Search Results

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of X-ray transmission data.

The images delivered by the system can be used by a trained staff as an aid in diagnosis, treatment, and radiation therapy planning as well as for diagnostic and therapeutic interventions.

This CT system can be used for low dose lung cancer screening in high risk populations*.

*As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

Siemens intends to market a new software version, SOMARIS/10 syngo CT VB20 for the following SOMATOM Computed Tomography (CT) Scanner Systems:

a) Single Source CT Scanner systems (SOMATOM go. Platform):

• SOMATOM go.Now
• SOMATOM go.Up
• SOMATOM go.All
• SOMATOM go.Top
• SOMATOM go.Sim
• SOMATOM go.Open Pro

In this submission, the above listed CT scanner systems are jointly referred to as subject devices by "SOMATOM go. Platform" CT scanner systems.

b) Dual Source CT Scanner system:

• SOMATOM Pro.Pulse

The above listed subject devices with SOMARIS/10 syngo CT VB20 are Computed Tomography X-ray Systems which feature one (Single Source) or two (Dual Source) continuously rotating tube-detector system and function according to the fan beam principle. The SOMATOM go. Platform and the SOMATOM Pro.Pulse with software SOMARIS/10 syngo CT VB20 produce CT images in DICOM format, which can be used by trained staff for software applications, e.g. post-processing applications, commercially distributed by Siemens Healthcare and other vendors as an aid in diagnosis, treatment preparation and therapy planning support (including, but not limited to, Brachytherapy, Particle including Proton Therapy, External Beam Radiation Therapy, Surgery). The computer system delivered with the CT scanner is able to run optional post processing applications.

The provided FDA 510(k) Clearance Letter for the SOMATOM CT Systems focuses heavily on establishing substantial equivalence to predicate devices through comparisons of technological characteristics, hardware, and software. It generally asserts that the device has met performance criteria through verification and validation testing, but it does not provide a detailed "Acceptance Criteria Table" with specific quantitative metrics and reported device performance. Similarly, it describes the types of studies performed (e.g., bench testing, retrospective blinded rater study), but it lacks the specific details requested regarding sample sizes, data provenance, expert qualifications, and effect sizes that would typically be found in a detailed study report.

Therefore, I will extract and synthesize the information that is available in the document and explicitly state where the requested information is not provided.

Understanding the Device and its Changes

The devices under review are Siemens SOMATOM CT Systems (SOMATOM go.Now, SOMATOM go.Up, SOMATOM go.All, SOMATOM go.Top, SOMATOM go.Sim, SOMATOM go.Open Pro, and SOMATOM Pro.Pulse) with a new software version, SOMARIS/10 syngo CT VB20. This new software version builds upon the previous VB10 version cleared in K233650 and K232206.

The submission focuses on modifications and new features introduced with VB20, including:

• Eco Power Mode: New feature for reduced energy consumption during idle times (not supported on go.Now and go.Up).
• Oncology Exchange: New feature for transferring prescription information from ARIA Oncology Information System.
• myExam Contrast: New feature for exchanging contrast injection parameters.
• FAST 3D Camera/FAST Integrated Workflow: Modifications including retrained algorithms, collision indication, and Centerline/Grid Overlay.
• FAST Planning: Extended to detect additional body regions.
• myExam Companion (myExam Compass/myExam Cockpit): Clinical decision trees now available for child protocols.
• HD FoV 5.0: New extended field of view reconstruction algorithm (for go.Sim and go.Open Pro only).
• CT guided intervention – myAblation Guide interface: New interface.
• Flex 4D Spiral: Modifications regarding dynamic tube current modulation.
• ZeeFree RT: New stack artifact reduced reconstruction for respiratory-related examinations (for go.Open Pro only).
• DirectDensity: Modified to include stopping-power ratio (Kernel St).
• DirectLaser: Patient Marking workflow improvement.
• Respiratory Motion management - Open Online Interface: New interface for respiratory gating.
• DirectSetup Notes: Enabled for certain SOMATOM go. Platform systems.

The core argument for clearance is substantial equivalence to predicate devices. This means that, despite modifications, the device is as safe and effective as a legally marketed device (the predicates).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not contain a specific table of quantitative acceptance criteria with corresponding reported device performance values. Instead, it describes general acceptance criteria related to verification and validation tests and then provides qualitative statements about the test results demonstrating comparability or improvement over predicate devices.

