Search Results

The Vitrea CT VScore™ option is a calcium scoring application intended for the visualization, evaluation, and documentation of calcified lesions on non-contrast ECG-gated, cardiac CT DICOM images for patients aged 30 years or older. The application allows the user to segment and categorize the calcified lesions and calculate the calcium scores. The user can create a report including the data, images, literature, and additional relevant information. The application is intended to be used by qualified medical professionals to assist the physician in medical imaging assessment based on their professional judgment and other patient information. The calcification segmentation map is intended for informational use only.

The Vitrea CT VScore™ option is a calcium scoring application intended for the visualization, evaluation, and documentation of calcified lesions on cardiac CT images for patients aged 30 years or older.
The application allows the user to segment and categorize calcified lesions and calculate the calcium scores. The user can create a report including the data, images, literature, and additional relevant information. The application is intended to be used by qualified medical professionals to assist the physician in medical imaging assessment based on their professional judgment and other patient information.
The Vitrea CT VScore™ option is an interactive user-driven application. The application allows users to perform visualization, quantification and documentation of calcium lesions on cardiac CT studies.
The application provides a user interface with the following main functions:

• Allows manual selection of calcified lesions that meet selection criteria such a 3-pixel threshold and a 130 HU density threshold.
• Allows users to manually assign the selected calcium to the appropriate coronary and non-coronary categories.
• For selected calcium, calculates Agatston and volume scores.
• Allows users to select well-established, standard population databases and risk categories, along with literature references, to include in reports.
• Allows users to output documentation using standard DICOM objects (such as DICOM structured reporting objects).

The application takes standard DICOM images generated by CT scanners as input and provides a user interface permitting users to create the desired outputs as part of their clinical workflow. The device returns Agatston and volume calcium scores; well-established methods of calculation exist for these scores. Optionally, and for reporting purposes, the device displays patient scores in the context of well-established population reference databases and calcium scoring reporting systems.

The application is intended to operate on cardiac CT images. The device is indicated for patients aged 30 or above.

The device is Software as a Medical Device (SaMD) and has no hardware or material components.

The device is a software application that runs on the Vitrea Advanced Visualization platform. The device operates on cardiac CT DICOM images of a patient after they have been acquired. The device produces DICOM output, including DICOM SR objects.

This looks like a challenging task. I'm unable to process this request. As a large language model, I am still learning and not yet equipped to handle such complex and nuanced information extraction from a document. I cannot confidently determine the acceptance criteria and study details from the provided text given the depth and specificity of the request. Furthermore, the provided text does not contain the detailed study results needed to complete the requested tables and descriptions.

To provide a helpful response, I would need a document that explicitly outlines the acceptance criteria (numerical thresholds for performance metrics) and the detailed results of a performance study, including metrics like accuracy, sensitivity, specificity, or inter-reader variability.

If you have a document that includes these specific details, please provide it, and I will do my best to extract and present the information as requested.

Ask a specific question about this device

Open Rib is image analysis software for chest CT images. Open Rib offers a visualization of the unfolded rib cage that allows a physician to instantly view the full rib anatomy and should be used as an additional view in adjunct to conventional multiplanar reformat views. Open Rib offers geometric and HU measurement tools.

Open Rib is image analysis software for chest CT images. The software resides on the Vitrea Advanced Visualization (AV) platform.

Open Rib offers a visualization of the unfolded rib cage called an "unfolded cylindrical projection" (UCP) that allows a physician to instantly view the full rib anatomy and should be used as an additional view in adjunct to conventual multiplanar reformat views. Open Rib offers geometric and HU measurement tools.

The images can be directly exported to PACS and batch saved.

Here's a breakdown of the acceptance criteria and the study details for the Open Rib device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance

• Test Set Sample Size: 30 chest CT cases.
• Data Provenance: The cases were acquired with various CT scanners from different manufacturers (Canon: 17, Siemens: 8, GE: 4, Philips: 1). The country of origin for the data is not explicitly stated, but the study evaluators were U.S. board-certified radiologists, implying the study was conducted in the US. The data appears to be retrospective, as it refers to "datasets included" rather than prospectively acquired data for the study.

3. Number of Experts and Qualifications

• Number of Experts: 3.
• Qualifications of Experts: U.S. board-certified radiologists. No specific years of experience are provided, but board certification implies a certain level of expertise.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated as a formal adjudication method. Instead, each evaluator (radiologist) reviewed 10 cases, with cases evenly distributed among them. They were then presented with a list of questions about clinical utility and effectiveness. A "pass" result required positive answers to all questions from all three readers. This suggests a consensus-based evaluation where all experts had to agree on the positive assessment for the device to pass. There was no explicit mention of an adjudicator to resolve disagreements, as "positive answers to all questions" from all three was the criterion.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• MRMC Study: No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not performed. The study focused on the standalone performance and perceived utility of the Open Rib visualization and tools when used as an adjunct to conventional views. It did not quantify an improvement in human reader performance directly attributable to the AI.

6. Standalone Performance (Algorithm Only)

• Standalone Performance: Yes, the study essentially describes a standalone performance evaluation of the "Open Rib" software. The evaluators were assessing the generated unfolded rib views and measurement tools themselves. While radiologists were "using" the device, their evaluation was of the output of the algorithm (the UCP view) and its utility, not a comparison of their diagnostic accuracy with and without the device. The prompt asks for "algorithm only without human-in-the loop performance," and while radiologists were in the loop for evaluation, the core function being assessed was the software's ability to generate the UCP view and its perceived utility. The "pass" criteria rely on the radiologists' positive assessment of the device's output.

7. Type of Ground Truth Used

• Type of Ground Truth: The ground truth for the presence or absence of abnormalities (e.g., normal vs. abnormal cases like rib fractures, bony lesions, kyphosis) was likely established by the referring physician's diagnosis, prior imaging reports, or a consensus of experts prior to the study, as cases were selected to include both normal (12 cases) and abnormal (18 cases) findings. However, the evaluation for device performance was based on expert consensus (radiologist assessment) of the clinical utility and effectiveness of the device's output (the UCP view, measurement tools, and workflow).

8. Sample Size for the Training Set

• Training Set Sample Size: Not provided in the document. The document describes the validation/test set but does not mention the size or characteristics of any training data used to develop the Open Rib algorithm.

9. How Ground Truth for the Training Set Was Established

• Ground Truth for Training Set: Not provided. Since the training set size is not mentioned, how its ground truth was established is also not detailed in this section of the 510(k) summary.

Ask a specific question about this device

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.

Ask a specific question about this device