(15 days)
The Viatronix V3D Vascular is intended to be used for the display and 2D/3D visualization of medical image data derived from CT, MRI scans or 3D X-Ray angiography of the selected human vessels, e.g., the coronary arteries, the carotid arteries, the peripheral arteries, the aorta, arteries of the brain, and any opacified veins. The goal of this device is to automate routine inspection of human vessels to detect stenosis, plaque, bulge, aneurismal sac and dissection in the vessel. It also supports the interactive segmentation of any vessel by hiding certain parts of the data set from display for critical evaluation of selected part(s) of vessel. It is intended for use by radiologists, clinicians and referring physicians to acquire, process, render, measure, evaluate, archive, print and distribute DICOM 3.0 compliant vessel image studies, utilizing PC hardware.
The V-3D Vascular is a software device for evaluating scanned images of selected vessels. The V3D Vascular module is designed to aid the physician in analyzing the vascular system based on images from a CT or MR scan or X-Ray angiography. The vessels include the coronary arteries, the carotid arteries, the peripheral arteries, the aorta, arteries of the brain, and any opacified veins. The goal is to automate routine inspection of the vessels as much as possible. It is an additional image processing option added to our V-3D visualization system for which pre-market clearance was granted by the FDA vide K#002780, dated November 17, 2000. It is a general software module, designed for use as a part of our V-3D visualization system core technology. The system consists of a V-3D processor and a V-3D viewer in two computer configuration or V-3D processor and V3D viewer in a stand alone one computer configuration. Upon receipt of a multislice CT or MR scan image for any selected vessel in a DICOM format, the V-3D processor converts the DICOM image data into an internally recognized volume data format using our core software. technology. The V-3D viewer provides interactive orthogonal and multiplanar reformatted 2D and 3D images from the V-3D processor and user can evaluate these images for any abnormality or malformation in specified vessels obtained from scanned images using the following methods:
a ) The V3D Vascular shall initially segment out all the possible vessels of interest in the dataset.
b } The V3D Vascular shall provide a selection view that allows selection of the vessels that the user wishes to visualize. Any vessels not desired or not actually vessels will then be hidden from view unless the user goes back to the view to re-select.
When examining a vessel the module shall be used to aid in the following ways: c ) The V3D Vascular shall be used to aid the physician in the determination and localization of stenosis in the vessels.
d ) The V3D Vascular shall be used to help determine the type of plaque in the vessels. e ) The V3D Vascular shall be used to determine the presence or absence of a bulge or an aneurysmal sac in the wall of the vessel.
f ) The V3D Vascular shall be used to determine the presence or absence of a dissection. A dissection is a break in the interior lining of the vessel - the intima - that leads to pooled fluid between the intima and media that form the wall of the vessel. The intended user can use the software device to acquire, process, render, evaluate, archive, print and distribute DICOM 3.0 compliant images of any vessel, utilizing PC hardware.
Here's a breakdown of the acceptance criteria and study information based on the provided 510(k) summary:
Acceptance Criteria and Device Performance
The device, Viatronix V3D Vascular, Revision 1.0, is a software system intended to aid physicians in analyzing scanned images of vessels. Its acceptance criteria are implicitly defined by its ability to perform the same functions as the predicate devices, particularly in measurement and evaluation of vessel abnormalities, and by demonstrating substantial equivalence.
