Search Results

The VMS+ 4.0 system is an adjunct to existing ultrasound imaging systems and is intended to record, analyze, store and retrieve digital ultrasound images for computerized 3-dimensional image processing.

The VMS+ 4.0 system is indicated for use where Left Ventricle (LV), Left Atrium (LA), and Right Atrium (RA) volumes and ejection fractions are warranted or desired.

The Ventripoint VMS+ 4.0 System is a medical imaging device designed to assist clinicians in evaluating cardiac function through 3D reconstruction of heart chambers. It uses a Knowledge-Based Reconstruction (KBR) algorithm to recreate the heart's shape by capturing 2D ultrasound images at specific angles and referencing a database of MRI heart shape catalogs. The reconstructed 3D heart models are used to calculate volumes of any of the four chambers at end-diastolic and/or end-systolic phases. The software can also be installed on a separate workstation to import 3D datasets, MRI studies, and VMS+ studies.

The system employs user-driven anatomical control point placement to generate 3D models. Users manually adjust control points based on an anatomical template aligned with the patient's ultrasound images. An edge detection algorithm refines these points to match detected anatomical boundaries, ensuring model precision.

The VMS+ system includes a hardware stand with a computer, position sensors to track the 3D orientation of the ultrasound transducer and patient movement, and software to handle image capture, landmark placement, and reconstruction. By leveraging its sensor system and statistical shape analysis, the VMS+ transforms 2D ultrasound data into accurate 3D models. The workflow takes approximately 15 minutes and provides detailed volumetric data and reports for clinical review.

Here's a summary of the acceptance criteria and study information for the Ventripoint Medical System Plus (VMS+) 4.0, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: For the user validation study, 160 ultrasound images of the right ventricle were used.
• Data Provenance: Not explicitly stated for the ultrasound images used in the user validation. The document is from Canada (Ventripoint Diagnostics Ltd. is based in Toronto, ON, Canada), but the country of origin of the patient data is not specified. The studies are implicitly retrospective for the user validation ("160 ultrasound images...").

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

• Number of Experts: Not explicitly stated. The text mentions "expert consensus region" for anatomical points, implying multiple experts, but does not provide an exact number.
• Qualifications of Experts: Not explicitly stated.

4. Adjudication Method for the Test Set

• Adjudication Method: "Expert consensus region" is mentioned for the user validation study on anatomical point placement. This suggests that the ground truth for point localization was established by consensus among experts, but the specific method (e.g., 2+1, 3+1) is not detailed.

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

• MRMC Study: The document describes an "internal user validation study" comparing user performance with VMS+ 4.0 to the predicate (VMS+ 3.0). This is a form of comparative effectiveness study involving human readers.
• Effect Size of Human Reader Improvement: The study demonstrated that "user performance for final point localization using VMS+ 4.0 was at least as good as the predicate, when used by the same users for the same imaging set." It also notes that the automated point placement feature's accuracy was not evaluated and should only be viewed as a "first guess." Therefore, the improvement is primarily in workflow efficiency for initial point placement, not necessarily improved accuracy of human readers with AI vs. without AI, as users still manually adjust. The text implies no negative impact on the final accuracy achieved by human users.

6. Standalone (Algorithm Only) Performance Study

• Standalone Study: No standalone (algorithm-only) performance study is explicitly described for the new automated first guess feature's accuracy. The document states: "However, the study did not evaluate accuracy of the initial point placed by the AI software, which should only be viewed as a first guess and used with caution." Performance is measured based on the user's final placement after adjustment.

7. Type of Ground Truth Used

• Ground Truth Type: For the user validation study, the ground truth for anatomical point placement was an "expert consensus region." For the overall system performance, the ground truth for volume measurements and ejection fractions would likely be derived from the KBR algorithm's established accuracy against other modalities (like MRI), which is the basis of the VMS+ system itself, but this is not specifically described for the 4.0 version's validation directly.

8. Sample Size for the Training Set

• Training Set Sample Size: Not explicitly mentioned in the provided text. The VMS+ system uses a "database of MRI heart shape catalogs" for its Knowledge-Based Reconstruction (KBR) algorithm, but the size of this database (training set for the KBR) is not specified for VMS+ 4.0 or its predicate.

