Search Results

Ask a specific question about this device

Arterys MICA software is a medical diagnostic application that displays, processes, stores, and transfers DICOM and non-DICOM medical data. It provides the capability to store images and patient information, and perform filtering, digital manipulation, and quantitative measurements. The client software is designed to run on standard personal and business computers and on monitors/screens that meet appropriate technical specifications for image diagnosis.

Arterys MICA includes an optional Cardio AI module which is used to analyze the heart and its major vessels using multi-slice, multi-phase, and velocity-encoded cardiovascular magnetic resonance (MR) imges. It provides clinically relevant and reproducible, quantitative data, and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners.

Arterys MICA includes an optional Oncology AI module which provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations. It is a tool used to support the oncological workflow by helping the user confirm the absence of lesions, including evaluation, quantification, follow-up, and documentation of any such lesions.

Arterys MICA software is intended to be used as a support tool by trained healthcare professionals to aid in diagnosis. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.

Arterys MICA, already cleared as per the predicate, is a dedicated software application used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. Pre-existing DICOM images, such as CT or MR, are uploaded into Arterys MICA from a PACS or a scanner. Arterys MICA is completely hosted in the cloud and is accessed using a compatible web browser by navigating to the following https://app.arterys.com. Cloud servers are provided by Amazon Web Services (AWS) and service is accessible globally.

The Viewer AI application of Arterys MICA is designed around a modular architecture of separate components that make up a basic image viewer. These include the Studylist, from which studies are selected and opened, the image display (2D, 3D, MIP, etc), view synchronization, metadata information, and various navigational, measurement, and other action tools.

Functionality provided by the Viewer AI is extended by the additional Cardio AI and Oncology AI application modules which add support for specific clinical workflows:

• Cardiac Workflow Module: Evaluates multi-slice and multi-phase velocity-encoded . cardiovascular magnetic resonance (MR) images to quantify blood flow and ventricular function. In addition, perfusion and delayed enhancement datasets are analyzed and quantified, and for parametric mapping, T1, T2, and T2* values are obtained to assess tissue changes in the myocardium, as well as ECV calculations.
• Arterys MICA includes an optional Oncology AI module which provides analytical tools ● to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations. It is a tool used to support the oncological workflow by helping the user confirm the absence or presence of lesions, including evaluation, quantification, follow-up, and documentation of any such lesions.

Arterys MICA uses many deep learning algorithms to reduce many tedious, time-consuming manual steps, such as segmentation, landmark identification, etc. The results of these AI models are available on-screen to the user for further review and editing. The software does not perform any functions that could not be accomplished by a trained user with a manual method; the purpose of the automation is to save time and automate potential error-prone manual tasks, while allowing the results to be reviewed as per the normal clinical workflow.

NOTE: The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of images. Artervs MICA software is a complement to these standard procedures.

The provided text describes the Arterys MICA device and its regulatory submission (K203744). While it mentions some validation efforts and performance data, it does not contain a dedicated table of acceptance criteria paired with reported device performance results for a specific clinical study set up to prove the device meets these criteria. The information is fragmented and generally describes software verification and validation, along with a brief mention of a "standalone performance assessment" for the T1 workflow.

However, based on the provided text, I can extract and infer some information relevant to your request.

Here's an attempt to address your request based on the provided document, highlighting where information is present and where it is lacking:

Acceptance Criteria and Device Performance (Inferred/Extracted)

As explicitly requested, a direct "table of acceptance criteria and the reported device performance" is not present in the provided document. However, the document alludes to certain performance expectations and a specific assessment for the T1 workflow.

Inferred Acceptance Criteria / Performance Study Highlights:

Detailed Information on the Study Proving Device Meets Acceptance Criteria:

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

   • As shown above, an explicit table is not provided in the document. The performance information is embedded within text describing the validation process. The closest to quantitative acceptance criteria are the accuracy requirements for T1 and T2 values (30 ms and 4 ms, respectively), and the stated performance "within predefined accuracy requirements."

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

   • T1 Workflow Standalone Assessment: "90 Cardiac T1 Mapping MRI short axis (SAX) scans from 16 studies."
   • Data Provenance: Not explicitly stated (e.g., country of origin, multiple sites). It's not specified if this was retrospective or prospective data. The general context of "validation assessment" often implies retrospective data, but it's not confirmed.

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

   • Information Not Provided: The document does not specify the number of experts or their qualifications (e.g., radiologist with X years of experience) used to establish ground truth for any of the described tests.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

   • Information Not Provided: The document does not mention any adjudication method for establishing ground truth for the test sets.

