Search Results

The HeartView system is an internet-based application intended for use by nuclear medicine or radiology practitioners and referring physicians for the automated processing, review, quantification, and multidimensional review of nuclear medicine cardiology medical images, and specifically, radionuclides distributed in the body using planar and tomographic short axis images.

HeartView may be used in various clinical settings including a hospital, clinic, imaging center, physician office, or remote locations.

The HeartView system implements algorithms for automatic quantification of myocardial perfusion single photon emission computerized tomography (SPECT) as well as quantification of ejection fraction, wall motion, and thickening from gated myocardial perfusion SPECT images.

Gated results are presented as 3D plots that can be used to depict, localize, and/or quantify the distribution of radionuclide tracers and anatomical structures in scanned body tissue for clinical diagnostic purposes, including quantitative assessments of cardiac function (e.g., systolic and diastolic function, regional wall thickening, wall motion, transient ischemic dilation, and phase analysis).

The HeartView platform is a comprehensive internet-based application designed to process, review, and automatically perform quantitative analysis of cardiac nuclear medicine procedures. HeartView implements algorithms for automatic quantification of myocardial perfusion SPECT, as well as quantification of ejection fraction, wall motion, and thickening from gated myocardial perfusion SPECT. The algorithm takes short axis slices reconstructed from raw datasets of gated and averaged acquisitions in rest and stress, and operates in multi-dimension (3D), rather than processing individual slices separately. For gated datasets, it processes the dataset as a whole rather than processing each frame separately, which adds additional knowledge to the algorithm for its computations, and allows enforcement of the constraint that the mid-myocardium volume is constant during the whole heart beat cycle.

Here's an analysis of the acceptance criteria and study details for the VidiStar HeartView, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state formal "acceptance criteria" with specific numerical thresholds for performance metrics. Instead, it describes a comparative performance study against a predicate device. The implied acceptance criterion is that the subject device (VidiStar HeartView) is "comparable to the predicate device in terms of qualitative and quantitative output."

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

• Test Set Sample Size: Not explicitly stated. The document mentions "anonymized patient imaging studies" were used.
• Data Provenance: Not explicitly stated (e.g., country of origin, retrospective or prospective). It only mentions "anonymized patient imaging studies."

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

• Number of Experts: One.
• Qualifications of Expert: "blinded independent cardiologist." No further detail on experience level (e.g., years of experience) is provided.

4. Adjudication Method for the Test Set

• Adjudication Method: "clinical review by a blinded independent cardiologist." This suggests a single reader assessment rather than an adjudication process involving multiple experts for consensus.

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

• MRMC Study: No, an MRMC comparative effectiveness study was not explicitly described. The study involved a single "blinded independent cardiologist" for qualitative comparison and statistical comparison of software-calculated values.
• Effect Size of Human Readers with vs. without AI: Not applicable, as an MRMC study and AI-assisted performance evaluation of human readers were not conducted or reported.

6. Standalone (Algorithm Only) Performance Study

• Standalone Performance: Yes, a standalone performance assessment was done for quantitative output. The device's algorithms for "automatic quantification of myocardial perfusion SPECT, as well as quantification of ejection fraction, wall motion, and thickening" were compared against the predicate device's software-calculated values using statistical software.

7. Type of Ground Truth Used

• Quantitative Ground Truth: The "ground truth" for quantitative output was established by the software-calculated values of the predicate device (Xeleris 3.1 Processing and Review Workstation). This implies that the predicate device's outputs were considered the reference for comparison.
• Qualitative Ground Truth: For qualitative assessments, the "ground truth" was established by the "subjective clinical reading" of a "blinded independent cardiologist," compared against the predicate device. This suggests the cardiologist's assessment of either the raw images or the predicate device's output served as the reference for evaluating the subject device's qualitative output.

8. Sample Size for the Training Set

• Training Set Sample Size: Not mentioned. The document primarily focuses on the validation/comparison study.

9. How Ground Truth for the Training Set Was Established

• Training Set Ground Truth: Not mentioned. Since the training set size is not provided, neither is details on how its ground truth was established.

