Search Results

QFR 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 QFR 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.

QFR is delivered as a standalone software package which is installed and running on a server system in the server room of the cathlab or the hospital. The server offers all functionalities that are required to work with the quantitative measurement in X-ray Angiographic (XA) patient studies supported by the QFR device.

QFR will be used by interventional cardiologists and researchers to obtain quantifications of lesions in coronary vessels. QFR has been developed as a web-based application to run in a web browser in the control room of the cathlab or in a hospital image review room. The import of images and the export of analysis results are via PACS.

The QFR device calculates the QFR value based on an anatomical model which is the result of a 3D reconstruction using the 2D contours obtained from two angiographic projections with angles >=25 degrees apart. These projections are acquired through monoplane or biplane XA systems. The algorithm involves three key steps: (1) Vessel Selection, (2) Contours Detection, and (3) QFR Analysis:

1. Vessel Selection: Angiograms are pre-classified by a deep learning model, identifying main epicardial vessels such as RCA, LAD, and LCx. The user then chooses the segment for analysis, and the software automatically selects end-diastolic image frames. The end-diastolic frame is determined as the angiogram frame with the vessel lumen adequately filled with contrast in both image sequences. This selection is either based on the patient's electrocardiogram when available or performed by the software using a deep learning model. It is essential for the user to verify this selection before proceeding with the analysis. The chosen end-diastolic frame serves as the projection view for the subsequent 3D reconstruction of the vessel.

2. Contours Detection. First, the system runs another deep learning model for coronary vessel segmentation as input to identify anatomical corresponding points on both projections for automatic correction of the system distortions introduced by the isocenter offset and the respiration-induced heart motion. Second, begins the automatic detection of start and end positions of the vessel segment to be reconstructed on the projection views, and extract its contours and centerline. Third, the position of the start and end point must be confirmed by the user.

3. QFR Analysis: The QFR value is computed from the arterial and reference diameter function calculated from the 3D reconstruction based on the contours detected on the cross-sections of the vessel segment, and the patient-specific volumetric flow rate calculated from the automated TIMI frame count. The reference diameter and bifurcations are used to determine the flow distribution at coronary bifurcations and calculate the reference diameter function. The reconstructed 3D model is used to calculate the QFR value.

A report is generated by QFR that shows patient information, image acquisition information (both obtained from the DICOM input), analysis results (vessel sizing and QFR value) and snapshot images showing the vessel boundaries.

The provided FDA 510(k) Clearance Letter for QFR (3.0) outlines the device's acceptance criteria and performance data from a study. Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are not explicitly stated in a single, clear table. Instead, they are defined for specific algorithmic improvements. The reported performance is then compared against these defined criteria.

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

• Test Set Sample Size: For the "Vessel classification," "Start and end point detection," and "End-Diastolic (ED) frame detection" evaluations, the document mentions being performed "on a representative dataset." However, the exact sample size (number of patients or images) for these test sets is not explicitly stated.
• Data Provenance: The document does not specify the country of origin of the data or whether the data 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 explicitly state the number of experts used to establish the ground truth for the test set or their specific qualifications (e.g., "radiologist with 10 years of experience"). The context implies that for functionalities "supporting the user and not to completely automate the functionality," human review and correction are part of the process, suggesting expert involvement, but the formal ground truth establishment process is not detailed.

4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set

The document does not specify an adjudication method (such as 2+1 or 3+1) for establishing the ground truth 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 describe a formal Multi Reader Multi Case (MRMC) comparative effectiveness study designed to measure the improvement of human readers with AI assistance versus without AI assistance. The performance evaluations stated are for the algorithm's ability to assist (e.g., correct classification or detection rates) rather than human performance metrics. The statement "For all of these algorithmic improvements the user is able to review and correct the results before the QFR value is calculated" implies that the AI is assistive, but no data on human performance improvement is presented.