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:

   • No MRMC Study Described: The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. The device is generally described as a "support tool" and that "the clinician retains the ultimate responsibility for making the pertinent diagnosis." The studies mentioned focus on quantitative accuracy and standalone performance of the AI components.

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

   • Yes: A standalone performance assessment was explicitly done for the T1 workflow: "A standalone performance assessment was performed on 90 Cardiac T1 Mapping MRI short axis (SAX) scans from 16 studies."
   • Additionally, the T1 and T2 value accuracy assessment implies a comparison of the algorithm's output to some "expected" value, which suggests a standalone component of evaluation.

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

   • For T1/T2 Accuracy: Ground truth was "the average intensity value obtained in a similar ROI delineated in OEM vendor generated inline maps." This implies a comparison to a known, perhaps previously validated, standard or reference.
   • For T1 Workflow Contours: Ground truth was referred to simply as "ground-truth contours." It's not specified how these "ground-truth contours" were established (e.g., expert manual segmentation, consensus).

8. The sample size for the training set:

   • Information Not Provided: The document does not disclose the sample size used for training the deep learning models.

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

   • Information Not Provided: The document does not specify how the ground truth for the training set was established.

Summary of Gaps in Information:

The provided document, being an FDA 510(k) summary, focuses on demonstrating substantial equivalence rather than providing a detailed clinical study report. Key information typically found in a comprehensive clinical validation study, such as details about human experts, adjudication methods, detailed ground truth establishment (especially for training data), and full MRMC study results, are largely absent. The document emphasizes software verification and validation, and a specific standalone AI assessment for a component of the device (T1 workflow contours) and quantitative accuracy for T1/T2 values.

Ask a specific question about this device

Arterys MICA software is a medical diagnostic application that displays, processes, stores, and transfers DICOM and non-DICOM medical data. It provides the capability to store images and patient information, and perform filtering, digital manipulation, and quantitative measurements. The client software is designed to run on standard personal and business computers and on monitors/screens that meet appropriate technical specifications for image diagnosis.

Arterys MICA includes an optional Cardio AI module which is used to analyze the heart and its major vessels using multi-slice, multi-phase, and velocity-encoded cardiovascular magnetic resonance (MR) images. It provides clinically relevant and reproducible, quantitative data, and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners.

Arterys MICA includes an optional Oncology AI module which provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations. It is a tool used to support the oncological workflow by helping the user confirm the absence of lesions, including evaluation, quantification, follow-up, and documentation of any such lesions.

Arterys MICA software is intended to be used as a support tool by trained healthcare professionals to aid in diagnosis. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.

Arterys MICA, already cleared as per the predicate, is a dedicated software application used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. Pre-existing DICOM images, such as CT or MR, are uploaded into Arterys MICA from a PACS or a scanner. The software has two components: i) client, and ii) server. The client software (i) can be used in a Chrome desktop web browser. The server software (ii) runs on the Linux operating system.

The Viewer application of Arterys MICA is designed around a modular architecture of separate components that make up a basic image viewer. These components include the Worklist, from which studies are selected and opened, the Uploads list that displays all uploaded studies for the current organization, and the basic image display itself, which allows for viewing and working with 2D and 3D images.

Functionality provided by the Viewer is extended by the additional Cardio AI and Oncology AI (Oncology AI: Lung AI and Oncology AI: Liver AI) application modules which add support for specific clinical workflows:

• Cardiac Workflow Module: evaluates multi-slice and multi-phase velocity-encoded cardiovascular MR images to quantify blood flow and ventricular function.
• Oncology Workflow Module: supports the oncological workflow by helping the user confirm the absence or presence of lesions including evaluation, quantification, follow-up and documentation of any such lesions within MR or CT images.

The provided text does not contain specific acceptance criteria or a detailed study proving that the device meets such criteria. It primarily focuses on the FDA 510(k) clearance process, stating that the device is substantially equivalent to a predicate device and has undergone software verification and validation.

However, based on the information provided, we can infer some details and highlight the missing information according to your request.

