(127 days)
HeartPro consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartPro specifically analyzes the blood flow to the heart and its major vessels using multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible, quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners.
The data produced by HeartPro is intended to be used to support qualified cardiologist, radiologist or other licensed professional healthcare practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.
MedVoxel HeartPro is a web-accessible, self-contained image analysis software application. The application uses cardiac-specific MR scans as a data source for their blood flow analysis computations.
Pre-existing MR images are sent from the PACS (or scanner) to the MedVoxel HeartPro software application, image corrections (specific to aliasing errors) are applied to the set of images prescribed by the user, contour are placed and advanced analysis algorithms are applied. Easily reproducible test results are produced and stored in the Measurement Record of the patients' study.
HeartPro does not interface directly with any MR or data collection equipment; instead HeartPro imports data files previously generated by such equipment.
HeartPro provides quantitative measurements specific to blood flow analysis for MRI data sequences. The software application focuses on what is visible to the eye and applies advanced automated methods to avoid tedious, time-consuming manual methods. The software does not perform any functions which cannot be accomplished by a trained user utilizing manual tracing methods; the intent of the software is to save time and automate potential error-prone manual tasks.
The software has functions for loading, analysing, saving datasets and will generate screen displays, computation and aggregated statistics.
Here's a breakdown of the acceptance criteria and the study information for the MedVoxel HeartPro Software Application, based on the provided 510(k) summary:
Note: The provided document is a 510(k) summary, which often provides high-level information. While it states that "Nonclinical verification and validation test results established that the device meets its design requirements and intended use," it does not provide detailed quantitative acceptance criteria or a specific study report that explicitly lists those criteria and directly compares them to detailed device performance metrics. The information below is extracted and inferred from the available text.
Regarding the "study that proves the device meets the acceptance criteria," the document implicitly refers to the "Nonclinical verification and validation test results." However, it does not provide details about the specific study design, methodologies, or the raw performance data from that study.
1. Table of Acceptance Criteria and Reported Device Performance
As mentioned, specific quantitative acceptance criteria are not explicitly detailed in the provided 510(k) summary. The document focuses on demonstrating substantial equivalence to a predicate device and states that the device "meets its design requirements and intended use."
The primary reported performance claims relate to the device's capabilities and qualitative attributes, rather than specific numerical accuracy thresholds.
| Acceptance Criteria Category (Inferred from product description) | Reported Device Performance (as stated in the document) |
|---|---|
| Functionality: DICOM Compliance | Supports DICOM 3.0 |
| Functionality: Image Input Methods | DICOM 3.0 via TCP/IP, DICOM via secure FTP |
| Functionality: Data Acquisition Protocol for Blood Flow Analysis | Analyzes cardiovascular images (multi-phase, multi-slice, velocity encoded MR) to perform blood flow calculations and output data parameters. |
| Functionality: User Interactions | Browse, select, load CMRI scan files; save/load analyses; export to files; generate PDF reports with quantitative data; display DICOM info. |
| Functionality: Measurement Information Display | Blood flow chart displayed. |
| Functionality: Repeatability (Automated ROI) | Fully repeatable when relying on automated ROI definition. |
| Functionality: Repeatability (Manual ROI) | Not easily reproducible (identical to predicate) due to significant manual involvement. |
| Functionality: ROI Vessel Contour Detection | Automatic contour detection with user input (optional: can be followed by manual user editing). |
| Functionality: Phase Aliasing Error Correction | Phase alias correction provided via user interface. |
| Functionality: Quantitative Clinical Data Generation | Measurement algorithm generates quantitative clinical data, including parameters such as net blood flow rate, and blood flow volume. |
| Functionality: Image Manipulation Features | Extensive set of features: toolbars, mouse-overs, screen-tips, pan/zoom, scroll bars, pull-down menus; pan/zoom, magnify, maximize/minimize image displays, scroll through slice stack, adjust window level/contrast/brightness, single image ROI placement, automated 2D ROI copy, ROI edit functions, 2D Velocity Color Map. |
| Functionality: Scan Quality Assessment (Input Format) | Expected format is DICOM, must receive DICOM compliant image studies. Only lossless compression. |
| Intended Use Fulfillment: Clinical Relevance | Provides clinically relevant and reproducible, quantitative data. |
| Compatibility: MR Scanners | Tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. |
| Safety & Effectiveness: Comparison to Predicate | Substantially equivalent to predicate device; does not pose any new issues of safety and effectiveness. |
| Overall Performance: Meets Design/Intended Use | Meets its design requirements and intended use. |
Key Takeaway from the Table: The provided document emphasizes feature parity and functional equivalence with the predicate device (Siemens Argus). It does not present a statistical study with numerical acceptance criteria (e.g., minimum sensitivity, specificity, accuracy, or inter-reader/intra-reader agreement thresholds) and corresponding test results against those criteria. The "Summary of Testing" section is a general declaration rather than a detailed report.
2. Sample Size Used for the Test Set and Data Provenance
The document states: "Nonclinical verification and validation test results established that the device meets its design requirements and intended use..." However, it does not specify the sample size for the test set or the data provenance (e.g., country of origin, retrospective or prospective nature) used for these verification and validation tests.
3. Number of Experts Used to Establish the 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, as it does not detail the methodology of the verification and validation tests.
4. Adjudication Method for the Test Set
The document does not mention any adjudication method used for the test set, as details of the verification and validation tests are not provided.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was performed. There is no mention of comparing human readers with AI assistance versus without AI assistance, nor any reported effect size for such a comparison. The focus is on the software automating "tedious, time-consuming manual methods" and providing "reproducible test results" that "save time."
6. Standalone (Algorithm Only) Performance Study
The document states that the software has functions for loading, analyzing, saving datasets, and generating displays and statistics. It also mentions "Automated contouring" and "Automated measurements." This implies a standalone algorithm's ability to perform these tasks.
However, the document also notes: "The software does not perform any functions which cannot be accomplished by a trained user utilizing manual tracing methods; the intent of the software is to save time and automate potential error-prone manual tasks." And for "Contouring/Editing," it specifically says "Automatic contour detection with user input (optional: can be followed by manual user editing)." This suggests that while the algorithm has standalone capabilities, the intended workflow may involve human oversight and potential correction.
Therefore, while the core algorithms likely have standalone performance, the provided summary does not present a dedicated standalone performance study with specific metrics (e.g., sensitivity, specificity, accuracy) for the algorithm in isolation.
7. Type of Ground Truth Used
The document does not explicitly state the type of ground truth used (e.g., expert consensus, pathology, outcomes data) for the verification and validation tests. Given the nature of cardiac MR image analysis for blood flow, it's highly probable that some form of "expert consensus" or "expert manual tracing" would have been used as a comparator for automated measurements, but this is an inference.
8. Sample Size for the Training Set
The document does not provide any information regarding the sample size for the training set. It focuses on the verification and validation of the product, not its development or training process.
9. How the Ground Truth for the Training Set Was Established
As no information is provided about the training set, the method for establishing its ground truth is also not mentioned.
§ 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).