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 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.

The subject device SOMATOM CT Scanner Systems with SOMARIS/7 syngo CT VB30 are Computed Tomography X-ray Systems which feature one (single source) continuously rotating tube-detector system and function according to the fan beam principle. The SOMATOM CT Scanner Systems with Software SOMARIS/7 syngo CT VB30 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.

The platform software for the SOMATOM CT Scanner Systems, SOMARIS/7 syngo CT VB30, is a commandbased program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text.

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on functional verification and validation testing rather than explicit, quantifiable acceptance criteria with corresponding performance metrics for each feature in a tabular format. Instead, it describes the objective of each test and then states that the results were found to be acceptable or passed.

However, we can extract the objectives and the documented outcomes for features where some quantifiable or descriptive performance is mentioned:

• Median difference between true and personalized delay 90% of patients.
• Higher overall and more uniform attenuation in individualized cohort vs. fixed.
• Higher contrast-to-noise ratio (CNR) and subjective image quality in individualized cohort.
• Able to adjust scan timing to altered protocols to reach diagnostic image quality despite slower injection rate and reduced iodine dose.
• Images with individualized post-trigger delay provided higher attenuation for all organs.
• Mean vessel enhancement significantly higher in individualized scan timing group. |
  | FAST 3D Camera (Adolescent support) | Achieve comparable or more accurate results than predicate for adults, while supporting adolescent patients (120 cm+) with comparable accuracy as adult patients. | Achieves the objective of the test. (Implies comparable or more accurate results). |
  | FAST Isocentering (Adolescent support) | Lateral isocenter accuracy of subject device comparable to predicate for adult patients, and similar accuracy for adolescent patients. | Comparable to predicate for adult patients; similar accuracy for adolescent patients. |
  | FAST Range (Adolescent support) | Robustness of groin landmark improved; other landmarks detected with comparable accuracy for adults; accuracy of landmark detection for adolescents similar to adults. | Robustness of groin landmark improved; other landmarks with comparable accuracy. For adolescents, similar accuracy to adults. |
  | FAST Direction | Comparable accuracy of pose detection to predicate device. | Comparable accuracy. |
  | FAST Planning | Fraction (percentage) of correct ranges that can be applied without change; calculation time meets interactive requirements. | For >90% of ranges, no editing action was necessary to cover standard ranges. For >95%, the speed of the algorithm was sufficient. |
  | Tin Filtration (New kV combinations) | Successful implementation of new voltage combinations (80/Sn140 kV and 100/Sn140 kV) verified; description of spectral properties given; improved CNR in spectral results (monoenergetic images). | Successful implementation verified via phantom scans and image quality criteria evaluation. All applied tests concerning image quality passed. Different spectral properties with and without Sn filter evident, and Sn filter improves spectral separation considerably. Results support claims related to improved CNR. |
  | General Non-Clinical Testing (Integration & Functional) | Verify and validate functionality of modifications. Ensure safe and effective integration. Conformance with special controls for software medical devices. Risk mitigation. | All software specifications met acceptance criteria. Testing supports claims of substantial equivalence. |

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

• FAST Bolus: The test describes using a "real contrast enhancement curve" determined by measurements with a dynamic scan mode. The subsequent supporting peer-reviewed studies provide more detail:

  • Korporaal et al. (2015): Not explicitly stated, but implies a cohort undergoing bolus tracking.
  • Hinzpeter et al. (2019): 108 patients received patient-specific trigger delay (subject), 108 patients received fixed trigger delay (reference). Prospective CT angiography scans of the aorta.
  • Gutjahr et al. (2019): 3 groups, 20, 20, and 40 patients respectively.
  • Yu et al. (2021): 104 patients (52 per group, implied) in abdominal multiphase CT, comparing individualized vs. fixed post-trigger delay.
  • Yuan et al. (2023): 204 consecutive participants randomly divided into two groups (102 patients each). A prospective study in coronary CT angiography (CCTA).
  • Schwartz et al. (2018): Not explicitly stated, but implied patient-specific data.
  • Data Provenance: The supporting studies imply a mix of retrospective analysis (e.g., Korporaal et al. simulating retrospectively differences) and prospective studies based on the descriptions provided. The locations of these studies are not explicitly mentioned in the excerpt, but given Siemens' global presence, it's likely multi-national.

