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, and possibly other medical imaging modalities (e.g. MR scanners). An interface shall enable the connection between the syngo. CT Extended Functionality software package and the interconnected CT Scanner system.

Resulting 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 that offers tools to support special clinical evaluations. The "tools" are represented by the so-called Extensions. 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 or other medical imaging modalities (e.g. MR scanners) by using the Extensions. Advanced visualizations and measurements are listed as follows. The subject device in the current software version SOMARIS/8 VB70 has been extended/modified as follows:

• Support of the extension "Average"
• Modifications to the extension "Vessel"
• Modifications to the extension "Interactive Spectral Imaging"
• Modifications to the extension "Oncology"
• "Trauma" Extension – No changes
• "Osteo" Extension - No changes
• "Neuro DSA" Extension – No changes
• "ROI HU Threshold" Extension – No changes
• . "Dual Energy" Extension – No changes
• "Endoscopic Viewing" Extension - No changes
• . "Pulmonary Density" Extension – No changes
• . "General" (Extension Independent Features) – No changes

The provided text is a 510(k) Summary for a medical device called "syngo.CT Extended Functionality." It extensively describes the device, its intended use, comparison to a predicate device, and the non-clinical testing performed.

However, the document does not contain the specific information requested regarding acceptance criteria and a study proving the device meets those criteria. The provided text states:

• "This submission contains performance tests (Non-clinical test reports) to demonstrate continued conformance with special controls for medical devices containing software. Non-clinical tests (integration and functional) were conducted for syngo.CT Extended Functionality during product development. These tests have been performed to test the ability of the included features of the subject device. The results of these tests demonstrate that the subject device performs as intended." (Page 6)
• "The risk analysis was completed, and risk control implemented to mitigate identified hazards. The testing results support that all the software specifications have met the acceptance criteria. Testing for verification and validation of the device was found acceptable to support the claims of substantial equivalence." (Page 6)

While it mentions that tests were conducted and acceptance criteria were met, it does not detail what those acceptance criteria are in a tabular format, nor does it describe a specific study with sample sizes, expert involvement, ground truth methods, or MRMC comparative effectiveness. The tests mentioned are high-level "integration and functional" tests, and "verification and validation" tests, common for software development, but not a detailed clinical performance study as might be expected for an AI/ML-driven device with specific performance claims.

The key modifications to the device, as noted in the document, are:

• Support of the extension "Average" (new functionality)
• Modifications to the extension "Vessel" (improved bone removal using a deep learning algorithm)
• Modifications to the extension "Interactive Spectral Imaging" (support of circular and elliptic ROIs)
• Modifications to the extension "Oncology" (spectral information for arbitrarily shaped ROIs)

Given that the "Vessel" extension now incorporates a deep learning algorithm for bone removal, one might expect a study to validate the performance of this AI-driven component. However, the provided document only states that "Non-clinical tests (integration and functional) were conducted" and that "The testing results support that all the software specifications have met the acceptance criteria." No specific study details are given for this, or any other, AI/ML component.

Therefore, for your specific questions:

1. A table of acceptance criteria and the reported device performance: Not provided in the document.
2. Sample sizes used for the test set and the data provenance: Not provided in the document.
3. Number of experts used to establish the ground truth for the test set and the qualifications: Not provided in the document.
4. Adjudication method for the test set: Not provided in the document.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and its effect size: Not provided in the document. The document primarily focuses on non-clinical software testing for substantial equivalence to a predicate device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not explicitly detailed. The document mentions "non-clinical tests" and "verification and validation," but these are general software testing terms, not specific performance evaluations for an AI component.
7. The type of ground truth used: Not provided in the document.
8. The sample size for the training set: Not provided in the document. (Only mentions a deep learning algorithm in the "Vessel" extension, but no training details).
9. How the ground truth for the training set was established: Not provided in the document.

