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

uOmnispace. CT is a software for viewing, manipulating, evaluating and analyzing medical images. It supports interpretation and evaluation of examinations within healthcare institutions. It has the following additions: -The uOmnispace. CT Colon Analysis application is intended to provide the user a tool to enable easy visualization and efficient evaluation of CT volume data sets of the colon. -The uOmnispace. CT Dental application is intended to provide the user a tool to reconstruct panoramic and paraxial views of jaw. -The uOmnispace. CT Lung Density Analysis application is intended to segment pulmonary, lobes, and airway, providing the user quantitative parameters, structure information to evaluate the lung and airway. -The uOmnispace.CT Lung Nodule application is intended to provide the user a tool for the review and analysis of thoracic CT images, providing quantitative and characterizing information about nodules in the lung in a single study, or over the time course of several thoracic studies. -The uOmnispace.CT Vessel Analysis application is intended to provide a tool for viewing, and evaluating CT vascular images. -The uOmnispace. CT Brain Perfusion is intended to calculate the parameters such as: CBV, CBF, etc. in order to analyze functional blood flow information about a region of interest (ROI) in brain. -The uOmnispace.CT Heart application is intended to segment heart and extract coronary artery. It also provides analysis of vascular stenosis, plaque and heart function. -The uOmnispace. CT Calcium Scoring application is intended to identify calcifications and calculate the calcium soore. -The uOmnispace. CT Dynamic Analysis application is intended to support visualization of the CT datasets over time with the 3D/4D display modes. -The uOmnispace.CT Bone Structure Analysis application is intended to provide visualization and labels for the ribs and spine, and support batch function for intervertebral disk. -The uOmnispace. CT Liver Evaluation application is intended to processing and visualization for liver segmentation and vessel extraction. It also provides a tool for the user to perform liver separation and residual liver segments evaluation. -The uOmnispace. CT Dual Energy is a post-processing software package that accepts UIH CT images acquired using different tube voltages and/or tube currents of the same anatomical location. The u0mnispace.CT Dual Energy application is intended to provide information on the chemical composition of the scanned body materials and/or contrast agents. Additionally, it enables images to be generated at multiple energies within the available spectrum. -The uOmnispace.CT Cardiovascular Combined Analysis is an image analysis software package for evaluating contrast enhanced CT images. The CT Cardiovascular Combined Analysis is intended to analyze vascular and cardiac structures. It can be used in the qualitative and quantitative for the analysis of head-neck, abdomen, multi-body part combined, TAVR (Transcatheter Aortic Valve Replacement) CT data as input for the planning of cardiovascular procedures.

The uOmnispace.CT is a post-processing software based on the uOmnispace platform for viewing, manipulating, evaluating and analyzing medical images, can run alone or with other advanced commercially cleared applications.

The provided text describes the performance data for three AI/ML algorithms integrated into the uOmnispace.CT software: Spine Labeling Algorithm, Rib Labeling Algorithm, and TAVR Analysis Algorithm.

Here's a breakdown of the acceptance criteria and study details for each:

1. Spine Labeling Algorithm

Acceptance Criteria Table:

Study Proving Device Meets Acceptance Criteria:

• Sample Size for Test Set: 120 subjects.
• Data Provenance: Retrospective, with data collected from five major CT manufacturers (GE, Philips, Siemens, Toshiba, UIH). Clinical subgroups included U.S. (90 subjects) and Asia (30 subjects) for ethnicity.
• Number of Experts for Ground Truth: At least two licensed physicians with U.S. credentials.
• Qualifications of Experts: Licensed physicians with U.S. credentials.
• Adjudication Method: Ground truth annotations were made by "well-trained annotators" using an interactive tool to set annotation points and assign anatomical labels. All ground truth was finally evaluated by two licensed physicians with U.S. credentials. This suggests a post-annotation review/adjudication by experts.
• MRMC Comparative Effectiveness Study: No, this was a standalone performance evaluation of the algorithm against established ground truth.
• Standalone Performance: Yes, the performance of the algorithm itself was evaluated based on a scoring system against ground truth.
• Type of Ground Truth Used: Expert consensus (annotators + review by licensed physicians).
• Sample Size for Training Set: Not specified, but stated that "The training data used for the training of the spine labeling algorithm is independent of the data used to test the algorithm."
• How Ground Truth for Training Set was Established: Not specified beyond the implication that a ground truth process was followed for training data as well.

2. Rib Labeling Algorithm

Acceptance Criteria Table:

Study Proving Device Meets Acceptance Criteria:

• Sample Size for Test Set: 120 subjects.
• Data Provenance: Retrospective, with data collected from five major CT manufacturers (GE, Philips, Siemens, Toshiba, UIH). Clinical subgroups included U.S. (80 subjects) and Asia (40 subjects) for ethnicity.
• Number of Experts for Ground Truth: At least two licensed physicians with U.S. credentials.
• Qualifications of Experts: Licensed physicians with U.S. credentials.
• Adjudication Method: Ground truth annotations were made by "well-trained annotators" using an interactive tool to generate initial rib masks, which were then refined, and anatomical labels assigned. After the first round, annotators "checked each other's annotation." Finally, all ground truth was evaluated by two licensed physicians with U.S. credentials. This indicates a multi-step adjudication process.
• MRMC Comparative Effectiveness Study: No, this was a standalone performance evaluation of the algorithm against established ground truth.
• Standalone Performance: Yes, the performance of the algorithm itself was evaluated based on a scoring system against ground truth.
• Type of Ground Truth Used: Expert consensus (annotators + cross-checking + review by licensed physicians).
• Sample Size for Training Set: Not specified, but stated that "The training data used for the training of the rib labeling algorithm is independent of the data used to test the algorithm."
• How Ground Truth for Training Set was Established: Not specified beyond the implication that a ground truth process was followed for training data as well.