• FAST 3D Camera, FAST Isocentering, FAST Range, FAST Direction, FAST Planning, Tin Filtration: For these features, the testing is described as "bench testing" using phantoms and internal validation. "Patient data" is mentioned for FAST Planning but without specific numbers.

  • Sample Size: Not specified for these internal bench tests; often involves phantom studies rather than patient-level data for performance metrics. For FAST Planning, it refers to "patient data" for validation, but the sample size is not indicated.
  • Data Provenance: Implied internal testing, likely at Siemens R&D facilities. No external patient data provenance details are given.

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

• For FAST Bolus, the "ground truth" for the internal bench test was defined as an "ideal post bolus delay" determined by measurements with a dynamic scan mode. This suggests an objective, data-driven approach rather than expert consensus on individual cases for the initial ground truth. However, the supporting studies mention:
  • Hinzpeter et al. (2019): Mentions subjective image quality and CNR, which would typically involve expert readers, but the number and qualifications are not provided.
  • Yuan et al. (2023): Mentions "Both readers rated better subjective image quality." suggesting at least two readers, but their qualifications are not provided.
• For other features (FAST 3D Camera, FAST Planning, etc.), the ground truth seems to be established through objective measurement against predefined targets (e.g., "calculated by FAST Planning algorithm that are correct and can be applied without change"). No specific expert involvement for ground truth establishment for these features is detailed.

4. Adjudication Method for the Test Set

• The document does not describe a formal adjudication method (e.g., 2+1, 3+1) for the establishment of ground truth or for reader studies. Where multiple readers are mentioned (e.g., Yuan et al. for FAST Bolus), it only states their findings without detailing an adjudication process. This suggests either independent readings or consensus where needed, but not a formal adjudication protocol.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and Effect Size

• Yes, implicitly for FAST Bolus: The supporting publications function as comparative effectiveness studies where human assessment (e.g., subjective image quality, diagnostic confidence) is evaluated with or without the aid of the FAST Bolus prototype.
  • Hinzpeter et al. (2019): "higher overall and more uniform attenuation in the individualized cohort compared to the fixed cohort. No difference between the cohorts for image noise was found, but a higher contrast-to-noise ratio (CNR) and higher subjective image quality in the individualized cohort compared to the fixed cohort." This indicates improvement with the AI-assisted timing.
  • Yu et al. (2021): "In the arterial phase, the images of group A with the individualized post-trigger delay provided higher attenuation for all organs... Furthermore, the contrast-to-noise ratio (CNR) of liver, pancreas and portal vein were significantly higher in the group with the individualized scan timing compared to the fixed scan delay. The overall subjective image quality and diagnostic confidence between the two groups were similar." This indicates improved quantitative metrics, with subjective similar.
  • Yuan et al. (2023): "Both readers rated better subjective image quality for Group B with the individualized scan timing. Also, the mean vessel enhancement was significantly higher in Group B in all coronary vessels. After adjusting for the patient variation, the FAST Bolus prototype was associated with an average of 33.5 HU higher enhancement compared to the fixed PTD." This provides a direct effect size for enhancement.
• For the other features, the description is focused on the device's inherent performance (e.g., accuracy of landmark detection, successful implementation) rather than human reader improvements. So, no MRMC study for those.