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

• Training Set Ground Truth: The KBR algorithm references a "database of MRI heart shape catalogs." This implies that the ground truth for the training of the KBR algorithm (which reconstructs the heart's shape) is derived from MRI data, generally considered a gold standard for cardiac chamber quantification. However, the specific methodology for collecting and verifying this MRI data for the KBR training is not detailed for this device submission.

Ask a specific question about this device

The VMS+ 3.0 is an adjunct to existing ultrasound imaging systems and is intended to record, analyze, store and retrieve digital ultrasound images for computerized 3-dimensional image processing.

The VMS+ 3.0 is indicated for use where Left Ventricle (LV), Right Ventricle (RV), Left Atrium (LA), and Right Atrium (RA) volumes and ejection fractions are warranted or desired

The VMS+ was cleared under 510(k) (K173810) for use in evaluation where Right Ventricle (RV). Left Ventricle (LV). Right Atrium (RA), and Left Atrium (RA) volumes and eiection fractions are warranted or desired. The modified VMS+ (VMS+ 3.0) has the same operating principle and employs the same fundamental scientific technology to that of the cleared device.

The Ventripoint Medical System Plus (VMS+) 3.0 is a modified version of a previously cleared device (VMS+). The FDA letter and 510(k) summary do not detail a study involving AI assistance or a multi-reader multi-case (MRMC) comparative effectiveness study, nor do they specify acceptance criteria related to a general performance benchmark table or expert-based ground truth establishment as one might find for an AI/ML device.

Instead, the documentation focuses on demonstrating substantial equivalence to the predicate device (GE EchoPAC) and the reference device (VMS+) by showing that the modifications do not introduce new questions of safety or effectiveness and that the device performs as intended and as well as the predicate device(s).

Here's an breakdown of the information that is available and a note on what is not provided in the given text:

Acceptance Criteria & Device Performance:

The document broadly states that "Predefined acceptance criteria were applied during testing and were met" for specific types of nonclinical performance bench studies. However, the specific quantitative acceptance criteria for performance metrics (e.g., accuracy, precision) of volume measurements are not explicitly provided in a table within this document. It states that the device "delivers volume measurements that are equivalent in accuracy when compared with volumes obtained using the legally marketed VMS+."

Study Details (Based on the provided text):

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

   • The document mentions "nonclinical performance bench study" and "software verification and validation testing" but does not specify the sample size (e.g., number of cases or patients) used for these tests.
   • The document does not specify the country of origin of the data or whether the data was retrospective or prospective. Given it's a bench study and software V&V, it likely refers to engineered test data or data from phantoms/previous device performance.

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

   • The document does not specify a number of experts, their qualifications, or their role in establishing ground truth for the test set as one might expect for a clinical performance study. The ground truth appears to be based on comparison to a previously cleared device's performance benchmarks.

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

   • The document does not mention any adjudication method for a test set based on expert review.

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, an MRMC comparative effectiveness study was not explicitly mentioned or detailed. The device appears to be an image analysis system, but the submission focuses on its equivalence to a previous version and predicate, not on human-AI interaction or improvement. The document explicitly states "No clinical tests were conducted to support substantial equivalence for the subject device."

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

   • The "nonclinical performance bench study" and "software verification and validation" would represent standalone performance assessments of the algorithm and system. The text states these tests demonstrate the device "performs as intended" and "delivers volume measurements that are equivalent in accuracy when compared with volumes obtained using the legally marketed VMS+." This implies an algorithm-only evaluation against established benchmarks from the reference device.

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

   • The "ground truth" for the nonclinical performance bench study was the "volumes obtained using the legally marketed VMS+" (the reference device). This implies a comparison to the established performance of a prior cleared device, rather than an independent expert consensus, pathology, or outcomes data.

7. The sample size for the training set:

   • The document describes the VMS+ 3.0 as an updated version of a previous device utilizing a "Knowledge-Based Reconstruction (KBR) algorithm." It does not specify a separate "training set" in the context of machine learning model development. For "knowledge-based" systems, the "training" often refers to the creation and refinement of the underlying rules and models based on anatomical principles and potentially a dataset of examples. The document does not provide a sample size for a training set.

