Search Results

AccuCTP Pro 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 a virtual platform, such as VMware, and can be used to perform image viewing, processing and analysis of brain images. Data and images are acquired through DICOM compliant imaging devices.

AccuCTP Pro provides both viewing and analysis capabilities for functional and dynamic imaging datasets acquired with CT Perfusion (CTP), which can visualize and analyze 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.

AccuCTP Pro is an extension to legally cleared device AccuCTP (K220663).

AccuCTP Pro is a standalone software package that provides visualization and study of changes of tissue perfusion in digital images captured by CT (Computed Tomography). The software provides viewing, quantification, analysis and reporting capabilities, and it allows repeated use and continuous processing of data and can be deployed on a supportive customer's PC or a virtual platform that meets the minimum system requirements.

AccuCTP Pro works with the DICOM compliant medical image data. AccuCTP Pro provides tools for performing the following types of analysis:

• Volumetry of threshold maps
• Time intensity plots for dynamic time courses
• Measurement of mismatch between rCBF and Tmax threshold volumes obtained from the same scan.

The provided text describes the AccuCTP Pro device, which is an extension of a previously cleared device, AccuCTP. The submission is a "Special 510(k) Summary," indicating that it relies on substantial equivalence to a predicate device and focuses on minor changes.

Based on the provided information, the document does not contain details about a clinical study with acceptance criteria and a human reader performance study (MRMC) to prove the device meets specific performance metrics. Instead, it states that the algorithm and output settings of the AccuCTP Pro are the same as the predicate device (AccuCTP). Therefore, it relies on the previous predicate device's validation and general software verification and validation tests for the updated features.

Here's an analysis of the provided text with respect to your requested information:

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

The document does not provide a specific table of acceptance criteria for clinical performance and reported device performance metrics in the way one might expect for a new or significantly modified device requiring de novo validation. It primarily focuses on software verification and validation for the changes made.

The closest statement regarding "acceptance criteria" for performance is: "All tests met the pre-defined acceptance criteria and were passed." However, these refer to software verification tests, not clinical performance metrics.

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

• Test Set: No specific sample size for a clinical test set is mentioned for AccuCTP Pro's validation. The document explicitly states: "No additional pre-clinical or clinical data is being provided with this submission." It defers to the predicate device's validation.
• Data Provenance: Not applicable as no new clinical data is presented.

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)

Not applicable, as no new clinical study data is presented requiring expert ground truth establishment for a test set.

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

Not applicable, as no new clinical study data is presented requiring adjudication.

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 such MRMC study was performed or presented in this submission for AccuCTP Pro. The document focuses on software updates and relies on the predicate device's previous validation.

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

This is implicitly addressed by the statement: "Phantom test and validation study were completed and reviewed as part of the predicate review (K220663), and the results concluded AccuCTP was safe and effective. As all algorithm and output of the subject device AccuCTP Pro is same as the predicate device AccuCTP, it can be concluded that AccuCTP Pro is acceptable for use." This suggests that the predicate device had a standalone evaluation, and since the algorithm hasn't changed, the standalone performance is assumed to be the same.

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

For the predicate device's "phantom test and validation study," the ground truth would likely be established through physical phantom measurements or a gold standard comparison. The document does not specify the type of ground truth for the predicate.

8. The sample size for the training set

Not mentioned. The document describes the device as an "extension" with the "same fundamental scientific technology" and "same operation principle and algorithm embedded in the software" as the predicate. This suggests the training would have occurred for the original AccuCTP, and no new training data is discussed for AccuCTP Pro given that the algorithm is the same.

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

Not mentioned, for the same reasons as in point 8.

Summary of what the document does provide regarding device acceptance and performance:

The acceptance of AccuCTP Pro is based on its substantial equivalence to the predicate device AccuCTP (K220663). The core argument is:

• The intended use, intended user, intended patient population, fundamental scientific technology, operation principle, and algorithm of AccuCTP Pro are the same as the predicate device.
• The changes in AccuCTP Pro are primarily related to data transmission mode, simplified manual operation, and updated software installation environments (e.g., compatibility with Linux and Windows, and virtual platforms like VMware, and basic PACS functions).
• These minor differences were evaluated through software verification and validation tests (import/export of DICOM, automatic selection/calculation, software management, case management, recalculation/adjustment, operating environment tests).
• Cybersecurity testing was performed according to FDA guidance.
• Human factors testing was conducted with fifteen qualified participants to validate usability and the user manual, concluding safe and effective use without residual use-related risks.
• The manufacturer relies on the original phantom test and validation study conducted for the predicate device (AccuCTP), arguing that since the algorithm and output are identical, the conclusions of safety and effectiveness for the predicate device extend to AccuCTP Pro.