Here's a breakdown of the requested information, with an emphasis on what is present and what is absent in the provided document:

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

The document does not provide a table of acceptance criteria or specific reported device performance metrics. It generally states that "Hundreds of software verification and validation tests, including the display quality of mammography images and a performance test comparison to Medis MR-CT VVA, were repeatedly conducted throughout the software development effort." It also mentions that the Cardio AI module "provides clinically relevant and reproducible, quantitative data, and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners." However, no precise metrics, thresholds, or results are presented.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document does not specify the sample size used for the test set(s), nor does it describe the data provenance (e.g., country of origin, retrospective or prospective nature of the data).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

The document does not provide information on the number of experts used to establish ground truth or their qualifications.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document does not describe any adjudication method used for 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 indicate that a multi-reader, multi-case (MRMC) comparative effectiveness study was performed to evaluate human reader improvement with AI assistance. The focus is on the device as a "support tool" that "does not directly generate any diagnosis or potential findings," implying it's not a direct comparative AI-assisted vs. non-AI-assisted reader study for diagnostic accuracy.

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

The document states that the Cardio AI module "provides clinically relevant and reproducible, quantitative data, and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners." This implies a form of standalone performance evaluation for its quantitative data generation. However, it does not provide specific metrics for this standalone performance. The Oncology AI module is described as providing "analytical tools to help the user assess and document changes," suggesting its role is primarily assistive and not a standalone diagnostic algorithm.

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

The document does not explicitly state the type of ground truth used for validation. Given the description of the AI modules, it could involve:

• Cardio AI: Comparison of quantitative measurements (e.g., blood flow, ventricular function) against a gold standard or established clinical methods, possibly involving expert review of MR images.
• Oncology AI: Comparison of lesion detection, evaluation, quantification, and follow-up against expert consensus readings or potentially pathology/outcomes data where applicable for confirmable lesions.
  However, these are inferences, as the document does not specify the ground truth methodology.

8. The sample size for the training set

The document does not provide any information regarding the sample size of the training set for the AI modules.

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.

Summary of what is present and missing:

The provided FDA 510(k) clearance letter and summary primarily address the substantial equivalence of Arterys MICA to a predicate device, focusing on its intended use, technological characteristics, and general software validation processes (IEC 62304, ISO 14971, FDA Guidance documents). It explicitly states that "Arterys MICA software is intended to be used as a support tool by trained healthcare professionals to aid in diagnosis. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings."

Crucially, the document lacks the specific technical details of the AI module's performance evaluation as requested, such as numerical acceptance criteria, specific performance metrics, sample sizes for test and training sets, details of ground truth establishment (number/qualifications of experts, adjudication methods), and results of MRMC studies. This type of detailed study information is often found in the full 510(k) submission, not typically summarized in the public clearance letter or a brief 510(k) summary.

Ask a specific question about this device

Arterys® MICA software is a medical diagnostic application that displays, processes, stores, and transfers DICOM and non-DICOM medical data, with the exception of mammography. It provides the capability to store images and patient information, and perform filtering, digital manipulation, and quantitative measurements. The client software is designed to run on standard personal and business computers.

Arterys MICA includes an optional Cardio Al module which is used to analyze the heart and its major vessels using multi-slice, multi-phase, and velocity-encoded cardiovascular magnetic resonance (MR) images. It provides clinically relevant and reproducible, quantitative data, and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners.

Arterys MICA includes an optional Oncology AI module which provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations. It is a tool used to support the oncological workflow by helping the user confirm the absence of lesions, including evaluation, quantification, follow-up, and documentation of any such lesions.

Arterys MICA software is intended to be used as a support tool by trained healthcare professionals to aid in diagnosis. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/ or diagnosis, but it does not directly generate any diagnosis or potential findings.

Arterys MICA is a dedicated software application used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. Arterys MICA can also be used for analyzing multi-slice and multi-phase computed tomography (CT) or magnetic resonance (MR) image. Pre-existing CT or MR images are uploaded into Arterys MICA in a DICOM format from PACS or a scanner. The software has two components: i) client, and ii) server. The client software (i) can be used in a Chrome desktop web browser. The server software (ii) runs on the Linux operating system.

The basic image Viewer application of Arterys MICA is designed around a modular architecture of separate components that make up the basic image Viewer. These components include the Worklist, from which studies are selected and opened, the Uploads list that displays all uploaded studies for the current organization and the basic image Viewer itself, which allows for viewing and working with 2D and 3D images.

Functionality provided by the basic image Viewer is extended by additional Cardio Al and Oncology AI application modules and can add support for specific clinical workflows. The Cardio module adds support for flow-4D studies and provides additional functionality specific to cardiac studies. The Oncology module adds functionality specific to evaluating and measuring lesions, including lung and liver lesions/nodules.