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

Yes, standalone performance of the algorithm components (e.g., vessel classification, start/end point detection, ED frame detection by AI/ML model alone) was evaluated and reported against the acceptance criteria. For example, for vessel classification, 96% correct for RCA, 88% for LAD, and 78% for LCx are standalone algorithmic performance numbers before human review and correction. Similarly, the 77% correct for start/end point detection and 81% for ED frame detection are standalone algorithmic performances.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

The document implies that the ground truth for the "correct" classifications/detections was based on some form of human reference standard or expert review, as the system is designed to "support the user" and allows for "manual correction." However, the specific method of establishing this ground truth (e.g., expert consensus, comparison to a gold standard, or clinical outcomes) is not explicitly detailed. For the flow velocity calculation influencing QFR, the ground truth is implicitly related to QFR results and their validation against FFR (Fractional Flow Reserve) reproducibility, which is a physiological measurement.

8. The Sample Size for the Training Set

The document does not specify the sample size for the training set used for the deep learning models. It only mentions that the angiograms are "pre-classified by a deep learning model" and that the system "runs another deep learning model for coronary vessel segmentation."

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

The document does not explicitly describe how the ground truth for the training set was established. It is implied that for deep learning models, labeled data would have been required, but the process of labeling (e.g., by experts, automated methods, or a combination) is not detailed.

Ask a specific question about this device

CAAS Workstation features segmentation of cardiovascular structures, 3D reconstruction of vessel segments and catheter path based on multiple angiographic images, measurement and reporting tools to facilitate the following use:

• Calculate the dimensions of cardiovascular structures;
• Quantify stenosis in coronary vessels;
• Determine C-arm position for optimal imaging of cardiovascular structures;
• Quantify pressure drop in coronary vessels;
• Enhance stent visualization and measure stent dimensions;
  CAAS Workstation is intended to be used by or under supervision of a cardiologist.

CAAS Workstation is an image post-processing software package for advanced visualization and ysis in the field of cardiology or radiology and offers functionality to view X-Ray angiographic images, to segment cardiovascular structures in these images, to analyze and quantify these cardiovascular structures and to present the results in different formats.
CAAS Workstation is a client-server solution intended for usage in a network environment or standalone usage and runs on a PC with a Windows operating system. It can read DICOM X-ray images from a directory, or receive DICOM images from the X-ray or PACS system.
CAAS Workstation is composed out of the following analysis workflows: StentEnhancer and vFFR for calculating dimensions of coronary vessels, quantification of stenosis and calculating the pressure drop and vFFR value based on two 2D X-Ray angiographic images. Semi-automatic contour detection forms the basis for the analyses.
Results can be displayed on the screen, printed or saved in a variety of formats to hard disk, network, PACS system or CD. Results and clinical images with overlay can also be printed as a hardcopy and exported in various electronic formats. The functionality is independent of the type of vendor acquisition equipment.

The provided text describes a 510(k) premarket notification for the CAAS Workstation, a software package for advanced visualization and analysis in cardiology and radiology. However, it does not contain specific details about acceptance criteria or a study proving the device meets those criteria with quantitative performance metrics for AI/ML components.

The document states: "Performance testing demonstrated that the numerical results for the analysis workflows StentEnhancer and vFFR, as already available in predicate device K180019, were comparable." This is a qualitative statement of comparability to a predicate device, not a detailed presentation of acceptance criteria and the results of a study designed to meet them.

Therefore, I cannot fulfill all parts of your request with the provided input. I will outline what can be extracted and note what information is missing.

Summary of Device and Approval:

• Device Name: CAAS Workstation
• Applicant: Pie Medical Imaging B.V.
• FDA K-Number: K232147
• Regulation Name: Angiographic X-Ray System
• Regulatory Class: Class II
• Product Codes: QHA, LLZ
• Predicate Device: CAAS Workstation (K180019) – an earlier version of the same product.
• Basis for Clearance: Substantial Equivalence to the predicate device.