In essence, AccuCTP Pro's "acceptance" is not demonstrated by new clinical performance data but by proving that its software updates do not introduce new questions of safety or effectiveness, due to the unchanged core algorithm and the successful completion of software engineering, cybersecurity, and usability tests.

Ask a specific question about this device

AccuFFRangio Plus is indicated for use in clinical settings where validated and reproducible quantified results are needed to support the assessment of coronary vessels in X-ray angiographic images, for use on individual patients with coronary artery disease.

When the quantified results provided by AccuFFRangio Plus are used in a clinical setting on X-ray images of an individual patient, the results are only intended for use by the responsible clinicians.

AccuFFRangio Plus is a system that is used to perform calculations in X-ray angiographic images of the coronary arteries. It includes hardware and software (AccuFFRangio) and the hardware of the device which mainly has a display function and provide the software an operation environment. AccuFFRangio Plus is changed from our own legally marketed predicate device AccuFFRangio that is a stand-alone software package. Therefore, the significant change lies in equipping a computer system to the software on a particular mobile cart.

The provided text is a 510(k) summary for the device AccuFFRangio Plus. It primarily focuses on demonstrating substantial equivalence to a predicate device (AccuFFRangio) by highlighting that the core software is unchanged and the modifications are primarily hardware-related. As such, the document does not detail specific acceptance criteria or performance studies for the AI/algorithm itself for several reasons:

• The 510(k) is for a hardware modification of an already cleared device. The "significant change" lies in integrating the existing software into a new hardware system (a mobile cart with computer, monitor, etc.). Therefore, the performance data presented primarily addresses the new hardware aspects (electrical safety, EMC, etc.) and leverages the software's previous clearance.
• The software (AccuFFRangio) was likely cleared previously. The document states, "The software installed in the subject device is the same as the predicate device." This suggests that the clinical performance and acceptance criteria for the software were established and validated during the predicate device's (AccuFFRangio, K210093) original 510(k) clearance process. This document is not resubmitting that, but relies on it.
• The device calculates "quantified results" and "quantification of the pressure drop," not necessarily an AI-driven diagnosis or classification. While the term "AI" or "deep learning" is not explicitly used, the description of "quantified results" and "pressure drop" calculations suggests an analytical tool rather than a traditional diagnostic AI that might have sensitivity/specificity metrics.

Therefore, based solely on the provided text, I cannot provide a detailed response to your request regarding AI acceptance criteria and study proving the device meets them because this information is not present in this specific 510(k) summary. The summary explicitly states: "No clinical testing was necessary to support the device modifications described in this Special 510(k)." and "The following testing was leveraged from the predicate device. The results from the predicate were used to support the subject device the software contained in the AccuFFRangio Plus is the same as the predicate device."

To answer your request, one would need to refer to the original 510(k) submission for the predicate device, AccuFFRangio (K210093), as that is where the software's performance and validation data would have been submitted. This document focuses on the safety and efficacy of the hardware integration and the overall system's continued substantial equivalence.

However, I can extract information related to the general "performance data" presented for the current 510(k), which focuses on the hardware and usability aspects:*

Acceptance Criteria and Study for AccuFFRangio Plus (Hardware-Focused)

As established above, this 510(k) focuses on the hardware modifications. The "acceptance criteria" and "performance" are therefore related to the safety and functionality of the integrated system, not the clinical performance of the underlying software's calculations, as that was established during the predicate device's clearance (K210093).

