(74 days)
The Vitrea® CT Multi-Chamber CFA option is intended to be used with CT studies of the heart to assist cardiologists and radiologists in assessing function when producing a cardiac evaluation. The CT Multi-Chamber CFA option includes semi-automatic heart segmentation including three chambers (left ventricle, right ventricle, and left atrium) segmentation, including identification of long axis and mitral valve boundaries across multiple phases; calculation of global metrics, including end diastolic volume, end systolic volume, stroke volume, ejection fraction, cardiac output, cardiac index, stroke index, and myocardial mass; and calculation of regional metrics; including wall motion, percentage of wall thickening, regional ejection fraction, and polar plots.
The Vitrea CT Multi-Chamber Cardiac Functional Analysis (CFA) software application is a new post processing licensable software preset available on the Cardiac Functional CT protocol for the Vitrea Platforms. This product can be used in the analysis of CT angiographic images to calculate and display several functional cardiac parameters. The software has the ability to select the chambers of the heart and diastolic and/or systolic phases to evaluate the heart's function. The Vitrea CT Multi-Chamber CFA software application contains both graphic and text report capabilities with predefined templates for ease of use.
Here's a breakdown of the acceptance criteria and the study information for the Vitrea CT Multi-Chamber Cardiac Functional Analysis (CFA) device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document does not explicitly list quantitative acceptance criteria for the device's performance in terms of specific metrics (e.g., accuracy, precision for EDV, ESV, EF). Instead, the acceptance is based on demonstrating substantial equivalence to predicate devices and fulfilling general software development and risk management standards.
The "reported device performance" in this context refers to the successful completion of verification and validation tests, confirming the software operates according to its requirements and user needs.
| Category | Acceptance Criteria (Inferred/Stated) | Reported Device Performance |
|---|---|---|
| Functional Performance | Software operates according to its requirements (e.g., semi-automatic segmentation, calculation of cardiac parameters like EDV, ESV, EF, CO, etc., display of regional metrics, polar plots). | Test cases were executed against system features and requirements, and a Requirements Traceability Matrix (RTM) was used to ensure coverage. Workflow testing was conducted by experts. The device provides "Yes" for all listed characteristics comparable to predicate devices, indicating successful implementation. These characteristics include: |
- Semi-automatic segmentation of LV, RV, and LA chambers (for the new features).
- Calculation of various global and regional cardiac metrics.
- Image viewing, editing, and reporting capabilities. |
| Usability/User Needs | Software conforms to user needs and intended use, assisting cardiologists and radiologists in assessing cardiac function from CT studies. | Experienced cardiologists evaluated the application and "felt that the Vitrea CT Multi-Chamber Cardiac Functional Analysis (CFA) software application can be used successfully with CT studies of the heart to assist cardiologists and radiologists in assessing function when producing a cardiac evaluation." |
| Safety & Effectiveness | No new safety and efficacy concerns raised, overall residual risk deemed acceptable after mitigations based on risk analysis and compliance with standards. | Risk analysis conducted (ISO 14971:2012), all identified risks reduced as low as possible. Software developed and tested according to written procedures including risk management. New features (RV/LA evaluation, additional metrics) were assessed to have the same risk profile as the predicate or mitigated through design, labeling, and V&V tests, not raising new safety/effectiveness concerns. |
| Regulatory Compliance | Compliance with applicable regulations and recognized consensus standards (e.g., DICOM, ISO 14971, IEC 62304). | The software complies with PS 3.1-3.20 (2011) NEMA DICOM Set, ISO 14971:2007, and IEC 62304:2006. |
| Cybersecurity/Information | Adherence to principles of Confidentiality, Integrity, Availability, and Accountability. | Relies on Windows Login for access control (Confidentiality). Complies with DICOM for data transfer and storage, marking and encoding data it produces (Integrity). Always available to logged-on user given Windows machine maintenance (Availability). Includes audit capability with time-stamped logs for user operations and information accessed (Accountability). |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document does not specify an exact number of cases or studies used for the "verification of the software" or "validation of the software." It mentions "previously acquired medical images" and "workflow testing that provided evidence that the system requirements and features were implemented, reviewed and met."
- Data Provenance: The text states "previously acquired medical images" (for verification) and "CT studies of the heart" (for validation by cardiologists). The country of origin is not specified, and the data is retrospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: The document states that "experienced cardiologists evaluated the application" during external validation. It does not provide an exact number or a range for the "experienced cardiologists."
- Qualifications of Experts: They are described as "experienced cardiologists." No specific years of experience or sub-specialty details are provided beyond "cardiologists."
4. Adjudication Method for the Test Set
The document does not describe a formal adjudication method (like 2+1 or 3+1 consensus) for establishing ground truth within the validation process. The "experienced cardiologists" "evaluated the application" and "felt that" it could be successfully used. This suggests a qualitative assessment of functionality and clinical utility rather than a quantitative comparison against an adjudicated ground truth for specific measurements.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size (AI vs. without AI assistance)
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The submission explicitly states: "The subject of this traditional 510(k) notification, Vitrea CT Multi-Chamber Cardiac Functional Analysis (CFA) software application, did not require clinical studies to support safety and effectiveness of the software." The validation was focused on proving the software functions as intended and is perceived as useful by experts, rather than demonstrating an improvement in human reader performance with AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The device is described as an "option" and "application" intended "to assist cardiologists and radiologists in assessing function." The external validation involved "experienced cardiologists" evaluating the application, confirming it "can be used successfully... to assist." This indicates the device is designed for human-in-the-loop use. The document doesn't explicitly describe a standalone performance evaluation where the algorithm's output is judged without any human intervention or review. The semi-automatic nature of the segmentation also implies human interaction.
7. The Type of Ground Truth Used
The ground truth for the device's functional correctness was established through:
- Software Requirements: Internal verification against predefined software requirements.
- Predicate Device Equivalence: The primary basis for equivalence, where the device's functionalities were compared to those of two legally marketed predicate devices, implying those devices' output represents a form of accepted clinical "ground truth."
- Expert Qualitative Assessment: During "External Validation," experienced cardiologists qualitatively assessed the application's utility and usability, essentially acting as a form of "expert consensus" on whether the tool correctly assists in cardiac evaluation, rather than providing exact numerical ground truth for calculations.
There is no mention of pathology or outcomes data being used for ground truth.
8. The Sample Size for the Training Set
The document does not provide any information regarding the sample size used for training the algorithms within the Vitrea CT Multi-Chamber Cardiac Functional Analysis (CFA) software. Given the submission date (2014) and the description of the software as "semi-automatic heart segmentation," it's possible that traditional image processing and analysis algorithms were used, which might not rely on "training sets" in the same way modern deep learning AI models do.
9. How the Ground Truth for the Training Set Was Established
Since the document does not mention a training set or the type of algorithms used (beyond "semi-automatic segmentation"), there is no information on how ground truth for a training set (if one existed for elements like segmentation) would have been established.
§ 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).