(15 days)
Vitrea 2 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. In addition, the Vitrea 2 system has the following specific indication:
Fusion7D is an option within the Vitrea 2 system and is intended to register pairs of anatomical and functional volumetric images (e.g., MRI-SPECT, MRI-PET, CT-SPECT, CT-PET), or pairs of anatomical volumetric images (e.g., MRI-MRI, CT-CT, and MRI-CT) as a means to ease the comparison of image data. The result of the registration operations aims to help the clinician obtain a better understanding of the joint information that would otherwise have to be compared separately. This is useful for a wide range of clinical and therapeutic applications. It is important to note that the clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard procedures, including visual comparison of the separate unregistered images. Fusion7D is a complement to these standard procedures.
Softread, is an option within the Vitrea 2 system and is intended to allow the examination and manipulation of a series of 2D images in a variety of modalities, including CT, MR, CR/DR/DX, SC, US, NM, PET, XA, and RF, etc. The option also enables clinicians to compare multiple series' for the same patient, side-by-side, and to switch to Vitrea to further examine the data in a 3D volume.
The Vitrea 2 system is a medical diagnostic device that allows the processing, review, analysis, communication and media interchange of multi-dimensional digital images acquired from a variety of imaging devices. Vitrea 2, Version 3.5 is an upgrade to Vitrea 2, Version 3.4 (cleared under K032748).
The Vitrea 2 system provides multi-dimensional visualization of digital images to aid clinicians in their analysis of anatomy and pathology. The Vitrea 2 user interface follows typical clinical workflow patterns to process, review, and analyze digital images, including:
- . Retrieve image data over the network via DICOM
- . Display images that are automatically adapted to exam type via dedicated protocols
- . Select images for closer examination from a gallery of up to six 2D or 3D views
- . Interactively manipulate an image in real-time to visualize anatomy and pathology
- . Annotate, tag, measure, and record selected views
- Output selected views to standard film or paper printers, or post a report to an Intranet Web server or export views to another DICOM device
- . Retrieve reports that are archived on a Web server
Here's an analysis of the provided text regarding the acceptance criteria and study for the Vitrea 2, Version 3.5 Medical Image Processing Software:
Summary of Acceptance Criteria and Device Performance:
The provided document describes the Vitrea 2, Version 3.5 software as an upgrade to a previously cleared device (Vitrea 2, Version 3.4) and for image processing, review, analysis, communication, and media interchange of multi-dimensional digital images. It also includes specific options: Fusion7D for image registration and Softread for 2D image examination and manipulation.
However, the document does not explicitly state specific quantitative acceptance criteria or detailed device performance metrics in a structured table. The primary "acceptance criteria" presented is the determination of substantial equivalence to predicate devices. The study's conclusion is that the device "has the same intended use as the predicate device and has very similar technological characteristics. Minor technological differences do not raise any new questions regarding safety or effectiveness of the device."
Therefore, based on the provided text, a table summarizing quantitative acceptance criteria and reported performance cannot be generated as these details are not present. The "study" described is a declaration of compliance with internal development and testing procedures, culminating in a finding of substantial equivalence by the FDA.
Detailed Breakdown of Study Information (based on available text):
-
Table of Acceptance Criteria and Reported Device Performance:
Acceptance Criterion Reported Device Performance General: Substantial Equivalence to Predicate Devices "The Vitrea 2, Version 3.5 system has the same intended use as the predicate device and has very similar technological characteristics. Minor technological differences do not raise any new questions regarding safety or effectiveness of the device. Thus, the Vitrea 2, Version 3.5 system is substantially equivalent to the predicate device." Compliance with Design, Development, Testing Procedures "The software utilized was designed, developed, tested, and validated according to written procedures. These procedures specify individuals within the organization responsible for developing and approving product specifications, coding, testing, validating and maintenance." Integration/Verification Testing "The Vitrea 2, Version 3.5 system will successfully complete integration testing/verification testing prior to Beta validation." Beta Testing/Validation "Software Beta testing/validation will be successfully completed prior to release." Risk Management "potential hazards have been studied and controlled by a Risk Management Plan." Specific Functionality (Inferred): (No quantitative performance criteria or results are provided for specific functionalities like image registration accuracy or display performance beyond the general statement of substantial equivalence.) -
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- Sample Size: Not specified. The document mentions "integration testing/verification testing" and "Software Beta testing/validation" but does not provide details on the number of cases or images used in these tests.
- Data Provenance: Not specified.
-
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):
- Not specified. The document mentions "clinicians" in the intended use description but does not detail their involvement in establishing ground truth for any testing.
-
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not specified.
-
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 MRMC comparative effectiveness study is described. The document focuses on showing substantial equivalence based on technical characteristics and internal testing, not on comparative clinical performance or human reader improvement. The device's function (image processing, registration, visualization) is supportive of clinical analysis but is not presented as an AI solution for automated diagnosis or a system designed to improve human reader performance in a measurable way through a specific "AI assistance" metric in this context.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- No specific standalone performance study with quantitative results for the algorithm is described. The "study" pertains to internal software development and validation processes, and a general assertion of substantial equivalence. The discussion around "Fusion7D" explicitly states that the "clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard procedures, including visual comparison of the separate unregistered images." This indicates a human-in-the-loop expectation rather than a standalone diagnostic claim for the algorithm.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not specified. Given the nature of the device (image processing and visualization tools), ground truth would likely relate to the accuracy of image registration, quality of visualization, and correctness of measurements rather than diagnostic accuracy against pathology or outcomes data. However, the document does not elaborate on how this ground truth would be established or used.
-
The sample size for the training set:
- Not specified. The document describes a software upgrade and general development processes, not a machine learning model requiring a distinct training set. If there are any learning components within the device (e.g., for image recognition or feature extraction), the document does not detail their training.
-
How the ground truth for the training set was established:
- Not specified, as a training set and its associated ground truth are not mentioned in the context of this submission.
§ 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).