1. Table of Acceptance Criteria and Reported Device Performance (Hardware & Usability)

2. Sample Size and Data Provenance

• Test Set Sample Size:
  • Human Factors Testing: 15 qualified participants.
  • For other tests (Electrical Safety, EMC, Hardware Verification, Transportation, Accelerated Aging, Labeling), the sample size typically refers to the number of units tested, which isn't explicitly stated but is implicitly "sufficient" to meet the standard requirements.
• Data Provenance: Retrospective (leveraging data and conclusions from the predicate device's software clearance). No new clinical data was generated for this specific 510(k). Country of origin is not specified for the original data, but the submitter is from Hangzhou, China.

3. Number of Experts and Qualifications for Ground Truth

• Not applicable to the hardware/usability tests described in this document.
• For the Human Factors testing, "15 qualified participants" were used. Their specific qualifications (e.g., medical professionals, years of experience) are not detailed here, but they would be representative of the intended users.
• For the original software's ground truth establishment (from the predicate device's 510(k)), this information would be detailed in K210093.

4. Adjudication Method for the Test Set

• Not applicable for the hardware/usability tests.
• For the Human Factors testing, success was determined by the absence of "use errors" during "critical tasks," rather than a formal adjudication process.

5. MRMC Comparative Effectiveness Study

• No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted for this 510(k). The document explicitly states "No clinical testing was necessary to support the device modifications described in this Special 510(k)."

6. Standalone Performance (Algorithm Only without Human-in-the-Loop)

• The software aspect of the device ("AccuFFRangio") is described as a "stand-alone software package" in the predicate description. Therefore, standalone software performance was likely evaluated during the predicate device's (K210093) clearance. This 510(k) document does not provide those details, but leverages that previous data. The "AccuFFRangio Plus" is now an integrated hardware/software system.

7. Type of Ground Truth Used

• For the hardware studies, ground truth is based on engineering standards (e.g., IEC, ASTM) and internal quality control specifications.
• For the software's calculations (leveraged from the predicate), the type of ground truth (e.g., another device, invasive measurements, expert consensus on imaging) would have been established during K210093. This document describes the device as providing "quantified results of coronary vessel segments based on a 3D reconstructed model" and "Quantification of the pressure drop in coronary vessels," implying quantitative ground truth rather than subjective diagnostic labels.

8. Sample Size for the Training Set

• Not applicable to this 510(k) which covers hardware modifications and re-uses existing software.
• For the original software development (from the predicate device's 510(k)), this information would be detailed in K210093.

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

• Not applicable to this 510(k).
• For the original software (from the predicate device's 510(k)), this information would be detailed in K210093.

In summary, this 510(k) submission is a "special 510(k)" for a hardware modification, explicitly relying on the prior clearance of its predicate software. Therefore, the detailed AI/algorithm specific performance data and acceptance criteria you requested are not contained within this document but would be found in the original submission for the predicate device, AccuFFRangio (K210093).

Ask a specific question about this device

AcculCAS is software intended to be used for performing calculations in X-ray angiographic images of the intracranial vessels. AcculCAS enables neurointerventionalists to obtain quantifications of one or more lesions in the analyzed intracranial vessel segment. In particular, AccuICAS provides:
Quantitative results of intracranial vessel segments based on a 3D reconstructed model;
Dimensions of the intracranial vessels and lesions;
Quantification of the pressure gradient (PG) and pressure ratio (PR) in intracranial vessels.
AccuICAS is indicated for use in clinical settings where validated and reproducible quantified results are needed to support the assessment of intracranial vessels in X-ray angiographic images.
When the quantified results provided by AccuICAS are used in a clinical setting on X-ray images of an individual patient, the results are only intended for use by the responsible clinicians.