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

   • As this is described as a "Knowledge-Based Reconstruction (KBR) algorithm" and an update to an existing system, the concept of "ground truth for a training set" as typically applied to large-scale deep learning models is not explicitly detailed. The "ground truth" for developing such a knowledge-based system would involve meticulously defined anatomical landmarks and their relationships, likely established through anatomical studies or prior medical imaging analysis principles. The document does not provide details on how the original knowledge base was implicitly "trained" or how its "ground truth" was established.

Ask a specific question about this device

The VMS+ is an adjunct to existing ultraging systems and is intended to record, analyze, store and retrieve digital ultrasound images for computerized 3-dimensional image processing.

The VMS+ is indicated for use where Left Ventricle (LV), Right Ventricle (RV), Left Atrium (LA), and Right Atrium (RA) volumes and ejection fractions are warranted or desired.

The VentriPoint Medical System was cleared under 510(k) K150628 for use in right ventricle evaluation where RV volumes and ejection fractions are warranted or desired. This current submission is intended to expand system use to Left ventricle (LV), Right Atrium (RA), and Left Atrium (LA) volumes and ejection fractions. LV, RA, LA evaluation is accomplished by the addition of KBR heart catalogs containing a variety of heart models for each chamber. VMS+ employs the same fundamental scientific technology to that of the cleared device.

The provided text describes the Ventripoint Medical System Plus (VMS+) and its substantial equivalence to a predicate device, the Ventripoint Medical System (K150628). The submission aims to expand the system's use from only the right ventricle (RV) to include the left ventricle (LV), right atrium (RA), and left atrium (LA) volumes and ejection fractions.

However, the document explicitly states that "The VMS+, subject of this submission, did not require clinical studies to support the determination of substantial equivalence." This means that a clinical study proving the device meets specific acceptance criteria for clinical performance as an AI-powered diagnostic tool was not conducted or submitted for this particular expansion of indications for use. The focus of the provided text is on demonstrating substantial equivalence based on technological characteristics and the performance of its "catalogs" for LV, LA, and RA evaluation through bench testing.

Therefore, many of the requested elements for describing clinical acceptance criteria and a study proving their fulfillment cannot be directly extracted from the provided text for the expanded indications.

Here's a breakdown of what can and cannot be answered based on the provided text:

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

Based on the provided text, specific clinical acceptance criteria (e.g., sensitivity, specificity, accuracy targets) for LV, LA, and RA volume/ejection fraction measurement are not explicitly stated or reported.

The document mentions "Performance bench testing of the LV, LA, and RA catalogues was completed to verify suitability for left ventricle, left atrium, and right atrium evaluation. Testing of the LV, LA, and RA catalogs consisted of a robust series of automated and manual testing to verify reconstruction accuracy."
However, the results of this testing, in terms of quantitative performance against specific criteria, are not detailed in this submission summary.

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

The text mentions "Performance bench testing" but does not specify a "test set" in the context of human subject data, nor does it provide details on sample size, or data provenance. This is consistent with the statement that clinical studies were not required.

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 a clinical test set with expert-established ground truth is not described.

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

Not applicable.

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 study is mentioned or described in the provided text. The device is described as an "adjunct to existing ultraging systems" and a "computerized 3-dimensional image processing" system, implying it's a tool for measurement rather than an AI for interpretation that would typically require MRMC studies.

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

The "Performance bench testing of the LV, LA, and RA catalogues... to verify reconstruction accuracy" could be considered a form of standalone performance evaluation for the reconstruction accuracy component. However, the quantitative results and the specific methodology are not detailed.

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

For the "reconstruction accuracy" bench testing, the ground truth would likely be a known, precisely measured physical model or a highly accurate reference standard within the testing environment. The text does not specify the exact nature of this ground truth.

8. The sample size for the training set

The device uses "KBR heart catalogs containing a variety of heart models for each chamber." This refers to a "Knowledge Based Reconstruction database." The sample size or specific details of this "training set" (in the machine learning sense) are not provided. The term "catalogs" suggests a collection of models used by the system for its reconstruction process, rather than a dynamically trained AI model in the contemporary sense.