3. TAVR Analysis Algorithm

Acceptance Criteria Table:

Study Proving Device Meets Acceptance Criteria:

• Sample Size for Test Set: 60 subjects.
• Data Provenance: Retrospective. Clinical subgroups included Asia (25 subjects) and U.S. (35 subjects) for ethnicity, including data from U.S. Facility 1 (25 subjects) and U.S. Facility 2 (10 subjects).
• Number of Experts for Ground Truth: At least two licensed physicians with U.S. credentials for the final evaluation of the ground truth.
• Qualifications of Experts: Licensed physicians with U.S. credentials (specifically, "two MD with the American Board of Radiology Qualification" for the subjective scoring).
• Adjudication Method: Ground truth annotations were made by "well-trained annotators." After the first round of annotation, they "checked each other's annotation." Finally, all ground truth was evaluated by two licensed physicians with U.S. credentials. This indicates a multi-step adjudication process.
• MRMC Comparative Effectiveness Study: No, this was a standalone performance evaluation of the algorithm against established ground truth and subjective expert scoring.
• Standalone Performance: Yes, the performance of the algorithm itself was evaluated based on landmark error and subjective expert scoring.
• Type of Ground Truth Used: Expert consensus (annotators + cross-checking + review by licensed physicians).
• Sample Size for Training Set: Not specified, but stated that "The training data used for the training of the post-processing algorithm is independent of the data used to test the algorithm."
• How Ground Truth for Training Set was Established: Not specified beyond the implication that a ground truth process was followed for training data as well.

Ask a specific question about this device

Rapid is an image processing software package to be used by trained professionals, including but not limited to physicians (medical analysis and decision making) and medical technicians (administrative case processing). The software runs on a 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 compliant imaging devices. Rapid is indicated for use in Adults only.

Rapid provides both viewing and analysis capabilities for functional and dynamic imaging datasets acquired with CT, CT Perfusion (CTP), CT Angiography (CTA), C-arm CT Perfusion and MRI including a Diffusion Weighted MRI (DWI) Module and a Dynamic Analysis Module (dynamic contrast-enhanced imaging data for MRI, CT, and C-arm CT).

Rapid C-arm CT Perfusion can be used to qualitatively assess cerebral hemodynamics in the angiography suite.

The CT analysis includes NCCT maps showing areas of hypodense and hyperdense tissue.

The DWI Module is used to visualize local water diffusion properties from the analysis of diffusion - weighted MRI data.

The Dynamic Analysis 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.

Rapid CT Perfusion and Rapid MR Perfusion can be used by physicians to aid in the selection of acute stroke patients (with known occlusion of the intracranial internal carotid artery or proximal middle cerebral artery). Instructions for the use of contrast agents for this indication can be found in Appendix A of the User's Manual. Additional information for safe and effective drug use is available in the product-specific iodinated CT and gadolinium-based MR contrast drug labeling.

In addition to the Rapid imaging criteria, patients must meet the clinical requirements for thrombectomy, as assessed by the physician, and have none of the following contraindications or exclusions:

· Bolus Quality: absent or inadequate bolus.

· Patient Motion: excessive motion leading to artifacts that make the scan technically inadequate.

· Presence of hemorrhage.

· C-Arm CTP is not to be used in the Rapid Thrombectomy indication criteria, other modalities should be consulted.

Cautions:

· C-Arm CTP provides qualitative data only, review other modalities prior to diagnosis. CBV and CBT are not absolute and CBT, CBV, MTT and Tmax are supported for qualitative interpretation of the perfusion maps only.

Rapid is a software package that provides for the visualization and study of changes in tissue using digital images captured by diagnostic imaging systems including CT (Computed Tomography) and MRI (Magnetic Image Resonance), as an aid to physician diagnosis.

Rapid can be installed on a customer's Server or it can be accessed online as a virtual system. It provides viewing, quantification, analysis and reporting capabilities.

Rapid works with the following types of (DICOM compliant) medical image data:

• CT (Computed Tomography)
• MRI(Magnetic Image Resonance) ●

Rapid acquires (DICOM compliant) medical image data from the following sources:

• . DICOM file
• DICOM CD-R ●
• Network using DICOM protocol. ●

Rapid provides tools for performing the following types of analysis:

• selection of acute stroke patients for endovascular thrombectomy ●
• volumetry of thresholded maps
• time intensity plots for dynamic time courses
• measurement of mismatch between labeled volumes on co-registered image ● volumes
• large vessel density. ●

Rapid is a Software as a Medical Device (SaMD) consisting of one or more Rapid Servers (dedicated or virtual). The Rapid Server is an image processing engine that connects to a hospital LAN, or inside the Hospital Firewall. It can be a dedicated Rapid Server or a VM Rapid appliance, which is a virtualized Rapid Server that runs on a dedicated server.

