FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

importing digital diagnostic and functional imaging datasets (e.g. . MR, MRA, CT, CTA, fMRI, X-ray, DSA, PET, SPECT, MEG, MSI, US )
. reviewing and analyzing the data in various 2D and 3D presentation formats.
. performing image fusion (co-registration) of datasets,
. segmenting structures in the images with manual and automatic tools and converting them into 3D objects for display,
. exporting results to other Medtronic Navigation planning applications, to a PACS or to Medtronic Navigation surgical navigation systems such as the StealthStation System.

The StealthDTI Package is a subset of StealthViz that implements a special case of segmenting 3D structures from the datasets. It is indicated for use in the processing of diffusion-weighted MRI sequences into 3D objects that represent white-matter tracts.

Only DICOM for presentation images can be used on an FDA approved monitor for mammography for primary image diagnosis. Only uncompressed or non-lossy compressed images must be used for primary image diagnosis in mammography.

Device Description

StealthViz is a general purpose 2D/3D surgical planning and image review and analysis software application running on a standard computer. It enables:

importing digital diagnostic and functional imaging datasets (e.g. MR, MRA, CT, CTA, fMRI, X-ray, DSA, PET, SPECT, MEG, MSI, US) across a LAN, the internet or a modem, or via local transfer from physical media (e.g. CD, DVD, USB drive),
reviewing and analyzing the data (e.g. making measurements) in various 2D and 3D presentation formats,
performing image fusion (co-registration) of datasets using automated or a manual image-matching technique,
segmenting structures in the images with manual and automatic tools and converting them into 3D objects for display,
creating hybrid datasets by filling in segmented regions slice-by-slice on anatomical datasets, and
exporting results to other Medtronic Navigation planning applications, to a PACS or to other Medtronic Navigation surgical navigation systems such as the StealthStation System.

The StealthDTI Package provides the following additional capabilities:

import diffusion-weighted sequence datasets (gradients),
co-register the gradients with anatomical studies using an automatic algorithm or a manual technique,
perform diffusion tensor calculations to create intermediate datasets such as Fractional Anisotropy and Apparent Diffusion Coefficient and the ability to display these results with, for example, Directionally Encoded Color or grayscale mapping,
enable the user to define regions-of-interest (ROI) from which to . perform white matter tractography (WMT, also known as fiber tracking). The user can define multiple ROIs or use previously segmented objects as ROIs (e.g. an fMRI activation area that has been segmented into a 3D object).
calculated fiber tracts can be displayed and converted into 3D . objects,
all results can be exported as noted for the base StealthViz . application description.

AI/ML Overview

The provided text describes a 510(k) premarket notification for Medtronic Navigation, Inc.'s StealthViz Advanced Planning Application with StealthDTI Package. However, it does not contain the specific details required to fully address your request regarding acceptance criteria and a study that proves the device meets those criteria.

Here's what can be extracted and what information is missing:

1. Table of Acceptance Criteria and Reported Device Performance:

The document explicitly states: "Test Testing was performed in two phases. Testing was performed by Visage Imaging, the third party developer, to ensure that all Requirements were met by the product." However, the specific "Requirements" (acceptance criteria) and their corresponding reported device performance values are not detailed in this summary.

2. Sample size used for the test set and the data provenance:

The document mentions "a subset of testing was also performed in-house," but does not specify the sample size used for the test set or the provenance (country of origin, retrospective/prospective) of the data.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

This information is not available in the provided text.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

This information is not available in the provided text.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs. without AI assistance:

This document describes a 2008 submission. The StealthViz Advanced Planning Application with StealthDTI Package is a tool to process and visualize diffusion-weighted MRI sequences into 3D objects representing white-matter tracts for surgical planning and image review/analysis. It is not an AI diagnostic tool and does not involve human readers interpreting results with or without AI assistance in the way modern AI devices do. Therefore, a MRMC comparative effectiveness study in that context would not be applicable to this device. The document does not mention such a study.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

The document states, "Testing was performed by Visage Imaging, the third party developer, to ensure that all Requirements were met by the product. This testing is referenced in the Trace Matrix which ensures that all requirements were successfully verified." This implies standalone testing of the software's functionality. However, specific details about the "standalone" performance metrics (e.g., accuracy, precision of fiber tracking) are not provided.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

This information is not available in the provided text. Given the nature of white-matter tractography, "ground truth" would likely involve anatomical atlases, direct anatomical correlation, or expert neuroanatomical review, but this is not stated.

8. The sample size for the training set:

Medtronic Navigation, Inc.'s StealthViz Advanced Planning Application with StealthDTI Package, as described in this 2008 510(k) summary, is a software tool for image processing, co-registration, segmentation, and visualization, particularly for diffusion tensor imaging (DTI). It uses algorithms to perform these functions (e.g., automatic co-registration, diffusion tensor calculations, white matter tractography based on user-defined ROIs).

While such algorithms are developed, they are not typically "trained" in the machine learning sense with a large "training set" of patient data as modern AI/ML devices are. The algorithms are based on established image processing and mathematical principles (e.g., for DTI calculations). Therefore, the concept of a "training set sample size" as relevant to AI/ML is not applicable to this type of device as described in this document.

9. How the ground truth for the training set was established:

As mentioned above, the concept of a "training set" in the context of modern AI/ML is not directly applicable to this device. Therefore, how ground truth for such a set was established is not discussed in the document.

In summary, while the document confirms testing was performed to verify requirements for the StealthDTI package, it lacks the detailed quantitative information on acceptance criteria, specific performance metrics, sample sizes, expert involvement, and ground truth establishment that would typically be found in a comprehensive study report for a modern AI/ML medical device. The context is a 2008 510(k) summary for a software planning tool, not an AI diagnostic algorithm.

Summary

Regulation Number and Section

§ 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).