(83 days)
GE View Applications is a medical image viewing software device that allows a user to select, send, receive, and review DICOM images from modalities, such as computed tomography ("CT"), magnetic resonance ("MR"), x-ray ("XR"), nuclear medicine ("NM"), ultra sound ("US"), computed radiography ("CR"), and modalities that generate secondary capture ("SC") images. GE View Applications is intended to meet different application requirements ranging from simple medical image viewing on the physician's desktop to clinical image review (e.g., in the ICU).
GE View Applications is medical image viewing software that consists of two products: the GE Viewing Station and the GE Extended Viewing Station. GE View Applications is a two-dimensional ("2D") review application software for a PC/WIN platform that allows a user to select, send, receive, display, and review of patient image data using the DICOM communication standard. DICOM images can be displayed from any of the following modalities: computed tomography ("CT"); magnetic resonance ("MR"); x-ray ("XR") (XA, R/F); nuclear medicine ("NM"); ultra sound ("US"); computed radiography ("CR"); and modalities that generate secondary capture ("SC") images. GE View Applications can be installed on a PC in the hospital on a local area network ("LAN") or wide area network ("WAN") and includes teleradiology, connectivity, and display features.
The provided document, K991629 for GE View Applications, is a 510(k) summary for a medical image viewing software. Unfortunately, it does not contain the detailed performance data typically required to answer your specific questions about acceptance criteria and the comprehensive study that proves the device meets those criteria.
Here's an analysis based on the available information:
1. Table of acceptance criteria and the reported device performance:
The document states: "System design verification tests have been conducted to assure conformance with the design specifications. Validation testing will be conducted according to the validation test plan and procedures."
This indicates that acceptance criteria and performance data exist, but they are not provided in this 510(k) summary. The summary focuses on established substantial equivalence rather than presenting detailed performance metrics. Therefore, a table cannot be populated from the given text.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
No information is provided regarding the sample size of any test set, nor the data provenance (country of origin, retrospective/prospective).
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):
No information is provided regarding the number or qualifications of experts used to establish ground truth for any test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
No information is provided regarding an adjudication method for a test set.
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:
A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported in this 510(k) summary. This device is described as "medical image viewing software" and its primary function is display and review, not an AI-powered diagnostic aid that would typically involve an MRMC study measuring reader improvement.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
A standalone performance study was not reported in this 510(k) summary. The device is a "medical image viewing software" intended for human review, not an autonomous algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
No information is provided regarding the type of ground truth used.
8. The sample size for the training set:
No information is provided regarding the sample size of a training set. This device is a viewing application, not an AI/ML algorithm that typically has a training set.
9. How the ground truth for the training set was established:
No information is provided regarding how ground truth for a training set was established.
Summary of what the document does tell us:
- Device Type: Medical image viewing software (GE View Applications, including GE Viewing Station and GE Extended Viewing Station).
- Functionality: Select, send, receive, display, and review patient image data using the DICOM communication standard from various modalities (CT, MR, XR, NM, US, CR, SC).
- Intended Use: Simple medical image viewing on a physician's desktop to clinical image review (e.g., in the ICU).
- Regulatory Pathway: 510(k) substantial equivalence.
- Predicate Devices: GE Advantage Review Remote Workstation (K936179) and GE Advantage Windows Diagnostic Review Workstation (K960613).
- Performance Data (General Statement): "System design verification tests have been conducted to assure conformance with the design specifications. Validation testing will be conducted according to the validation test plan and procedures."
Conclusion:
The provided 510(k) summary for GE View Applications (K991629) is a premarket notification for a medical image viewing software. As is common for many non-AI/ML devices cleared via the 510(k) pathway, it primarily establishes substantial equivalence to predicate devices and states that design verification and validation testing were, or will be, conducted. It does not contain the detailed clinical performance study data (acceptance criteria, sample sizes, ground truth establishment, expert qualifications, MRMC studies, standalone performance, etc.) that would be expected for a more complex diagnostic algorithm or an AI/ML-driven device. These details would typically be found in the full 510(k) submission, not necessarily in the publicly available summary.
§ 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).