Rapid is designed to streamline medical image processing tasks that are time consuming and fatiguing in routine patient workup. Once Rapid is installed it operates with minimal user interaction. Once the CT [NCCT, CT, CTA, C-arm CT(CBCT)] or MR (MR, MRA) data are acquired, the CT or MRI console operator selects Rapid as the target for the DICOM images, and then the operator selects which study/series data to be sent to Rapid. Based on the type of incoming DICOM data, Rapid will identify the data set scanning modality and determine the suitable processing module. The Rapid Platform is a central unit which coordinates the execution image processing modules which support various analysis methods used in clinical practice today:

• Rapid CTP/MRP/C-arm CTP, DWI, Dynamic Analysis (Original: K121447, Updated ● with K172477, K182130, K213165, K233512 and K233582)
• Rapid CTA (K172477) ●
• Rapid ASPECTS (K200760, K232156)
• Rapid ICH (K193087, K221456)
• Rapid LVO (K200941, K221248)
• Rapid NCCT Stroke (K222884)
• . Rapid RV/LV (K223396)
• Rapid PETN (K220499)
• Rapid ANRTN (K230074) ●
• Rapid SDH (K232436) ●

The iSchemaView Server is a dedicated server that provides a central repository for Rapid data. All iSchemaView Server data is stored on encrypted hard disks. It also provides a user interface for accessing Rapid data. It connects to a firewalled Data Center Network and has its own firewall for additional cyber/data security. The iSchemaView Server connects to one or more Rapid Servers via WAN. Available types of connection include VPN (Virtual Private Network - RFC2401 and RFC4301 Standards) Tunnel and SSH (Secure Shell).

The provided text describes the iSchemaView Rapid device, an image processing software package. The document focuses on its 510(k) submission (K233582) and demonstrates its substantial equivalence to a previously cleared predicate device (K213165). The new submission primarily extends the device's functionality to include C-arm CT for qualitative cerebral hemodynamics assessment and qualitative analysis of perfusion parameters.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not explicitly present a "table of acceptance criteria" with corresponding "reported device performance" in the format typically used for performance studies with specific metrics and thresholds (e.g., sensitivity, specificity, accuracy). Instead, it states that the device was validated to provide "accurate representation of key processing parameters" and "met all design requirements and specifications."

The key performance claims and their validation are described qualitatively:

2. Sample size used for the test set and the data provenance

The document states that iSchemaView conducted "extensive phantom validation testing" and "software verification and validation testing of the Rapid system" using "the use of phantoms and case data." However, it does not specify the sample size for the test set (number of phantoms or cases).

The data provenance is stated as:

• Phantoms: Used for characterizing perfusion imaging performance.
• Case Data: Used for validating the Rapid System performance.

The document does not explicitly mention the country of origin of the data or whether it was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not specify the number of experts used to establish ground truth for the test set or their specific qualifications. It mentions that the device is "to be used by trained professionals, including but not limited to physicians (medical analysis and decision making) and medical technicians (administrative case processing)" and that "Rapid C-arm CT Perfusion can be used to qualitatively assess cerebral hemodynamics in the angiography suite." While this indicates the intended users, it does not explicitly detail the experts involved in establishing ground truth for the validation studies.

4. Adjudication method for the test set

The document does not mention any adjudication method (e.g., 2+1, 3+1) used for establishing ground truth in the test set.

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 document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The current submission focuses on demonstrating substantial equivalence and the performance of the device itself (including its new feature for C-arm CT) rather than its direct comparative effectiveness with human readers.

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

The provided text only discusses "extensive phantom validation testing" and "software verification and validation testing." The results presented ("accurate representation of key processing parameters," "met all design requirements and specifications," and "comparable with small biases") appear to be from an algorithm-only (standalone) performance assessment, particularly for the software's ability to process and represent data from phantoms and cases, and the comparability of C-arm CT processing to conventional CT. There is no mention of human-in-the-loop performance in the context of these validation studies.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

For the "phantom validation testing," the ground truth would inherently be known physical and temporal parameters designed into the phantoms.
For the "case data," the document does not explicitly state the type of ground truth. Given the nature of a software processing and analysis system, it likely relies on a combination of:

• Established interpretations from other modalities or clinical diagnoses, particularly for "selecting acute stroke patients."
• Quantitative measurements derived from advanced imaging, which the software aims to replicate or analyze.

8. The sample size for the training set

The document does not specify the sample size for the training set. It details the device's functionality and validation rather than its development or machine learning training specifics.

9. How the ground truth for the training set was established

Since the document does not mention the sample size for the training set, it also does not describe how the ground truth for the training set was established. The focus is on the validation of the developed software, which includes algorithms, some of which may be AI/ML-based as indicated by "Mixed Traditional and AI/ML" under Software in Table 1 (page 10). However, the specifics of ML model training, including data and ground truth establishment, are not detailed in this summary.

Ask a specific question about this device

Rapid is an image processing software package to be used by trained professionals,including but not limited to physicians and medical technicians. The software runs ona 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 compliant imaging devices.

Rapid provides both viewing and analysis capabilities for functional and dynamic imaging datasets acquired with CT Perfusion (CTP). CT Angiography (CTA), and MRI including a Diffusion Weighted MRI (DWI) Module and a Dynamic Analysis Module (dynamic contrast-enhanced imaging data for MRI and CT).

The CT analysis includes NCCT maps showing areas of hypodense and hyperdense tissue.

The DWI Module is used to visualize local water diffusion properties from the analysis of diffusion weighted MRI data.

The Dynamic Analysis 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.

Rapid CT-Perfusion and Rapid MR-Perfusion can be used by physicians to aid in the selection of acute stroke patients (with known occlusion of the intracranial internal carotid artery or proximal middle cerebral artery)Instructions for the use of contrast agents for this indication can be found in Appendix A of the User's Manual. Additional information for safe and effective drug use is available inthe product-specific iodinated CT and gadolinium-based MR contrast drug labeling.

In addition to the Rapid imaging criteria, patients must meet the clinical requirements for thrombectomy, as assessed by the physician, and have none of the following contraindications or exclusions:

• · Bolus Quality: absent or inadequate bolus.
• · Patient Motion: excessive motion leading to artifacts that make the scan technically inadequate
• Presence of hemorrhage

Rapid is a software package that provides for the visualization and study of changes in tissue using digital images captured by diagnostic imaging systems including CT (Computed Tomography) and MRI (Magnetic Image Resonance), as an aid to physician diagnosis. Rapid can be installed on a customer's Server or it can be accessed online as a virtual system. It provides viewing, quantification, analysis and reporting capabilities.

