Search Results

syngo.CT Extended Functionality is intended to provide advanced visualization tools to prepare and process medical images for diagnostic purpose. The software package is designed to support technicians and physicians in qualitative and quantitative measurements and in the analysis of clinical data that was acquired and reconstructed by Computed Tomography (CT) scanners.

An interface shall enable the connection between the syngo.CT Extended Functionality software package and the interconnected CT Scanner system.

Result images created with the syngo.CT Extended Functionality software package can be used to assist trained technicians or physicians in diagnosis.

syngo.CT Extended Functionality is a software bundle consisting of previously cleared unmodified and modified post-processing applications that offer tools to support special clinical evaluations. syngo.CT Extended Functionality can be used to create advanced visualizations and measurements on clinical data that was acquired and reconstructed by Computed Tomography (CT) scanners.

Depending on the clinical question, the user can select functionality which supports the explicit clinical fields as listed below. The syngo.CT Extended Functionality software package is designed to operate on the most recent version syngo-compatible postprocessing platform, which currently supports the following four tools:

• 1. Preparation of Vascular Case for Reading Physician
• 2. Preparation of Oncology Case for Reading Physician
• 3. Preparation of Osteo Case for Reading Physician
• 4. Preparation of Neuro DSA Bone Subtraction for Reading Physician

The supported functionality can be used on any CT data if basic requirements are met (e.g. spiral or sequence scan, reconstruction kernel). The supported functionality will check to ensure the basic requirements are met and will not allow its execution or will provide a warning or info message to the user if appropriate. This check also allows combination of functionality of different clinical fields, (e.q. a vascular case can be prepared also on Neuro DSA bone subtracted data or on the same case as Lung CAD computation, etc.). Afterwards, any tool can be accessed as long as the data and viewing type allows it. For example, an evaluation of a ROI defined by a contour and two HU thresholds can be used to measure a certain area. No specific sequential workflow is required.

The original clinical data that was acquired and reconstructed by Computed Tomography (CT) scanners will not be modified in any form. The results of the syngo.CT Extended Functionality can be stored as additional DICOM images if needed as kev images or range or images. The subject device syngo.CT Extended Functionality is designed to operate on a syngo compatible host system (e. g. syngo.via VB20 software platform or higher).

The provided text describes the 510(k) premarket notification for "syngo.CT Extended Functionality." However, it does not contain the specific details required to fully address all parts of your request regarding acceptance criteria and a detailed study proving device performance. The information provided is high-level and focuses on regulatory compliance and substantial equivalence to predicate devices, rather than a specific clinical performance study.

Here's a breakdown of the available information and what's missing:

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

The provided document does not include a specific table of acceptance criteria with corresponding performance metrics for the syngo.CT Extended Functionality as a whole, or for its individual modified components. It generally states:

• "All verification and validation testing has been completed and meets Siemens acceptance criteria." (Page 7)
• "The testing results support that all the software specifications have met the acceptance criteria." (Page 7)
• "The results of these tests demonstrate that the subject device performs as intended." (Page 7)
• "The results of all conducted testing was found acceptable to support the claim of substantial equivalence." (Page 7)

This is a general statement of compliance, not a detailed report of specific performance metrics against defined acceptance criteria.

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

The document does not specify the sample size used for any test sets, nor does it provide information about the provenance of the data (country of origin, 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)

The document does not mention the use of experts to establish ground truth for any test set or their qualifications.

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

The document does not describe any adjudication methods used 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

The document does not mention an MRMC comparative effectiveness study, nor does it discuss improvements in human reader performance with or without AI assistance. The device is described as providing "advanced visualization tools to prepare and process medical images for diagnostic purpose" and assisting "trained technicians or physicians in diagnosis," but not as an AI-powered diagnostic tool in the sense of comparing human performance with and without its specific assistance.

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

The document does not describe any standalone algorithm performance studies. The device is explicitly intended to "assist trained technicians or physicians in diagnosis," implying human-in-the-loop usage.

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

The document does not specify the type of ground truth used for any testing.

8. The sample size for the training set

The document does not mention a training set or its sample size. This is consistent with the device being a "software bundle consisting of previously cleared unmodified and modified post-processing applications," rather than a novel AI/ML algorithm that requires a dedicated training phase reported in this context.

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

As no training set is mentioned, information on how its ground truth was established is also absent.

Summary of what is present in the document regarding testing:

The document focuses on "Non-Clinical Testing Summary" (Page 7) to demonstrate substantial equivalence, rather than detailed clinical performance studies.

• Type of Study: Non-clinical tests (integration and functional) were conducted. Verification/validation testing was performed for modifications to previously cleared components.
• Acceptance Criteria (General): "All verification and validation testing has been completed and meets Siemens acceptance criteria." "The testing results support that all the software specifications have met the acceptance criteria."
• Risk Analysis: A risk analysis was completed, and risk control was implemented in accordance with ISO 14971.
• Software Verification and Validation: Documentation for "Moderate Level of Concern" software was included, conforming to FDA's "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005).
• Intended Use: The tests demonstrated the device "performs as intended."
• Comparison to Predicate: "Siemens used the same testing with the same workflows as used to clear the predicate device."

Conclusion based on the provided text:

The submission confirms that the device underwent verification and validation testing as part of the regulatory approval process for software, especially for modifications made to existing functionalities (like the Osteo feature). However, it does not provide the detailed clinical performance study data (including specific acceptance criteria, sample sizes, expert involvement, and ground truth methodologies) often associated with new diagnostic algorithms or AI-driven systems. The clearance is based on demonstrating substantial equivalence to predicate devices, supported by non-clinical performance data and software validation, suggesting the device's functionality is well-understood and its safety and effectiveness are established through these engineering and software-level tests.

