(228 days)
The Neuro.AI Algorithm is an algorithm for use by trained professionals, including but not limited to physicians, surgeons and medical clinicians.
The Neuro.Al Algorithm is a standalone image processing software device that can be deployed as a Microsoft Windows® executable on off-the-shelf hardware or as a containerized application (e.g., a Docker container) that runs on off-the-shelf hardware or on a cloud platform. Data and images are acquired via DICOM compliant imaging devices. DICOM results may be exported, combined with or utilized by other DICOM-compliant systems and results.
The Neuro.AI algorithm provides analysis capabilities for static, functional, dynamic and derived imaging datasets acquired with CT or MRI. It can be used for the analysis of dynamic brain image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vasular assessment and tissue blood volume and other parametric maps with or without the ventricles included in the calculation. The algorithm also includes volume reformat in various orientions, rotational MIP 3D batch while removing the skull. This "tumble view" allows qualitative review of vascular structure in direct correlation to the perfusion maps for comprehensive review.
The results of the Neuro.AI Algorithm can be delivered to the end-user through image viewers such as TeraRecon's Aquarius iNtuition system, TeraRecon's Northstar AI Results Explorer, or other image viewing systems like PACS that can support DICOM results generated by Neuro.AI.
The Neuro.AI Algorithm results are designed for use by trained healthcare professionals and are intended to assist the physician in diagnosis, who is responsible for making all final patient management decisions.
The Neuro.Al Algorithm is a modification of the predicate device, iNtuition-TDA, TVA, Parametric Mapping which was cleared under K131447. The predicate device is an optional module/workflow for the iNtuition system (K121916). The Neuro.Al Algorithm is a standalone image processing software device that can be deployed as a Microsoft® Windows executable on off-the-shelf hardware or as a containerized application (e.g., Docker container) that runs on off-the-shelf hardware or on a cloud platform. The device has limited network connectivity or external medical support.
The Neuro.Al Algorithm allows motion correction and processes, calculates and outputs brain perfusion analysis results for static, functional, dynamic and derived imaging datasets acquired with CT or MRI. Neuro.Al results are used for visualization and analysis of dynamic brain perfusion image data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to brain tissue perfusion, vascular assessment displayed in rotational Maximum Intensity Projection (MIP) called the tumble view, and tissue blood volume and other parametric maps with or without brain ventricles included in the calculation.
Outputs include text and parametric map displays of measurements including time to peak (TTP), take off time (TOT), recirculation time (RT), mean transit time (MTT), blood volume (BV/CBV), blood flow (BF/CBF), classification maps, reformatted images and rotational MIPs for 2D and 3D visualization of brain tissues and blood vessels, and for correlation to the perfusion maps.
The results of the Neuro.Al Algorithm can be delivered to the end-user through image viewers such as TeraRecon's iNtuition system, TeraRecon's Northstar Al Results Explorer ("Northstar"), or other third-party image viewing systems like PACS that can display the DICOM results generated by Neuro.Al output does not depend on the viewing system's capabilities as the results are self-contained and the only interface is through DICOM.
When the Neuro.Al Algorithm results are used on iNtuition, all the standard features offered by iNtuition are employed such as image manipulation tools like drawing the region of interest, manual or automatic segmentation of structures, tools that support creation of a report, transmitting and storing this report in digital form, and tracking historical information about the studies analyzed by the software.
The Neuro.Al algorithm can be used by physicians to aid in the diagnosis. The software is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by individuals that have been trained in the software's function, capabilities and limitations. The device is intended to provide supporting analytical tools to a physician, to speed decision-making and to improve communication, but the physician's judgment is paramount, and it is normal practice for physicians to validate theories and treatment decisions multiple ways before proceeding with a risky course of patient management.
The provided document describes the Neuro.AI Algorithm and its substantial equivalence to a predicate device, iNtuition-TDA, TVA, Parametric Mapping (K131447). However, it does not contain a detailed performance study with specific acceptance criteria and reported device performance in the format requested. The document focuses on regulatory compliance, outlining the device's indications for use, technological characteristics, and a general statement about software verification and validation.
Therefore, many of the requested items cannot be extracted directly from this document.
Here's a breakdown of what can and cannot be answered based on the provided text:
1. A table of acceptance criteria and the reported device performance
Not provided in the document. The text states: "During software testing, all predefined acceptance criteria for the Neuro.Al Algorithm were met and all software test cases passed." However, it does not specify what those acceptance criteria were or provide a table of performance metrics.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not provided in the document. The document mentions "software testing and performance evaluation" but does not detail the test set's sample size or data provenance.
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)
Not provided in the document. The document describes the device's intended use by "trained professionals, including but not limited to physicians, surgeons and medical clinicians" but doesn't specify how ground truth was established for testing.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not provided in the document.
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
Not provided in the document. The document does not describe a comparative effectiveness study involving human readers with and without AI assistance. The focus is on the device's substantial equivalence to a predicate device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, implicitly. The document describes the "Neuro.AI Algorithm as a standalone image processing software device." The testing mentioned ("software testing and performance evaluation") would inherently be evaluating the algorithm's standalone performance against its predefined acceptance criteria, even if those criteria aren't explicitly detailed. The statement "The Neuro.AI Algorithm is as safe and effective as the predicate device" implies standalone testing for functional equivalence.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not explicitly provided in the document. While the device assists in diagnosis, the method for establishing ground truth for testing is not described.
8. The sample size for the training set
Not provided in the document. The document describes a "510(k) summary," which focuses on demonstrating substantial equivalence to a predicate device rather than detailing AI model development specifics like training set size.
9. How the ground truth for the training set was established
Not provided in the document. Similar to the training set size, the method for establishing ground truth for training is not included in this regulatory 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).