The provided text is a 510(k) summary for the Arterys MICA device. It describes the device, its indications for use, and a comparison to predicate devices, but it does not contain detailed acceptance criteria or a study that proves the device meets those criteria.

The "Performance Data" section (Section 5) on page 7 states: "Safety and performance of Arterys MICA has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing." However, it does not provide the specific acceptance criteria, reported performance values, or any details about the studies conducted, such as sample size, data provenance, expert consensus details, or results.

Therefore, I cannot provide the requested information in the structured format because it is not present in the given document.

Ask a specific question about this device

Arterys Oncology DL is a medical diagnostic application for viewing, manipulation and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering.

Arterys Oncology DL enables visualization of information that would otherwise have to be visually compared disjointedly. Arterys Oncology DL provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations.

Arterys Oncology DL is designed to support the oncological workflow by helping the user confirm the absence or presence of lesions, including evaluation, quantification, follow-up and documentation of any such lesions.

Note: The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of the separate unregistered images. Arterys Oncology DL is a complement to these standard procedures.

This traditional 510(k) is being submitted for Arterys Oncology DL which is intended for viewing, manipulation, 3D-visualization and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering. The software supports the oncological workflow by helping the user to confirm the absence or presence of lesions, including evaluation, follow-up and documentation of any such lesions.

Key features of the software are:

• 2D and 3D visualization and comparative review
• Manual volumetric segmentation
• Semi-automatic volumetric segmentation of lung nodules and liver lesions
• Co-registration
• Longitudinal tracking
• Nodule/lesion size quantifications
• Data reporting based on Lung-RADS and LI-RADS guidelines

The provided text describes the Arterys Oncology DL device and its 510(k) submission for FDA clearance. While it outlines general performance data and verification activities, it lacks the specific details required to fully address all aspects of the acceptance criteria and the study that proves the device meets them.

Here's an analysis based on the available information:

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

The document mentions "software specifications" and "design requirements" but does not explicitly state quantitative acceptance criteria for the device's performance (e.g., specific accuracy, sensitivity, or specificity thresholds). Instead, it broadly states that "the device meets its design requirements and intended use, that it is as safe and as effective as the predicate devices, and that no new issues of safety and effectiveness were raised."

Therefore, a precise table of acceptance criteria and reported device performance cannot be generated from the given text.

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

The document mentions "Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." However, it does not specify the sample sizes used for these test sets.

It also does not provide information on the data provenance (e.g., country of origin, retrospective or prospective nature) for the test sets.

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

The document does not provide any information regarding the number of experts used to establish the ground truth for the test set or their qualifications.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document does not provide any information about the adjudication method used for 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 explicitly state that a multi-reader multi-case (MRMC) comparative effectiveness study was done, nor does it provide any effect size for human reader improvement with AI assistance. It mentions that "the clinician retains the ultimate responsibility" and that the device "is a complement to these standard procedures," suggesting an AI-assisted workflow, but no specific study details are provided.

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

The document states, "Arterys non-clinical V&V testing included Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." This suggests that performance of the deep learning models themselves was evaluated, which would align with standalone algorithm performance, particularly for the "segmentation of lung nodules and liver lesions" feature. However, the document does not explicitly present or detail standalone (algorithm only) performance metrics or studies.

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

The document does not specify the type of ground truth used for any of the testing mentioned (Liver MR Deep Learning Model Testing, Lung MR Deep Learning Model Testing, Lung Longitudinal Tracking).

8. The sample size for the training set

The document does not provide the sample size for the training set.

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

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

Summary of Missing Information:

The provided text focuses on the regulatory submission process, the device's intended use, and its general adherence to safety and performance standards. It lacks the detailed technical and scientific study information typically found in a clinical study report or technical performance evaluation, specifically:

• Quantitative acceptance criteria.
• Specific sample sizes for test and training sets.
• Data provenance for test and training sets.
• Details on expert involvement (number, qualifications, adjudication) for ground truth establishment.
• Specific performance metrics for the deep learning models (standalone or assisted).
• Details of any comparative effectiveness studies with human readers.
• Methods for establishing ground truth for both training and testing.

Ask a specific question about this device

Arterys Viewer is intended to be used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The Arterys Viewer displays, processes, stores, and transfers medical data from original equipment manufacturers (OEMs) that support the DICOM standard, with the exception of mammography. It provides the capability to store images and patient information from OEM equipment, and perform filtering, digital manipulation and quantitative measurements.

