Search Results

Cercare Medical Neurosuite (CMN) and associated modules is an image processing software package to be used by trained professionals, including physicians and medical technicians.

The CMN software package runs on standard off-the-shelf computer or a virtual platform, such as VMware, and can be used to perform image viewing, processing, and analysis of images. Data and images are acquired through DICOM (Digital Imaging and Communications in Medicine) compliant imaging devices. CMN provides viewing capabilities of datasets acquired with CT and MRI.

The Capillary Function module provides analysis capabilities for functional and dynamic imaging datasets acquired with MRI including a Diffusion Weighted MRI (DWI) Module and a Dynamic Analysis Module (dynamic contrast-enhanced imaging data for MRI and CT). The Capillary Function module is used for visualization and analysis of dynamic imaging data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to tissue flow (perfusion) and tissue blood volume. In addition, the Capillary Function module's DWI technology is used to visualize local water diffusion properties from the analysis of diffusion-weighted MRI data.

The Virtual Expert module allows the calculation of regions of interest and the visual inspection of time attenuation curves. For MRI, one clinical application is to visualize the apparent blood perfusion and diffusion and to calculate ADC threshold volume, Tmax threshold volume, and Mismatch Ratio in the brain tissue affected by acute stroke.

For CT, one clinical application is to visualize the apparent blood perfusion and to calculate rCBF threshold volume, Tmax threshold volume, and Mismatch Ratio in the brain tissue affected by acute stroke.

Areas of decreased perfusion appear as areas of changed signal intensity:

• Lower signal intensity for CBF and CBV
• Higher signal intensity for TTP, MTT, and Tmax

Cercare Medical Neurosuite is a software-only device designed to streamline medical inage processing by providing for the visualization and study of medical images. CMN can be installed on a customer PC, or it can be accessed remotely using remote desktop technologies. CMN provides viewing, quantification, analysis and reporting capabilities. CMN is not intended as a dedicated PACS system for long term persistent storage of patient data.

CMN is software that is intended for use by trained professionals, including physicians and medical technicians. The software provides cerebral image processing capabilities. CMN is intended to be used as decision support software only and the clinician continues to provide all treatment decisions.

The software is intended to visualize and study neuroimaging by image viewing and registration of medical images. CMN works with MRI (Magnetic Resonance Image) and CT (computed tomography) technologies.

CMN accepts and produces data sets in the DICOM format. DICOM is a standard format for storing and transmitting medical image data in vendor neutral format and is managed by the DICOM Standards Committee.

CMN is a platform that allows for the addition of certain modules for further analysis. One of these modules included in this submission is Capillary Function.

CMN Capillary Function:
Capillary Function, when activated in the installed Cercare Medical Neurosuite, provides further functionalities for reading, writing, visualizing and studying medical images.

Capillary Function provides perfusion post-processing technologies, where dynamically acquired perfusion MRI or perfusion CT series can be processed to yield information relevant for assessment of the hemodynamic status of a patient.

Capillary Function generates hemodynamic markers, which can be used for management of diseases with possibly compromised hemodynamic function, such as ischemic stroke and tumors.

The generated output maps can be viewed by standard DICOM image viewers. In addition, Capillary Function includes the possibility for post-processing diffusion-weighted imaging (DWI) MRI data. Post-processing of DWI data results in maps reflective of local water diffusion properties. The post-processed DWI-derived maps can be viewed in standard DICOM image viewers. Capillary Function thus works with MRI and CT technologies.

CMN Virtual Expert:
Virtual Expert, when activated in the installed CMN Capillary Function, provides further functionalities for reading, writing, visualizing, and studying medical images.

Virtual Expert provides automatic delineation of regions of interest (ROI) relevant for stroke patient assessment based on perfusion and diffusion image output generated by the Capillary Function module. Specifically, diffusion MRI images are used to generate threshold masks of perceived core lesions, whereas MRI or CT perfusion images are used to generate threshold masks of perceived perfusion restriction. For CT perfusion, derived perfusion images are used to generate threshold masks of perceived core lesions. Virtual Expert thus works with MRI and CT technologies.

