(38 days)
Vitrea® is a medical diagnostic system that allows the processing, review, analysis, communication and media interchange of multi-dimensional digital images acquired from a variety of imaging devices. Vitrea is not meant for primary image interpretation in mammography. Vitrea has the following additional indication:
The Endovascular Stent Planning Software application is intended for use with CT (computed tomography) images to assist medical professionals in the analysis, treatment and follow-up of aortic vascular disorders that may require a stent procedure. The software provides 3D segmentation of the aorta and initializes stent measurements based on a template provided by the stent manufacturers. The user can review the 2D and 3D images, verify and correct the results of the segmentation and initialization, and generate a report with the stent measurements.
The Endovascular Stent Planning software is intended for use with CT (computed tomography) images to assist medical professionals in the analysis, treatment and follow-up of aortic vascular disorders that may require a stent procedure. The endovascular stent planning application module enables visualization and measurements of the aortic vessel for evaluation, treatment and follow up for aortic vascular disorders that may require a stent procedure. The software performs automated 3D segmentation of the aorta and initializes stent measurements based on a template provided by the stent manufacturers. The physicians can review the 2D and 3D images, verify and correct the results of the segmentation and initialization, and generate a report with the stent measurements, in a fast and efficient manner.
The software provides imaging information as an assist to the physician. The software does not provide diagnostic information or determine recommended medical care. In summary, the software provides:
- Automated segmentation of the aortic vessel, including thrombus with centerline . and contour editing tools
- . Stent-graft templates for abdominal and thoracic aortic aneurysms
- User-quided workflow with automated identification of anatomical landmarks and automated initialization of endovascular measurements (diameters, lengths, angles, volumes) based on the stent template selection, with easy centerline and contour editing tools
- Auto-populated reporting worksheet with selected stent template measurements ●
- Key measurements that helps medical professionals to identify location of . fenestrations to support fenestrated stent planning by adding the clock angle tool and the clock angle overlay functionality
- . Create new, add/or modify, stent planning templates with the Custom Device Template Editor
- Data tables export results to CSV ●
- Multi-study support for longitudinal comparison ●
- 3D measurement overview for streamlined communication of results ●
- Volume measurements for pre and post aneurysmal size measurement ●
- Workflows for pre-treatment (stent, surgery) planning and post-treatment follow ● up, including a side-by-side comparative review layout and longitudinal measurements
The provided documentation is a 510(k) Summary for the Endovascular Stent Planning Software (K143079), which is primarily an update to an already cleared device (K091498) to add a "Clock Angle" tool. As such, the document focuses on demonstrating substantial equivalence rather than presenting a full de novo study with detailed performance metrics against acceptance criteria.
The document does not explicitly list acceptance criteria in a table format with corresponding reported device performance metrics for the "Endovascular Stent Planning Software" as a whole. Instead, it describes a process of verification and validation to show that the new feature (Clock Angle tool) does not negatively impact the previously cleared device's safety and effectiveness.
Here's an analysis based on the provided text for the new Clock Angle tool and the overall software:
1. A table of acceptance criteria and the reported device performance
The document does not provide a table with explicit acceptance criteria and quantitative performance metrics for the Clock Angle tool or the overall device in the way a typical clinical study would. The non-clinical testing focuses on demonstrating that the software operates "according to its requirements" and that the modifications do not raise new questions of safety or effectiveness.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: The document mentions "previously acquired medical images" for verification and validation but does not specify a sample size for the test set used for validating the software, or specifically the Clock Angle tool.
- Data Provenance: Not specified. It refers to "previously acquired medical images," but no details on country of origin, whether it was retrospective or prospective, or patient demographics are 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)
- Number of Experts: The "External Validation" section states that "experienced medical professionals evaluated the application." The plural "professionals" suggests more than one, but an exact number is not specified.
- Qualifications of Experts: They are described as "experienced medical professionals." No further details on their specific qualifications (e.g., specialty, years of experience) are provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not describe a formal adjudication method for ground truth establishment. It states that "Both validators confirmed that the Fenestrated Stent Planning using Endovascular Stent Planning software was safe and effective and met the intended use." This suggests a consensus or affirmation, but not a structured adjudication process.
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
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted. The document states, "The subject of special 510(k) notification, Endovascular Stent Planning software, did not require clinical studies to support safety and effectiveness of the software." The emphasis is on demonstrating substantial equivalence to the predicate device, not on improved human reader performance with AI assistance. The software is described as an "assist," but its impact on human reader performance is not quantified.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document focuses on the software assisting medical professionals, with users reviewing and correcting results. While verification and validation tests were performed on the software, the "External Validation" section refers to "experienced medical professionals evaluated the application." This suggests a human-in-the-loop evaluation for the external validation. Therefore, a purely standalone performance evaluation is not explicitly described as the primary validation for this submission. The software performs automated segmentation and initializes measurements, but users retain control for review and correction.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the "External Validation," the ground truth appears to be established by the "experienced medical professionals" confirming that the software "was safe and effective and met the intended use." This is closest to expert consensus/opinion regarding the software's functionality and utility for its intended purpose of assistance. It is not based on pathology or long-term outcomes data presented in this document.
8. The sample size for the training set
The document does not specify a sample size for any training set. This 510(k) is for a modification to an already cleared device, and the focus is on the added feature within the context of the existing system. Details about the original training set for the predicate device (K091498) are not provided in this specific document.
9. How the ground truth for the training set was established
As no training set information is provided, the method for establishing its ground truth is also not specified.
§ 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).