Indications for Use (Key Features):
CAAS Workstation features segmentation of cardiovascular structures, 3D reconstruction of vessel segments and catheter path based on multiple angiographic images, measurement and reporting tools to facilitate the following use:

• Calculate the dimensions of cardiovascular structures;
• Quantify stenosis in coronary vessels;
• Determine C-arm position for optimal imaging of cardiovascular structures;
• Quantify pressure drop in coronary vessels;
• Enhance stent visualization and measure stent dimensions;

Missing Information:

The provided text focuses on the regulatory clearance process through 510(k) substantial equivalence. This pathway often relies on demonstrating that a new device is as safe and effective as a legally marketed predicate device, rather than requiring extensive de novo clinical performance studies with specific acceptance criteria as you've requested for an AI/ML component. The document mentions "Performance testing," but it does not provide the details required to answer your specific questions about acceptance criteria, study design, sample sizes, ground truth establishment, or expert involvement for a new AI/ML model's performance.

The "AI" mentioned appears to refer more to automated image processing algorithms (semi-automatic contour detection, vFFR workflow involving pressure drop quantification, StentEnhancer workflow) rather than a novel, deep learning-based AI/ML algorithm that would typically necessitate the detailed performance study described in your prompt. The emphasis is on comparability of "numerical results" to the predicate, implying validation of existing algorithms, possibly with minor improvements, not a new AI/ML model with distinct performance criteria.

Based on the provided text, here's what can be inferred or explicitly stated, and what remains unknown:

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

• Acceptance Criteria: Not explicitly stated in quantitative terms in the provided text. The document broadly indicates that "numerical results for the analysis workflows StentEnhancer and vFFR...were comparable" to the predicate. This implies the acceptance criterion was "comparability" to the predicate's performance, but no specific thresholds (e.g., accuracy > X%, ROC AUC > Y) are given.
• Reported Device Performance: No quantitative performance metrics (e.g., sensitivity, specificity, accuracy, precision, recall) are provided in the text. The statement is qualitative: "numerical results...were comparable."

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

• Sample Size: Not specified.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The document mentions reading DICOM X-ray images, but not the source of the test data.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The device is intended for use by or under the supervision of a cardiologist, suggesting expert cardiac imaging knowledge would be relevant, but details about ground truth establishment are absent.

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

• Not specified.

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 described. The focus is on the device's standalone performance compared to a predicate, not on a human-in-the-loop MRMC study.

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

• Yes, implicitly. The "Performance testing demonstrated that the numerical results for the analysis workflows StentEnhancer and vFFR...were comparable" indicates an evaluation of the algorithm's output. This is consistent with a standalone performance assessment, as the comparison is about the output of the software itself.

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

• Not explicitly stated. Given the functionalities (quantifying stenosis, dimensions, pressure drop), the ground truth for these "numerical results" would likely involve comparison against a gold standard derived from established imaging methods, potentially quantitative measurements from calibrated imaging devices, or expert consensus measurements, but the document does not elaborate.

8. The sample size for the training set:

• Not specified. The document mentions "semi-automatic contour detection forms the basis for the analyses" for the vFFR workflow, which could imply a training process, but no details are given.

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

• Not specified.

In conclusion, the K232147 FDA clearance document for the CAAS Workstation confirms its regulatory pathway via substantial equivalence to a predicate device. While it mentions "Performance testing" and "comparable numerical results," it does not provide the detailed quantitative acceptance criteria, study methodology, or specific performance metrics that would typically be found in an in-depth clinical validation study for a novel AI/ML device. The information provided is sufficient for a 510(k) submission based on predicate equivalence but lacks the granularity for the specific technical and clinical performance questions asked.

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

QANGIO XA 3D 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 QANGIO XA 3D 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.

QANGIO XA 3D is the Medis software solution for the quantitative analysis of cardiac X-ray Angiography (XA) studies. QANGIO XA 3D features:

• Acquisition guide and series selection guide
• Annotations and basic measurements
• 2D and 3D OCA vessel detection
• 2D and 3D OCA vessel quantification
• QFR calculations: Quantitative Flow Ratio (QFR) analysis with fixed flow model (fQFR) and contrast flow models (cQFR).
• Single vessel report

QANGIO XA 3D will be used by interventional cardiologists and researchers to obtain quantifications of lesions in coronary vessels, to determine the functional significance of the individual or consecutive multiple lesions, prior, during or after percutaneous coronary intervention treatment. QANGIO XA 3D has been developed as a standalone application to run on a Windows based operating system. The import of images and the export of analysis results are via CD / DVD, a PACS or network environment.