ArteryFlow AcculCAS is designed as a stand-alone software package to run on a PC. This software can read traditional x-ray angiographic images with DICOM format from the local file directory.
AcculCAS is composed of the following analysis workflows: Image Loading, Frame Selection, Vessel Reconstruction and Hemodynamics Calculation for visualization of the target intracranial vessel segment, quantification of morphological parameters and pressure drop of the intracranial vessel segment. AcculCAS is only for quantitative imaging output but not for diagnosis.
AcculCAS calculates the pressure gradient (PG) and pressure ratio (PR) value for the intracranial vessel. To obtain these values for a specific lesion in an intracranial vessel, the user needs to start with Frame Selection using the same vessel under different angulation. In each of these images, a classic 2D intracranial vessel contour detection is performed, after which a reconstruction of the intracranial vessel segment is obtained in 3D space. Based on the 3D reconstruction and patients' mean arterial pressure, the corresponding pressure gradient (PG) and pressure ratio (PR) value at each position can be calculated.
AcculCAS enables neurointerventionalists to obtain accurate anatomical quantifications of one or more lesions in the analyzed intracranial vessel segment, and to assess the best viewing angles which can be helpful for optimal visualization of the lesion.
AcculCAS's outputs mainly include quantitative dimension results of intracranial vessel and lesions segments based on a 3D reconstructed model and quantification of the pressure gradient (PG) and pressure ratio (PR) in intracranial vessels. Besides, other information provided to the end user also belongs to the outputs, such as display of reference vessels and lesions, display of target vessel lumen contour, 3D reconstructed model of intracranial vessels, the diameter stenosis distribution and PG/PR distributions.

Here's a breakdown of the acceptance criteria and study details for the AccuICAS device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with numerical targets. Instead, it describes a qualitative acceptance: that "All of these tests met the predefined criteria, indicating that the AccuICAS algorithm is accurate, and the device is clinically acceptable." The performance is described by the successful validation of various outputs and calculations.

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

• Sample Size:

  • Morphological parameters: "three brass phantoms and a dozen clinical data." (A dozen typically means 12, so 15 total, 12 clinical data points).
  • Diameter stenosis distribution, PG/PR distributions: "several clinical patients with stenosis lesions." (The exact number is not specified but is less precise than "a dozen").
  • Hemodynamics calculation: "calculated results with the measured results." (Implies the testing involved a dataset that had both device-calculated and independently measured PG/PR values, but the sample size is not stated beyond "results").

• Data Provenance: The document does not explicitly state the country of origin for the clinical data or whether it was retrospective or prospective. Given the submitter's address (Hangzhou, CHINA), it is possible the clinical data originated from China, but this is not confirmed. The nature (retrospective/prospective) is also not specified.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth for the test set. The ground truth for hemodynamics validation seems to have come from "measured results" rather than expert consensus on images.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method (e.g., 2+1, 3+1) for the test set. The validation seems to rely on comparisons against phantoms, "measured results," and unspecified clinical data outcomes.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, What was the Effect Size of how much human readers improve with AI vs without AI assistance

No MRMC comparative effectiveness study involving human readers with and without AI assistance is mentioned or described in the provided text. The device is for "quantitative imaging output but not for diagnosis" and the validation focuses on the accuracy of its calculations.

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

Yes, the performance data presented appears to be a standalone (algorithm only) evaluation. The validation described tests the accuracy of the algorithm's outputs (segmentation, reconstruction, morphological parameters, hemodynamics calculations) against established references (phantoms, measured results), not against human interpretation assisted by the AI.

7. The Type of Ground Truth Used

• Phantoms: For morphological parameters (brass phantoms).
• "Measured Results": For hemodynamics calculations (PG and PR values). This suggests an independent, possibly invasive or highly accurate, method of obtaining these measurements, rather than clinical consensus readings from images.
• Clinical Data/Patient Observations: For diameter stenosis and PG/PR distributions, and implicitly for the "dozen clinical data" for morphological parameters. The exact nature of how this "ground truth" was established for clinical data is not specified (e.g., expert consensus, other imaging modalities, surgical findings, pathology reports, or long-term outcomes). However, the phrasing "compared the calculated results with the measured results" for PG/PR strongly implies an objective, independent measurement was the ground truth for that specific aspect.

8. The Sample Size for the Training Set

The document does not provide any information about the sample size used for the training set.

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

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

Ask a specific question about this device

AccuCTP 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, and can be used to perform image viewing, processing and analysis of brain images. Data and images are acquired through DICOM compliant imaging devices.

AccuCTP provides both viewing and analysis capabilities for functional and dynamic imaging datasets acquired with CT Perfusion (CT-P), which can visualize and analyze dynamic imaging data, showing properties of changes in contrast over time. This functionality includes calculation of parameters related to tissue blood volume.