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

• Yes, for multiple features. The "Bench Testing" descriptions primarily evaluate the algorithm's performance in a standalone manner against a defined ground truth or objective:
  • FAST Bolus: "the post bolus delay as calculated by FAST Bolus to an ideal post bolus delay... was calculated. The objectives of the test were to investigate the deviation from the post bolus delay as determined by FAST Bolus to an ideal/ground truth delay..." This is standalone.
  • FAST 3D Camera, FAST Isocentering, FAST Range, FAST Direction: The tests "demonstrate that the FAST 3D Camera feature... achieves comparable or more accurate results," "lateral isocenter accuracy... comparable," "robustness of the groin landmark is improved," "comparable accuracy of the pose detection." These are assessments of the algorithm's direct performance.
  • FAST Planning: "assess the fraction (percentage) of ranges calculated by the FAST Planning algorithm that are correct and can be applied without change." This is a direct measurement of the algorithm's output quality.
  • Tin Filtration: Verifies "successful implementation" and investigates "improved contrast-to-noise ratio (CNR) in spectral results." This is standalone performance of the image reconstruction/processing.

7. The Type of Ground Truth Used

• Objective/Measured Data:
  • FAST Bolus: "ideal post bolus delay" determined by "measurements with a dynamic scan mode" and "averaged dynamic scans."
  • FAST 3D Camera, FAST Isocentering, FAST Range, FAST Direction: Implied ground truth based on objective measurements of spatial accuracy relative to predefined targets or phantoms.
  • FAST Planning: "correct" ranges are the ground truth, implying comparison to a predefined standard or ideal plan.
  • Tin Filtration: Objective image quality criteria and spectral property measurements are used as ground truth indicators.
• Expert Consensus/Subjective Assessment (as secondary metric in supporting studies): Some of the supporting publications for FAST Bolus also incorporate subjective image quality ratings by human readers, which would likely involve some form of expert consensus or individual expert assessment.

8. The Sample Size for the Training Set

• The document does not provide information on the sample size used for the training set for any of the AI/algorithm features. This information is typically proprietary and not usually disclosed in a 510(k) summary unless specifically requested or deemed critical for demonstrating substantial equivalence.

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

• The document does not provide information on how the ground truth for the training set was established. Given the nature of these features (automated bolus timing, patient positioning, scan range planning), the training data would likely involve large datasets of CT scans annotated with physiological events, anatomical landmarks, and optimal scan parameters. These annotations would typically be established by highly qualified medical professionals (e.g., radiologists, technologists) or through automated processes validated against gold standards. However, the specific methodology is not detailed in this excerpt.

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 *

• 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 subject device SOMATOM CT Scanner Systems with SOMARIS/7 syngo CT VB20 are Computed Tomography X-ray Systems which feature one (single source) or two (dual source) continuously rotating tubedetector system and function according to the fan beam principle. The SOMATOM CT Scanner Systems with Software SOMARIS/7 syngo CT VB20 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.

The platform software for the SOMATOM CT Scanner Systems, SOMARIS/7 syngo CT VB20, is a commandbased program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation.

Here's an analysis of the acceptance criteria and supporting study information based on the provided text, broken down by your requested points:

Acceptance Criteria and Study Information for SOMATOM CT Scanner Systems-Software Version SOMARIS/7 syngo CT VB20

The provided document (a 510(k) summary) describes an update to existing Computed Tomography (CT) scanner systems (SOMATOM Force, SOMATOM Definition Flash, SOMATOM Drive, SOMATOM Definition Edge, SOMATOM Definition AS Open, SOMATOM Definition AS/AS+, SOMATOM Confidence, and SOMATOM Edge Plus) with new software version SOMARIS/7 syngo CT VB20. The primary goal of the submission is to demonstrate substantial equivalence to previously cleared predicate devices (K173630 and K173607).

The document does not explicitly list specific numerical acceptance criteria for device performance beyond stating that "all software specifications have met the acceptance criteria" and "the SOMATOM CT Scanner Systems perform comparably to the predicate devices." It focuses on confirming the updated device maintains the safety and effectiveness of the predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance

As specific numerical acceptance criteria are not presented in the document, I will infer the high-level acceptance criteria from the submission's focus on demonstrating substantial equivalence and list the general performance statements made.

