(69 days)
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 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.
The Vitrea Software Package, VSTP-002A, is a portfolio of applications software designed to be used in the Canon Medical Informatics Vitrea workstation. VSTP-002A currently includes a post processing application, Auto MPR, which use CT brain image data, obtained from Canon CT Systems, to assist physicians in performing specialized measurements and analysis.
Auto MPR is a software application that aligns CT brain images into a standard anatomical position for review.
Here's a breakdown of the acceptance criteria and the study details for the Vitrea Software Package, VSTP-002A, specifically focusing on the Auto MPR application, based on the provided text:
Acceptance Criteria and Reported Device Performance
The provided document details the testing performed for the Auto MPR application within the Vitrea Software Package. The core function of Auto MPR is to align CT brain images into a standard anatomical position.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Output Image Alignment | Bench studies were conducted to test Auto MPR output image alignment into a standard anatomical position. The results demonstrated that Auto MPR "met established specifications and performed as intended." |
| Impact of Various Conditions | Bench studies also assessed the impact of various conditions on Auto MPR image alignment. The results demonstrated that Auto MPR "met established specifications and performed as intended." This implies the device maintained its alignment performance under different, unspecified conditions. |
Study Details
The information provided is somewhat limited as it's a 510(k) summary, which often condenses detailed study information.
-
Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated in the provided text. The document mentions "bench studies" and "various conditions," but specific numbers of images or cases used for evaluation are not given.
- Data Provenance: Not explicitly stated. There is no information regarding the country of origin of the data or whether it was retrospective or prospective.
-
Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
- Not explicitly stated. The document refers to "established specifications" but does not detail how these specifications were derived or who established the ground truth for image alignment.
-
Adjudication Method for the Test Set:
- Not explicitly stated. There is no mention of an adjudication process (e.g., 2+1, 3+1) for the ground truth.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No evidence of an MRMC study is provided. The submission focuses on device performance against specifications rather than a comparative effectiveness study with human readers. There is no mention of human improvement with or without AI assistance.
-
Standalone (Algorithm Only Without Human-in-the-loop Performance) Study:
- Yes, a standalone study was performed. The "bench studies" described assess the Auto MPR's output image alignment and performance under various conditions, implicitly without human intervention beyond setting up the tests and evaluating the results against established specifications.
-
Type of Ground Truth Used:
- The ground truth appears to be based on "established specifications" for what constitutes a "standard anatomical position" for CT brain images. The details of how these specifications were defined (e.g., based on anatomical landmarks, expert consensus on "correct" alignment) are not provided. It's not explicitly stated to be pathology or outcomes data.
-
Sample Size for the Training Set:
- Not explicitly stated. The document describes the device as a "post processing software" but does not provide details about its development, including training set size if machine learning was used.
-
How the Ground Truth for the Training Set Was Established:
- Not explicitly stated. Without information on a training set or the use of machine learning, there's no detail on how ground truth for training would have been established.
In summary, the 510(k) emphasizes that the Auto MPR application met its established technical specifications for aligning CT brain images into a standard anatomical position during bench testing. However, specific quantitative metrics for performance, details about the dataset used for testing (size, provenance), and the process of establishing ground truth (human expert involvement, adjudication) are not included in this summary document.
§ 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).