AccuCTP is a standalone software package that provides visualization and study of changes of tissue perfusion in digital images captured by CT (Computed Tomography). The software provides viewing, quantification, analysis and reporting capabilities, and it allows repeated use and continuous processing of data and can be deployed on a supportive customer's PC that meets the minimum system requirements.

AccuCTP works with the DICOM compliant medical image data. AccuCTP provides tools for performing the following types of analysis:

• volumetry of threshold maps .
• time intensity plots for dynamic time courses .
• . measurement of mismatch between rCBF and Tmax threshold volumes obtained from the same scan.

The provided text, a 510(k) Summary for the AccuCTP device, focuses on demonstrating substantial equivalence to a predicate device (RAPID) rather than providing detailed acceptance criteria and the results of a statistically powered clinical study. However, it does outline performance validation activities.

Here's an analysis of the available information regarding acceptance criteria and performance studies, structured according to your request, with limitations noted due to the nature of the document:

1. Table of Acceptance Criteria and Reported Device Performance

The document states: "Parameter map and Volume results were quantitatively analysed and met the pre-defined pass/fail criteria." However, the specific numerical pre-defined pass/fail criteria are not explicitly stated in this document. The performance is reported in terms of agreement with a "ground truth" (phantom data) and agreement with the predicate device (RAPID CTP).

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

• Test Set Sample Size: The document mentions a "group of phantoms" for the phantom test and a "calculation performance validation" using data to compare with RAPID CTP. However, the exact numerical sample size (number of CT perfusion studies or phantoms) used in these validation studies is not specified.
• Data Provenance: The document does not specify the country of origin for the data used in the "validation study" that compared AccuCTP to RAPID CTP. It also does not explicitly state whether the data was retrospective or prospective. The phantom study clearly used synthetic data.

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

The document does not mention the use of human experts to establish ground truth for the test sets.

• For the phantom test, the ground truth was inherently known from the design of the phantoms.
• For the "validation study" comparing AccuCTP to RAPID CTP, the ground truth was effectively the output of the predicate device (RAPID CTP), implying a comparison for concordance rather than independent expert adjudication.

4. Adjudication Method for the Test Set

No adjudication method involving human experts is described since the ground truth for the validation was either known from phantoms or based on the predicate device's output.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was it done? No, the document does not describe an MRMC study. The validation described focuses on the agreement of AccuCTP's output (parameter maps and volumes) with physical phantoms and with the predicate device's output. There is no mention of human readers or AI assistance in diagnostic tasks.
• Effect Size of Human Improvement: Not applicable, as no MRMC study was conducted.

6. Standalone (Algorithm Only) Performance

Yes, the studies described are standalone performance evaluations of the AccuCTP algorithm. The phantom test directly evaluated the algorithm's accuracy against known physical properties, and the comparison with RAPID CTP assessed the algorithm's concordance with another software's output. The device is described as "a standalone software package."

7. Type of Ground Truth Used

• Phantom Test: The ground truth was known physical properties/measurements derived from the design of the phantoms.
• Validation Study (comparison with RAPID CTP): The "ground truth" for this comparison was effectively the results/output of the predicate device (RAPID CTP). This is a comparison of computational results for substantial equivalence, not a clinical ground truth for diagnostic accuracy (e.g., pathology, clinical outcomes).

8. Sample Size for the Training Set

The document does not specify the sample size of the training set used for developing or training the AccuCTP algorithm. Performance data in this section refers to validation testing, not training data.

9. How Ground Truth for the Training Set Was Established

The document does not provide any information on how the ground truth for the training set (if supervised learning was used) was established, as it doesn't discuss the training phase of the algorithm development.

Ask a specific question about this device

AneuGuide enables visualization of intracranial vessels for preoperational planning and sizing for neurovascular interventions. AneuGuide also allows for the ability to computationally model the placement of neurointerventional devices. General functionalities are provided such as:

• Segmentation of neurovascular structures .
• Automatic centerline detection
• . Visualization of X-ray based images for 2D review and 3D reconstruction
• . Placing and sizing tools
• Reporting tools

Information provided by the software is not intended in any way to eliminate, replace or substitute for, in whole or in part, the healthcare provider's judgment and analysis of the patient's condition.

