SYNGO, CT LIVER ANALYSIS

• K Number: K133643
• Device Name: SYNGO, CT LIVER ANALYSIS
• Manufacturer: SIEMENS MEDICAL SOLUTIONS, INC.
• Date Cleared: 2014-11-13 ( 351 days)
• Product Code: JAK , 90J , LLZ
• Regulation Number: 892.1750
• Type: Traditional
• Panel: RA
• Reference & Predicate Devices: K061696 , K071310

Intended Use

syngo. CT Liver Analysis is an image analysis software for CT volume data sets. It analyses the liver and its intrahepatic vessel structures to identify the vascular territories of sub-vessel systems in the liver. These regions can be evaluated by exploring the volume of the liver and its vascular territories.

Using syngo.CT Liver Analysis, you can evaluate the liver volume and examine the vessels of the liver.

The following evaluation tools are provided:

• · Computation and manual correction of liver volumes
• · Computation and manual correction of tumor volumes and extent
• · Computation and manual correction of liver vessel tree structure
• · Computation of territories based on vessel branches
• · Tumor position in relation to vessels (i.e. 3D visualization of liver, tumor and vessels)
• · Manual definition of separation plane proposals
• · Computation of volume of liver parts
• · Combination of information from different CT and MR phase volumes

syngo. CT Liver Analysis facilitates reporting by using of appropriate reporting tools, for example, volume statistics and key image creation.

You can use syngo.CT Liver Analysis to create a DICOM Structured Report.

Device Description

synqo.CT Liver Analysis is an image analysis software for CT volume data sets. It analyses the liver and its intrahepatic vessel structures to identify the vascular territories of sub-vessel systems in the liver. These regions can be evaluated by exploring the volume of the liver and its vascular territories. The syngo.CT Liver Analysis Software is designed to operate on the most recent syngo.via platform.

The task is organized as a linear workflow providing the following task steps (several task steps can be skipped to allow fast processing in cases with limited clinical needs):

· Assignment of CT phase volumes relevant for anatomical information
· Manual rigid registration of CT phase volumes
· Automatic segmentation of liver, interactive manual correction of result
· Semi-automatic seqmentation of lesions, interactive manual correction of result
· Semi-automatic seqmentation of vasculature, interactive manual correction of result
· Manual anatomical classification of vascular objects, calculation and visualization of vascular territories
· Interactive definition of parts of the liver and calculation of partial volumes
· Inspection of results (2D/3D):
· Reporting

AI/ML Overview

The provided text does not contain specific acceptance criteria, detailed study design, or quantitative performance metrics for the syngo.CT Liver Analysis device. It primarily focuses on the device's description, indications for use, comparison to predicate devices, and a general statement about nonclinical testing and software verification/validation.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them with the requested details, as that information is not present in the provided document.

Here's what I can extract and what is missing:

1. A table of acceptance criteria and the reported device performance

• Missing: The document states "The testing results supports that all the software specifications have met the acceptance criteria," but it does not specify what those acceptance criteria are or provide quantitative performance results (e.g., accuracy, precision, sensitivity, specificity) against them.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Missing: The document states, "To ensure performance of the semi-automatic segmentation algorithm, the algorithms were tested on clinical data sets." However, it does not specify the sample size of these clinical data sets, their provenance (country of origin), or whether they were retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Missing: There is no mention of experts used to establish ground truth or their qualifications.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Missing: No information on adjudication methods for ground truth establishment.

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

• Missing: There is no mention of an MRMC comparative effectiveness study or any effect size related to human reader improvement with AI assistance. The document discusses "software for CT volume data sets" and "image analysis software" but does not detail human-in-the-loop performance studies.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Present (partially): The document states: "To ensure performance of the semi-automatic segmentation algorithm, the algorithms were tested on clinical data sets." This implies standalone testing of the algorithms. However, no specific performance metrics of this standalone testing are provided. The product description emphasizes "Computation and manual correction," which suggests a hybrid human-AI workflow, but the testing mentioned focuses on algorithm performance.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Missing: The document does not specify how the "ground truth" was established for the clinical data sets used for testing. It only mentions testing on "clinical data sets."

8. The sample size for the training set

• Missing: No information is provided regarding a training set or its sample size. The document refers to "product development" and "verification/validation testing" but not distinct training.

9. How the ground truth for the training set was established

• Missing: Since no training set is described, there's no information on how its ground truth would have been established.

In summary, the provided text offers a high-level overview of the device and its regulatory submission but lacks the detailed study design, specific acceptance criteria, and quantitative performance data required to answer your questions comprehensively. It confirms that non-clinical tests were conducted and that the software specifications met acceptance criteria, but these specifics are not elaborated upon.

Regulation Number and Section

§ 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.