(196 days)
VitreaAdvanced is a medical diagnostic system for the processing, review, analysis, communication and media interchange of multi-dimensional digital images acquired from a variety of imaging devices. VitreaAdvanced is not meant for primary image interpretation in mammography. It can be used with a variety of cleared Vitrea® based software applications. In addition, VitreaAdvanced includes three Vitrea applications:
Vitrea® CT Body Perfusion is a noninvasive post-processing application designed to evaluate perfusion of organs and tumors. The software can calculate perfusion characteristics from dynamic CT image data acquired after the injection of contrast media. The software also allows the separate calculation of the arterial and venous components of perfusion in organs. It supports evaluation of regions of interest and the visual inspection of time density curves. When used by a trained and qualified physician a potential application is to differentiate blood flow between normal and diseased tissue. Determination of the change of perfusion parameters during the course of treatment may be helpful in therapy monitoring.
Vitrea® CT Liver Analysis is a noninyasive post-processing application designed to evaluate liver tumors and plan for liver surgery. It displays images for analysis and preoperative liver surgery planning, such as organ segmentation, tumor segmentation and intrahepatic vessels seqmentation, as well as the approximation of vascular territories. It supports preoperative evaluation of specific surgery strategies by allowing the user to interactively define virtual resections splitting the liver. It also allows the user to evaluate safety-margins around lesions and to identify affected vascular branches and territories. Vitrea® CT Liver Analysis also provides automatic registration of multiple series and measurement tools for characterization and follow-up of the lesions. When used by a trained and qualified physician a potential application is to assist in the assessment of tumor response to therapy.
Vitrea CT Brain Perfusion is a noninvasive post-processing application designed to evaluate areas of brain perfusion. The software can calculate cerebral blood flow (CBF), cerebral blood volume (CBV), local bolus timing (i.e., delay of tissue response, time to peak), and mean transit time (MTT) from dynamic CT image data acquired after the injection of contrast media. The package also allows the calculation of regions of interest and mirrored reqions, as well as the visual inspection of time density curves. Vitrea® CT Brain Perfusion supports the physician in visualizing the apparent blood perfusion in brain tissue affected by acute stroke. Areas of decreased perfusion, as is observed in acute cerebral infarcts, appear as areas of changed signal intensity (lower for both CBF and CBV and higher for time to peak and MTT).
VitreaAdvanced is a package of noninvasive post-processing software applications for the Vitrea software platform. The system is a software only medical device to be installed on common IT hardware. VitreaAdvanced leverages existing Vitrea® functionality for the processing, review, analysis, communication, and media interchange of multi-dimensional digital images acquired from a variety of imaging devices. It provides multi-dimensional visualization of digital images to aid medical professionals in their analysis of analomy and pathology. VitreaAdvanced can be used with a variety of cleared Vitrea based software applications. VitreaAdvanced uses the Vitreas system user interface to follow typical clinical workflow patterns and process, review, and analyze digital images, including:
- Receive DICOM image data from a variety of sources .
- Display images using dedicated protocols adapted to exam types .
- Select images for closer examination from collection of 2D. 3D or 4D views .
- Interactively manipulate an image in real-time to visualize anatomy and pathology ●
- Annotate, tag, measure, and record selected views .
- . Output selected views to compatible devices and publishing tools (e.g. printers, DICOM devices, etc.)
In addition, VitreaAdvanced includes three Vitrea® applications:
Vitrea CT Body Perfusion is noninvasive post-processing software that has been designed to assess dynamic (time lapsed collections) CT volume scans and provide data related to the volume sets. It displays blood flow parametric maps for single-input and dual-input workflows.
Vitrea® CT Liver Analysis is noninvasive post-processing software that displays CT image data. It processes image data to segment liver structures and evaluate resection surfaces as well as volumes. Vitreas CT Liver Analysis provides automatic registration and composite views of mulliple series, optimized screen layouts and measurement tools. It also generates standardized reports for WHO and RECIST protocols and for percentage change tumor response values.
Vitrea®CT Brain Perfusion is noninvasive post-processing software that calculates cerebral blood flow (CBF), cerebral blood volume (CBV), local bolus timing (i.e., delay of tissue response, time to peak), and mean transit time (MTT) from dynamic CT image data. It displays time density curves, perfusion characteristics in parametric and summary maps, as well as regions of interest and mirrored regions.
Here's a breakdown of the acceptance criteria and the study information for KIBI213 (VitreaAdvanced), based on the provided text:
Acceptance Criteria and Device Performance for VitreaAdvanced
The submission does not explicitly define specific numerical "acceptance criteria" in the format of a typical performance study with thresholds for metrics like sensitivity, specificity, or accuracy. Instead, the acceptance is based on demonstrating substantial equivalence to predicate devices through a combination of verification, validation, and qualitative assessments.
