(74 days)
UniSyn is a software application for image registration and fusion display of scanned image data from CT, PET, SPECT and MR scanners. It is to be used by qualified radiology and nuclear medicine professionals. UniSyn creates multi-planar reformat and maximum intensity projection displays of the data and provides measurements such as area, volume and Standard Uptake Values for user defined regions on the image.
UniSyn is a software only package designed for use on Intel Pentium and higher compatible computers running Microsoft Windows XP and later operating systems. It loads and writes images using a proprietary format.
UniSyn provides the following features:
- manual registration of images, where users can use user interface widgets to align the images in three dimensions;
- automated registration of images from hybrid PET-CT and SPECT-CT scanners, which provide the registration parameters in their image headers;
- multi-planar reformat (MPR) and image triangulation using cursors: linked transverse, sagittal and coronal views. When the user moves a cursor on one view, the corresponding orthogonal planes of the image are computed and displayed on the other.
- image fusion with variable opacity
- Maximum Intensity Projection (MIP)
- 3D Render
- Surface Render
- 2D regions of interest and 2D statistics such as area
- 3D volumes of interest and 3D statistics such as volume, average Standard Uptake Value (SUV) and maximum SUV
- user configurable layouts: type of image (ie which modality and what type of display: one of MIP, MPR/), size, color map, position - can be preconfigured;
- triangulation from MIP image: if the user clicks on the MIP image when it is in the coronal view, the MPR/fusion displays will update their position to that point
- color maps individually assigned for fusion and non-fusion views
- screen capture to clipboard and to disk
The provided text for KO81997 does not contain the detailed information necessary to complete a table of acceptance criteria and reported device performance, nor does it describe a study that explicitly proves the device meets specific acceptance criteria in the manner requested.
Instead, this document is a 510(k) summary for a medical device (UniSyn) seeking clearance based on substantial equivalence to predicate devices, rather than comprehensive performance testing against numerical acceptance criteria.
However, based on the information provided, I can infer some aspects and highlight what is missing.
1. Table of Acceptance Criteria and Reported Device Performance
The 510(k) summary for UniSyn does not define explicit "acceptance criteria" in a quantitative sense (e.g., accuracy percentages, sensitivity/specificity thresholds) or report device performance against such criteria. The document focuses on demonstrating substantial equivalence to predicate devices by comparing features.
Here's an attempt to structure a table based on the provided information, emphasizing the comparison to predicates as the "performance" described:
| Feature/Criterion | Predicate Device(s) (Syntegra, Medical Image Merge) Performance/Presence | UniSyn Performance/Presence | Basis for "Meeting Criteria" |
|---|---|---|---|
| Software Device | ✓ (Present) | ✓ (Present) | Identical feature. |
| Intended Use | Similar | Similar | Similar. |
| Multimodality Registration | ✓ (Present) | ✓ (Present) | Identical feature. |
| Multimodality Fusion Display | ✓ (Present) | ✓ (Present) | Identical feature. |
| Fusion Opacity Control | ✓ (Present) | ✓ (Present) | Identical feature. |
| Regions of Interest | ✓ (Present) | ✓ (Present) | Identical feature. |
| Standard Uptake Value Calc. | ✓ (Present) | ✓ (Present) | Identical feature. |
| Multiplanar Reformat with Triangulation | ✓ (Present) | ✓ (Present) | Identical feature. |
| Maximum Intensity Projection (MIP) | ✓ (Present) | ✓ (Present) | Identical feature. |
| 3D (Surface) Render | ✓ (Present) | ✓ (Present) | Identical feature. |
| Variable Color Maps | ✓ (Present) | ✓ (Present) | Identical feature. |
| Configurable Image Pres. Layouts | ✓ (Present) | ✓ (Present) | Identical feature. |
| PC Hardware Compatibility | ✓ (Present) | ✓ (Present) | Identical feature. |
| Automated Registration (patient outlines/fiducial markers) | ✓ (Present on Syntegra, not on Medical Image Merge) | ✗ (Absent) | Difference noted, but cleared as substantially equivalent. |
| Export of 3D contours for treatment planning | ✓ (Present on Syntegra) | ✗ (Absent) | Difference noted, but cleared as substantially equivalent. |
Important Note: The "acceptance criteria" here are implicitly "having features substantially equivalent to the predicate devices." The document explicitly states: "UniSyn is substantially equivalent to the predicate devices Syntegra and Medical Image Merge, in terms of its image processing and display capability. UniSyn does not introduce any new features or issues of safety and effectiveness."
The following information is largely not present in the provided 510(k) summary for KO81997. The document is for a software device seeking clearance based on substantial equivalence, which typically does not require extensive clinical studies or detailed performance metrics against ground truth like a novel diagnostic algorithm might.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not provided. The document does not describe a specific test set or data used for performance evaluation in the context of clinical accuracy.
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)
- Not provided. Ground truth establishment for a test set is not discussed as no such test set for performance evaluation is detailed.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not provided. No test set or adjudication method is described.
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 conducted/described. This device is an image processing and display software for image fusion, not a diagnostic AI algorithm intended to assist human readers in a comparative effectiveness study. Its purpose is to present existing image data in a fused format, similar to its predicates.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
- Not applicable/described as a standalone performance study. The device is software for image manipulation and display, which inherently relies on user input for tasks like manual registration and region of interest definition. Its "performance" is in its ability to execute these functions as expected, similar to the predicates.
7. The type of ground truth used (expert concensus, pathology, outcomes data, etc)
- Not provided/applicable. Given the nature of the device (image processing/fusion software) and the 510(k) pathway, these types of ground truth for performance evaluation are not discussed. The "ground truth" for this type of device would likely be its success in accurately performing image registration and display functions, which is assessed through technical verification and validation, rather than clinical outcome data.
8. The sample size for the training set
- Does not apply / Not provided. The document does not describe a "training set" in the context of machine learning or AI. UniSyn is described as software that performs image registration and display functions based on programmed algorithms, not trained models.
9. How the ground truth for the training set was established
- Does not apply / Not provided. As there is no described training set, there is no mention of how ground truth would be established for it.
§ 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).