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

The text states the device uses a "Knowledge Based Reconstruction database" for its 3-D reconstruction. For such a system, the "ground truth" for building these "heart catalogs" would typically involve precise anatomical measurements from a diverse set of real hearts (cadaveric, surgical, or high-fidelity imaging such as MRI/CT) to create a statistical model or library of normal and abnormal heart shapes and sizes. However, the specific methodology for establishing this ground truth for the KBR catalogs is not detailed in the provided document.

Summary regarding acceptance criteria and study details based solely on the provided text:

The submission for the VMS+ expanding its indications to LV, LA, and RA did not include clinical studies demonstrating performance against specific clinical acceptance criteria. The basis for substantial equivalence for these new indications rested on the device employing the "same fundamental scientific technology" as the cleared predicate and undergoing "Performance bench testing... to verify reconstruction accuracy" for the new LV, LA, and RA catalogs. No specific quantitative targets or results from this bench testing are provided in this summary, nor are details on the test set, ground truth derivation, or expert involvement for clinical validation.

Ask a specific question about this device

The VMS system is an adjunct to existing ultrasound imaging systems and is intended to record, analyze, store and retrieve digital ultrasound images for computerized 3-dimensional image processing.

The VMS system is indicated for use where RV volumes and ejection fractions are warranted or desired.

The VentriPoint Medical System was cleared under 510(k) K140153 for use in adult patients with Pulmonary Arterial Hypertension. This current submission is intended to expand system use to right ventricle evaluation where RV volumes and ejection fractions are warranted or desired in patients other than those diagnosed with PAH. Right ventricle evaluation is accomplished by the addition of a KBR heart catalog containing a variety of heart models that are not specific to PAH. All other system operational characteristics remain unchanged from the cleared device.

Here's a breakdown of the acceptance criteria and the study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document describes the submission as an expansion of use for the VentriPoint Medical System (VMS) to include a new "RV catalog" for evaluating right ventricle volumes and ejection fractions in patients beyond those diagnosed with Pulmonary Arterial Hypertension (PAH). The primary claim is substantial equivalence to the previously cleared device (K140153).

The document does not explicitly state specific quantitative acceptance criteria (e.g., minimum accuracy percentages, specific Bland-Altman limits of agreement) for the expanded use. Instead, it relies on the comparison to the existing predicate device and the rigor of the nonclinical testing for the new RV catalog.

However, we can infer the guiding principle for acceptance:

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

• Test Set for K150628 (Expanded Use): The document states, "Performance bench testing of the RV catalog was completed..." and "Testing of the RV catalog consisted of a robust series of automated and manual testing to verify reconstruction accuracy."

  • Sample Size: The specific number of cases or data points used in this "robust series of automated and manual testing" for the RV catalog is not specified in the provided text.
  • Data Provenance: This was nonclinical bench testing, meaning it likely involved simulated data, phantoms, or possibly previously acquired anonymized patient data used in a controlled laboratory setting. The document does not specify country of origin for this bench testing data. It is neither prospective nor retrospective clinical data.

• Test Set for K140153 (Predicate Device Clinical Testing):

  • Sample Size: The document refers to "Prior clinical testing was completed in adult Pulmonary Arterial Hypertension (PAH) patients which was the basis for pre-market notification K140153." The specific sample size for this clinical testing is not provided in this document.
  • Data Provenance: This was "clinical testing" in "adult Pulmonary Arterial Hypertension (PAH) patients." The country of origin is not specified, and it would have been prospective or retrospective clinical data related to PAH patients.

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

• For K150628 (Bench Testing for New RV Catalog): The document mentions "automated and manual testing to verify reconstruction accuracy." It does not explicitly state the involvement of human experts for establishing ground truth during this specific bench testing. If manual verification was performed, it would imply human review, but the number and qualifications are not specified.
• For K140153 (Clinical Testing for Predicate Device): The ground truth for the predicate device's clinical testing was "volumes derived from cardiac MRI." While cardiac MRI interpretation requires expert radiologists/cardiologists, the document does not specify the number of experts or their qualifications used to establish these MRI-derived ground truth values.

4. Adjudication Method:

• For K150628 (Bench Testing for New RV Catalog): The document describes "robust series of automated and manual testing." An explicit adjudication method (e.g., 2+1, 3+1) for resolving discrepancies in manual testing, if any, is not specified.
• For K140153 (Clinical Testing for Predicate Device): Not specified.

