(301 days)
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
| Feature/Characteristic | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Overall Performance | System performs as intended and meets specifications/requirements. | "The verification and validation of the existing and new features of the VMS+ demonstrate that the VMS+ 4.0 performs as intended, specifications conform to user needs and intended uses, and that the requirements implemented can be consistently fulfilled." |
| "All test reports were successful according to the acceptance criteria." | ||
| Bench Testing | Substantial equivalence in performance specifications to the previously cleared device. | "Predefined acceptance criteria were applied during testing and were met." |
| Software V&V | Software performs as intended, conforms to user needs/intended uses, and requirements are consistently fulfilled. | "The verification and validation of the existing and new features of the VMS+ 4.0 software demonstrate that the VMS+ 4.0 software performs as intended, specifications conform to user needs and intended uses, and that the requiremented can be consistently fulfilled." |
| "All test reports were successful according to the acceptance criteria." | ||
| Electrical Safety & EMC | Compliance with IEC 60601-1 and IEC 60601-1-2 standards. | "The system complies with the applicable requirements of IEC 60601-1 standard for safety and essential performance and IEC 60601-1-2 standard for electromagnetic compatibility." |
| User Performance (Point Localization) | User performance for final point localization using VMS+ 4.0 is at least as good as the predicate (VMS+ 3.0). | "The test criteria were met, demonstrating 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." |
| Cybersecurity | All existing vulnerabilities discovered and addressed; device is cyber safe. | "This included both internal cybersecurity validation and external penetration testing to ensure that any existing vulnerabilities were discovered and addressed, and that the device is cyber safe." |
| Technological Characteristics (Modified Features) | Overall performance remains the same as the predicate with acceptable results. | "These proposed modifications are verified to ensure overall performance remains the same as the predicate with acceptable results." (Referring to the automated control point first guess and magnet-free tracking system changes) |
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.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).