Here's a summary of the described performance evaluations:

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

The document provides very limited, qualitative information:

• FAST 3D Camera: Optimized using "additional data from adults and adolescence patients." No specific number of patients or images mentioned.
• FAST Planning: Evaluated on "patient data." No specific number of patients or images mentioned.
• HD FoV 5.0: Evaluated with "physical and anthropomorphic phantoms."
• Flex 4D Spiral: No specific sample size or data type mentioned for performance assessment.
• ZeeFree RT: Evaluated with "homogeneous water phantom," "phantom with tissue-equivalent inserts," "static torso phantom," and "dynamic thorax phantom." Also, "retrospective blinded rater studies of respiratory 4D CT examinations performed at two institutions." No specific number of phantoms, images per phantom, or patient cases mentioned.
• DirectDensity: Evaluated on "SOMATOM CT scanner models." No specific sample size or data type mentioned.

Data Provenance:

• Country of Origin: Not specified for the patient data used for algorithm optimization/validation.
• Retrospective or Prospective:
  • FAST 3D Camera: Implied retrospective as it uses "additional data."
  • FAST Planning: Implied retrospective as it uses "patient data."
  • HD FoV 5.0: Retrospective for the blinded rater study.
  • ZeeFree RT: Retrospective for the blinded rater study of clinical cases. The phantom tests are by nature not retrospective/prospective.

3. Number of Experts and Qualifications for Ground Truth

• HD FoV 5.0: "board-approved radio-oncologists and medical physicists." The number of experts is not specified.
• ZeeFree RT: "board-approved radio-oncologists and medical physicists." The number of experts is not specified.

For other tests, ground truth appears to be established by phantom measurements or internal engineering verification, rather than human expert reads validating clinical ground truth.

4. Adjudication Method for the Test Set

The document mentions "retrospective blinded rater study" for HD FoV 5.0 and ZeeFree RT. However, it does not specify the adjudication method used (e.g., 2+1, 3+1, none) for these studies. It only states they were "blinded."

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

• A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was mentioned for HD FoV 5.0 and ZeeFree RT. Both were "retrospective blinded rater studies."
• Effect Size: The document does not report specific effect sizes (e.g., how much human readers improve with AI vs. without AI assistance). It only states that the purpose of the comparison was to "demonstrate that the HD FoV 5.0 algorithm is as safe and effective as the HD FoV 4.0 algorithm" and for ZeeFree RT that it "enables the optional reconstruction of stack artefact corrected images, which reduce the strength of misalignment artefacts." This implies an assessment of non-inferiority or improvement in image quality, but specific quantitative results for reader performance are not provided in this excerpt.

6. Standalone (Algorithm Only) Performance

The document describes tests for several algorithms (FAST 3D Camera, FAST Planning, HD FoV 5.0, Flex 4D Spiral, ZeeFree RT, DirectDensity) using phantoms and "patient data." These evaluations seem to be focused on the algorithm's performance in generating images or calculations, independent of human interpretation in some cases (e.g., accuracy of FAST 3D Camera, correctness percentage of FAST Planning).

However, it does not explicitly use the term "standalone performance" to differentiate these from human-in-the-loop assessments. The mention of "retrospective blinded rater studies" for HD FoV 5.0 and ZeeFree RT indicates a human-in-the-loop component for that specific evaluation, but the phantom testing mentioned alongside them would be considered standalone.

7. Type of Ground Truth Used

• Phantom Data: For HD FoV 5.0, Flex 4D Spiral, ZeeFree RT, and DirectDensity, physical and/or anthropomorphic phantoms were used, implying the ground truth is precisely known physical characteristics or pre-defined phantom configurations.
• Expert Consensus/Reads: For HD FoV 5.0 and ZeeFree RT, board-approved radio-oncologists and medical physicists performed retrospective blinded rater studies, implying their interpretations/ratings served as a form of ground truth or evaluation metric. It's not explicitly stated if this was against a clinical gold standard (e.g., pathology) or if it was a comparative assessment of image quality and clinical utility.
• Internal Verification: For FAST 3D Camera, FAST Planning, accuracy was assessed, likely against internal system metrics or pre-defined ideal outcomes.