The client software is designed to run on standard personal and business computers. The product is intended to be used by trained medical professionals, including but not limited to radiologists, and physicians. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis, but it does not directly generate any diagnosis or potential findings.

Arterys Viewer is intended to be used as a Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The Arterys Viewer displays, processes, stores, and transfers medical data from original equipment manufacturers (OEMs) that support the DICOM standard, with the exception of mammography. It provides the capability to store images and patient information from OEM equipment, and perform filtering, digital manipulation and quantitative measurements.

The client software is designed to run on standard personal and business computers. The product is intended to be used by trained medical professionals, including but not limited to radiologists, oncologists, and physicians. It is intended to provide image and related information that is interpreted by a trained professional to render findings and/or diagnosis. but it does not directly generate any diagnosis or potential findings.

The following visualization, quantification and data-reporting functionalities are provided by the software:

Visualization:

• 2D image review -
• 3D image review by means of MIP, MinIP, Surface or Average -
• Multi-planar reconstruction (MPR) views (axial, coronal, sagittal, and oblique) -
• Image navigation tools -
• Cine play -

Quantification:

• Distance and area measurements -
  Data reporting:
  The distance, area, and user-selected annotated images are displayed to the user within the software client web browser. The user has the option to save the data for later use. The user can also send the data to PACS, for review.

This document describes the Arterys Viewer, a medical imaging software. However, the provided text does not contain acceptance criteria, a study proving the device meets those criteria, or specific performance data related to accuracy or clinical effectiveness.

The document focuses on:

• General Information: Manufacturer, contact, date prepared.
• Device Description: Intended use (DICOM and non-DICOM data management, display, processing, storage, transfer), functionalities (visualization, quantification, data reporting).
• Indications for Use: What the device is intended for and who uses it (trained medical professionals).
• Comparison to Predicate and Reference Devices: A detailed table comparing feature sets, highlighting similarities and minor differences, and concluding substantial equivalence to a predicate PACS system and a previous version of their own software. This comparison is primarily about feature parity and technological characteristics, not clinical performance.
• Performance Data (General Statement): A general statement that safety and performance have been evaluated and verified according to software specifications, applicable performance standards, and relevant FDA/IEC guidance documents.

Therefore, I cannot provide the requested table or detailed study information because it is not present in the given text. The document asserts that the device is substantially equivalent to a predicate, meaning it performs similarly and raises no new questions of safety or effectiveness, but it does not present a specific study with acceptance criteria and a detailed demonstration of the device meeting those criteria.

Here's a summary of what can be extracted from the provided text regarding performance context:

• Device Name: Arterys Viewer
• Regulation Number: 21 CFR 892.2050
• Regulation Name: Picture archiving and communications system
• Product Code: LLZ
• Regulatory Class: II

Regarding the specific questions:

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

   • Acceptance Criteria: Not explicitly stated as quantifiable performance metrics for clinical use. The "acceptance" is implied through substantial equivalence to a predicate device, meaning it performs its intended functions similarly and safely.
   • Reported Device Performance: No specific numerical performance data (e.g., accuracy, sensitivity, specificity, or measurement agreement) is provided. The performance is described in terms of its functionalities (display, processing, storage, measurements) and claimed to be verified through software V&V.

2. Sample size used for the test set and the data provenance: Not provided. The document mentions "software verification and validation testing" but does not detail the size or nature of the test data (e.g., retrospective/prospective, country of origin).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not provided.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not provided. The device is a "Viewer" and "does not directly generate any diagnosis or potential findings," implying it's a tool for professionals rather than an AI-assisted diagnostic algorithm in the sense of directly improving reader performance on a diagnostic task specified here.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done: Not provided. The device is intended to be used by "trained medical professionals" who interpret the information, so a purely standalone performance claim would be contrary to its stated use.

7. The type of ground truth used (expert concensus, pathology, outcomes data, etc): Not provided.

8. The sample size for the training set: Not applicable based on the available information. The device is described as a "Viewer" with visualization and measurement tools, rather than a machine learning model that requires a distinct "training set" in the common understanding of AI/ML devices.

9. How the ground truth for the training set was established: Not applicable, as no training set is described.

In conclusion, the document primarily makes a case for substantial equivalence based on functional and technological characteristics compared to predicate devices, supported by general software verification and validation activities, rather than presenting a detailed clinical performance study with acceptance criteria.

