(274 days)
To receive, store, transmit, post-process, display and allow manipulation of reports and medical images from acquisition devices, including optical or other non-DICOM format images. DICOM images with modality type XA, US, CR, DR, SPECT, NM and MG, and images from volumetric medical scanning devices such as EBT, CT, PET or MRI. To provide access to images derived data and derived images via client-server software, web browser and mobile technology.
Visualization in 2D, 3D and 4D are supported for single or multiple datasets, or combinations thereof. Tools are provided to define and edit paths through structures such as centerlines, which may be used to analyze cross-sections of structures, or to provide flythrough visualizations rendered along such a centerline. Segmentation of regions of interest and quantitative analysis tools are provided, for images of vasculature, pathology and morphology, including distance, angle, volume, histogram, ratios thereof, and tracking of quantities over time. A database is provided to track and compare results using published comparison techniques such as RECIST and WHO. Calcium scoring for quantification of atherosclerotic plaque is supported.
Support is provided for digital image processing to derive metadata or new images from input image sets, for internal use or for forwarding to other devices using the DICOM protocol. Image processing tools are provided to extract metadata to derive parametric images from combinations of multiple input images, such as temporal phases, or images co-located in space but acquired with different imaging parameters, such as different MR pulse sequences, or different CT image parameters (e.g. dual energy).
iNtuition is designed for use by healthcare professionals and is intended to assist the physician in diagnosis, who is responsible for making all final patient management decisions.
Interpretation of mammographic images or digitized film screen images is supported only when the software is used without compression and with an FDA-Approved monitor that offers at least 5Mpixel resolution and meets other technical specifications reviewed and accepted by the FDA.
iNtuitionMOBILE provides wireless and portable access to medical images. This device is not intended to replace full workstations and should be used only when there is no access to a workstation. Not intended for diagnostic use when used via a web browser or mobile device.
iNtuition is a software device generally used with off-the-shelf hardware, offered in various configurations, with the simplest configuration being a stand-alone workstation capable of image review, communications, archiving, database maintenance, remote review, reporting and basic 3D capabilities described elsewhere in this document. The system can also be configured as a server with some, all, or none of its optional features disabled. Whether provided as a workstation or a server, the iNtuition software is designed to provide access by a local user physically sitting at the computer hosting the iNtuition server software, and/or by one or more remote users who concurrently connect to the server using a freely-downloadable thin client application (with conference capabilities). iNtuition supports the physician in medical image viewing.
A fully-configured iNtuition system is capable of various image processing and visualization functions, including full-color Volume Rendering, Calcium Scoring, Segmentation Analysis and Tracking (SAT), Vessel Analysis, Flythrough, Multi-phase review, CT/ CTA Subtraction, Lobular Decomposition (LD), iGENTLE, Maxillo-Facial, Volumetric Histogram, Findings Workflow, Fusion CT/ MR/ PET/ SPECT, MultiKV etc. Each of these features may be offered as an independent upgrade option to the basic configuration.
The intended use of the device is to provide solutions to various medical image analysis and viewing problems, which come about as modalities generate more and more images. It also supports image distribution over networks, and is DICOM compliant.
The provided 510(k) summary for the iNtuition device (K121916) explicitly states that no clinical studies were required or performed to prove the safety and effectiveness of the software. This is a critical piece of information. The assessment relies on non-clinical performance tests and a comparison to predicate devices to establish substantial equivalence.
Therefore, many of the requested categories related to clinical studies and ground truth establishment will be "Not Applicable" or "Not Reported" based on the provided document.
Here's the breakdown based on the given text:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Compliance with internal company procedures | Performance testing carried out according to internal company procedures. |
| Compliance with voluntary standards (e.g., DICOM) | Voluntary standards such as DICOM are in place and utilized in the production of the software. |
| Software testing and validation according to written test protocols | Software testing and validation were done according to written test protocols established before testing was conducted. |
| Software fully satisfies all expected and previously defined system requirements and features | Test results were reviewed by designated technical professionals, ensuring the software fully satisfies all expected and previously defined system requirements and features. |
| Actual device performance satisfies design intent | Test results support the conclusion that actual device performance satisfies the design intent. |
| Substantial equivalence to predicate devices | Device is substantially equivalent to predicate devices (Aquarius Workstation (K011142), AquariusNET Server (K012086), AquariusAPS Server (K061214), VitreaView (K122136), IQQA-Liver Software (K061696)). |
| No significant concerns of safety and efficacy | "The introduction of iNtuition has no significant concerns of safety and efficacy." |
| Performs as well as predicate devices | "iNtuition... performs as well as the predicate devices." |
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size for Test Set: Not reported. The document states "no clinical studies were required to show safety and effectiveness of the software." Performance testing was non-clinical.
- Data Provenance: Not reported, as no clinical data was used for direct safety and effectiveness demonstrations. Non-clinical performance tests would likely use synthetic or internal test data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of Experts: Not applicable/Not reported. Ground truth in a clinical sense was not established for non-clinical performance tests. "Designated technical professionals" reviewed test results for software validation, but their qualifications are not specified beyond that title.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: Not applicable/Not reported. This relates to clinical studies for establishing ground truth, which were not performed.
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
- MRMC Study: No. The summary explicitly states: "The subject of this traditional 510k notification, iNtuition, did not require clinical studies to show safety and effectiveness of the software." Therefore, no MRMC study comparing human readers with or without AI assistance was performed.
- Effect Size: Not applicable.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Not explicitly detailed as a separate study. The device is a "software device" and "offers convenient tools to support creation of a report," but its performance metrics are established through non-clinical software validation and comparison to predicate devices, not through a standalone performance study with specific metrics like sensitivity/specificity against a gold standard. The device is "intended to assist the physician in diagnosis, who is responsible for making all final patient management decisions," implying a human-in-the-loop context for diagnostic use.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: Not applicable/Not reported for demonstrating safety and effectiveness. For non-clinical software performance tests, the "ground truth" would be established by the expected output based on the defined system requirements and internal test protocols.
8. The sample size for the training set
- Sample Size for Training Set: Not applicable/Not reported. The device is a general medical imaging system, not an AI/ML device in the modern sense that requires a specific training set to learn from data for a particular diagnostic task. Its functionality is based on established algorithms and image processing techniques.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable/Not reported, as there is no mention of a training set for an AI/ML model.
§ 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).