8. Sample Size for the Training Set

The document does not provide any specific information about the sample size used for training the algorithms (e.g., for FAST 3D Camera, FAST Planning, HD FoV 5.0, ZeeFree RT). It only states that FAST 3D Camera was "optimized using additional data" and FAST Planning's algorithm had "product development, validation, and verification on patient data."

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

The document does not provide any specific information on how the ground truth for the training set was established. It only mentions the data types used for validation/verification (phantoms, patient data from two institutions, expert raters).

Ask a specific question about this device

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of x-ray transmission data.

The images delivered by the system can be used by a trained staff as an aid in diagnosis, treatment and radiation therapy planning as well as for diagnostic and therapeutic interventions.

This CT system can be used for low dose lung cancer screening in high risk populations*. *As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

Siemens intends to market a new software version, SOMARIS/10 syngo CT VB10 for the following SOMATOM Computed Tomography (CT) Scanner Systems:

SOMATOM go. Platform CT scanner systems:

• . SOMATOM go.Up
• . SOMATOM go.Now
• SOMATOM go.All
• SOMATOM go.Top
• . SOMATOM go.Sim
• . SOMATOM go.Open Pro

SOMATOM X. Platform CT scanner systems:

• . SOMATOM X.cite
• . SOMATOM X.ceed

In this submission, the above listed CT scanner systems are jointly referred to as subject devices by "SOMATOM go. Platform" and "SOMATOM X. Platform" CT scanner systems.

The subject devices SOMATOM go. Platform and SOMATOM X. Platform with SOMARIS/10 syngo CT VB10 are Computed Tomography X-ray Systems which feature one continuously rotating tubedetector system and function according to the fan beam principle (single source). The SOMATOM go. Platform and SOMATOM X. Platform with software SOMARIS/10 syngo CT VB10 produces CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens Healthcare and other vendors as an aid in diagnosis, treatment preparation and therapy planning support (including, but not limited to, Brachytherapy, Particle including Proton Therapy, External Beam Radiation Therapy, Surgery). The computer system delivered with the CT scanner is able to run optional post processing applications.

Only trained and qualified users, certified in accordance with country-specific regulations, are authorized to operate the system. For example, physicians, radiologists, or technologists. The user must have the necessary U.S. qualifications in order to diagnose or treat the patient with the use of the images delivered by the system.

The platform software for the SOMATOM go. Platform and SOMATOM X. Platform, SOMARIS/10 synqo CT VB10, is a command-based program used for patient management, data management, Xray scan control, image reconstruction, and image archive/evaluation.

The software platform provides plugin software interfaces that allow for the use of specific commercially available post processing software algorithms in an unmodified form from the cleared stand-alone post processing version.

New software version syngo CT VB10 (SOMARIS/10 syngo CT VB10) is a modified software version based on syngo CT VA40 (SOMARIS/10 syngo CT VA40) which was cleared for the predicate device in K211373.

Software version SOMARIS/10 syngo CT VB10 will be offered ex-factory and as an optional upgrade for the applicable existing SOMATOM go. Platform and SOMATOM X. Platform CT Scanner Systems.

The bundle approach is feasible for this submission since the subject devices have similar technological characteristics, software operating platform, and supported software characteristics. The supporting data are similar, primarily one review division/group will be involved, and the indications for use is the same between the devices. All subject devices will support previously cleared software and hardware features in addition to the applicable modifications as described within this submission. The intended use remains unchanged compared to the predicate devices.

The provided text is a 510(k) summary for a Computed Tomography (CT) system. It focuses on demonstrating substantial equivalence to previously cleared predicate devices, primarily through non-clinical testing and comparison of technological characteristics. The document does not contain information about comparative effectiveness studies, multi-reader multi-case (MRMC) studies, or detailed clinical study results with ground truth establishment as one might find for a novel AI/ML-driven diagnostic device.

Therefore, many of the requested items (e.g., sample size for the test set, number of experts, adjudication methods, MRMC study effect size, training set details) are not explicitly mentioned in this type of submission. The focus here is on the CT system itself and its software updates, not on a new AI algorithm for detection or diagnosis where such detailed performance metrics against ground truth would be paramount.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria & Reported Device Performance

The document describes "bench testing" as non-clinical supportive testing for specific features. The acceptance criteria are generally qualitative (e.g., "comparable accuracy," "reduce the number of alignment artefacts," "successfully detect needle-tips") rather than specific numerical thresholds.