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

The document states that "phantom tests were conducted" and refers to "dosimetry and imaging performance, and analysis of phantom images to assess device and feature performance." However, no specific sample size for the test set (number of phantom scans, patient data, etc.) is provided.

Data Provenance: The tests are described as "non-clinical test (integration and functional) including phantom tests... during product development." This indicates that the testing was conducted internally by the manufacturer,Siemens, likely on prototypes or production units, using phantoms. There is no mention of human subject data, country of origin, or whether the tests utilized retrospective or prospective data. The nature of phantom studies typically makes them prospective in this context.

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

The document does not provide information on the number of experts used to establish ground truth or their specific qualifications (e.g., number of radiologists, years of experience). Given the nature of this submission (software upgrade for a CT system, focusing on technical performance and substantial equivalence rather than a new diagnostic algorithm's clinical efficacy), it's less likely to involve extensive expert-driven ground truth establishment as would be seen for AI/CADe devices. The "ground truth" for technical performance is typically established via physical measurements and established phantom metrics.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (e.g., 2+1, 3+1). As stated above, the testing appears to be primarily technical and phantom-based, where ground truth is often objectively measurable through physical properties or established methods, rather than subjective expert interpretation requiring adjudication.

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

No MRMC comparative effectiveness study was done or reported in this document. The submission focuses on demonstrating substantial equivalence of the updated CT system to its predicates through technical and non-clinical testing, not on measuring improvements in human reader performance with or without AI assistance.

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

While the document focuses on the performance of the CT system and its software, it does not specifically describe a standalone algorithm-only performance study in the context of an AI/CADe device. The SOMARIS/7 syngo CT VB20 is a platform software update for CT scanners, enhancing system functionality and image reconstruction capabilities (e.g., "Enhanced FAST DE Results," "Precision Matrix," "DirectDensity™"). The "performance" being evaluated is the system's ability to generate cross-sectional images and support diagnostic tasks, as opposed to a specific AI algorithm. The performance evaluation discussed would inherently be of the "algorithm" integrated into the system, contributing to the overall image quality and functional capabilities.

7. Type of Ground Truth Used

The ground truth for the non-clinical testing appears to be based on:

• Physical Measurements and Phantom Readings: "Non-clinical test (integration and functional) including phantom tests were conducted." This implies that phantoms with known properties or simulated pathologies were used, and the system's output (image quality, dose metrics, etc.) was measured against these known values.
• Engineering Specifications / Reference Data: For software functional tests ("all software specifications have met the acceptance criteria"), the ground truth would be the defined engineering and design specifications for the software's intended behavior.

There is no mention of pathology, outcomes data, or expert consensus (in the typical sense of clinical ground truth for diagnostic accuracy) for establishing the ground truth described in this submission.

8. Sample Size for the Training Set

The document does not mention a training set sample size or the use of a separate training set. This is consistent with the nature of the submission, which describes a software update for a CT system rather than a machine learning or AI algorithm submission where training data sets are explicitly separated from test data. The software updates described are enhancements to the system's core functionality, reconstruction, and workflow, which are typically developed and verified through engineering processes rather than large-scale machine learning training.

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

Since no training set is mentioned in the context of typical AI/ML development, this information is not applicable based on the provided document. The "training" for such system software updates primarily refers to the iterative development and internal testing processes by the engineers, where specifications serve as the "ground truth."

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 *

• 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/7 syngo CT VB10 for the following SOMATOM Computed Tomography (CT) Scanner Systems:

Dual Source CT Systems:

• SOMATOM Force
• SOMATOM Drive
• SOMATOM Flash

Single Source CT Systems:

• SOMATOM Definition AS/AS+
• SOMATOM Definition AS Open
• SOMATOM Definition Edge
• SOMATOM Confidence

The subject device SOMATOM CT Scanner Systems with SOMARIS/7 syngo CT VB10 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 CT Scanner Systems with Software SOMARIS/7 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.

The platform software for the SOMATOM CT Scanner Systems, SOMARIS/7 syngo CT VB10, is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation.