Table 1: Acceptance Criteria (as inferred by comparison to predicate devices) and Reported Device Performance
| Acceptance Criteria (Functionality/Capability) | Reported Device Performance |
|---|---|
| Aid in determination and localization of stenosis in vessels. | The V3D Vascular module can evaluate and quantify abnormalities, including stenosis. Evaluation results (Length, Area, Minimum Diameter, Maximum Diameter) were "same" as predicate devices. |
| Aid in determining the type of plaque in vessels. | The V3D Vascular module can evaluate and quantify abnormalities, including plaque. Evaluation results (Length, Area, Minimum Diameter, Maximum Diameter) were "same" as predicate devices. |
| Determine the presence or absence of a bulge or an aneurysmal sac in the wall of the vessel. | The V3D Vascular module can evaluate and quantify abnormalities, including bulges and aneurysmal sacs. Evaluation results (Length, Area, Minimum Diameter, Maximum Diameter) were "same" as predicate devices. |
| Determine the presence or absence of a dissection. | The V3D Vascular module can evaluate and quantify abnormalities, including dissections. Evaluation results (Length, Area, Minimum Diameter, Minimum Diameter) were "same" as predicate devices. |
| Segment out all possible vessels of interest in the dataset. | The V3D Vascular module performs initial segmentation of possible vessels. |
| Provide a selection view to allow user selection/hiding of desired vessels. | The V3D Vascular module provides a selection view for user control over visualization. |
| Provide interactive orthogonal and multiplanar reformatted 2D and 3D images. | The V3D Vascular module provides these interactive imaging capabilities. |
| Measure Length, Area, Minimum Diameter, and Maximum Diameter of vessels. | The V3D Vascular module provides these measuring features. Testing showed these measurements were "same" as predicate devices. |
| Process image data from CT, MR, or 3D X-Ray angiography. | The V3D Vascular module operates on data from all three modalities (CT, MR, XA), which is an improvement over Predicate Device #2 (CT and MR exclusively) and similar to Predicate Device #1 (various sources). |
| Substantial equivalence to predicate devices (GE Medical - Smart Vessel Analysis Option (K993792) and Vital Images Vitrea 2 (K002519)). | "Substantially equivalent" demonstrated through non-clinical and clinical tests, with "no significant differences" detected in evaluation and quantification results compared to the predicate device. The V3D Vascular system utilizes the same technological characteristics (software for post-processing vascular studies, selection/segmentation, multiplanar reformats, 3D views, and measurement). |
Study Details
-
Sample size used for the test set and the data provenance:
- Sample Size: Not explicitly stated as a number. The document mentions "Scanned image datasets of various patients vessels with known abnormalities or status" were used. For clinical tests, it mentions "Patients' various vessels."
- Data Provenance: The data consisted of "patients' vessels" with "known abnormalities or status." It is implied to be retrospective, as the data already existed with known statuses. The country of origin is not specified.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified.
- Qualifications: Not specified. The summary only mentions "known abnormalities or status," implying these were clinically determined.
-
Adjudication method for the test set:
- Not specified. The ground truth seems to be based on pre-existing clinical diagnoses or "known abnormalities or status" rather than an active adjudication process for the study.
-
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 comparative effectiveness study was done to assess human reader improvement with AI assistance. The study focused on comparing the device's measurements and evaluations directly against a predicate device using the same scanned images. The device is an "aid" to the physician, but its comparative effectiveness in improving human reader performance was not evaluated in this submission.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment was effectively done. The "non-clinical tests" involved testing "software functionalities in accordance with a test protocol" using datasets with "known abnormalities or status." The "clinical tests" separately loaded the same scanned images into the device and recorded results for evaluation and quantification. The comparison was primarily between the V3D Vascular device's outputs and the predicate device's outputs, acting as a standalone performance check against an established device.
-
The type of ground truth used:
- Clinical/Expert Diagnosis: The ground truth for the test datasets was based on "known abnormalities or status" of the vessels. This implies previously established clinical diagnoses or expert assessments. For non-clinical tests, "phantom datasets" were used, for which the "level of accuracy... correlates perfectly with pre-calculated values," indicating a synthetic ground truth for those specific tests.
-
The sample size for the training set:
- Not specified. The document primarily discusses testing and validation; there is no mention of a distinct "training set" or its size.
-
How the ground truth for the training set was established:
- Since a training set is not explicitly mentioned, the method for establishing its ground truth is also not provided. The development process mentions "both unit and system integration testing protocols," but does not detail how data for initial algorithm development or parameter tuning (if any) was handled regarding ground truth.
§ 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).