(42 days)
Vitrea® Coronary Artery Analysis (CT Cardiac Analysis) is intended for investigating coronary obstructive disease by providing a non-invasive survey of a patient's coronary arteries.
Clinicians can select any coronary artery to view the following anatomical references: the highlighted vessel in 3D, two rotatable curved MPR vessel views displayed at 90 degree angles to each other, and cross sections of the vessel. The clinician can semi automatically determine contrasted lumen boundaries, stenosis measurements, and maximum and minimum lumen diameters. In addition, clinicians can edit lumen boundaries and examine Hounsfield unit statistics.
This submission is for the addition of a new feature, the Multi-Vessel preset, to the Vitrea CT Cardiac Analysis application. This application was originally cleared as "CT Coronary Analysis" in the predicate submission K052632 Witreal Image Processing Software). The application resides on the Vitrea AV platform, most recently cleared as K172855 (Vitrea Advanced Visualization, Version 7.6).
The submission is also intended to notify the Agency of the following non-significant changes to the previous clearance, documented by Letters to File (LTF):
· Vessel Tracking for Low kV Scans
· Angiographic View
The previously cleared Vitea CT Cardiac Analysis option (cleared in the predicate submission K052632 under the name "CT Coronary Analysis") provides a variety of tools and vith clinical CT images of the coronary arteries, heart, and surrounding tisse. The software supports CTA studies acquired by 4-slice and above multislice CT scanners, and includes the following features:
- · Automatic segmentation of the heart from the rest of the anatomy
- · Zero-click coronary vessel tree segmentation and automatic labeling of the three main coronary arteries
- · Selection of any coronary artery for viewing with the Vessel Probe tool with easy centerline review and editing
- · Full Vessel Probe capabilities for coronary arteries including the Lesion Tool, Vessel Walk, and Cath View
· A flythrough preset configured for flying through the coronary vessels (Global Illumination Rendering not available in the flythrough view) - Unique Heart Mode to automatically orient oblique MPR views to show one short-axis view and two long-axis views
- · Key findings classification during reading of the study for semi-automated structured report generation
- · Measurement of plaque burden between the lumen and the outer wall with the SUREPlaque tool
- · Display of a Transluminal Attenuation Gradient for probed vessels.
This submission adds the new Multi-Vessel preset feature. Whereas the offered initial automated probing and labeling of the three main coronary arteries, the new feature adds an additional initial automated probing (without labeling) of up to seventeen additional vessels in the vessel trees associated with the main coronary arterior tree, the left circumflex artery (LCX) tree, and the right coronary artery (RCA) tree. The tree structure allows edits to the trunk to be reflected on all the branch vessels. In both the subject and the predicate devices, the user has the ability to manually probe an unlimited number of additional vessels. The capability of either manually or automatically "probing" vessels was present in the predicate software.
The provided text describes a 510(k) premarket notification for a medical device called "Vitrea CT Cardiac Analysis" and includes information about its functionalities and validation. However, it does not contain specific acceptance criteria, reported device performance metrics in a defined table format, sample sizes for test sets, data provenance, details on experts, adjudication methods, or results of MRMC or standalone studies clearly related to acceptance criteria.
The submission focuses on a new feature, the "Multi-Vessel preset," and general software verification and validation. It states that "the software achieved all product release criteria" but does not enumerate what those criteria are or present quantitative results against them.
Therefore, many of the requested information points cannot be extracted directly from the provided text. I will provide the information that is available and explicitly state where the requested information is not present.
1. A table of acceptance criteria and the reported device performance
Unfortunately, the provided text does not contain a specific table of acceptance criteria with corresponding reported device performance metrics. It generally states that "the software achieved all product release criteria" and that "testing confirmed that the software functions according to its requirements," but does not detail these criteria or the quantitative results.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The text mentions "executing cardiac CTA test cases" for validation but does not specify the sample size of the test set nor the data provenance (e.g., country of origin, retrospective/prospective nature).
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)
This information is not provided in the text. The document refers to internal software verification and validation, but no details about expert involvement in establishing ground truth for testing are mentioned.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not provided in the text.
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 text does not indicate that a multi-reader multi-case (MRMC) comparative effectiveness study was done. The focus is on the device's functionality and its internal validation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The provided text describes the device as a tool for clinicians to "semi automatically determine contrasted lumen boundaries, stenosis measurements, and maximum and minimum lumen diameters," and allows clinicians to "edit lumen boundaries." This implies human-in-the-loop interaction. While the new "Multi-Vessel preset" offers "initial automatic probing (without labeling)," the device's overall design is for clinical use with clinician interaction. A standalone (algorithm-only) performance study is not explicitly mentioned or detailed in the text.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The text mentions "internal software verification and validation" and "cardiac CTA test cases," but it does not specify the type of ground truth used for these tests.
8. The sample size for the training set
The text describes "Vitrea CT Cardiac Analysis" as an application with new features being added. It does not provide information about a "training set" or its sample size. This type of information is usually associated with machine learning model development, and while the device has "automatic segmentation" and "automatic labeling" features, the document focuses on the validation of software functionality rather than the development and training of new AI models.
9. How the ground truth for the training set was established
As no training set is discussed, this information is not provided in the text.
§ 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).