Rapid is a Software as a Medical Device (SaMD) consisting of one or more Rapid Servers (dedicated or virtual) in on-premises or hybrid (on-premises/cloud) configurations. The Rapid Server is an image processing engine that connects to a hospital LAN, or inside the Hospital Firewall in the on-premises configuration or in conjunction with a secure link to the cloud in the hybrid configuration. It can be a dedicated Rapid Server or a VM Rapid appliance, which is a virtualized Rapid Server that runs on a dedicated server.

Rapid is designed to streamline medical image processing tasks that are time consuming and fatiguing in routine patient workup. Once Rapid is installed it operates with minimal user interaction. Once the CT (NCCT, CT, CTA) or MR (MR, MRA) data are acquired, the CT or MRI console operator selects Rapid as the target for the DICOM images, and then the operator selects which study/series data to be sent to Rapid. Based on the type of incoming DICOM data. Rapid will identify the data set scanning modality and determine the suitable processing module. The Rapid platform is a central control unit which coordinates the execution image processing modules which support various analysis methods used in clinical practice today.

Here's an analysis of the provided text to fulfill your request, noting that the document is an FDA 510(k) clearance letter and summary, which typically focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed de novo device performance study. Therefore, some of the requested information (like specific effect sizes from MRMC studies or detailed ground truth establishment for a training set) might not be explicitly present if the submission didn't require entirely new clinical performance data for clearance.

Key Observation from the Document:
The document (K233512) is a 510(k) summary for iSchemaView Rapid (6.0), claiming substantial equivalence to a previously cleared predicate device, Rapid (K213165). The primary change appears to be an "extension of installation in a hybrid configuration (on-premises and hybrid)." This implies that extensive new clinical performance studies for the core functionality may not have been required, as the device is deemed "as safe and effective as the previously cleared Rapid (K213165) with an extension of installation in a hybrid configuration."

Given this, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" are largely framed around demonstrating equivalence to the predicate and ensuring the new configuration doesn't introduce new safety or effectiveness concerns.

Acceptance Criteria and Device Performance (Based on the provided document)

Since this is a 510(k) submission for substantial equivalence based on a predicate, the "acceptance criteria" are implied to be that the device performs equivalently to the predicate and any new features (like hybrid configuration) do not negatively impact safety or effectiveness. The document highlights software verification and validation as the primary means of demonstrating compliance.

1. Table of Acceptance Criteria and Reported Device Performance

• Image viewing, processing, and analysis of CT/MRI images for functional and dynamic imaging datasets.
• Specific modules: CT-Perfusion, MR-Perfusion, DWI, Dynamic Analysis, NCCT maps (hypodense/hyperdense tissue), CTA.
• Aid in selection of acute stroke patients (with known occlusion of intracranial ICA or proximal MCA).
• Calculation of parameters related to tissue flow (perfusion) and tissue blood volume. | "Rapid has the same intended use and similar indications, technological characteristics and principles of operation as its predicate devices."
  "Rapid is as safe and effective as the previously cleared Rapid (K213165) with an extension of installation in a hybrid configuration..." |
  | Technical Compliance:
• DICOM compliance.
• Operates on standard off-the-shelf computers or virtual platforms.
• Handles DICOM medical image data (CT, MRI) from various sources.
• Secure communication protocols (SMTP with security extensions, VPN, SSH). | "Rapid complies with DICOM (Digital Imaging and Communications in Medicine) - Developed by the American College of Radiology and the National Electrical Manufacturers Association. NEMA PS 3.1 - 3.20."
  "Rapid is a DICOM-compliant PACS software..."
  "Rapid runs on standard 'off-the-shelf' computer and networking hardware."
  "Rapid generally connects to the infrastructure of the medical partner... Rapid uses a SMTP protocol with security extensions to provide secure communications."
  "Available types of connection include VPN (Virtual Private Network - RFC2401 and RFC4301 Standards) Tunnel and SSH (Secure Shell)." |
  | Performance Accuracy & Reliability:
• Accurate representation of key processing parameters.
• Handles clinically relevant parameters and perturbations.
• Meets all design requirements and specifications. | "iSchemaView conducted extensive performance validation testing and software verification and validation testing of the Rapid system."
  "This performance validation testing demonstrated that the Rapid system provides accurate representation of key processing parameters under a range of clinically relevant parameters and perturbations associated with the intended use of the software."
  "Software performance, validation and verification testing demonstrated that the Rapid system met all design requirements and specifications."
  "The Rapid System performance has been validated with phantom and case data." |
  | Safety & Effectiveness (no new issues compared to predicate):
• Compliance with QSR (21 CFR Part 820.30).
• Risk management (EN ISO 14971:2019).
• Software lifecycle processes (IEC 62304:2016).
• Usability engineering (IEC 62366:2015). | "Rapid has been designed, verified and validated in compliance with 21 CFR, Part 820.30 requirements. The device has been designed to meet the requirements associated with EN ISO 14971:2019 (risk management)."
  "Rapid raises no new issues of safety or effectiveness compared to Rapid (K2131650), as demonstrated by the testing conducted with Rapid." |

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

The document mentions "The Rapid System performance has been validated with phantom and case data." However, it does not specify the sample size for the test set of "case data" or "phantom data", nor does it specify the country of origin or whether the data was retrospective or prospective. For a 510(k), particularly one proving substantial equivalence to a predicate, new large-scale clinical studies are not always required if software verification and validation suffice, as implied here.