The "device performance" is primarily reported as confirming that the software's functionality, usability, and performance are similar to or meet the user's needs, as assessed during external validation.
Table of Acceptance Criteria (Inferred) and Reported Device Performance
Given the nature of the submission (510(k) for a post-processing software package without specific de novo clinical claims), the acceptance criteria are more functional and qualitative than quantitative.
| Acceptance Criteria (Inferred from Validation Activities) | Reported Device Performance (Summary) |
|---|---|
| Vitrea® CT Body Perfusion | |
| Deformable (non-rigid) registration produces similar results to scanner console. | Confirmed by external cardiologist. |
| Registration time is equal to or less than scanner console. | Confirmed by external cardiologist. |
| Measurements are clinically acceptable. | Confirmed by external cardiologist. |
| Qualitative analysis (visual verification) of registration is visually similar to scanner-applied registration. | Supported by qualitative analysis. |
| Vitrea® CT Liver Analysis | |
| Functionality, usability, and performance are acceptable. | Evaluated by two external 3D Technicians, passed external validation. |
| Vitrea® CT Brain Perfusion | |
| Summary map feature functionality and performance correlation with associated perfusion maps is acceptable. | Evaluated by external radiologist. |
| Software meets intended use and effectively provides summary image and supports characterization/communication. | Confirmed by external radiologist. |
| General VitreaAdvanced | |
| Conformance to new and previously defined specifications. | Ensured via manual, automated, and regression tests. |
| Risks are properly mitigated. | Addressed through risk analysis and testing. |
| Compliance with DICOM standard. | Designed to meet NEMA PS 3.1 - 3.18 Digital Imaging and Communications in Medicine (DICOM) standard. |
| Spatial accuracy of image rendering, distance, angular measurement, and navigational tools. | Verified using imaging phantoms. |
| Accuracy of orientation markers. | Verified using imaging phantoms. |
Study Details
-
Sample size used for the test set and the data provenance:
- Test Set Size: The document does not specify a numerical sample size for "test sets" in the context of a traditional performance study. The validation involved qualitative assessments by experts using "previously acquired medical images" and "various imaging phantoms."
- Data Provenance: The data provenance is not explicitly stated (e.g., country of origin). It refers to "previously acquired medical images" and "imaging phantoms," suggesting retrospective use for verification testing and validation demonstrations.
-
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):
- Vitrea® CT Body Perfusion: An "external cardiologist" was used. Specific years of experience are not mentioned.
- Vitrea® CT Liver Analysis: "Two external 3D Technicians" were used. Specific qualifications (e.g., years of experience) are not mentioned.
- Vitrea® CT Brain Perfusion: An "external radiologist" was used. Specific years of experience are not mentioned.
- General: "Several Radiologists and 3D Technologists" provided feedback and formal acceptance during software testing, but these were for initial validation rather than formal ground truth establishment for a specific test set.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- No formal adjudication method (like 2+1 or 3+1) is described for establishing a "ground truth" in the context of comparative performance. The external validation appears to rely on individual expert confirmation of clinical acceptability and similarity to existing methods.
-
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:
- No MRMC study was done. This 510(k) submission describes verification and validation activities for a post-processing software package, not a comparative clinical effectiveness study designed to measure human reader improvement with or without AI assistance. The focus is on demonstrating substantial equivalence to predicate devices and meeting user needs through functional and qualitative assessments.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- The submission describes "Automated integration level Build Verification Tests (BVT)," "Automated software rendering tests," "Automated algorithm smoke tests and automated algorithm regression tests," and "Automated performance tests." These can be considered forms of standalone algorithm testing for functional correctness, stability, and performance. However, these are technical tests, not clinical performance tests in a standalone diagnostic capacity. The device is a "post-processing software application" intended for use by a "trained and qualified physician."
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The "ground truth" for verification testing of measurements and orientation involved imaging phantoms with known spatial properties.
- For the external validation of the applications, the "ground truth" was effectively expert qualitative assessment and clinical judgment by the cardiologist, 3D technicians, and radiologist, who confirmed clinical acceptability, similarity to existing methods, and fulfillment of intended use. There's no mention of pathology or outcomes data being used for ground truth.
-
The sample size for the training set:
- The document does not specify a sample size for a training set. The described development and testing process is typical for software validation rather than a deep learning model that requires explicit training data. The software utilizes "previously acquired medical images" for testing, but these are for verification and validation, not specifically for training a machine learning model in the sense of a dataset for supervised learning.
-
How the ground truth for the training set was established:
- As no training set is explicitly mentioned or described for a machine learning model, the method for establishing its ground truth is not applicable/not provided in this document.
§ 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).