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

• No, a MRMC comparative effectiveness study was not explicitly mentioned or described for either the current submission (K150628) or the predicate (K140153) in the provided text.
  • The K140153 clearance "demonstrated the substantial equivalence of VentriPoint Knowledge Based Reconstruction (KBR) with volumes derived from cardiac MRI." This suggests a comparison of the algorithm's performance to a gold standard, rather than a study comparing human readers with and without AI assistance.
  • For K150628, the justification for not conducting additional human clinical trials was that the RV catalog development was similar to the PAH catalog and that extensive bench testing was performed.

6. Standalone ("Algorithm Only") Performance Study:

• Yes, standalone performance was implicitly studied.
  • "Performance bench testing of the RV catalog was completed to verify suitability for right ventricle evaluation..." and "Testing of the RV catalog consisted of a robust series of automated and manual testing to verify reconstruction accuracy." This describes evaluating the algorithm's output directly against some form of ground truth or benchmark during bench testing.
  • Similarly, the K140153 clearance involving "substantial equivalence of VentriPoint Knowledge Based Reconstruction (KBR) with volumes derived from cardiac MRI" represents a standalone performance evaluation of the algorithm against a clinical gold standard. The device's description clarifies it's "computerized 3-dimensional image processing" and uses "Knowledge Based Reconstruction (KBR)" via a server, indicating an algorithmic analysis.

7. Type of Ground Truth Used:

• For K150628 (New RV Catalog Bench Testing): The ground truth for the bench testing was derived from methods used to "verify reconstruction accuracy" through "automated and manual testing." The exact nature (e.g., synthetic phantoms with known volumes, highly curated images with expert annotations) is not detailed, but it's related to the "Knowledge Based Reconstruction database."
• For K140153 (Predicate Device Clinical Testing): The ground truth was volumes derived from cardiac MRI. Cardiac MRI is generally considered a gold standard for cardiac chamber volume measurements.

8. Sample Size for the Training Set:

• The document mentions "Development of the RV catalog was conducted according to VentriPoint established procedures in the same way as the PAH catalog that was cleared as part of K140153." and refers to a "KBR heart catalog containing a variety of heart models."
• The specific sample size of data used to train or develop the "KBR heart catalog" or "RV catalog" is not provided in the document.

9. How Ground Truth for Training Set Was Established:

• The document mentions "Knowledge Based Reconstruction (KBR)" and the "KBR heart catalog." The KBR system fundamentally relies on a database of heart models. How these initial heart models and their associated ground truth (e.g., precise anatomical measurements, volumes) were established for the training/development of the original KBR system and the new RV catalog is not detailed in this summary. It would likely involve meticulously characterized anatomical data, potentially from diverse sources (e.g., cadaveric studies, high-resolution imaging modalities with expert segmentation).

Ask a specific question about this device

The VMS system is an adjunct to existing ultrasound imaging systems and is intended to record. analyze. store and retrieve digital ultrasound images for computerized 3-dimensional image processing. The VMS system is used to record a sequence of conventional cardiac 2-D ultrasound images with the transducer position recorded for each image acquired to compute right ventricular volumes and ejection fraction. Specific anatomic landmarks identified by the product user are transmitted by secure internet connection to a VMS server where 3-D assembly of the right ventricle in adult patients with Pulmonary Arterial Hypertension takes place using Knowledge Based Reconstruction (KBR). The results are then returned to the VMS system for display and further consideration or evaluation by the product user.

