K Number
K120331
Date Cleared
2012-04-13

(71 days)

Product Code
Regulation Number
892.1750
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The syngo.CT Dynamic Angio software package has been designed to evaluate CT data which has been continuously acquired with computed tomography (CT) imaging systems. Contrast enhanced CT images are used to visualize the flow of contrast from the arteries to the veins.

syngo.CT Dynamic Angio can be used to assist the physician in the diagnosis of blood vessels and it supports in the evaluation of regions of interest, the visual inspection of time attenuation curves, and the creation of specific CT volumes, for example, arterial or venous phase. It will aid in the inspection of diseases which affect the vessel system, for example, vessel stenosis, collateral or late filling of vessels, vascular malformations, control of stent graft extravasation, or in the evaluation of tumor vascularization.

Device Description

syngo.CT Dynamic Angio is a software, which was developed to visualize dynamic CT datasets in a three and four dimensional view. Possible input data are Siemens CT Dynamic Sequence, Dynamic Multiscan, Adaptive 4D Spiral and Heart Perfusion Scanning datasets.

syngo.CT Dynamic Angio supports the overlay free visualization of the vessel enhancement with the help of motion correction and bone segmentation. The software can be used to run a movie of a time series or to create CT phase volumes (e.g. arterial phase or venous phase) by combining multiple neighboring time points from the dynamic CT data. It also supports the evaluation of regions of interest and the visual inspection of time attenuation curves.

syngo.CT Dynamic Angiois a post-processing software package which provides a combination of functionality similar to functionality provided by one or more of the predicate devices as listed above. It uses the same data for evaluation as the predicate devices and provides results in the same format as the predicate devices

All result volumes created by CT Dynamic Angio are stored in separate series and consist of a set of standard DICOM single frame CT images. All finding snapshot images are stored in a different series as DICOM secondary captures.

As basis for data viewing, syngo.CT Dynamic Angio uses basic reader and image display functionality as provided by syngo.via. Different visualization filters like multiplanar reformatting (MPR, MPR Thick), maximum intensity projection (MIP, MIP Thin) and volume rendering techniques (VRT, VRT Thin) can be applied. Windowing of the visualized data cao be done by mouse interaction and with predefined CT window presets. Zooming and panning of the CT volumes is supported.

In addition to basic viewing capabilities, syngo.CT Dynamic Angio provides tools for visualization, analysis and reporting of vascular conditions.

Standard syngo.via analysis tools are Distance Line, Pixel Lens, Marker, Arrow and ROI (Region of Interest).

AI/ML Overview

The Siemens syngo.CT Dynamic Angio is a software designed to visualize dynamic CT datasets in three and four dimensions. It aids physicians in diagnosing blood vessel conditions by allowing for the evaluation of regions of interest, visual inspection of time attenuation curves, and creation of specific CT volumes (e.g., arterial or venous phase). It helps in inspecting diseases affecting the vessel system, such as vessel stenosis, vascular malformations, and tumor vascularization.

Here's an analysis of the acceptance criteria and the study provided:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't provide specific numerical acceptance criteria or performance metrics for the syngo.CT Dynamic Angio's diagnostic capabilities (e.g., sensitivity, specificity, accuracy). Instead, it focuses on general safety and effectiveness, and equivalence to predicate devices.

Acceptance Criteria CategoryDescriptionReported Device Performance
SafetyMinimize electrical, mechanical, and radiation hazards.Risk management via hazard analysis and control implemented through software development, verification, and validation testing. Adheres to recognized and established industry practice and standards (IEC 60601-1-6:2006, IEC 62304:2006, ISO 14971:2007). Device labeling includes instructions, cautions, and warnings for safe use.
EffectivenessProvide specific functionalities for visualizing and analyzing dynamic CT datasets (motion correction, bone segmentation, time series movie, CT phase volumes, ROI evaluation, time attenuation curves, various visualization filters).The software supports all listed functionalities. Its post-processing capabilities and generated results (DICOM images, secondary captures) are described as substantially equivalent to predicate devices. It uses the same data for evaluation and provides results in the same format.
Substantial EquivalencePerform as well as and have similar technological characteristics and intended uses as identified predicate devices.The syngo.CT Dynamic Angio is described as a post-processing software package that combines functionality from multiple predicate devices. It uses the same data, provides results in the same format, and utilizes similar image processing algorithms and basic viewing functionality as the predicate devices. It claims to introduce no new safety risks.
Standards ComplianceFulfill requirements of IEC 60601-1-6, IEC 62304, ISO 14971, and DICOM.The device is designed to fulfill these standards. DICOM conformity is covered by syngo.via implementations.

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

The document does not specify a sample size for a test set (e.g., a specific number of CT scans or patient cases). The non-clinical testing mentioned is "conducted for syngo.CT Dynamic Angio software package during product development" and includes "verification and validation testing." The data provenance (e.g., country of origin, retrospective or prospective) is also not mentioned.

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

This information is not provided in the document. No details about expert involvement in establishing ground truth are given for any testing.

4. Adjudication Method for the Test Set:

No adjudication method (e.g., 2+1, 3+1, none) is mentioned, as there is no specific test set or reader study described.

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

A multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported in this summary. The document does not describe any study comparing human readers with and without AI assistance to determine an effect size.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

A standalone performance study of the algorithm without human-in-the-loop performance is explicitly not described. The "testing results supports that all the software specifications have met the acceptance criteria," but these acceptance criteria appear to be related to internal software development and safety standards rather than a formal standalone clinical performance evaluation against a gold standard. The device's purpose is to "assist the physician," implying a human-in-the-loop scenario.

7. Type of Ground Truth Used:

The document does not specify the type of ground truth used for any testing. Given the nature of the software (post-processing and visualization tools), internal software specifications and functional verification likely served as the "ground truth" for the non-clinical tests mentioned. There is no indication of expert consensus, pathology, or outcomes data being used as ground truth.

8. Sample Size for the Training Set:

The document does not provide any information about a training set or its sample size. This is a post-processing visualization tool, and the summary focuses on its functionality and equivalence to predicate devices, not on a machine learning model that would require a distinct training set.

9. How the Ground Truth for the Training Set Was Established:

Since no training set is mentioned, the method for establishing its ground truth is also not provided.

§ 892.1750 Computed tomography x-ray system.

(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.