2. Sample Size for the Test Set and Data Provenance

• Sample Size: Not explicitly stated for any of the individual feature tests. The tests refer to "phantom tests" and "analysis of phantom images". For "myNeedle Guide," it mentions "a wide variety of scans," but no specific number.
• Data Provenance: The document does not specify the country of origin for the test data (phantoms) or if any retrospective/prospective human data was used. Given the nature of these tests (bench testing on phantoms), human patient data is generally not the primary focus for these types of technical evaluations.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• This information is not provided as the testing primarily involves technical and phantom-based evaluations, not clinical reader studies requiring expert ground truth.

4. Adjudication Method for the Test Set

• This information is not applicable/provided as detailed clinical studies with reader adjudication are not described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size

• No, an MRMC comparative effectiveness study is not mentioned in this 510(k) summary. The submission focuses on demonstrating substantial equivalence through technical testing and feature comparison, not on quantifying improvement in human reader performance with or without AI assistance.

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

• For the "myNeedle Guide" feature, the 90.76% detection rate of needle tips might be considered a form of standalone performance for that specific algorithmic component, though it's still being evaluated in the context of aiding a human user. For other features, the tests are primarily system-level or component-level functional checks.

7. The Type of Ground Truth Used

• For the non-clinical tests described, the "ground truth" would be established through phantom specifications and controlled experimental setups with known parameters (e.g., precise needle location in a phantom, known artifact presence/absence in a reconstructed image). This is typical for engineering verification and validation testing for CT systems.
• For the "myNeedle Guide," the "ground truth" for needle tip detection would likely be based on the known, true location of the needle tip within the phantom or experimental setup.

8. The Sample Size for the Training Set

• This information is not provided. The document describes software updates and system features, not the development of a new AI model from a training set. If the "myNeedle Guide" used machine learning, its training set details are not described here.

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

• This information is not provided as no training sets are explicitly described.

Ask a specific question about this device

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of x-ray transmission data. The images delivered by the system can be used by a trained physician as an aid in diagnosis.
The images delivered by the system can be used by trained staff as an aid in diagnosis, treatment preparation and radiation therapy planning.
This CT system can be used for low dose lung cancer screening in high risk populations. High risk populations are as defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The in-room scan application is a planning and information system designed to perform the necessary functions required for planning and controlling scans of supported SIEMENS CT scanners. It allows users to work in close proximity to the scanner.
The in-room scan application runs on standard information technology hardware and software, utilizing the standard information technology operating systems and user interface. Communication and data exchange are done using special protocols

The SOMATOM go.Platform is comprised of the following 4 CT scanners and optional mobile workflow:

• SOMATOM go.Up
• SOMATOM go.Now
• SOMATOM go.Top
• SOMATOM go.All
• Scan&GO Mobile Medical Application (optional mobile workflow component)

The CT scanners feature one continuously rotating tube-detector system and function according to the fan beam principle. The system software is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation. The above referenced CT scanners produce CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors as an aid in diagnosis and treatment preparation. The computer system delivered with the CT scanner is able to run optional post processing applications.

The Scan&GO mobile workflow is an optional planning and information software designed to perform the necessary functions required for planning and controlling of the workflow of the SOMATOM go.Platform CT scanners. Scan&GO can be operated on a Siemens provided tablet or a commercially available that meets certain minimum technical requirements. It allows users to work in close proximity to the scanner and the patient.

The provided text describes the acceptance criteria and supporting studies for the Siemens SOMATOM go.Platform CT scanners (SOMATOM go.All, SOMATOM go.Top, SOMATOM go.Now, SOMATOM go.Up) and the Scan&GO mobile workflow application.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document describes general "acceptance criteria" for software specifications and "pre-determined acceptance criteria" for customer use testing, but it does not provide specific quantitative acceptance criteria or reported performance values for clinical metrics. Instead, it emphasizes that testing demonstrated substantial equivalence to predicate devices and conformance to various performance, safety, and regulatory standards.