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

The document states, "The primary users of Rapid software are medical imaging professionals who analyze tissue using CT or MRI images." However, it does not specify the number of experts used to establish ground truth for the test set, nor does it provide their specific qualifications (e.g., number of years of experience, specific board certifications). It only generically refers to "trained professionals, including but not limited to physicians and medical technicians."

4. Adjudication Method for the Test Set

The document does not specify any adjudication method (e.g., 2+1, 3+1) used for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done comparing human readers with AI vs. without AI assistance, nor does it state an effect size for such an improvement. The focus is on the device's standalone performance and its equivalence to the predicate.

6. If a Standalone Performance Study (Algorithm Only Without Human-in-the-Loop Performance) Was Done

Yes, the document implies that a standalone performance evaluation of the algorithm's core processing capabilities was conducted. It states: "iSchemaView conducted extensive performance validation testing and software verification and validation testing of the Rapid system. This performance validation testing demonstrated that the Rapid system provides accurate representation of key processing parameters under a range of clinically relevant parameters and perturbations associated with the intended use of the software." This refers to the algorithm's performance in processing images and generating analyses.

7. The Type of Ground Truth Used

The document states, "The Rapid System performance has been validated with phantom and case data." This suggests that the ground truth for "phantom data" would be known physical or simulated values. For "case data," the document does not explicitly state the type of ground truth, such as expert consensus, pathology, or outcomes data. However, given the context of stroke patient selection, clinical outcomes or expert consensus on imaging findings would typically be relevant for such applications.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set. As this is a 510(k) for an updated version of an existing device, it's possible that the training data for the core AI components was part of earlier development and was not re-evaluated for this specific submission, or that detailed training data was not a required element for this type of substantial equivalence claim.

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

The document does not provide any information on how the ground truth for the training set was established.

Ask a specific question about this device

Cercare Medical Neurosute and associated modules, including the Capillary Function module, is an image processing software package to be used by trained professionals, including physicians and medical technicians.

The 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

Cercare Medical Neurosuite provides viewing capabilities, whereas 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).

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. One clinical application is to visualize the apparent blood perfusion and to calculate ADC 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 image 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) technology.

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.

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 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 technology.

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 perfusion MRI images are used to generate threshold masks of perceived perfusion restriction. Virtual Expert thus works with MRI technology.

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.

Here's a breakdown of the acceptance criteria and study information for the Cercare Medical Neurosuite (CMN) Capillary Function with Virtual Expert, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Capillary Function Module:

  • Test Set: Predominantly digital phantoms. The text mentions "human-like phantom testing."
  • Data Provenance: Not explicitly stated for retrospective clinical data, but the phantoms are simulated.
  • Note: Retrospective clinical data was primarily used for visual inspection, not rigorous quantitative testing in this module's validation.

• Virtual Expert Module:

  • Test Set: Retrospective patient MR perfusion and diffusion imaging.
  • Data Provenance: Not explicitly stated (e.g., country of origin). The data is described as "retrospective clinical data."

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

• The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth for either module's test sets.
• For the Virtual Expert module, it mentions "comparison testing...in the associated published technical comparison study (Bathla et al, J. Neurointerventional Surg., 12:1028-1032 (2020))." This external publication might contain more details on expert involvement, but it's not present in this document.

4. Adjudication Method for the Test Set:

• The document does not explicitly state the adjudication method used for either module's test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its Effect Size:

• No, an MRMC comparative effectiveness study comparing human readers with and without AI assistance was not explicitly described in this document. The performance testing focused on the device's accuracy and agreement with ground truth or a predicate device, not on human reader improvement.
• The Virtual Expert module's secondary application assessment mentioned "image-driven decision to treat analysis through the so-called DEFUSE3 criteria," which hints at clinical relevance, but it's not a formal MRMC study of human performance improvement.

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

• Yes, standalone performance testing was conducted. The entire performance data section describes the testing of the CMN Capillary Function with Virtual Expert as a software-only device. The device was compared against known parameters (digital phantoms) and retrospective clinical data (yielding volumetric and spatial agreement) without explicit mention of human-in-the-loop performance during these validation steps.

7. The Type of Ground Truth Used:

• Capillary Function Module:
  • Digital Phantoms: "True parameter combinations were known." This means the ground truth was synthetically generated and precisely defined.
• Virtual Expert Module:
  • Retrospective Clinical Data: Ground truth implies a reference standard or consensus derived from the clinical images themselves for volumetric and spatial agreement. The comparison was modeled after a published technical study, which may provide insight into how ground truth was typically established in such contexts (likely expert consensus or a validated reference method).

8. The Sample Size for the Training Set:

• The document does not explicitly state the sample size used for the training set.

9. How the Ground Truth for the Training Set Was Established:

• The document does not explicitly state how the ground truth for the training set was established. In fact, it doesn't mention training data at all. The description focuses on validation and verification rather than model development.

Ask a specific question about this device

The TeraRecon Neuro Algorithm is an algorithm for use by trained professionals, including but not limited to physicians, surgeons and medical clinicians.

The TeraRecon Neuro 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 TeraRecon Neuro Algorithm provides analysis capabilities for functional, dynamic, and derived imaging datasets acquired with CT or MRI. It can be used for the 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, tissue blood volume, and other parametric maps with or without the ventricles included in the calculation. The algorithm also include volume reformat in various orientation, 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 TeraRecon Neuro Algorithm can be delivered to the end-user through image viewers such as TeraRecon's Aquarius Intuition system, TeraRecon's Eureka AI Results Explorer, TeraRecon's Eureka Clinical AI Platform, or other image viewing systems like PACS that can support DICOM results generated by the TeraRecon Neuro Algorithm.

