(305 days)
The CT TAVI Planning application is intended to be used for patients with aortic valvular disease, severe symptomatic aortic stenosis or tricuspid aortic valve. The intended part of the body for this application is the human heart, specifically the ascending aorta, aortic root, coronary ostia and left ventricle in order to assess the aortic valve in pre-operational planning of transcatheter aortic valve replacement procedures.
CT TAVI Planning is a non-invasive post-processing application providing 3D model-based segmentation of the aortic valve and aortic arch. The CT TAVI Planning application provides assessment and measurements of relevant heart structures for TAVI-device sizing, and allows the user to select a starting angle for C-arm position from the possible optimal positions from the CT TAVI and select a C-arm angle the user feels is appropriate to use in the catheterization laboratory by the Interventional team performing the procedure (to be used during the procedure itself).
The physician retains the ultimate responsibility for making the determination of patient eligibility or which device is implanted based on their standard practices and additional imaging modalities such as echocardiography.
The CT TAVI Planning application is intended for visualization, assessment and quantification of medical images, specifically quantitative distance and area measurements for CT images from adult patients with a diagnosis of aortic stenosis in which a non-surgical approach is recommended.
The application supports contrast-enhanced. prospectively ECG-gated axial or retrospectivelygated helical CT images as well as un-gated helical scans.
The application provides visualization and measurement tools for qualitative and quantitative visualization and assessment of the input data.
It provides tools to determine the size and shape of the aortic root anatomy, ascending aorta and left ventricular outflow tract.
The CT TAVI Planning Application provides model-based segmentation of the aortic valve, ascending aorta and left ventricle, detection of the coronary ostia, planes detection and dimensions measurements of the aortic annulus, left ventricular outflow tract, simotubular junction, sinus of valsalva, ascending aorta and distance to coronary ostia for TAVI-device sizing. While both predicate devices and CT TAVI Planning provide detection and manual correction of the annulus plane, Philips CT TAVI Planning, utilizing the same planes and landmarks detection algorithm as Philips HeartNavigator, has extended that functionality to also include additional planes relevant to the planes at which physicians currently measure for pre-planning: Left Ventricular Outflow Tract (LVOT). Sinotubular Junction, Sinus of Valsalva, and Ascending Aorta planes.
Here's a breakdown of the acceptance criteria and study information for the Philips CT TAVI Planning Application, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided 510(k) summary focuses on demonstrating substantial equivalence to predicate devices and describes the verification and validation activities. It does not explicitly state specific numerical acceptance criteria for performance metrics (e.g., accuracy percentages, error margins for measurements). Instead, it states that the verification and validation activities confirmed the device met its design specifications and user needs.
Therefore, the table below reflects the nature of the verification and validation activities and the general conclusion, rather than discrete numerical criteria.
| Acceptance Criteria Category (Derived from document) | Reported Device Performance (General Conclusion) |
|---|---|
| Functional Requirements | Application met its design specifications. |
| Implementation | Application met its design specifications. |
| Risk Management File (RMF) | Risk management file requirements were met. |
| Calculations, Measurements, Patient Details | Checked within RMF tests. |
| Main Features & Workflow (Critical Tests) | Tested and confirmed. |
| Full Functionality | All TAVI functionality cases covered. |
| Defect Fixes | Covered. |
| User Needs (Internal & External Validation) | Met user needs and intended uses. |
| Intended Use | Device works according to its intended use. |
| Safety | Device is safe. |
| Effectiveness / Performance | Performs as well as or better than predicate devices. |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document does not specify a numerical sample size for either the internal validation (by clinical experts) or the external validation (at beta sites). It broadly refers to "patient CT studies from various vendors."
- Data Provenance:
- The document states, "CT TAVI Planning allows users to select patient CT studies from various vendors." This implies the data could originate from multiple sources and potentially different geographic regions, though specific countries are not mentioned.
- It mentions that the application supports "contrast enhanced CT images" and "prospectively ECG-gated axial or retrospectively-gated helical CT images as well as un-gated helical scans." This indicates both retrospective and prospective data types are compatible with the system, but it doesn't explicitly state the nature of the data used for validation. Given the context of a 510(k) summary, it's highly probable that existing, often retrospective, de-identified patient data was used for validation purposes.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: The document refers to "clinical experts" for internal validation and "local medical staff (radiologists and/or cardiologists)" for external validation. It does not provide a specific number for either.
- Qualifications of Experts:
- Internal Validation: "Clinical experts can be non-Philips employees that can simulate the work of a typical clinical user as long as they did not participate in the development process and verification process." Specific professional qualifications (e.g., radiologist, cardiologist) or years of experience are not mentioned for these internal experts.
- External Validation: "local medical staff (radiologists and/or cardiologists)." Specific years of experience are not mentioned.
4. Adjudication Method for the Test Set
The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1 consensus) for establishing ground truth from the experts. It mentions that clinical experts and medical staff used the system in a validation context and that a "clinical expert report" was part of the verification report. This suggests qualitative or comparative assessment rather than a formal, quantitative ground truth adjudication process for specific measurements.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, the document does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study to quantify how much human readers improve with AI vs. without AI assistance. The validation activities focus on the device's performance in meeting its intended use by supporting expert workflows, but not on a formal head-to-head comparison of human performance with and without the device.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, the verification activities described suggest a form of standalone testing for the algorithm's core functionalities. The "Full functionality test included all TAVI functionality cases and covered all of the detailed requirements," and "RMF tests which in general check calculations, measurements, patient details and information and other scenarios which might lead to misdiagnosis" implies testing the algorithm's output (segmentation, measurements) against expected values or design specifications. However, the exact methodology for assessing accuracy in a purely standalone, ground-truth-driven way is not detailed beyond these statements. The validation activities, which involve clinical experts using the system, are ultimately human-in-the-loop, where the device "provides assessment and measurements" for the user.
7. The Type of Ground Truth Used
The primary type of "ground truth" used for validation appears to be expert assessment and consensus on clinical utility and accuracy of measurements/segmentation. While the document mentions "checks calculations, measurements, patient details and information," it doesn't specify if an independent, gold-standard reference (like pathology or subsequent clinical outcomes) was used to establish the absolute correctness of every measurement. Instead, the focus is on the device supporting the expert's workflow and providing relevant information. The "clinical experts" and "radiologists and/or cardiologists" were involved in judging if the application met user needs and intended uses, implying their expert opinion served as the de-facto ground truth for usability and clinical relevance.
8. The Sample Size for the Training Set
The document does not provide any information regarding the sample size used for the training set of the algorithm. This is typical for a 510(k) summary, which focuses on validation after development rather than the details of the development process (like training data).
9. How the Ground Truth for the Training Set Was Established
The document does not provide any information on how the ground truth for the training set was established. This detail would typically be part of algorithm development documentation, not necessarily a 510(k) summary for a post-processing application.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.