(107 days)
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:
| Feature/Metric | Acceptance Criteria (Qualitative) | Reported Device Performance (Qualitative) |
|---|---|---|
| Overall | Meet acceptance criteria for all software specifications. Enable safe and effective integration. Perform as intended in specified use conditions. | "All software specifications have met the acceptance criteria." "Verification and validation support the claims of substantial equivalence." "Perform(s) as intended in the specified use conditions." "As safe, as effective, and perform as well as or better than the predicate devices." |
| FAST 3D Camera Accuracy (Isocentering, Range, Direction) | Comparable or better accuracy to predicate device for adults; extend support to adolescents. | "Overall, the subject devices with syngo CT VB20 delivers comparable or improved accuracy to the predicate devices with syngo CT VB10 predicate device for adults and extends the support to adolescents." |
| FAST Planning Correctness | High fraction (percentage) of ranges calculated correctly and without needing change. Meets interactive requirements (fast calculation time). | "For more than 90% of the ranges no editing action was necessary to cover standard ranges." "For more than 95%, the speed of the algorithm was sufficient." |
| HD FoV 5.0 Performance (vs. HD FoV 4.0) | As safe and effective as HD FoV 4.0. | "Results obtained with the new HD FoV 5.0 algorithm are compared with its predecessor, the HD FoV 4.0 algorithm, based on physical and anthropomorphic phantoms...This comparison is conducted to demonstrate that the HD FoV 5.0 algorithm is as safe and effective as the HD FoV 4.0 algorithm." (No quantitative metrics provided in this document excerpt regarding this comparison's outcome). |
| Flex 4D Spiral Functionality & Image Quality | Proper function and acceptable image quality. | "The performed bench test report describes the technical background of Flex 4D Spiral and its functionalities with SOMATOM CT scanners, demonstrate the proper function of those, and assess the image quality of Flex 4D Spiral." (No quantitative metrics provided) |
| ZeeFree RT Reconstruction Performance | No relevant errors in CT values and noise in homogeneous phantoms. No relevant errors in CT values in tissue-equivalent phantoms. No relevant geometrical distortions in static phantoms. No relevant deteriorations of position/shape in dynamic phantoms. No relevant new artifacts. Maintain performance with iMAR. Independent of detector width. | "introduces no relevant errors in terms of CT values and noise levels measured in a homogeneous water phantom" "introduces no relevant errors in terms of CT values measured in a phantom with tissue-equivalent inserts, even in the presence of metals and in combination with the iMAR algorithm" "introduces no relevant geometrical distortions in a static torso phantom" "introduces no relevant deteriorations of the position or shape of a dynamic thorax phantom" "does not introduce relevant new artefacts" "can be successfully applied in combination with metal artifact correction (iMAR)" "is independent from the physical detector width" |
| DirectDensity Performance (iBHC variants) | Reduced dependence on tube voltage and filtration for non-water-like tissues. Image values aligned with material properties. | "reduced dependence on tube voltage and filtration compared to the corresponding quantitative kernel (Qr) with iBHC Bone for non-water-like tissues, such as adipose and bone." "generate image value closely aligned with the respective material properties." "has been validated." |
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).
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.