Ask a specific question about this device

syngo.via is a software solution intended to be used for viewing, manipulation, communication, and storage of medical images. It can be used as a stand-alone device or together with a variety of cleared and unmodified syngo based software options. syngo.via supports interpretation and evaluation of examinations within healthcare institutions, for example, in Radiology, Nuclear Medicine and Cardiology environments. The system is not intended for the displaying of digital mammography images for diagnosis in the U.S.

syngo.via is a software solution intended to be used for viewing, manipulation, communication, and storage of medical images. It can be used as a stand-alone device or together with a variety of cleared and unmodified syngo based software options. syngo.via supports interpretation and evaluation of examinations within healthcare institutions, for example, in Radiology, Nuclear Medicine and Cardiology environments. The system is not intended for the displaying of digital mammography images for diagnosis in the U.S. The system is a software only medical device. It defines minimum requirements to the hardware it runs on. The hardware itself is not seen as a medical device and not in the scope of this 510(k) submission. It supports the physician in diagnosis and treatment planning. syngo.via also supports storage of Structured DICOM Reports. In a comprehensive imaging suite syngo.via integrates Radiology Information Systems (RIS) to enable customer specific workflows. The predicate device, syngo.via allows for the use of a variety of advanced applications (clinical applications) These applications are medical devices on their own rights and filed separately. They are not part of this 510(k) submission and not part of the syngo.via medical device. syngo.via has a universal component called generic reader application which is part of this medical device and it allows no newly introduced imaging and post processing algorithms compared to the above mentioned predicate devices. syngo.via is based on Windows. Due to special customer requirements and the clinical focus syngo.via can be configured in the same way as the predicate device with different combinations of syngo- or Windows based software options and clinical applications which are intended to assist the physician in diagnosis and/or treatment planning. This includes commercially available post-processing software packages.

Here's an analysis of the provided 510(k) summary regarding acceptance criteria and supporting studies:

This 510(k) pertains to "syngo.via," a PACS system. Based on the document, this 510(k) is for enhanced functionalities of syngo.via, making it an update or extension of a previously cleared device (K123375). The key here is that it's not a new AI algorithm designed for a
specific diagnostic task with associated performance metrics. Instead, it seems to be primarily a software platform update that integrates functionalities already present in other cleared Siemens products.

Therefore, the typical structure for reporting AI/CADe/CADx device performance (sensitivity, specificity, AUROC, etc.) involving a test set, ground truth, and expert readers is not applicable in this submission. The "acceptance criteria" discussed are likely related to software verification and validation, adherence to standards, and demonstrating substantial equivalence to existing devices with similar functionalities.

1. Table of Acceptance Criteria and Reported Device Performance

As mentioned above, this 510(k) is for an enhanced PACS system and does not present specific diagnostic performance metrics. The "performance" is primarily demonstrated through compliance with standards and equivalence to predicate devices. There are no explicit quantitative acceptance criteria for diagnostic performance in terms of sensitivity, specificity, etc., as it's not a new diagnostic algorithm.

The "performance" described is in terms of:

• Software Functionality: Viewing, manipulation, communication, and storage of medical images.
• Integration: HL7-/DICOM-compatible RIS workflow.
• Technological Characteristics: Runs on Windows OS, supports DICOM images, image data compression (lossless and lossy).
• Imaging Algorithms (inherited/similar to predicates): MPR, MIP, MinIP, VRT, SSD, Digitally Reconstructed Radiograph, Editor functionality, Registration, Region Growing, Quantitative measurements.
• Automatic Spine Labeling (inherited/similar to predicates): Anatomy Labeling of Vertebra bodies, automatically suggested labels with manual override.

2. Sample size used for the test set and the data provenance

The document does not describe a "test set" in the context of diagnostic performance evaluation (e.g., a set of medical images used to evaluate an algorithm's diagnostic accuracy). The testing performed was software verification and validation testing at Unit, Integration, and System levels, as per IEC 62304. This type of testing uses various software inputs and configurations to ensure functional correctness, rather than a diagnostic image dataset. No specific sample size of images or data provenance (country, retrospective/prospective) is provided because it's not relevant for this type of submission.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable. There was no diagnostic "test set" requiring expert ground truth for diagnostic accuracy evaluation.

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

Not applicable. There was no diagnostic "test set" requiring expert ground truth or adjudication.

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

Not applicable. This 510(k) does not present an MRMC study comparing human reader performance with and without AI assistance, as it is a PACS system enhancement, not a new AI-powered diagnostic tool.

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

Not applicable. This is not a standalone diagnostic algorithm. syngo.via is a platform for viewing, manipulation, communication, and storage of medical images, intended to "support the physician in diagnosis and treatment planning." The functionalities described (like automatic spine labeling) are features within this broader platform, and their performance is indicated as being similar to those from previously cleared predicate devices.

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

Not applicable. As there was no diagnostic test set in the traditional sense, there was no ground truth for diagnostic accuracy established through expert consensus, pathology, or outcomes data. The "ground truth" for the software's functional performance would be defined by the software requirements and design specifications, verified through testing procedures.

8. The sample size for the training set

Not applicable. This 510(k) does not describe a new AI algorithm that requires a training set. The enhanced functionalities are stated to have "similar technological characteristics as the predicate device" and incorporate "imaging and post processing algorithms compared to the above mentioned predicate devices." This implies that any underlying algorithms for features like "Automatic Spine Labeling" are either existing, well-established, or derived from components previously cleared, rather than newly developed and trained models.

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

Not applicable, as there is no mention of a training set for a new algorithm in this 510(k) submission.

Ask a specific question about this device