The AneuGuide software is a medical device intended to provide a 3D view of the final placement of implants. It uses an image of the patient produced by 3D rotational angiography. It offers clinicians the possibility of computationally modeling the flow diverters (FD) in the artery to be treated through endovascular surgery.

AneuGuide is intended to import DICOM images and to provide a 3D reconstruction of the vascular tree in the surgical area. Also, it allows to pre-operationally estimate the size of flow diverter devices.

AneuGuide is composed of the following analysis workflows: image loading, selection of the volume of interest (VOI), segmentation threshold adjustment, reconstruction, selection of the region of interest (ROI), selection of the vessel inlet, generation of centerline, initializing the flow diverter, and sizing the flow diverter.

The flow diverter supported by the software is the Pipeline Flex Embolization Device (Micro Therapeutics, Inc. d/b/a ev3 Neurovascular, PMA: P100018/S015), which is an FDA-approved neurointerventional device. AneuGuide software has a "moderate" level of concern. It is intended only for preoperational planning. It is not intended for diagnosis.

The ArteryFlow Technology AneuGuide software is a medical device intended for preoperational planning of neurovascular interventions, specifically for visualizing intracranial vessels and computationally modeling the placement of neurointerventional devices like flow diverters.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them:

1. Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" with specific quantitative thresholds. Instead, it describes general performance tests and a validation study for a key functionality: calculating the deployed length of a flow diverter. The overall acceptance criterion is implied to be that the software functions as intended, and for the flow diverter deployment, that its simulated length is sufficiently accurate compared to real-world implantation.

2. Sample Size and Data Provenance

• Test Set Sample Size: The document mentions two performance tests for computational modeling:
  • Silicone Phantoms: "Using silicone phantoms representative of patients presenting with intracranial aneurysms." The exact number of phantoms is not specified.
  • Patient Implantation Data: "Validation study of the AneuGuide performance comparing the simulated deployed length of the Pipeline Flex Embolization Device with its implanted length in patients with intracranial aneurysms." The exact number of patients or cases is not specified.
• Data Provenance: The document does not specify the country of origin for the patient data used in the validation study. It also does not explicitly state whether the patient data was collected retrospectively or prospectively. Given the context of comparing simulated vs. implanted lengths, it strongly implies retrospective analysis of existing patient implant data.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number of experts used to establish the ground truth for the test set, nor does it detail their specific qualifications (e.g., radiologist with X years of experience). The general description implies that the "implanted length" from patients would serve as a real-world ground truth, presumably measured by clinical professionals.

4. Adjudication Method for the Test Set

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

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

An MRMC study was not explicitly done or reported. The performance tests described focus on the software's capability to accurately model physical parameters (flow diverter length) rather than evaluating human reader performance with or without AI assistance. The device is for "preoperational planning" and "not intended in any way to eliminate, replace or substitute for...the healthcare provider's judgment." This suggests it's a tool for the human, not an AI to be compared against human readers for diagnostic accuracy.

6. Standalone (Algorithm Only) Performance

Yes, the described "Performance Testing - Bench" section primarily focuses on the standalone (algorithm only) performance of AneuGuide in calculating the deployed length of the Pipeline Flex Embolization Device. The tests involved comparing the software's simulated output against physical measurements (from silicone phantoms and implanted patient data).

7. Type of Ground Truth Used

The type of ground truth used for the computational modeling performance evaluation appears to be:

• Physical Measurements/Knowns: For the silicone phantom study, the "in vitro" placement is likely based on precise physical measurements of the actual flow diverter deployment in the phantoms.
• Outcomes Data/Clinical Measurement: For the patient study, the "implanted length" of the flow diverter is derived from real-world patient data, presumably measured from post-implantation imaging or surgical records. This leans towards clinical outcomes/measurements as ground truth.

8. Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set of the AneuGuide software.

9. How Ground Truth for Training Set was Established

The document does not provide any information on how ground truth was established for the training set. Given that the software is for "computational modeling" of device placement and not explicit diagnostic AI, it's possible that the "training" (if it involved machine learning) might have used simulated data, or that "training" in this context refers more to the development and calibration of the underlying physical models rather than a typical supervised learning approach with human-labeled ground truth images.

