Search Results

Vitrea Software Package is an application package developed for use on Vitrea®, 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 Software Package has the following additional indications:

Auto MPR Brain application is a post processing software of CT brain images that is intended to align images into a standard anatomical position for review. It provides tools to reformat images parallel to a standard anatomical position.

Subtraction Viewer is a viewer application that is intended for viewing original, subtraction and fusion CT images, but such subtraction processing is not a part of this application. This application supports fusion display of original image and subtraction image generated by other applications.

Device Description

The Vitrea Software Package, VSTP-002A V2.0, is a portfolio of applications software designed to be used in the Canon Medical Informatics Vitrea workstation. VSTP-002A currently includes post processing applications, Auto MPR Brain and Subtraction Viewer, which use CT image data, obtained from Canon CT Systems, to assist physicians in performing specialized measurements and analysis.

Auto MPR Brain is a software application that aligns CT brain images into a standard anatomical position for review.

Subtraction Viewer, also marketed as SCT Viewer, is a software application intended to view original, subtraction and fusion CT images. This application supports fusion display of original images and subtraction images generated by other applications and includes the ability to adjust fusion rate and ROI measurements of fusion images.

AI/ML Overview

The provided text describes a 510(k) premarket notification for the "Vitrea Software Package, VSTP-002A V2.0". Based on the information provided, the acceptance criteria and study proving the device meets these criteria can be described as follows:

Acceptance Criteria and Device Performance

The acceptance criteria are implicitly derived from the "Performance Testing - Bench" section, which focuses on the "Evaluation of CE Boost Contrast-to-Noise Ratio (CNR)" for the Subtraction Viewer software.

Acceptance Criteria (Implicit)	Reported Device Performance
CE Boost images should have a higher CNR than the CE image.	"It was confirmed that the CE Boost images have a higher CNR than the CE image..."
The CNR of CE Boost images should increase with the CE Boost level.	"...and the CNR of these images increases with the CE Boost level."
The modifications to the subject device did not impact the performance or intended use compared to the predicate device.	"testing demonstrates that the modifications to the subject device did not impact the performance or intended use compared to the predicate device." (This is a broader statement, the specific performance supporting this for the Subtraction Viewer is the CNR evaluation). The 510(k) submission generally relies on demonstrating substantial equivalence to a predicate device, meaning the new device performs as safely and effectively for its intended use.

Study Details:

Sample Size Used for the Test Set and Data Provenance:
- Sample Size: "images of adult cases". No specific number of cases or images is provided.
- Data Provenance: The images were "derived from a Canon CT scanner." The anatomical regions included "abdomen, brain, neck, chest, pulmonary embolism, and limb scans." The country of origin is not specified, nor is whether the data was retrospective or prospective.
Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:
- The document does not mention the use of experts or the establishment of ground truth by experts for the performance testing. The evaluation described is a quantitative measurement (CNR) of the output from the "Subtraction Viewer" application.
Adjudication Method for the Test Set:
- Not applicable, as no human reader evaluation or expert consensus for ground truth establishment is described. The performance test is a quantitative measurement of CNR.
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No MRMC or human-in-the-loop study is mentioned. The performance evaluation focuses on the technical performance of the software (CNR measurement), not on how human readers interact with or benefit from the AI.
Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
- Yes, the described "Evaluation of CE Boost Contrast-to-Noise Ratio" is a standalone, algorithm-only performance assessment. It directly evaluates the output of the software (CE Boost images) by comparing CNR, without involving human interpretation or decision-making as part of the primary performance metric.
Type of Ground Truth Used:
- The concept of "ground truth" as a clinical reference standard (e.g., pathology, outcomes data, or expert consensus on disease presence) is not directly applicable to the described performance test. The "ground truth" for the CNR evaluation is the original CE image against which the CNR of the CE Boost image is compared. The purpose of the test is to verify the software's ability to enhance contrast as intended.
Sample Size for the Training Set:
- The document does not provide information about the training set size or methodology. This submission is for a "modification of a cleared device" (VSTP-002A V2.0 from VSTP-002A), and the focus of the testing section is on the performance validation of the modified features, specifically the CE Boost functionality within the Subtraction Viewer.
How the Ground Truth for the Training Set Was Established:
- Not specified, as information regarding the training set and its ground truth establishment is not provided in this document.

Ask a Question

Ask a specific question about this device

Page 1 of 1