(88 days)
The MRI-PlaqueView software provides a set of post-processing tools to assist trained cardiologists and radiologists in the quantitative analysis of atherosclerotic carotid arteries from 1.5T or 3.0T magnetic resonance imaging (MRI) studies acquired with a combination of one or more contrast weightings such as T1, T2, Proton Density, and Time of Flight. Users of MRI-Plaque View perform semiautomatic delineation of lumen and outer vessel wall boundaries. Users may also perform semi-automatic, user configurable segmentation or manual drawing for delineation of atherosclerotic plaque components within the vessel wall. Users may edit the results on the fly. The software enables length, thickness, area, and volume measurements of the vessel wall as well as quantification of user-indicated areas. MRI-PlaqueView further aids in the visualization of atherosclerotic arteries (for example, through maximum intensity projections) of MRI data and color-coded maps of segmented arteries. When interpreted by a trained physician, the output of this image analysis toolbox can be used to support the decision-making process in clinical practice or to support investigations in clinical research and trials.
MRI-PlaqueView is an image analysis software toolbox that facilitates visualization and quantitative analysis of MR images of carotid arteries acquired on 1.5T or 3.0T scanners. MRI-PlaqueView provides a set of image review, delineation, registration, editing, visualization, and measurement tools. The MRI-Plaque View user interface is designed to follow typical clinical workflow patterns to review, process, edit, validate, analyze, and visualize digital images and to present, distribute and save the findings.
The software application operates on a Windows XP platform that may be installed on a standalone PC, PACS or other medical imaging system. The software is designed to read MRI images from DICOM-compliant medical devices distributed by various OEM vendors.
The input to the system consists of one to six standard MRI series, which provide information through use of different MRI contrast weightings, such as T1, T2, Proton Density, and TOF weighted images
Once the user has selected a region of interest (ROI) for analysis, the MRI-PlaqueView tools will help to delineate the lumen and outer wall boundaries using either semi-automatic boundary detection or manual drawing/editing tools
The software provide the user an option to further analyze the multiple contrast weighted MRI data using either semi-automated algorithms or manual drawing/editing tools to segment and label the internal structure of the vessel wall, delineating calcified and soft plaque regions.
To facilitate the use of multiple contrast weighted data, the software displays the identified contours simultaneously on original images from all available series. Automated and user-controlled registration functions enable mapping of contours from one contrast weighting to another.
The quantitative measurements this software provides include volumes, thicknesses, maximal areas, and area ratios of the different regions outlined. The software also supports review and visualization of the data using standard rendering techniques, such as maximum intensity projections. The analysis results (both contours and quantitative measurements) can be saved in separate files to facilitate restoring previous works for subsequent sessions, and for reporting results.
The provided 510(k) summary for MRI-PlaqueView does not contain detailed information about specific acceptance criteria or an explicit study proving performance against those criteria. The document focuses on device description, indications for use, and comparison to predicate devices to establish substantial equivalence.
However, based on the information provided, we can infer some aspects and highlight what is missing.
Here's an attempt to answer your questions based on the available text:
Acceptance Criteria and Device Performance
1. A table of acceptance criteria and the reported device performance
The 510(k) summary does not explicitly state quantitative acceptance criteria for metrics like accuracy, precision, or agreement with a ground truth, nor does it present reported device performance results in a table. The submission establishes substantial equivalence primarily through comparison of indications for use and general functionality with predicate devices.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The 510(k) summary does not provide information on the sample size used for any test set or the provenance of the data.
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)
The 510(k) summary does not provide information on the number or qualifications of experts used to establish ground truth. The indications for use state "When interpreted by a trained physician, the output of this image analysis toolbox can be used to support the decision-making process," implying human interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The 510(k) summary does not describe any adjudication method for a test set.
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 510(k) summary does not mention a multi-reader multi-case (MRMC) comparative effectiveness study or any effect size regarding human reader improvement with AI assistance. The device is described as an "image analysis software toolbox" that "assists trained cardiologists and radiologists," suggesting a user-in-the-loop approach, but no study details are provided.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The 510(k) summary does not detail any standalone algorithm-only performance study. The description consistently emphasizes user interaction ("Users of MRI-Plaque View perform semi-automatic delineation," "Users may edit the results on the fly").
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The 510(k) summary does not specify the type of ground truth used for any validation. Given the device's function in quantitative analysis of carotid arteries, it would typically involve comparisons to expert annotations or potentially more invasive validation methods if available (e.g., histology from resected plaques, though this is less common for carotid MRI).
8. The sample size for the training set
The 510(k) summary does not provide information on the sample size for any training set.
9. How the ground truth for the training set was established
The 510(k) summary does not describe how ground truth for any training set was established.
Conclusion based on the provided text:
The 510(k) summary for MRI-PlaqueView lacks the specific details regarding acceptance criteria, study methodologies, sample sizes, and ground truth establishment that you've requested. This is common for 510(k) submissions, especially older ones, which often relied heavily on demonstrating substantial equivalence to predicate devices rather than providing extensive quantitative performance data against specific acceptance criteria. The approval indicates that the FDA found the device "substantially equivalent" to legally marketed predicate devices, meaning it has similar intended use, technological characteristics, and safety and effectiveness profiles, even if detailed performance metrics are not publicly disclosed in this summary.
§ 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).