(151 days)
3mensio Workstation enables visualization and measurement of the heart and vessels for:
- · Pre-operational planning and sizing for cardiovascular interventions and surgery
- · Postoperative evaluation
- · Support of clinical diagnosis by quantifying dimensions in coronary arteries
- · Support of clinical diagnosis by quantifying calcifications (calcium scoring) in the coronary arteries
To facilitate the above, the 3mensio Workstation provides general functionality such as:
- · Segmentation of cardiovascular structures
- · Automatic and manual centerline detection
- · Visualization and image reconstruction techniques: 2D review, Volume Rendering, MPR, Curved MPR, Stretched
- CMPR, Slabbing, MIP, AIP, MinIP
- · Measurement and annotation tools
- Reporting tools
The 3mensio Workstation software allows cardiologists, radiologist and clinical specialists to select patient studies from various data sources, view them, and process the images with the help of a comprehensive set of tools. 3mensio Workstation works with all major medical image formats and can access multiple data stores and across networks.
3mensio Workstation can combine 2D scan slices into comprehensive 3D models of the patient, and can display supporting ultrasound and X-ray Angio data. The software accurately represents different types of tissue, making it easier to diagnose anomalies in scans.
3mensio Workstation contains two modules, 3mensio Structural Heart (containing submodule cCTA), and 3mensio Vascular which can be marketed in combination or as separate solutions:
3mensio Structural Heart enables assessment and measurement of differen structures of the heart, e.g. aortic valve, mitral valve and ventricles. It provides analysis of the feasibility of a transapical, transfemoral or subclavian approach to structures for replacement or repair procedures. 3mensio cCTA enables assessment and measurement of the coronary arteries and can help in the quantification of the dimensions of the coronary arteries and of the calcified plaques present in coronary arteries. 3mensio Vascular enables assessment of vessels and can help identify calcifications, aneurysms and other anomalies to quickly and reliably prepare for various types of vascular procedures.
The results can be displayed, printed or saved in a variety of formats to a hard disk, network, PACS system or CD. Results can also be printed as a hardcopy.
The provided document describes the 3mensio Workstation, a software device for visualizing and measuring the heart and vessels. The submission focuses on demonstrating substantial equivalence to predicate devices, particularly for newly added features: 3mensio cCTA Calcium scoring and 3mensio cCTA Coronary vessel measurement.
Here's an analysis of the acceptance criteria and study information:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria (e.g., specific accuracy thresholds) for the device's performance. Instead, it relies on demonstrating that the new features are "very similar" in technology and user interface to legally marketed predicate devices and that they produce "the same results" as a comparable module in a predicate.
| Acceptance Criterion (Implied) | Reported Device Performance |
|---|---|
| 3mensio cCTA Calcium scoring: | "Technologically and in terms of GUI interaction, both features are very similar." (in comparison to HeartBeat CS module of Philips Intellispace Cardiovascular K153022) |
| Functional equivalence to predicate for calcium scoring | |
| 3mensio cCTA Coronary vessel measurement: | "Both types of measurements produce the same results, are measured in the same type of images, and use the same techniques: perform measurement on areas in reconstructed cross-sectional images based on a 3D centerline." "Technologically and in terms of GUI interaction, both features are very similar." (in comparison to the vascular measurement module of 3mensio Workstation K120367) |
| Functional equivalence to predicate for coronary vessel measurement | |
| Overall device functionality Verification | "Verification of the 3mensio Workstation showed that the system requirements – derived from the intended use and indications for use – were implemented correctly, demonstrating the effectiveness of the device." A validation plan was executed, and "A test report comparing the numerical results of the device compared with the predicate devices is also available." (Specific numerical results are not provided in this document.) |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective) for the studies performed. It only mentions that a "test report comparing the numerical results of the device compared with the predicate devices is also available."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not provide any information regarding the number of experts used or their qualifications for establishing ground truth. The nature of the comparison ("producing the same results" as predicate devices) suggests that the ground truth might implicitly be the results generated by the predicate devices, rather than a separate expert-derived ground truth.
4. Adjudication Method
The document does not specify any adjudication method for a 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
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed or reported in this document. The submission focuses on technical equivalence to predicate devices, not on demonstrating improved human reader performance with AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
This appears to be a standalone algorithm, as the comparison is made directly between the device's numerical results and those of predicate devices. The document does not describe any human-in-the-loop performance studies, but rather the device's ability to render, segment, and measure cardiovascular structures by itself, similar to the predicate. Specifically, the "3mensio cCTA Calcium scoring" and "3mensio cCTA Coronary vessel measurement" are standalone features being compared to their counterparts in predicate devices. The overall 3mensio Workstation is a software solution for clinicians to use, but the testing reported here refers to the functional equivalence of the algorithms within it.
7. The Type of Ground Truth Used
The ground truth implicitly used for the performance comparison is the results generated by the predicate devices. The document states that the new features "produce the same results" and are "very similar" in technology and GUI interaction to the predicate devices. This indicates that the predicate's output serves as the reference for equivalence.
8. The Sample Size for the Training Set
The document does not specify any sample size for a training set. This is consistent with the nature of the submission, which is for equivalence based on functional similarity to predicates, rather than a de novo submission for a novel AI algorithm requiring extensive training data validation.
9. How the Ground Truth for the Training Set Was Established
Since no training set is described, information on how its ground truth was established is not provided.
§ 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).