The generated masks can be combined into a mismatch region of interest.

Volumetric calculations and ratios can be calculated from the computed regions of interest.

The provided document describes the acceptance criteria and the study conducted for the Cercare Medical Neurosuite (CMN) Capillary Function with Virtual Expert device.

Acceptance Criteria and Device Performance Study

The acceptance criteria for the CMN Capillary Function with Virtual Expert device were established through performance validation testing, encompassing both simulated digital phantoms and retrospective clinical data. The document states that "The established acceptance criteria were reached in all tests conducted" (page 10).

1. Table of Acceptance Criteria and Reported Device Performance

For the Capillary Function module, the acceptance criteria focused on quantitative comparisons using digital phantoms, ensuring accuracy under varying hemodynamic parameters and experimental conditions. For the Virtual Expert module, the acceptance criteria involved volumetric and spatial agreement for lesion identification and secondary clinical application assessments like the DEFUSE3 criteria.

2. Sample Size Used for the Test Set and Data Provenance

• Capillary Function Module:

  • Test Set: Included simulated digital phantoms with variations of hemodynamic parameter combinations, as well as retrospective clinical data primarily for visual inspection (page 10). No specific numbers for the retrospective clinical data sample size are provided, and no country of origin is explicitly stated, though it's typically global or multi-center for such studies. The data from digital phantoms is synthetic.
  • Provenance: "retrospective clinical data" and "simulated digital phantoms" (page 10).

• Virtual Expert Module:

  • Test Set: "retrospective patient CT perfusion imaging" (page 10). The specific sample size is not stated in the provided text.
  • Provenance: "retrospective patient CT perfusion imaging" (page 10). The associated published technical comparison study (Bathla et al, J. Neurointerventional Surg., 12:1028-1032 (2020)) might contain details on data provenance, but it's not present in this document.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not explicitly state the number or qualifications of experts used to establish ground truth for the test set. However, for the Virtual Expert module, it references a published study (Bathla et al, J. Neurointerventional Surg., 12:1028-1032 (2020)) which would typically involve expert consensus for ground truth. For the Capillary Function module, ground truth for the simulated phantoms is "known" (inherent to the phantom design), and clinical data was used for "visual inspection" which implies expert review.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). For quantitative phantom testing, adjudication is not typically needed as the ground truth is predefined. For retrospective clinical data, particularly for "visual inspection" and comparison to a published study, it is common to have multiple readers involved, but the specific adjudication protocol is not detailed here.

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

The provided text does not indicate that an MRMC comparative effectiveness study was performed to evaluate human reader improvement with AI assistance versus without. The studies described are performance validation tests of the device itself (standalone or comparative to predicate/reference), not human-in-the-loop clinical utility studies.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done

Yes, the performance validation testing described for both the Capillary Function module (using digital phantoms and visual inspection of clinical data) and the Virtual Expert module (volumetric and spatial agreement, DEFUSE3 criteria) appears to be focused on standalone algorithm performance. The comparative testing against a predicate and reference device also implies standalone performance evaluation.

7. The Type of Ground Truth Used

• Capillary Function Module: For simulated digital phantoms, the "true parameter combinations were known" (page 10), indicating a simulation-based (synthetic) ground truth. For retrospective clinical data, it was primarily used for "visual inspection," implying a clinical expert-derived visual ground truth.
• Virtual Expert Module: For retrospective patient CT perfusion imaging, the ground truth for volumetric and spatial agreement would likely be expert consensus or highly delineated clinical ground truth based on expert review of the images. The reference to the DEFUSE3 criteria also points to clinically relevant ground truth.

8. The Sample Size for the Training Set

The document does not specify the sample size used for the training set. It focuses on the performance validation testing.

9. How the Ground Truth for the Training Set was Established

The document does not specify how the ground truth for the training set was established, as it does not elaborate on the training process or data.

Ask a specific question about this device