Ask a specific question about this device

Arterys Cardio DL consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. Arterys Cardio DL specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically-relevant and reproducible, quantitative data, and it has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by Arterys Cardio DL is intended to support qualified cardiologist, radiologist, or other licensed professional healthcare practitioners for clinical decision-making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.

Arterys Cardio DL is a web-accessible image post-processing analysis software device used for viewing and quantifying cardiovascular MR images. The device is intended to visualize and quantify MRI data in DICOM format. Manual and semi-automatic border detection forms the basis for analysis. The software has features for loading, saving, generating screen displays, and aggregating quantitative data from cardiovascular images acquired from magnetic resonance (MR) scanners. Arterys Cardio DL is intended for use in both pediatric (neonate, infant, child and adolescent) and adult populations.

Here's an analysis of the acceptance criteria and study information for the Arterys Cardio DL device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided FDA 510(k) summary (K163253) for Arterys Cardio DL does not explicitly list specific quantitative acceptance criteria or their corresponding reported device performance values in a table format.
Instead, it indicates that "Safety and performance of Arterys Cardio DL has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing." The submission focuses on demonstrating substantial equivalence to predicate devices (Arterys Software v2.0 and Medis Imaging QMass) by comparing technological characteristics and asserting that it "raises no new questions of safety and effectiveness."

The "Features/Functions" table (pages 5-6) compares the proposed device's capabilities to its predicates but does not include quantitative performance metrics or acceptance criteria for those metrics.

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

The document does not specify the sample size used for the test set.
Data provenance (e.g., country of origin, retrospective or prospective) is not explicitly stated for any test data.

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

The document does not provide information regarding the number of experts used to establish ground truth or their specific qualifications for any test set.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1, none) used for establishing ground truth on a test set.

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

The document does not mention or describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study investigating human readers' improvement with AI assistance. The focus is on the device's standalone performance and substantial equivalence to predicates.

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

Yes, a standalone study (algorithm-only performance) appears to have been done. The statement "Safety and performance of Arterys Cardio DL has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing" (page 7) implies that the software's inherent capabilities were tested and validated. The entire submission focuses on the algorithm's functionality and its output.

7. The Type of Ground Truth Used

The document does not explicitly state the type of ground truth used for validation. While the device provides "clinically-relevant and reproducible, quantitative data," it doesn't specify if this was validated against expert consensus, pathology, or outcomes data. Given that it's a post-processing analysis software intended to quantify existing MR images, it's highly probable that some form of expert consensus or highly accurate manual measurements served as ground truth for quantitative validation (e.g., comparing algorithm-derived volumes or flow measurements to manually delineated ones). However, this is not stated.

8. The Sample Size for the Training Set

The document does not specify the sample size used for the training set.

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

The document does not provide information on how the ground truth for the training set was established. Given the "DL" (Deep Learning) in the product name, it's implied that machine learning was used, which would typically involve a training set with established ground truth, but the details are absent.

Ask a specific question about this device

The Arterys Software consists of software that analyzes DI COM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. Arterys Software specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically-relevant and reproducible, quantitative data, and it has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by the Arterys Software is intended to support qualified cardiologist, radiologist, or other licensed professional healthcare practitioners for clinical decision-making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.

The Arterys Software is a web-accessible image post-processing analysis software device for viewing and quantifying cardiovascular MR images. The device is intended to visualize and quantify MRI data in DICOM format. Manual and semi-automatic border detection forms the basis for the analysis. The software has features for loading, saving, generating screen displays, and aggregating quantitative data from cardiovascular images acquired from magnetic resonance (MR) scanners. The Arterys Software is intended for use in both pediatric (neonate, infant, child and adolescent) and adult populations.

The provided text describes the Arterys Software v2.0 and its substantial equivalence to predicate devices, but it does not contain specific acceptance criteria or a detailed study proving the device meets those criteria.

The document states that "Safety and performance of the Arterys Software has been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing, as well as software usability testing." However, the results of these tests, including the acceptance criteria used and the reported performance values, are not included in this summary.

Therefore, I cannot fulfill your request for:

1. A table of acceptance criteria and the reported device performance.
2. Sample size used for the test set and data provenance.
3. Number of experts used to establish ground truth and their qualifications.
4. Adjudication method for the test set.
5. MRMC comparative effectiveness study results.
6. Standalone performance results.
7. Type of ground truth used.
8. Sample size for the training set.
9. How ground truth for the training set was established.

This information would typically be found in the detailed performance data section of a 510(k) submission, which is summarized or referenced here but not fully disclosed.

Ask a specific question about this device