The TeraRecon Neuro 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 TeraRecon Neuro algorithm version 2.0.0 is a modification of the predicate device Neuro.AI Algorithm (K200750), which was a modification of the predicate device, Intuition-TDA, TVA, Parametric Mapping (which was cleared under K131447). The predicate device Intuition -TDA, TVA, Parametric Mapping is an optional module/workflow for the Intuition system (K121916). The TeraRecon Neuro algorithm is an 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.

TeraRecon Neuro allows motion correction and processes, calculates and outputs brain perfusion analysis results for functional, dynamic, and derived imaging datasets acquired with CT or MRI. TeraRecon Neuro results are used for the 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 and tissue blood volume.

Outputs include parametric map 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), time to maximum (Tmax) and penumbra/umbra maps that are derived from combinations of measurement parameters, such as mismatch maps and hypoperfusion maps with volumes and ratios, as well as 2D and 3D visualization of brain tissues and brain blood vessels (Note: Tmax, mismatch and hypoperfusion maps are only available for images of CT modality).

When TeraRecon Neuro results are used in external viewer devices such as TeraRecon's Intuition or Eureka medical devices, all the standard features offered by Intuition or Eureka 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 TeraRecon Neuro algorithm outputs can be used by physicians to aid in the diagnosis and for clinical decision support including treatment planning and post treatment evaluation. 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.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

Study Details

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

The document does not explicitly state the numerical sample size for the test set used in the qualitative clinical user evaluation or the quantitative Tmax measurement accuracy study. It refers to "comparison maps generated by the subject device, the predicate device and two additional reference devices." Without specific numbers, it's impossible to determine the precise size of the test set cases.

Regarding data provenance, the document does not provide details on the country of origin or whether the data was retrospective or prospective.

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

• Number of Experts: One expert was used.
• Qualifications: Dr. Robert Falk, MD. No additional details about his specific experience or sub-specialty (e.g., radiologist with X years of experience) are provided in the text.

4. Adjudication Method for the Test Set

The adjudication method used for the clinical user evaluation was not explicitly specified as 2+1, 3+1, or any other formal method. The study involved a single evaluator (Dr. Robert Falk, MD) who was "asked to confirm through qualitative assessment." This suggests a single-expert review, rather than a multi-expert adjudication process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of Improvement with AI vs. Without AI Assistance

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described. The evaluation involved a single expert providing a qualitative assessment. The study was focused on demonstrating substantial equivalence to predicate and reference devices, not on measuring the improvement of human readers with AI assistance. Therefore, there is no reported effect size of how much human readers improve with AI vs. without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, a standalone performance evaluation was conducted for the quantitative Tmax measurement. The acceptance criteria for Tmax accuracy were based on comparing the subject device's measurements directly against the ground truth (average of reference devices) in ROIs, without explicit human intervention in the measurement process for the test cases. While the "ground truth" itself is derived from other devices (which are used by humans), the comparison of the algorithm's output to this ground truth represents a standalone assessment of the algorithm's quantitative accuracy.

7. The Type of Ground Truth Used

• Qualitative Clinical User Evaluation: The ground truth for this evaluation appears to be the performance of the predicate and reference devices, as the subject device's maps were compared to these for substantial equivalence. It's a comparative assessment rather than an absolute ground truth (e.g., pathology).
• Quantitative Tmax Measurement Accuracy: The ground truth for Tmax measurements was defined as the average Tmax measurement of the two reference devices (GE Medical Systems FastStroke CT Perfusion 4D (K193289) and ISchemaView RAPID (K182130)) for a given ROI.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set for the TeraRecon Neuro algorithm.

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

The document does not provide any information on how the ground truth for the training set was established. Training set details are not discussed.

Ask a specific question about this device

Rapid is an image processing software package to be used by trained professionals, including but not limited to physicians and medical technicians. The software runs on a standard off-the-shelf computer or as VMware, and can be used to perform image viewing, processing and analysis of images. Data and images are acquired through DICOM compliant imaging devices.

Rapid provides both viewing and analysis capabilities for functional and dynamic imaging datasets acquired with CT, CT Perfusion (CTP), CT Angiography (CTA), and MRI including a Diffusion Weighted MRI (DWI) Module and a Dynamic Analysis Module (dynamic contrast-enhanced imaging data for MRI and CT).

The CT analysis includes NCCT maps showing areas of hypodense and hyperdense tissue.

The DWI Module is used to visualize local water diffusion properties from the analysis of diffusion - weighted MRI data.

The Dynamic Analysis 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.

Rapid CT-Perfusion and Rapid MR-Perfusion can be used by physicians to aid in the selection of acute patients (with known ocuusion of the intracranial internal carotid artery or proximal middle cerebral artery)

Instructions for the use of contrast agents for this in Appendix A of the User's Manual. Additional information for safe and effective drug use is available in the product-specific iodinated CT and gadolinium-based MR contrast drug labeling.

In addition to the Rapid imaging criteria, patients must requirements for thrombectomy, as assessed by the physician, and have none of the following contraindications or exclusions:

• Bolus Quality: absent or inadequate bolus.
• Patient Motion: excessive motion leading to artifacts that make the scan technically inadequate .
• . Presence of hemorrhage

Rapid is a software package that provides for the visualization and study of changes in tissue using digital images captured by diagnostic imaging systems including CT (Computed Tomography) and MRI (Magnetic Image Resonance), as an aid to physician diagnosis. Rapid can be installed on a customer's Server or it can be accessed online as a virtual system. It provides viewing, quantification, analysis and reporting capabilities.

