(105 days)
ANKYRAS enables visualization of cerebral blood vessels for preoperational planning and sizing for neurovascular interventions and surgery.
ANKYRAS also allows for the ability to computationally model the placement of neurointerventional braided endovascular devices.
General functionalities are provided such as:
- Segmentation of neurovascular structures*
- Semi-automatic centerline generation from segmented blood vessels*
- Visualization of X-ray based images*
- Placing and sizing tools for braided endovascular devices
- Save user data
- Download** and share simulation***
Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider´s judgment and analysis of the patient´s condition.
ANKYRAS is available in different platforms: Standalone, WebGL and Mobile App.
*Available for Standalone and WebGL platforms
**Available for WebGL platform
***Available for WebGL and Mobile App platforms
ANKYRAS is a medical device software application that allows the simulation of neurointerventional endovascular braided devices, such as flow diverters (FDs), and is intended to be used by physicians trained in medical procedures involving percutaneous and intravascular interventions for preoperational planning and sizing for neurovascular interventions and surgery. The software includes a database with braided endovascular FD devices: P100018/S015 - Pipeline Flex Embolization Device and P100018/S026 - Pipeline Flex Embolization Device with Shield Technology, Medtronic, Inc.; P170024/S003 - Surpass Evolve Flow Diverter System, Stryker Neurovascular; P180027 - Flow Re-Direction Endoluminal Device (FRED®) System and P180027/S002 - Flow Re-Direction Endoluminal Device (FRED®) X System, MicroVention, Inc. This database can be customized (among FDA cleared braided endovascular devices previously mentioned) according to the user's institution or needs.
ANKYRAS is intended to be used with 3D Rotational Angiography (3DRA) images or with VTK surface models from the target artery. From the 3DRA images, the user can extract the target artery vessel model using ANKYRAS segmentation functionality for further anatomical analysis and computational modeling (simulation) of the listed above FDs:
- First, using the vessel model and proximal and distal points selected by the user, ANKYRAS calculates the vessel centerline and displays cross-sectional dimensional information in an interactive chart.
- Second, using the vessel model, centerline, and morphology measurements, ANKYRAS simulates the FD devices selected by the user. The user can compare the results between different simulated FD devices and/or different FD positions including simulated device length, expansion along the centerline, and local porosity.
The information provided by the software is not intended in any way to eliminate, replace, or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition.
ANKYRAS software is intended to be user with a user license and can be installed on a computer with Windows operating systems or installed on an iOS/Android mobile device.
The FDA 510(k) clearance letter for ANKYRAS (K250160) states that the device was deemed substantially equivalent to the predicate device (K230006) based on verification, validation, and performance testing. While the document outlines the types of tests conducted, it does not provide specific quantitative acceptance criteria or detailed results of those tests. It states that "All tests have passed and demonstrate that the software is designed to meet the software requirements" and that "The computational modeling and prediction accuracy/error deployed length, expansion, and porosity of the selected flow diverters was evaluated through the following two tests." However, it lacks the numerical data to populate a table of reported device performance against specific criteria.
Therefore, many of the requested details about the study that proves the device meets the acceptance criteria are not explicitly present in the provided FDA 510(k) clearance letter. I will extract and infer what information is available and highlight what is missing.
Acceptance Criteria and Device Performance
The document describes the criteria used in software validation testing conceptually, but not with specific numerical thresholds for acceptance. It states what the accuracy of ANKYRAS's estimations "has to be equal or better than" certain references, but it doesn't quantify "equal or better than" in terms of a percentage or specific numerical tolerance.
Table 1: Acceptance Criteria (Conceptual) and Reported Device Performance (Not Quantified)
| Feature/Parameter | Acceptance Criteria (Conceptual) as stated in document | Reported Device Performance |
|---|---|---|
| Length Estimation Accuracy | Equal or better than the accuracy of the length calculated from the FD manufacturer specifications (reference length). | "All tests have passed and demonstrate that the software is designed to meet the software requirements." (No specific numerical accuracy reported) |
| Expansion Estimation Accuracy | Equal or better than the accuracy of the expansion calculated from the mean vessel diameter (reference expansion). | "All tests have passed and demonstrate that the software is designed to meet the software requirements." (No specific numerical accuracy reported) |
| Porosity Estimation Accuracy | Equal or better than: |
- The accuracy of the nominal porosity obtained from the nominal FD diameter and the FD manufacturer specifications, AND
- The accuracy of the reference porosity obtained from the patient's mean vessel diameter and the FD manufacturer specifications. | "All tests have passed and demonstrate that the software is designed to meet the software requirements." (No specific numerical accuracy reported) |
Study Details:
-
Sample Size and Data Provenance:
- Test Set Sample Size: The document mentions "physical phantoms representative of anatomy of patients presenting with intracranial aneurysms" and "retrospective clinical images." However, it does not specify the number of phantoms or retrospective clinical images used in the test set.
- Data Provenance:
- Physical Phantoms: Implied to be generated for the study, often representing generic or synthesized anatomies. No specific country of origin mentioned.
- Retrospective Clinical Images: Data provenance is "retrospective clinical images." No country of origin is specified.
-
Number of Experts and Qualifications for Ground Truth:
- The document states: "Segmentation by user with clinician review and comment." This implies human input for ground truth, particularly for the anatomical models used.
- However, the number of experts used to establish the ground truth for the test set and their specific qualifications (e.g., "radiologist with 10 years of experience") are not provided.
-
Adjudication Method for the Test Set:
- The document implies a "clinician review and comment" for segmentation.
- The specific adjudication method (e.g., 2+1, 3+1, none) for resolving discrepancies in ground truth establishment for the test set is not detailed.
-
Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- No, an MRMC comparative effectiveness study was not explicitly mentioned or described. The validation tests focused on the accuracy of the computational model's predictions (length, expansion, porosity) against a ground truth, rather than measuring how human readers improve with AI assistance compared to without.
-
Standalone Performance:
- Yes, a standalone (algorithm only) performance evaluation was done for the computational modeling functionality. The validation tests evaluated "the performance (error) of the ANKYRAS in calculating the deployed length, expansion, and porosity of the selected flow diverters." This refers to the accuracy of the algorithm's output itself, not its use by a human.
-
Type of Ground Truth Used:
- Combined approach:
- Physical Phantoms: Likely based on precisely measured physical properties or known configurations of flow diverters within phantoms.
- Clinical Images: The "true length of FD after intervention," "true expansion of FD after intervention," and "true porosity of FD after intervention" were used as reference for the retrospective clinical images. This implies that actual post-intervention measurements, potentially from follow-up imaging, surgical reports, or device specifications applied to the observed post-implant state, served as ground truth. The segmentation itself from 3DRA images involved "clinician review and comment," suggesting expert consensus for the anatomical model from which measurements were derived.
- Combined approach:
-
Training Set Sample Size:
- The document does not provide any information on the sample size used for the training set.
-
How Ground Truth for Training Set was Established:
- The document does not provide any information on how the ground truth for the training set was established. This information is typically proprietary to the manufacturer and not usually detailed in a 510(k) 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).