Here's a breakdown of the acceptance criteria and the study information for the QANGIO XA 3D, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state a table of acceptance criteria with numerical thresholds. Instead, it describes general validation approaches for its key functionalities.

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

• 3D Vessel Reconstruction: The text does not specify the sample size for the studies that validated 3D vessel reconstruction. It mentions "studies using QCA parameters and IVUS pullbacks in patients," implying patient data was used.
• QFR Calculation: Specifically for the prospective, observational, investigator-initiated multi-center studies for QFR vs. FFR (FAVOR II Europe-Japan and FAVOR II China), the text indicates:
  • Sample Size: Not explicitly stated as a number. It refers to "prospective, observational, investigator-initiated multi-center studies."
  • Data Provenance: Prospective and multi-center studies. The "FAVOR II Europe-Japan" and "FAVOR II China" study names directly indicate multiple countries (Europe and Japan for one, China for another). The nature is prospective.

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

• For QFR Calculation (FAVOR II studies):
  • Number of Experts: The text states, "QFR and FFR were analyzed separately by different observers." It does not specify the number of observers/experts involved in these studies.
  • Qualifications of Experts: Not explicitly stated, but the context of "interventional cardiologists and researchers" using the device for "assessment of coronary vessels" in clinical settings, and "pressure-wire derived fractional flow reserve (FFR) as reference standard" implies that the observers for FFR (the ground truth) would be qualified cardiologists or specialists in cardiovascular intervention.

4. Adjudication Method for the Test Set

• The text states, "QFR and FFR were analyzed separately by different observers." This implies independent assessment rather than a specific adjudication method like 2+1 or 3+1 for discrepancies. The FFR value itself from the pressure wire is considered the reference standard, so its "ground truth" establishment isn't subject to expert consensus adjudication in the same way an image interpretation might be.

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

• Was an MRMC study done? Yes, for QFR, the FAVOR II studies appear to fit the criteria of a multi-reader (different observers for QFR and FFR) multi-case (multiple patients/vessels) study comparing an AI-assisted measurement (QFR) against a reference standard (FFR).
• Effect Size of Human Readers Improve with AI vs. without AI assistance: This information is not provided. The studies focus on the agreement and diagnostic performance of QFR relative to FFR, not on how much human readers improve with AI assistance, as the QFR is presented as an alternative/comparative method to FFR for functional assessment. The QFR is derived from image analysis, which the device performs.

6. Standalone (Algorithm Only) Performance

• Yes, the performance data presented (e.g., QFR validation against FFR) reflects the standalone performance of the QANGIO XA 3D algorithm in generating QFR values from XA images. The device description emphasizes "QANGIO XA 3D is a standalone application." The QFR analysis is described as "calculated based on computer calculations."

7. Type of Ground Truth Used

• For 3D Vessel Reconstruction: "OCA parameters and IVUS pullbacks." Intravascular Ultrasound (IVUS) data is typically considered highly accurate and a robust reference standard for vessel dimensions and morphology, often involving pathology-level detail or direct physical measurement/imaging within the vessel.
• For QFR Calculation: "pressure-wire derived fractional flow reserve (FFR) as reference standard." FFR is a well-established and clinically accepted gold standard for assessing the hemodynamic significance of coronary artery stenoses, which is a form of physiological outcomes data or a highly validated physiological measurement.

8. Sample Size for the Training Set

• The text does not specify the sample size for the training set. It only refers to the validation studies. Since it's a 510(k) submission, the focus is on performance validation rather than detailed algorithm development specifics like training set size.

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

• The text does not provide details on how the ground truth for the training set was established. It primarily discusses the validation of the system's outputs.

Ask a specific question about this device