Rapid works with the following types of (DICOM compliant) medical image data:

• CT (Computed Tomography) ●
• MRI(Magnetic Image Resonance)

Rapid acquires (DICOM compliant) medical image data from the following sources:

• . DICOM file
• DICOM CD-R
• Network using DICOM protocol ●

Rapid provides tools for performing the following types of analysis:

• selection of acute stroke patients for endovascular thrombectomy ●
• volumetry of thresholded maps
• time intensity plots for dynamic time courses ●
• measurement of mismatch between labeled volumes on co-registered image ● volumes
• large vessel density

Rapid is a Software as a Medical Device (SaMD) consisting of one or more Rapid Servers (dedicated or virtual). The Rapid Server is an image processing engine that connects to a hospital LAN, or inside the Hospital Firewall. It can be a dedicated Rapid Server or a VM Rapid appliance, which is a virtualized Rapid Server that runs on a dedicated server.

Rapid is designed to streamline medical image processing tasks that are time consuming and fatiguing in routine patient workup. Once Rapid is installed it operates with minimal user interaction. Once the CT (NCCT. CT, CTA) or MR (MR, MRA) data are acquired, the CT or MRI console operator selects Rapid as the target for the DICOM images, and then the operator selects which study/series data to be sent to Rapid. Based on the type of incoming DICOM data, Rapid will identify the data set scanning modality and determine the suitable processing module. The Rapid platform is a central control unit which coordinates the execution image processing modules which support various analysis methods used in clinical practice today:

• Rapid CTP/MRP, DWI, Dynamic Analysis (Original: K121447, Updated with K172477; ● and K182130):
• Rapid CTA (K172477); ●
• Rapid ASPECTS(K190395); ●
• Rapid ICH (K193087);
• . Rapid LVO (K200941);

The iSchemaView Server is a dedicated server that provides a central repository for Rapid data. All iSchemaView Server data is stored on encrypted hard disks. It also provides a user interface for accessing Rapid data. It connects to a firewalled Data Center Network and has its own firewall for additional cyber/data security. The iSchemaView Server connects to one or more Rapid Servers via WAN. Available types of connection include VPN (Virtual Private Network - RFC2401 and RFC4301 Standards) Tunnel and SSH (Secure Shell).

Here's a breakdown of the acceptance criteria and study details for the Rapid device, specifically focusing on the NCCT Motion Artifact AI/ML Module performance, as described in the provided 510(k) summary:

Acceptance Criteria and Reported Device Performance (NCCT Motion Artifact AI/ML Module)

Study Details

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: N=619 axial image slices.
   • Data Provenance: The text does not explicitly state the country of origin for the test set data. It mentions that samples were obtained from "Siemens, GE, Toshiba, Philips, and Neurologica" for training, and for the independent validation, "The samples were primarily from Siemens with GE mixed." This suggests a multi-vendor, and likely multi-site, collection. The study appears to be retrospective as it uses existing medical images for evaluation.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: 3
   • Qualifications of Experts: Described as "experienced truthers." Specific qualifications (e.g., years of experience, subspecialty) are not provided.

3. Adjudication method for the test set:

   • The document states "ground truth established by 3 experienced truthers." While it doesn't explicitly mention a 2+1 or 3+1 method, the implication of "established by" multiple experts suggests a consensus-based approach was used to determine the ground truth from these three experts. It does not state "none."

4. 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, a multi-reader, multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not conducted or reported in this summary for the NCCT Motion Artifact AI/ML Module. The performance evaluation is for the standalone algorithm.

5. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

   • Yes, a standalone algorithm performance study was done for the NCCT Motion Artifact AI/ML Module. The reported metrics (AUC, Sensitivity, Specificity) are for the algorithm's performance in detecting motion artifacts.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The ground truth for the test set was established by expert consensus from 3 experienced truthers.

7. The sample size for the training set:

   • Training Set: 23,066 axial image slices (Positive: 1,021, Negative: 12,877).
   • Training Validation Set: 5,906 axial image slices (Positive: 422, Negative: 5,484).

8. How the ground truth for the training set was established:

   • The document does not explicitly detail how the ground truth for the training data was established. However, given the context of medical image analysis and the subsequent use of "experienced truthers" for independent validation, it's highly probable that human expert review and labeling were also used to establish the ground truth for the training and training validation sets.

Ask a specific question about this device

The syngo. CT Neuro Perfusion software package is designed to evaluate areas of brain perfusion. The software processes images or volumes that were reconstructed from continuously acquired CT data after the injection of contrast media.

It generates the following result volumes:

• . Cerebral blood flow (CBF)
• Cerebral blood volume (CBV) .
• Local bolus timing (time to start (TTS), time to peak (TTP), time to drain (TTD)) .
• Mean transit time (MTT) .
• o Transit time to the center of the IRF (TMax)
• . Flow extraction product (permeability)
• . Temporal MIP
• . Temporal Average
• . Baseline Volume
• Modified dynamic input data .

The software allows the calculation of mirrored regions of interest and the visual inspection of time attenuation curves. One clinical application is to visualize the apparent blood perfusion and to calculate Hypoperfused Area 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, TTD, MTT, and TMax

A second application is to visualize blood brain barrier disturbances by modeling extra-vascular leakage of blood into the interstitial space. This additional capability may improve the differential diagnosis of brain tumors and may be helpful in therapy monitoring.

The syngo. CT Neuro Perfusion software allows the quantitative evaluation of dynamic CT data of the brain acquired during the injection of a compact bolus of iodinated contrast material. It mainly aids in the early differential diagnosis of acute ischemic stroke. Blood-brain-barrier (BBB) imaging feature supports the diagnostic assessment of brain tumors.