Therefore, a table with specific acceptance criteria and reported numeric performance cannot be generated from the given text. The text indicates that:

• "All test performed meet the pre-determined acceptance criteria."
• "The test results show that all of the software specifications have met the acceptance criteria."
• "The data included in this submission demonstrates that the SOMATOM go.Platform performs comparably to the predicate devices currently marketed for the same intended use."

This implies that the acceptance criteria were qualitative (e.g., "operates as intended," "comparable to predicate") or met internal Siemens specifications not detailed in this public summary.

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

The document primarily focuses on non-clinical testing.

• Test Set Description: Phantom tests, verification and validation testing, software testing, electrical safety and EMC testing, wireless coexistence testing, and customer use testing.
• Sample Size: Not explicitly stated for any of the non-clinical tests.
• Data Provenance:
  • Phantom Tests: Conducted by Siemens during product development.
  • Customer Use Tests:
    • Internal Clinical Use Test: Simulated in Siemens Test Cabins with "customers with clinical expertise."
    • External Clinical Use Test: Performed with "selected customer" in a "clinic/hospital environment."
  • Additional Supportive Data (Lung Cancer Screening): Refers to the National Lung Screening Trial (NLST) (N Engl J Med 2011; 365:395-409) which was a randomized trial.
    • NLST Sample Size: Not explicitly stated in this document, but the external reference (N Engl J Med 2011; 365:395-409) would contain this information.
    • NLST Data Provenance: Prospective, multi-center trial (implied by "National" and publication in a journal like NEJM). Information regarding country of origin is not explicitly stated in this document but is generally associated with the US for NLST.

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

• Non-clinical Tests: Ground truth for non-clinical tests (e.g., phantom images, software specifications) would typically be established by engineering and quality assurance teams based on design specifications and measurements, rather than clinical experts. No specific number or qualifications of "experts" are provided for these internal assessments.
• Customer Use Testing: "Customers with clinical expertise" were invited for internal clinical use tests. "Selected customer" (plural, implying multiple individuals or sites) performed external clinical use tests. No specific number or qualifications (e.g., "radiologist with 10 years experience") are provided.
• NLST (for lung cancer screening indication): The NLST identified lung nodules of 4mm diameter or greater. The ground truth for this large-scale clinical trial would involve extensive processes for diagnosis, follow-up, and potentially pathology, but the specific number and qualifications of experts involved in establishing ground truth for the NLST data itself are not detailed in this submission. The submission references the published literature for NLST for further information.

4. Adjudication Method for the Test Set

• Non-clinical Tests: Not explicitly stated. For engineering and software testing, adjudication would likely involve issue tracking systems and resolution processes, rather than clinical consensus.
• Customer Use Testing: Not explicitly stated. It states that "All test performed meet the pre-determined acceptance criteria," implying that the results were simply assessed against those criteria.
• NLST (for lung cancer screening indication): The adjudication methods for the NLST (referencing N Engl J Med 2011; 365:395-409) would be detailed in that study's methodology, but are not described in this 510(k) summary.

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

• No, an MRMC comparative effectiveness study involving AI assistance for human readers was not done.
• This submission describes a CT scanner system and its optional mobile workflow application, not an AI-based diagnostic aid that assists human readers. The technologies described are fundamental CT imaging and workflow enhancements.
• The NLST is referenced to support the ability of CT systems (not necessarily this specific model or an AI component) to perform low-dose lung cancer screening, but it is not a study comparing human readers with and without AI assistance.

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

• No, a standalone algorithm performance study was not specifically done in the context of AI without human-in-the-loop.
• The device being cleared is a Computed Tomography (CT) system and an accompanying mobile workflow application. These are imaging devices and tools for workflow, not standalone diagnostic algorithms.
• The "software" mentioned (SOMARIS/10 syngo CT VA20) refers to the operating system and processing capabilities of the CT scanner itself, including basic post-processing and interfaces for advanced post-processing, not a standalone diagnostic algorithm for interpretation.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

• Non-clinical (Technical/Performance) Testing: Ground truth for these tests would likely be based on:
  • Design specifications: For software functionality and hardware performance (e.g., compliance with IEC standards).
  • Measurements against known standards/phantoms: For image quality, radiation dose, electrical safety.
• Customer Use Testing: Ground truth would be the intended performance and user experience as validated by clinical users, ensuring the system operates as expected in a clinical context.
• Lung Cancer Screening Indication: The justification for the low-dose lung cancer screening indication comes from clinical literature, specifically referencing the National Lung Screening Trial (NLST). For NLST, the ground truth for lung cancer detection would ultimately be pathology and long-term outcomes data (mortality reduction). The submission states NLST's interpretation task was to detect lung nodules ≥ 4mm.