The VentriPoint Diagnostic System is a client/server platform consisting of the VentriPoint Medical System (client) and VentriPoint Services (server). The VentriPoint Medical System (VMS) is a cart based system consisting of CE Marked off-the-shelf subassemblies which accepts the digital video output from any 2-D ultrasound machine. A 3-D tracking system is connected to the ultrasound transducer using a custom sleeve. This system provides 3-D spatial coordinates for the 2-D images. After recording the 2-D images and associated 3-D spatial coordinates. a trained medical professional uses the VMS graphical user interface to place a series of points on the 2-D images corresponding to selected anatomical structures. Those points. along with their 3-D spatial coordinates, are sent bv secure internet connection to the VentriPoint Services. The VentriPoint Services use a Knowledge Based Reconstruction expert system to convert those 3-D points into a dense 3-D model of the right ventricle and sends the model back to the VMS svstem where the results are displayed on the screen. This initial rendering is reviewed for accuracy by the product user. The border contours generated from the previously placed points are displayed and may be adjusted by the user to achieve a precise fit. Improvements are made by adding. deleting or moving points on the image slices where needed. after which the information is sent by secure internet connection to the VentriPoint Services to be reconstructed. The review and reconstruction process may be repeated until the user is satisfied that the best contour fit has been made. Once the 3-D model has been approved by credentialed site personnel, quantitative right ventricle measurements are reported. The data produced by VMS is intended to support qualified licensed medical professionals in clinical decision making when used in conjunction with other patient test information.

The VentriPoint Medical System (VMS) is intended to record, analyze, store, and retrieve digital ultrasound images for computerized 3-dimensional image processing. It is used to record a sequence of conventional cardiac 2-D ultrasound images with transducer position recorded to compute right ventricular volumes and ejection fraction. The system identifies anatomic landmarks, transmits them to a VMS server for 3-D assembly of the right ventricle in adult patients with Pulmonary Arterial Hypertension using Knowledge Based Reconstruction (KBR), and then returns the results for display and evaluation.

Here's an analysis of the acceptance criteria and study proving its performance:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly state numerical acceptance criteria (e.g., specific thresholds for accuracy, sensitivity, or specificity). However, the study aims to assess the accuracy of RV volumes and EF obtained with the VMS system compared to Cardiac Magnetic Resonance Imaging (MRI). The conclusion states that the VMS system is an accurate method of measuring RV volume and EF when compared with MRI analyzed using Simpson's method, implying that the performance met an internal or implicit accuracy standard.

2. Sample Size and Data Provenance for the Test Set

• Sample Size: A clinical study was conducted with 75 consenting adults with Pulmonary Arterial Hypertension.
• Data Provenance: The data was collected from prospective clinical study participants. The country of origin is not explicitly stated, but the submission is to the U.S. FDA, suggesting the study likely took place in the U.S. or under U.S. regulatory standards.

3. Number of Experts and Qualifications for Ground Truth Establishment

The document does not explicitly state the number of experts used to establish the ground truth or their specific qualifications (e.g., radiologist with X years of experience). It mentions:

• "Analysis of the patient imaging data was completed by independent imaging core labs." This implies that qualified professionals were involved in analyzing the MRI data for ground truth.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method beyond stating that "Analysis of the patient imaging data was completed by independent imaging core labs." This suggests that the core labs provided the ground truth measurements. It does not mention multiple readers, consensus meetings, or other specific adjudication processes like 2+1 or 3+1.

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

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported in this summary. The study focused on the standalone performance of the VMS system against a standard of care (MRI). The document does not describe human readers using the AI with or without AI assistance.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was conducted. The clinical study assessed "the accuracy of right ventricle (RV) volumes and ejection fraction (EF) obtained with the VMS system" by comparing "Analysis of the patient imaging data... completed by independent imaging core labs" using Cardiac Magnetic Resonance Imaging (MRI) as the comparator. This indicates that the VMS system's output (an algorithm-driven result after user contouring) was directly compared to the ground truth.

7. Type of Ground Truth Used

The ground truth used was Cardiac Magnetic Resonance Imaging (MRI) analyzed using Simpson's method. MRI is considered a gold standard for cardiac chamber quantification.

8. Sample Size for the Training Set

The document does not provide information about the sample size used for the training set for the Knowledge Based Reconstruction (KBR) expert system.

9. How Ground Truth for the Training Set Was Established

The document does not explicitly state how the ground truth for the training set was established for the Knowledge Based Reconstruction (KBR) system. It only states that the VMS system uses a "Knowledge Based Reconstruction expert system" and makes a comparison to Siemens' "Knowledge Based Reconstruction database (only Velocity Vector Imaging (VVI) component)." This implies that the KBR system would have been developed using a dataset with known RV volumes and EF values, likely derived from methods like MRI or other established volumetric measurements, but the specifics are not detailed.

Ask a specific question about this device