By providing images of e.g. cerebral blood flow (CBF), cerebral blood volume (CBV), time to peak (TTP), and Mean Transit Time (MTT) from one set of dynamic CT images or volumes, syngo.CT Neuro Perfusion allows a quick and reliable assessment of the type and extent of cerebral perfusion disturbances, including fast evaluation of the tissue at risk and non-viable tissue in the brain. The underlying approaches for this application were cleared as part of the predicate device and remain unchanged in comparison to the predicate device

syngo.CT Neuro Perfusion allows simultaneous multi-slice processing and supports the workflow requirements in a stroke workflow. The availability of flow extraction product imaging extends the option to the diagnosis of brain tumors. A listing of device modifications as part of the new software version VB50 of syngo.CT Neuro Perfusion is as follows:

Additional Parameters Hypoperfused Area and Mismatch Ratio:

These parameters are calculated based on NVT (non-viable tissue) and TAR (tissue at risk). Hypoperfused Area is calculated based on the sum of NVT and TAR while the Mismatch Ratio is calculated by dividing Hypoperfused Area by NVT.

The provided text describes the Siemens syngo.CT Neuro Perfusion software, which evaluates brain perfusion from CT data. The new version (VB50) adds "Hypoperfused Area" and "Mismatch Ratio" parameters to aid in acute ischemic stroke assessment.

Here's a breakdown of the acceptance criteria and the study that supports the device, based on the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative "acceptance criteria" for the device's performance in a traditional sense (e.g., "sensitivity must be > X%" or "ICC must be > Y"). Instead, the study aims to demonstrate equivalence of the new parameters with a reference device and high concordance between existing and new parameters in clinical decision-making.

The key performance metrics reported are focused on the concordance of clinical decisions and correlation of volumes between the subject device (syngo.CT Neuro Perfusion VB50, referred to as Package A in the study) and a reference device (iSchemaView RAPID, referred to as Package B in the study).

Note: The document emphasizes that despite some volumetric differences, these did not "impact eligibility for MT" and "high agreement" was achieved in clinical decision-making.

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

• Test Set Sample Size:
  • Mechanical Thrombectomy (MT) group: 62 patients
  • No Mechanical Thrombectomy (NMT) group: 56 patients
  • Total: 118 patients (62 + 56)
• Data Provenance: Retrospective. Patients presenting with Acute Ischemic Stroke (AIS) between January 2017 and December 2018 were screened. The study was conducted at a "single center." The country of origin is not explicitly stated in the provided text.

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

The document does not explicitly describe a separate ground truth establishment process involving a specific number of experts for the test set. The comparison is between the subject device's outputs and a reference device's outputs, as well as the observed clinical outcomes (MT vs. NMT) and adherence to a clinical standard (DEFUSE III criteria).

The "Methodology of the study" mentions evaluating "Individual patient triage between MT and NMT groups... to determine if the final clinical decision, based on a combination of factors, would remain the same regardless of eligibility determined based on perfusion imaging." This implies that actual clinical decisions by medical professionals (whose qualifications are not specified in this document) served as a benchmark in combination with the reference device's analysis.

4. Adjudication Method for the Test Set

The document does not describe an explicit "adjudication method" involving multiple experts resolving discrepancies for the test set results from the devices. Instead, it compares the outputs of two software packages (subject device and reference device) and then assesses the concordance of their outputs, particularly in the context of broader clinical guidelines (DEFUSE III). The focus is on how well the software outputs align with clinical decision-making criteria.

The "concordance" rates are reported based on direct comparison of the outputs and how they align with "go versus no-go" decisions for MT when perfusion criteria alone, and then additional clinical criteria, are considered.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not explicitly described in terms of human readers improving with AI vs. without AI assistance. The study described compares the outputs of two software packages (the subject device and a predicate device) and their alignment with clinical decision-making. It does not measure the improvement of human readers using these tools.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, the study described is a standalone performance evaluation of the algorithm. It compares the output parameters (e.g., core infarct volume, hypoperfused area, mismatch ratio) generated by the "syngo.CT Neuro Perfusion" software (Package A) with those generated by the "iSchemaView RAPID" software (Package B). The evaluation focuses on the concordance of the software's outputs with each other and with established clinical guidelines, without directly assessing human-in-the-loop performance.

7. The Type of Ground Truth Used

The type of "ground truth" used is a combination of:

• Reference Device Output: The outputs from the iSchemaView RAPID software (K182130) served as a key comparison point for the new parameters, as stated: "Equivalence of the parameters 'Hypoperfused Area' and 'Mismatch Ratio' with the reference device iSchemaView RAPID (K182130) was shown mainly by Bathla et al. 2020."
• Clinical Decision-Making Criteria/Outcomes: The study assessed concordance with "go versus no-go" decisions for Mechanical Thrombectomy (MT) based on perfusion outputs alone, and then incorporating additional neuroimaging eligibility criteria as defined in DEFUSE III (e.g., ASPECTS, site of vessel occlusion). This implies that adherence to established clinical guidelines and actual patient triage decisions served as a form of "ground truth" for clinical utility.
• Absence of Pathology/Direct Outcomes: There is no mention of pathology reports or direct patient outcomes data being used as ground truth for volumetric measurements or delineation of hypoperfused areas.

8. The Sample Size for the Training Set

The document does not provide information regarding the sample size used for the training set for the syngo.CT Neuro Perfusion software. The study presented focuses on the validation of the new parameters (Hypoperfused Area and Mismatch Ratio) in comparison to a reference device and clinical criteria.

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

As no information is provided about a training set, the method for establishing its ground truth is also not described in the document. The text highlights that "The calculation of these values are from already existing parameters NVT (non-viable-tissue) and TAR (tissue at risk) within the commercially available syngo.CT Neuro Perfusion SOMARIS/8 VB20 release (K163284)," suggesting that the core algorithms for NVT and TAR were previously established and cleared, and the new parameters are derived from them.

Ask a specific question about this device