusted right or left (thus adjusting the relative amounts of each image viewed), and each image can be panned horizontally within each split area. The result is two images, each of which is full height but cropped horizontally. The output composite image is compatible with high-resolution monitors capable of displaying high-line rate video which is compatible with EIA standard RS-343A.
The Merlin Engineering Works, Inc. SplitScreen (Model ME-975) is a digital image processing system that can display two pictures side-by-side on a single video monitor and provides video scan rate conversion.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Meets appropriate requirements of RS-170 and RS-343A standards for specific signals. | The data demonstrates that SplitScreen meets these standards, as appropriate to the specific signal, as is the case for the predicate devices. |
| Correctly compensates for aspect ratio changes in accordance with SMPTE RP-133 requirements for the selected scan conversion. | The system correctly compensates for aspect ratio changes in accordance with the requirements of the particular scan conversion selected. |
| Permits low-contrast imaging resolution at the 1% level. | The system permits low-contrast imaging resolution at the 1% level. |
| Electrically compatible with industry standard monochrome video signals. | SplitScreen is electrically compatible with industry standard monochrome video signals. |
| Preserves image quality (within the limits of standard video technology and selected line rates). | The image quality is preserved (within the limits of standard video technology and the line rates selected). |
| Functionality to convert and combine X-ray (stationary, C-arm, angiography, etc.), nuclear medicine, magnetic resonance, and ultrasound images, directly from source or intermediate storage, for display on monitors or other apparatus requiring a high-line rate video signal. | The intended use for SplitScreen is conversion and combining of X-ray (stationary, C-arm, angiography, etc.), nuclear medicine, magnetic resonance, and ultrasound images either directly from their source, or from an intermediate storage device (like a video tape or video disk), for use on display monitors, optical, tape, disk, or other apparatus requiring a video signal. The device is indicated whenever two images are required to be shown together side-by-side in a single image/display, and a high-line rate video signal is required. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size of images or video signals used for testing. The testing described focuses on evaluating the device's technical specifications and adherence to industry standards rather than a clinical performance study with a 'test set' in the typical sense of medical image analysis. No information on data provenance (country of origin, retrospective/prospective) is provided.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
Not applicable. The performance tests described are technical validations against established video standards (RS-170, RS-343A, SMPTE RP-133) rather than a clinical study requiring expert ground truth annotations for medical images.
4. Adjudication Method for the Test Set
Not applicable. As noted above, the validation involved technical adherence to standards, not human adjudication of medical image interpretations.
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 MRMC comparative effectiveness study was done. The SplitScreen device is a video processing system, not an AI-powered diagnostic tool, and therefore, its performance is not evaluated in terms of improving human reader effectiveness with AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone performance evaluation was conducted. The device was tested to ensure it met specific technical standards (RS-170, RS-343A, SMPTE RP-133) and maintained image quality and electrical compatibility without human interaction or interpretation as part of the core performance validation.
7. The Type of Ground Truth Used
The "ground truth" for the performance tests was based on established industry standards and specifications for video signals and image display, specifically:
- RS-170 and RS-343A: Standards for analog video signals.
- SMPTE RP-133: Recommended practice for aspect ratio compensation.
- 1% low-contrast imaging resolution: A quantitative performance metric.
- Electrical compatibility: Adherence to defined electrical characteristics for monochrome video signals.
8. The Sample Size for the Training Set
Not applicable. The SplitScreen device is a video hardware/firmware processing system, not a machine learning or AI model, thus no "training set" in the context of AI development was used.
9. How the Ground Truth for the Training Set was Established
Not applicable. As there is no training set, there is no ground truth established for it.
§ 892.2020 Medical image communications device.
(a)
Identification. A medical image communications device provides electronic transfer of medical image data between medical devices. It may include a physical communications medium, modems, and interfaces. It may provide simple image review software functionality for medical image processing and manipulation, such as grayscale window and level, zoom and pan, user delineated geometric measurements, compression, or user added image annotations. The device does not perform advanced image processing or complex quantitative functions. This does not include electronic transfer of medical image software functions.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 892.9.