Ask a specific question about this device

The VidiStar PACS & DICOM Viewer Software system is a picture archiving and communications system (PACS) intended to be used as a networked Digital Imaging and Communications in Medicine (DICOM) and non-DICOM information and data management system. The VidiStar PACS & DICOM Viewer Software is comprised of modular software programs that run on standard "off-the-shelf" personal computers, business computers, and servers running standard operating systems. VidiStar PACS & DICOM Viewer Software system is an image, data storage and display software that accepts DICOM data from laboratories, which support DICOM standard imaging data and structured reporting transfer(s). The system provides the capability to: organize images generated by OEM vendor equipment, perform digital manipulation, create graphical representations of anatomical areas, perform quantitative measurements, and create DICOM structure reports, all over the Internet.

All quantitative data ranges are derived from the clinical experience of laboratories and are included in observation libraries for VidiStar users. VidiStar strongly recommends that users review these ranges with their individual diagnostic needs in mind prior to using the VidiStar PACS & DICOM Viewer Software system for clinical reporting. The VidiStar PACS & DICOM Viewer Software system should not be used for reviewing full-field digital mammograms.

The VidiStar PACS & DICOM Viewer Software System is a picture archiving and communications system software used to process, display, transfer, enable reports, communicate, store and archive digital medical images using Transmission Control Protocol/Internet Protocol (TCP/IP). It supports DICOM structured reports for creating, rendering, storage and archiving.

The provided text describes the VidiStar PACS & DICOM Viewer Software System and its substantial equivalence to other PACS devices on the market. However, it does not contain information about specific acceptance criteria, a detailed study proving the device meets those criteria, or the methodology (sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, or ground truth establishment) typically associated with such studies for AI/CAD devices.

The document is a 510(k) summary focused on demonstrating "substantial equivalence" to predicate devices, which is a regulatory pathway for medical devices. This pathway often relies on comparing features and performance to existing, legally marketed devices rather than presenting novel clinical performance studies with acceptance criteria in the manner requested.

Therefore, most of the requested information cannot be extracted from the provided text.

Here's what can be inferred or explicitly stated from the document:

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

The document does not specify formal "acceptance criteria" for clinical performance. Instead, it demonstrates substantial equivalence by comparing features to predicate devices. The "performance" is implied by matching or exceeding the capabilities of the predicate devices.

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

Not mentioned. The 510(k) summary focuses on design control activities and comparison to predicates, not a specific clinical performance test set.

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 mentioned. Ground truth establishment for a specific test set is not detailed as there is no described clinical performance study of this nature.

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

Not mentioned.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

No MRMC study is mentioned. The device is a PACS and DICOM viewer, not an AI/CAD algorithm intended to assist human readers in a diagnostic capacity that would be evaluated by such a study in this document.

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

Not applicable. The device is a PACS system and viewer, not a standalone algorithm with diagnostic performance. Its function is to process, display, store, and manage images.

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

Not applicable for a clinical performance study as none is described for specific diagnostic tasks. The "ground truth" for the device's functionality would be adherence to DICOM standards and correct display/storage of images, which would be verified through functional testing (ALPHA, BETA testing), not clinical ground truth as defined for diagnostic AI.

8. The sample size for the training set

Not mentioned. A training set is typically associated with machine learning or AI algorithms, which is not the primary focus or nature of this PACS software as described for regulatory submission.

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

Not mentioned, as no training set is described.

Summary of available information:

The document describes the VidiStar PACS & DICOM Viewer Software System as a networked PACS intended for processing, displaying, storing, and managing DICOM and non-DICOM medical images and data. It outlines design control activities like validation planning and ALPHA/BETA testing. The core of its regulatory submission relies on demonstrating substantial equivalence to existing PACS products by comparing features such as operating system, image source, display rates, multiple window support, image export formats, network access, analysis capabilities, and reporting features. No specific clinical performance study with acceptance criteria, sample sizes, expert ground truth, or AI-specific evaluations (like MRMC or standalone performance) is detailed in this 510(k) summary.

Ask a specific question about this device