Ask a specific question about this device

AccuFFRangio is indicated for use in clinical settings where validated and reproducible quantified results are needed to support the assessment of coronary vessels in X-ray angiographic images, for use on individual patients with coronary artery disease.

When the quantified results provided by AccuFFRangio are used in a clinical setting on X-ray images of an individual patient, the results are only intended for use by the responsible clinicians.

ArteryFlow® AccuFFRangio is designed as a stand-alone software package to run on a PC. This software can read traditional x-ray angiographic images with DICOM format from the local file directory.

The AccuFFRangio is composed of the following analysis workflows: Image Loading, Frame Selection, Vessel Reconstruction, QCA Vessel Quantification, and AccuFFRangio Calculation for visualization of the target coronary segment, quantification of the stenosis and pressure drop of the coronary seqment. The AccuFFRangio parameter is only for quantitative imaging output but not for diagnosis and the AccuFFRanigo product has a moderate level of concern.

The user can calculate the pressure drop and AccuFFRangio (FFR) value for the coronary vessel. To obtain these values for a specific lesion in a coronary vessel, the user has to start with Frame Selection using two angiographic images from different views. In each of these images, a classic 2D coronary contour detection is performed, after which a reconstruction of the coronary segment is obtained in 3D space. Based on the 3D reconstruction and user input of the aortic pressure, the pressure drop and AccuFFRangio value can be calculated.

AccuFFRangio enables interventional cardiologists to obtain accurate anatomical quantifications of one or more lesions in the analyzed coronary segment, and to assess the best viewing angles which can be helpful for optimal visualization of the lesion during percutaneous coronary intervention (PCI) treatment.

Results can be displayed and generated by the software, which contains patient information, imaging of actual and reference vessel boundaries, dimensions of the vessel sizing, pressure drop, and AccuFFRangio value. The results can be export in PDF format. This functionality is independent of the type of vendor acquisition equipment.

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

Acceptance Criteria and Device Performance

Study Details for Acceptance Criteria Proof:

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

   • 3D Vessel Reconstruction: "A phantom study had been implemented by using three different types stenosis of brass model." The specific number of images or cases analyzed in this phantom study is not provided.
   • AccuFFRangio calculation: "a series of X-ray angiographic dataset with known pressure drops were analyzed." The specific number of cases or images in this dataset is not provided.
   • Data Provenance: Not explicitly stated for either study (e.g., country of origin, retrospective/prospective). The phantom study suggests a controlled laboratory environment rather than patient data. The AccuFFRangio Calculation refers to an "X-ray angiographic dataset," implying patient data, but details are missing.

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

   • The document does not mention the use of human experts to establish ground truth for the test sets in either the 3D vessel reconstruction or AccuFFRangio calculation studies.
   • For the 3D vessel reconstruction, the ground truth was based on "three different types stenosis of brass model," implying a physical model with known dimensions.
   • For the AccuFFRangio calculation, the ground truth was established by "X-ray angiographic dataset with known pressure drops." The method by which these "known pressure drops" were determined (e.g., invasive FFR measurements, expert consensus using other clinical data) is not specified, and therefore, the involvement or qualifications of experts are not described.

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

   • Not applicable/Not mentioned. The studies described do not involve human review for ground truth with an adjudication process.

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 MRMC comparative effectiveness study is described in the provided text. The studies focus on the standalone performance of the device compared to a predicate device or known physical/physiological values.

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

   • Yes, the studies described are standalone performance evaluations of the AccuFFRangio software. The text explicitly states that "AccuFFRangio is designed as a stand-alone software package." The performance data section describes evaluating the software's output directly against phantom measurements or known physiological values.

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

   • 3D Vessel Reconstruction: Physical phantom measurements (brass models).
   • AccuFFRangio calculation: "Known pressure drops" from an X-ray angiographic dataset. The origin or method of determining these "known pressure drops" is not detailed, so it's not explicitly stated as expert consensus, invasive FFR, or outcomes data.

7. The sample size for the training set:

   • The document does not provide information about the sample size used for the training set of the AccuFFRangio device. The performance data section focuses solely on validation/testing.

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

   • As training set details are not provided, how its ground truth was established is also not described in the document.

Ask a specific question about this device