In summary, the provided FDA 510(k) summary focuses on demonstrating substantial equivalence through non-clinical software testing and quality system compliance, rather than detailing a specific clinical performance study with defined acceptance criteria for AI components. The document indicates that the device's software specifications met acceptance criteria through general testing (integration, functional, verification, validation), but the specifics of those criteria and the studies proving they were met are not disclosed in this summary.

Ask a specific question about this device

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, and possibly other medical imaging modalities (e.g. MR scanners).

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

Resulting 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 that offers tools to support special clinical evaluations. The "tools" are represented by the so-called Extensions. 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 or other medical imaging modalities (e.g. MR scanners) by using the Extensions.

I am sorry, but the provided text does not contain any information about specific acceptance criteria, study details (like sample sizes, expert qualifications, or multi-reader multi-case studies), or performance data in the format of a table demonstrating how the device meets acceptance criteria.

The document is a 510(k) summary for the device "syngo.CT Extended Functionality," primarily focusing on:

• Regulatory Information: Product codes, classification, submission details, and FDA correspondence.
• Device Description: Explaining its purpose (advanced visualization tools for medical images) and listing its features/extensions, particularly highlighting modifications from a previous version.
• Comparison to Predicate Device: outlining similarities and differences with a previously cleared device.
• Performance Data (General Statement): It states that "performance tests (Non-clinical test reports) to demonstrate continued conformance with special controls for medical devices containing software" were conducted and that "The results of these tests demonstrate that the subject device performs as intended." It also mentions "Testing for verification and validation of the device was found acceptable to support the claims of substantial equivalence." However, it does not provide the specific acceptance criteria, numerical performance data, or details of the study design (e.g., sample sizes, expert ground truth, MRMC study results).

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them based on the provided text. The document confirms that testing was done and met acceptance criteria generally, but it lacks the specifics required for your detailed questions.

Ask a specific question about this device

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, and possibly other medical imaging modalities (e.g. MR 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 that offers tools to support special clinical evaluations. The "tools" are represented by the so-called Extensions. 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 or other medical imaging modalities (e.g. MR scanners) by using the Extensions.

Here's a breakdown of the acceptance criteria and study information for the syngo.CT Extended Functionality device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance Study

The provided document describes the syngo.CT Extended Functionality as a software bundle offering tools for advanced visualization and measurements on medical images. It serves as an extension of a previously cleared predicate device, syngo.CT Clinical Extensions (K173625). The focus of the 510(k) submission is to demonstrate substantial equivalence to the predicate device, primarily through verification and validation of software functionality, especially the new Interactive Spectral Imaging (ISI) feature and modifications to existing extensions.

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" in a quantitative table with specific target values (e.g., accuracy > X%, sensitivity > Y%). Instead, the acceptance criteria are implicitly defined by the successful completion of various software verification and validation activities, performance standards, and the demonstration that the device "performs as intended" and is "comparable to the predicate devices in terms of technological characteristics and safety and effectiveness."

Implicit Acceptance Criteria and Demonstrated Performance:

• Vascular/Vessel Extension: "This modification is a usability improvement." (Implies successful verification of the improved functionality).
• Oncology Extension: "Modified to support MR data for Diameter WHO." (Implies successful verification of MR data processing).
• Multiphase Support for Merged 4D Series: "Usability improvement: The grouping logic has been extended to include cardiac gated datasets." (Implies successful verification of the extended grouping logic). |
  | Compliance with Safety and Performance Standards | The device fulfills requirements of:
• Digital Imaging and Communications in Medicine (DICOM) Set; PS 3.1 – 3.20 (Recognition Number 12-300)
• Medical Device Software – Software Life Cycle Processes; 62304:2006 (1st Edition) (Recognition Number 13-32)
• Medical devices – Application of risk management to medical devices; 14971 Second Edition 2007-03-01 (Recognition Number 5-40)
• Medical devices - Part 1: Application of usability engineering to medical devices IEC 62366-1:2015 (Recognition Number 5-114) |
  | Software Quality and Risk Management | - "Software Documentation for a Moderate Level of Concern software per FDA's Guidance Document 'Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices' issued on May 11, 2005 is included as part of this submission."
• "Risk management is ensured via a hazard analysis, which is used to identify potential hazards. These potential hazards are controlled during development, verification and validation testing."
• "The device labeling contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of the device." |
  | Equivalence to Predicate Device | The device is deemed "as safe, as effective, and with performance substantially equivalent to the commercially available predicate devices." Test results show the subject device is "comparable to the predicate devices in terms of technological characteristics and safety and effectiveness." |