The provided document is a 510(k) premarket notification for Siemens SOMATOM CT Scanner Systems with software version SOMARIS/7 syngo CT VB10. It describes the device, its intended use, and a comparison with predicate devices to establish substantial equivalence.

However, the document does not contain specific details about acceptance criteria, reported device performance metrics (e.g., sensitivity, specificity, AUC), sample sizes for test sets, data provenance, number or qualifications of experts for ground truth, adjudication methods, multi-reader multi-case (MRMC) comparative effectiveness studies, standalone algorithm performance, or specific ground truth types for image-based diagnostic performance assessments.

The "Performance Data" section primarily focuses on non-clinical testing for system functionality, adherence to general medical device standards (ISO, NEMA, IEC), electrical safety, EMC, software verification and validation (including cybersecurity), and phantom tests to assess device and feature performance. It broadly states that "The test results show that all of the software specifications have met the acceptance criteria" and that "Verification and validation testing of the device was found acceptable to support the claim of substantial equivalence," but it does not quantify these acceptance criteria or the specific performance results in a table or detailed study findings.

The indications for use mention "aid in diagnosis, treatment preparation and radiation therapy planning" and "low dose lung cancer screening in high risk populations," which typically would involve performance metrics like sensitivity and specificity. However, these metrics are not presented. The reference to the National Lung Screening Trial (NLST) is for the clinical context of low-dose lung cancer screening, not for the performance validation of the Siemens CT system itself against a ground truth.

Therefore, I cannot populate a table with acceptance criteria and reported device performance, nor can I provide answers to the majority of the requested points, as that information is not present in the provided text.

Based on the provided text, here's what can be extracted regarding the study and performance claims:

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

The document does not provide specific quantitative acceptance criteria (e.g., sensitivity, specificity, reader performance metrics) or corresponding reported device performance values for diagnostic tasks. It broadly states that "all of the software specifications have met the acceptance criteria" and that testing demonstrates "comparability to the predicate devices in terms of technological characteristics and safety and effectiveness."

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

This information is not provided in the document. The testing mentioned is primarily "non-clinical test (integration and functional) including phantom tests."

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)

This information is not provided in the document. The testing described does not involve expert-adjudicated ground truth as it pertains to diagnostic performance on patient data.

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

This information is not provided in the document.

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

This information is not provided in the document. The study described focuses on technical verification and validation, and comparability to predicate devices, not on human-AI comparative effectiveness.

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

The document mentions "phantom tests" to assess device and feature performance. However, it does not specify performance metrics for a standalone algorithm related to diagnostic accuracy on clinical cases. The device is a CT scanner, and the software updates are for image processing and system functionality, not a standalone diagnostic AI algorithm.

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

For the non-clinical and phantom tests conducted, the ground truth would be the known and controlled parameters of the phantoms and the expected technical performance outputs. There is no mention of ground truth types for clinical diagnostic accuracy related to patient data.

8. The sample size for the training set

Not applicable. The document describes a software update for a medical imaging device (CT scanner) validated through non-clinical testing and phantom studies, not an AI model trained on a dataset.

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

Not applicable, as this is not an AI model requiring a training set with established ground truth.

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. *

• 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 Drive is a Computed Tomography X- ray System, which features two continuously rotating tube-detector systems and functions according to the fan beam principle. The SOMATOM Drive produces CT images in DICOM format, which can be used by post-processing applications commercially distributed by Siemens and other vendors. The computer system delivered with the CT scanner is able to run the post processing applications optionally. syngo CT VA62A (SOMARIS/7 VA62A) is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation available on the SOMATOM Drive CT system.

Here's a breakdown of the acceptance criteria and supporting studies for the SOMATOM Drive, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance:

The document doesn't explicitly state numerical acceptance criteria in a dedicated table for the SOMATOM Drive (the new device being reviewed). Instead, it focuses on demonstrating that the SOMATOM Drive meets software specifications and performs comparably to predicate devices. The "reported device performance" is largely implicitly stated by concluding that "all of the software specifications have met the acceptance criteria" and "the SOMATOM Drive performs as intended."

