(11 days)
The GEMS AW Pasting 1.1 software package is a display option, which combines a series of MR images acquired in multiple stations of the body into a single image. AW Pasting 1.1 provides the convenience of viewing a single image rather than several images.
The GEMS AW Pasting 1.1 software package is a display option, which provides the convenience of viewing a single image resulting from the automatic pasting of multiple images acquired in different stations of the body.
The provided text is a 510(k) summary for the GE Medical Systems Advantage Workstation Pasting 1.1 software. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study with acceptance criteria and device performance metrics. Therefore, much of the requested information regarding specific study details is not available in the provided document.
Here's a breakdown of what can and cannot be extracted from the text:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not specify quantitative acceptance criteria or report specific performance metrics (e.g., accuracy, sensitivity, specificity, processing time) for the AW Pasting 1.1 software. Instead, it states that the device "performs as well as devices currently on the market" and its features are "equivalent to those of AW X-Ray Pasting (K973270)." This indicates a qualitative assessment of substantial equivalence rather than meeting predefined numerical acceptance criteria.
2. Sample Size Used for the Test Set and Data Provenance:
This information is not provided in the document. There is no mention of a dedicated "test set" and thus no sample size or data provenance (e.g., country of origin, retrospective/prospective).
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
This information is not provided in the document. The concept of "ground truth" established by experts for a test set is not discussed.
4. Adjudication Method for the Test Set:
This information is not provided in the document. As there's no mention of a test set or ground truth establishment, there's no adjudication method described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done:
Based on the provided text, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported. The submission focuses on demonstrating substantial equivalence through functional comparison rather than a human-in-the-loop performance study. Therefore, there is no information on the effect size of how much human readers improve with AI vs. without AI assistance.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study Was Done:
The document mentions "Software Development, Validation and Verification Process to ensure performance to specifications, Federal Regulations and user requirements." This implies internal testing and validation of the algorithm's functionality. However, specific details of a standalone study, quantitative results, or performance metrics are not provided. The assessment appears to be based on whether the pasting function works as intended and is comparable to the predicate.
7. The Type of Ground Truth Used:
The concept of "ground truth" as typically understood in medical device AI (e.g., pathology, outcomes data) is not explicitly mentioned or used in this submission. The validation seems to rely on the software's ability to combine MR images correctly and produce a single, viewable image, functionally equivalent to a predicate device. The "ground truth" would implicitly be the established correctness of the image pasting process against its design specifications and the performance of the predicate device.
8. The Sample Size for the Training Set:
This information is not provided in the document. The device is a software package for image display and pasting, and it's from 2003, predating the widespread use of deep learning and large training datasets as we understand them today for diagnostic algorithms. It's likely that "training" involved software development and testing rather than machine learning model training on a distinct dataset.
9. How the Ground Truth for the Training Set Was Established:
This information is not provided in the document, for the reasons mentioned above.
Summary of Available Information from the Provided Text:
The provided 510(k) summary for K031396 focuses on establishing substantial equivalence for the AW Pasting 1.1 software package to a predicate device (AW X-Ray Pasting, K973270). The equivalence is based on the device's functional features: combining a series of MR images acquired in multiple stations into a single image for convenient viewing.
The document highlights the following:
- Device Description: The software automatically pastes multiple images acquired in different stations of the body into a single image.
- Indications for Use: To combine a series of MR images acquired in multiple stations of the body into a single image, providing convenience of viewing.
- Comparison with Predicate: Stated to be "substantially equivalent" in functional features to the AW X-Ray Pasting (K973270).
- Safety and Effectiveness: Potential hazards are identified and controlled through "Software Development, Validation and Verification Process to ensure performance to specifications, Federal Regulations and user requirements" and "Adherence to industry and international standards." The conclusion is that it "does not result in any new potential safety risks and performs as well as devices currently on the market."
In conclusion, this document is a regulatory submission for substantial equivalence based on functional equivalence and risk management, not a detailed scientific study outlining specific performance metrics against acceptance criteria using a defined test set and ground truth establishment methodology.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.