(36 days)
The CAAS MRV has been designed for quantitative functional analysis of the left and right ventricle of the heart based on multi-slice, multi-phase cine MRI images. Specifically, it enables the user to: 1. Delineate automatically or semi-automatically the inner and outer wall of the ventricles, as well as the papillary muscles, on the MRI images 2. Derive from these contours the global and regional functional parameters like Ejection Fraction, Stroke Volume, Wall Movement etc. The CAAS MRV has been designed to be used in everyday clinical practice, as well as for research purposes like clinical research trials.
The CAAS MRV is a software tool designed for the functional analysis of the heart based on multi-slice, multi-phase MR images of the heart. Therefore it provides functionality to import and view cine MR datasets of the heart from several vendors from CDROM, hard disk or (optionally) a PACS system. Next, the inner and outer wall of the ventricles can be determined either automatically, semi-automatically or manually. From these contours the ventricular volume, the ejection fraction and other related parameters are determined. Next to the quantification of the ventricular volumes, also the motion of the ventricular wall is quantified. All results of the analysis are available on screen as well as hardcopy, and can be saved.
The provided text describes the CAAS MRV software package, its intended use, and its substantial equivalence to a predicate device. However, it does not contain the detailed information necessary to fully answer your request regarding acceptance criteria, specific study designs, or performance metrics.
The document is a 510(k) summary and FDA clearance letter, which primarily focuses on demonstrating substantial equivalence to a legally marketed predicate device rather than presenting a full clinical validation study.
Based on the available information, here's what can be extracted and what is missing:
1. A table of acceptance criteria and the reported device performance:
-
Acceptance Criteria: Not explicitly stated in the document as quantitative criteria with thresholds. The key "acceptance criterion" for 510(k) clearance is demonstrating substantial equivalence to a predicate device.
-
Reported Device Performance: The document states that "CAAS MRV is substantially equivalent to the quantitative analysis software package MRI-Magnetic resonance Analytical Software System, K994283." It also mentions that the CAAS MRV "is substantially equivalent to the predicate device mentioned in this summary by using the same technological characteristics and intended use."
Acceptance Criteria (Inferred from 510(k)) Reported Device Performance Substantial equivalence to predicate device (K994283) in technological characteristics and intended use CAAS MRV found substantially equivalent to predicate device Ability to delineate inner/outer ventricle walls and papillary muscles (auto/semi-auto) Device provides functionality to "determine" inner and outer wall and papillary muscles (auto/semi-auto/manual) Ability to derive global/regional functional parameters (EF, SV, Wall Movement) Device determines ventricular volume, ejection fraction, and other related parameters; quantifies wall motion Missing:
- Specific quantitative performance metrics (e.g., accuracy, precision, inter-observer variability, intra-observer variability) for measurements like Ejection Fraction, Stroke Volume, Wall Movement compared to a gold standard or the predicate device.
- Defined thresholds for these metrics (e.g., "Ejection Fraction measurement will be within X% of the true value").
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- Missing: The document does not provide any information about a specific test set, its sample size, or data provenance. This level of detail is typically part of a separate validation report, not the 510(k) summary.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Missing: This information is not provided. The document does not describe the establishment of a ground truth for a test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Missing: This information is not provided.
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:
- No evidence: The document does not mention a multi-reader, multi-case comparative effectiveness study. The focus is on the device's inherent capabilities and its equivalence to a predicate, not on human-with-AI vs. human-without-AI performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Implied primary function: The device's description highlights its ability to "determine" ventricular parameters "either automatically, semi-automatically or manually." This suggests that a standalone (automatic algorithm only) performance would be a component of its functionality. However, specific standalone performance metrics from a study are not reported in this document. The 510(k) emphasizes its use by a user.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
- Missing: This information is not provided. Given that the device analyzes MRI images, a likely ground truth would involve expert manual contouring and calculation, but this is speculative based on the document.
8. The sample size for the training set:
- Missing: This information is not provided. The document does not discuss training data for the algorithms.
9. How the ground truth for the training set was established:
- Missing: This information is not provided.
In summary:
This 510(k) submission primarily demonstrates that CAAS MRV is "substantially equivalent" to an already marketed device (MRI-Magnetic resonance Analytical Software System, K994283) in terms of its intended use and technological characteristics. It outlines the device's functions (automatic/semi-automatic/manual delineation, calculation of parameters like EF, SV, wall movement) but does not provide the detailed validation study results, specific acceptance criteria with quantitative thresholds, sample sizes for test/training sets, ground truth establishment methods, or expert qualifications that you requested. These details would typically be found in a more comprehensive technical report or validation study that underpins such a submission, but are not included in the provided 510(k) summary or FDA clearance letter.
§ 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).