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

• Sample Size: The document explicitly mentions that for the Interactive Spectral Imaging (ISI) functionality, a "phantom-based validation" was conducted. However, no specific number of images, patient cases, or phantom instances are provided. For other features, it refers to "non-clinical tests" and "bench tests" but does not give sample sizes.
• Data Provenance:
  • The "phantom-based validation" suggests synthetic or controlled data.
  • No specific country of origin for any human patient data is mentioned, nor whether it was retrospective or prospective. Given that this is a software update for an existing imaging workstation, it's highly probable that internal test data, possibly from various sources (pre-existing clinical de-identified data or synthetic data), was used for verification.

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

The document does not specify the number of experts or their qualifications used to establish ground truth for any aspect of the testing. The testing described appears to be primarily focused on technical performance and functional verification rather than diagnostic accuracy studies involving human expert reads. The phrase "Result images created with the syngo.CT Extended Functionality software package can be used to assist trained technicians or physicians in diagnosis" implies that the software provides tools for diagnosis, not a diagnosis itself, which aligns with the focus on technical verification.

4. Adjudication Method for the Test Set

No information is provided regarding an adjudication method. This is consistent with the likely focus on technical functional testing (e.g., verifying image transformations, measurements within software, and compliance with standards) rather than clinical accuracy studies requiring human reader agreement.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, an MRMC comparative effectiveness study was not explicitly mentioned or performed. The submission focuses on demonstrating substantial equivalence through technical and functional verification and compliance with standards, rather than a clinical trial assessing human reader performance with and without AI assistance. The device is described as providing "advanced visualization tools" to "support technicians and physicians," not necessarily an AI-driven diagnostic aid that would directly influence human reader accuracy in the way a CAD (Computer-Aided Detection) system might.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

The document describes "performance tests" and "phantom-based validation" for the Interactive Spectral Imaging (ISI) functionality and "non-clinical tests and a phantom-based bench test" for other features. These types of tests are inherently standalone performance evaluations of the software's functionality, without a human in the loop for the performance assessment itself (though a human would operate the software). The focus is on whether the software performs its intended function accurately (e.g., correct image generation, measurement calculations).

7. The Type of Ground Truth Used for the Test Set

The ground truth for the testing appears to be primarily technical specifications, phantom measurements, and expected output values based on the software's design and engineering requirements. For the "phantom-based validation" of ISI, the ground truth would likely be the known material properties or quantitative measurements of the phantom. For other functional tests, it would be the expected software output when processing specific input data according to defined algorithms. No mention of expert consensus, pathology, or outcomes data as ground truth is made for the described testing.

8. The Sample Size for the Training Set

The document is a 510(k) summary for a software update and extension of an existing product, and the testing described is primarily for verification and validation, implicitly for a mature software product built upon established technology. It does not mention or provide information about a "training set" for AI/ML algorithms. The device's description as "advanced visualization tools" and "measurements" suggests traditional image processing and analysis algorithms, not necessarily deep learning or AI that would require large, labeled training datasets. The "Interactive Spectral Imaging" feature is described as allowing the user to display representations of Dual Energy data, which often relies on pre-defined material decomposition algorithms rather than trained models.

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

Since no "training set" for AI/ML is mentioned, the method for establishing its ground truth is not applicable here. The ground truth for the verification and validation of this device (as per point 7 above) would be based on technical specifications and known physical properties, not a labeled training dataset derived from human expert annotations.

Ask a specific question about this device

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