(156 days)
Acquire, store, transmit, and display medical images and patient reports of various types. Teleradiology image acquisition, distribution, archive and viewing.
The IiVS™ Integrated image Viewing Station is a product family, which comes in two different versions: DiVS: a DICOM viewer IiVS: a 3D viewer. The intended use of the devices is to provide solutions to various medical image-viewing problems, which come about as the modalities generate more and more images. They also support image distribution over networks, and are DICOM conformant. Finally, the IIVS™ Integrated image Viewing Station family supports the radiologist in writing a report, and transmitting and storing this report in digital form.
The provided text describes a 510(k) premarket notification for the TeraRecon IiVS™ Integrated Image Viewing Station (K994329). This document primarily focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed study proving the device meets specific acceptance criteria with quantifiable performance metrics.
Therefore, much of the requested information regarding acceptance criteria, study details, sample sizes, ground truth establishment, and MRMC studies is not explicitly available in the provided text.
However, I can extract and infer some information based on the document's content, particularly from the "Performance Standards" section and the "Comparison Table."
Here's the information that can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of acceptance criteria with corresponding reported performance metrics in the way a typical clinical study would. Instead, it relies on demonstrating compliance with standards and comparing features to a predicate device.
Inferred "Acceptance Criteria" (based on compliance and comparison):
| Acceptance Criteria Category | Specific Criteria (Inferred from documentation) | Reported Device Performance (Inferred from documentation) |
|---|---|---|
| Voluntary Standards | Compliance with DICOM 3 Query and Retrieve | "Compliance with DICOM 3 Query and Retrieve" |
| Compliance with ISO/IEC 12207:1995 (Software Life Cycle) | Software designed to control and manipulate images follows this standard. | |
| Hardware Requirements | Execute on Silicon Graphics SGI-320 and 540 and VW 320/540 workstations | Device is configured to run on these specified workstations with detailed CPU, RAM, and storage. |
| Memory requirement of 640 MB | VW 320/540 configurations specify 640 MB of SDRAM. | |
| User Interface | Standard keyboard and wheel-mouse input | "User interacts with the system through a standard keyboard and a wheel-mouse." |
| Buttons marked with commonly understood symbols or English | "All buttons are marked with commonly understood symbols or English language notation." | |
| Data Input | Max. file size: 512 MB or 1000 slices | "Max. file size: 512 MB or 1000 slices" |
| NTSC video input at 30 frames per second | "NTSC video input signals at 30 frames per second." | |
| Data Output | User defined output as DICOM file | "Data output is user defined and is one of 3 options: 1. DICOM file" |
| User defined output as JPEG compressed image file | "Data output is user defined and is one of 3 options: 2. JPEG compressed image file" | |
| User defined output as BMP file | "Data output is user defined and is one of 3 options: 3. BMP file" | |
| Video Output | NTSC-compatible video output as an option | "NTSC-compatible video output as an option." |
| Report Functionality | Provide preset image format for included images, easily modifiable | "Provide preset image format for included images. This format has to be easily modified." |
| Overlay of figures and characters to annotate findings | "Overlay of figures and characters on top of the images to annotate findings." | |
| Placing report on a network as DICOM, BMP, or JPEG | "Provide for placing the report on a network as DICOM files or BMP or JPEG format." | |
| Provide a print function | "Provide a print function." | |
| Comparison to Predicate | Teleradiology image acquisition, distribution, archival and 3D viewing | "SAME" as predicate AccuImage™ Viewer Products. |
| Network Connectivity: Ethernet 100 Base T | Different from predicate (GPIB IEEE488), but considered equivalent ("Yes" in SE column). | |
| Computer Platform: SGI VW-320 and -540 | Different from predicate (PC), but considered equivalent ("Yes" in SE column). | |
| Lossy Image Compression: JPEG | Different from predicate (BMP), but considered equivalent ("Yes" in SE column). | |
| DICOM Compliant: YES | "YES" (same as predicate) | |
| Image Display: Color, Grey scale, 1600x1200 | Higher resolution than predicate (512x512), considered equivalent ("Yes" in SE column). | |
| Image Edit: 8 object segmentation clipping planes in double oblique orientation | More advanced than predicate (Manual and threshold segmentation), considered equivalent ("Yes" in SE column). | |
| Volume Rendering: Voxel transmission, parallel and perspective ray casting | Different algorithms than predicate (MIP, Surface rendering, Depth encoded surface), considered equivalent ("Yes" in SE column). | |
| 2D/3D Integration: Automatic display of orthogonal planes | More advanced than predicate (Display of basic 2D views), considered equivalent ("Yes" in SE column). | |
| Operating System: SGI320, SGI-540 Windows NT | Different from predicate (Win95/Win98), but considered equivalent ("Yes" in SE column). |
Note on "Reported Device Performance": For a 510(k) submission like this, "reported performance" often means demonstrating that the device meets its design specifications, is compliant with relevant standards, and is substantially equivalent to a legally marketed predicate device. Actual quantitative performance metrics from a dedicated study are typically not included unless addressing a specific performance claim.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not describe a specific "test set" for performance evaluation in the context of a clinical study or image dataset. The submission focuses on technical specifications, compliance with standards (DICOM, ISO/IEC 12207), and a feature-by-feature comparison to a predicate device. Therefore, information about sample size, data provenance, and retrospective/prospective nature is not provided.
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)
Since there is no described "test set" or clinical study involving image interpretation, there is no information about experts establishing ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
As no test set involving expert review is described, there is no information on an adjudication method.
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
The document does not describe an MRMC comparative effectiveness study, nor does it refer to AI assistance. This device is an image viewing and communication system, not an AI-powered diagnostic aid.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device is an image viewing and communication system designed to be used by human radiologists. It is not an algorithm intended for standalone diagnostic performance. Therefore, analysis of "standalone" algorithm performance is not applicable or described.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Since no clinical performance study involving diagnostic interpretation is described, there is no mention of the type of ground truth used. The ground truth for this type of device relates to its technical functionality (e.g., a DICOM file is correctly transferred and displayed, a report is correctly generated).
8. The sample size for the training set
The document does not describe a "training set" as it is not an AI/machine learning device. The software development follows ISO/IEC 12207, implying standard software testing and validation, but not machine learning training.
9. How the ground truth for the training set was established
As there is no "training set" in the context of machine learning, this question is not applicable and no information is provided.
§ 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.