However, we can infer some "acceptance criteria" through the lens of what was tested and compared to predicate devices:

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

• Test Set Sample Size: Not explicitly stated for specific non-clinical tests. The document mentions "clinical images were evaluated" for Dual Source Dual Power mode, but the number of images/patients is not provided.
• Data Provenance:
  • Non-clinical/Software Testing: Conducted "during product development." This implies controlled, in-house testing, likely in Germany where the manufacturing site is located (Siemens Healthcare GmbH, Forchheim, Germany).
  • Clinical Images: "Clinical images were evaluated" suggests retrospective or newly acquired images for validation. No specific country of origin is mentioned.
  • National Lung Screening Trial (NLST): A multi-center randomized controlled trial conducted in the United States. The study started in August 2002 and completed in October 2010.

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

• For the device's technical performance (non-clinical tests, software evaluation):
  • No information is provided about expert involvement for establishing ground truth for the test set used in non-clinical or software testing. These typically rely on defined engineering specifications and quantitative measurements.
• For the clinical images evaluated for Dual Source Dual Power mode:
  • No information provided on experts or their qualifications for evaluating these images.
• For the NLST reference:
  • The NLST involved multiple radiologists at participating centers. The interpretation task for CT was to detect lung nodules of 4mm diameter or greater. The expertise of these radiologists would be broad, as it was a large-scale clinical trial. The document doesn't detail their specific years of experience or sub-specialties beyond being "trained physicians" in the general indications.

4. Adjudication Method for the Test Set:

• No specific adjudication method (e.g., 2+1, 3+1) is mentioned for any of the tests conducted for the SOMATOM Drive itself.
• The NLST, as a large clinical trial, would have had its own established protocols for interpretation, consensus, and potentially adjudication to establish ground truth for its primary endpoints, but this is not detailed in the 510(k) summary regarding the device's performance.

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

• No MRMC comparative effectiveness study was done regarding human readers improving with AI vs. without AI assistance.
• The SOMATOM Drive is a CT scanner, not an AI-assisted diagnostic tool. The document focuses on the hardware and reconstruction software performance, not on AI for interpretation.

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

• Yes, a standalone performance assessment was conducted for the device's capabilities. The document states:
  • "Nonclinical tests, including dosimetry and image performance, were conducted for the SOMATOM Drive during product development."
  • "The test results show that all of the software specifications have met the acceptance criteria."
  • "Non-clinical tests (integration and functional), including phantom test were conducted during the SOMATOM Drive product development."
  • These tests assess the system's output (images, dose measurements) directly against specified criteria, effectively evaluating its "standalone" algorithmic and hardware performance.

7. Type of Ground Truth Used:

• For non-clinical/software performance:
  • Ground truth was based on engineering specifications and phantom measurements. These are objective, quantifiable standards for image quality, dose, and system functionality.
• For clinical images for Dual Source Dual Power mode:
  • Not explicitly defined, but implied to be based on clinical evaluation of the images by unstated evaluators.
• For the NLST reference (supporting the Indication for Use for lung cancer screening):
  • The NLST's ground truth for lung cancer detection and mortality reduction would have been based on pathology results for confirmed cancers and long-term outcomes data (mortality).

8. Sample Size for the Training Set:

• Not applicable / Not provided. The SOMATOM Drive is a CT imaging system. While it uses complex algorithms for image reconstruction (e.g., ADMIRE, iMAR), these are typically engineered using physics-based models and iterative refinement, not "trained" on large datasets in the way modern deep learning AI models are. Therefore, there isn't a "training set" in the context of machine learning. The algorithms are part of the system's core functionality.

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

• Not applicable. As above, the system uses algorithms that are largely model-based and optimized through engineering principles, rather than being trained on a labeled dataset with a "ground truth" in the AI sense.

Ask a specific question about this device