8. The Sample Size for the Training Set

• Not applicable. This submission is for a CT scanner platform and a workflow application, not a machine learning or AI algorithm in the context of diagnostic image interpretation that would require a dedicated "training set" for model development. The software mentioned handles system operation, image reconstruction, and basic post-processing, and is not described as involving a machine learning training phase.

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

• Not applicable. As no training set for a machine learning algorithm is discussed, the establishment of its ground truth is not relevant here.

Ask a specific question about this device

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of x-ray transmission data. The images delivered by the system can be used by a trained physician as an aid in diagnosis. This CT system can be used for low dose lung cancer screening in high risk populations. High risk populations are as defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The Siemens SOMATOM go. Platform is comprised of 2 Computed Tomography (CT) Scanner Systems, SOMATOM go.Now and SOMATOM go.Up. These CT scanners feature one continuously rotating tube-detector system and function according to the fan beam principle. The system software is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation. The SOMATOM go.Now and SOMATOM go.Up scanners produce CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors as an aid in diagnosis and treatment preparation. The computer system delivered with the CT scanner is able to run optional post processing applications.

The provided document describes the Siemens Somatom Go.up and Somatom Go.now Computed Tomography (CT) systems. The focus of the performance data section is on non-clinical testing, verification and validation of hardware and software modifications, and compliance with various standards. There is no specific study described that establishes detailed acceptance criteria for diagnostic performance outcomes (e.g., sensitivity, specificity for a particular disease) or includes human readers evaluating images from the new CT systems in comparison to ground truth.

Here's the information extracted from the document:

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

The document does not provide a table with specific acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, accuracy) alongside reported performance values for those metrics. Instead, the acceptance criteria relate to compliance with regulatory standards, successful completion of verification and validation testing, and comparability to predicate devices.

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

• Test Set Sample Size: Not explicitly stated for specific diagnostic performance. The document refers to "phantom tests" and "verification and validation testing" without quantifying these test sets in terms of patient data or number of phantoms used in a way that suggests a diagnostic efficacy study.
• Data Provenance: The document emphasizes non-clinical testing (integration, functional, and phantom tests) and verification and validation of the device's hardware and software. It does not describe a clinical study with a patient test set. The National Lung Screening Trial (NLST) is cited as "Additional Supportive Data" to justify the indication for use for low-dose lung cancer screening, not as a direct performance study of the Somatom Go.up/Go.now CT systems themselves. The NLST was conducted in the USA (National Cancer Institute).

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):

Not applicable. The document describes non-clinical testing and general software/hardware validation. It does not detail a study where expert radiologists established a ground truth for a test set of images acquired by these specific new CT devices for diagnostic performance evaluation.

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

Not applicable. No diagnostic performance study with expert adjudication is described for these specific CT systems.

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:

No MRMC study is mentioned. This device is a CT scanner, not an AI-powered CADe/CADx device that assists human readers.

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

Not applicable. This is a CT scanner, not a standalone AI algorithm. While the device produces images, its performance validation focuses on technical specifications, image quality via phantoms, and substantial equivalence to predicate CT systems, not standalone diagnostic performance of an interpretive algorithm.

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

For the core technical and safety validation described:

• Non-clinical testing: Ground truth is against design specifications, physical measurements, and compliance with industry standards.
• Phantom tests: Ground truth is against known phantom characteristics (e.g., density, spatial resolution targets).
• Software V&V: Ground truth is against software specifications and risk analysis.

The NLST, cited for the lung cancer screening indication, relied on biopsy/pathology and clinical follow-up for its ground truth regarding cancer presence. However, this was for the general effectiveness of low-dose CT screening, not a performance evaluation of the specific Siemens devices.

8. The sample size for the training set:

Not applicable. The document describes the marketing clearance for a CT imaging system. CT imaging systems do not typically have "training sets" in the artificial intelligence sense.

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

Not applicable.

Ask a specific question about this device