(134 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 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 Pro.Pulse with software version SOMARIS/10 synqo CT VB10 is a Computed Tomography X-ray system which features two continuously rotating tube-detector system (dual source) and functions according to the fan beam principle. The SOMATOM Pro.Pulse with SOMARIS/10 syngo CT VB10 produces CT images in DICOM format. The images delivered by the system 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, radiation therapy planning, and therapeutic interventions (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 Pro.Pulse is SOMARIS/10 syngo CT VB10. It is a command-based program used for patient management, data management, X-ray 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.
The provided text describes the Siemens SOMATOM Pro.Pulse CT system, its modifications, and its substantial equivalence to predicate devices, but it does not contain a detailed study proving the device meets specific acceptance criteria in the format requested. Instead, it refers to broad categories of non-clinical testing and general statements about meeting pre-determined acceptance criteria.
Here's an attempt to structure the answer based on the available information. Many fields will be marked as "Not Provided" due to the nature of the document being a 510(k) summary, which often focuses on establishing substantial equivalence rather than detailed study results for specific performance metrics.
Acceptance Criteria and Device Performance Study for SOMATOM Pro.Pulse
The K232206 submission for the SOMATOM Pro.Pulse focuses on demonstrating substantial equivalence to its predicate devices (SOMATOM go.Top (K211373) and SOMATOM Drive (K230421)). The document details non-clinical testing performed to verify and validate modifications and ensure the device's functionality, image quality, and safety are comparable to the predicates.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not provide a table with specific quantitative acceptance criteria alongside numerical performance results for the device. Instead, it offers qualitative descriptions of performance objectives and outcomes for various features based on bench testing.
| Feature/Test | Acceptance Criteria (Stated Objective from Text) | Reported Device Performance (Summary from Text) |
|---|---|---|
| ZeeFree (Cardiac Stack Artefact Correction) | 1. Reduction of misalignment artifacts (e.g., discontinuities in vessel structures, anatomical steps at air-soft-tissue interfaces, doubling of anatomy) in SAC reconstruction compared to standard reconstruction. |
- No introduction of new artifacts by SAC reconstruction.
- Equivalent image quality (noise, homogeneity, high-contrast resolution, slice thickness, CNR) in phantom-based measurements compared to standard reconstruction.
- Equivalent image quality with metal objects compared to standard reconstruction.
- Successful application of SAC algorithm to phantom data, demonstrating correct technical function and independence from physical detector width. | 1. "If misalignment artefacts are identified in non-corrected standard ECG-gated reconstructed sequence or spiral images, the feature "Cardiac Stack Artefact Correction" (SAC, marketing name: ZeeFree) enables optional stack artefact corrected images, which reduce the number of alignment artefacts."
- "The SAC reconstruction does not introduce new artefacts, which were previously not present in the non-corrected standard reconstruction."
- "The SAC reconstruction does realize equivalent image quality in quantitative standard physics phantom-based measurements (ACR, Gammex phantom) in terms of noise, homogeneity, high-contrast resolution, slice thickness and CNR compared to a non-corrected standard reconstruction."
- "The SAC reconstruction does realize equivalent image quality in quantitative and qualitative phantom-based measurements with respect to metal objects compared to a non-corrected standard reconstruction."
- "The SAC algorithm can be successfully applied to phantom data if derived from a suitable motion phantom demonstrating its correct technical function on the tested device. The SAC algorithm is independent from the physical detector width of the acquired data." |
| Dual Source Dual Energy (DSDE) | Successful implementation of DSDE with 80 kV / Sn140 kV and 100 kV / Sn140 kV voltage combinations.
Image quality and spectral properties (iodine ratio) comparable to the reference device (SOMATOM Drive).
All applied image quality tests passed. | "The measurements show that the spectral characteristics of the system in terms of iodine ratio are well comparable to the reference device SOMATOM Drive. All applied tests concerning image quality passed." |
| FAST 3D Camera/FAST Integrated Workflow | Accuracy of FAST Isocentering, FAST Range, and FAST Direction comparable to the predicate device with syngo CT VA40 (old camera hardware, ceiling mount). | "The FAST Isocentering accuracy of the subject device with syngo CT VB10 is comparable to the predicate device with syngo CT VA40, regardless of the camera mounting position."
"For the FAST Range feature, the detection accuracy of all body region boundaries is comparable between the subject device with syngo CT VB10 and predicate device with syngo CT VA40."
"The FAST Direction pose detection results are of comparable accuracy for subject and predicate device, regardless of the camera mounting position."
"Overall, the SOMARIS/10 syngo CT VB10 delivers comparable accuracy to the SOMARIS/10 syngo CT VA40 predicate for the new FAST 3D Camera hardware, also in the new gantry position." |
| myNeedle Guide (with myNeedle Detection) | 1. High accuracy of automatic needle detection algorithm. - Reduction of necessary user interactions for navigating to a needle-oriented view. | 1. "It has been shown that the algorithm was able to consistently detect needle-tips over a wide variety of scans in 90.76% of cases."
- "Further, the results of this bench test clearly shows that the auto needle detection functionality reduces the number of interactions steps needed to generate a needle-aligned view in the CT Intervention SW. Zero user interactions are required and a needle-aligned view is displayed right away after a new scan, if auto needle detection is switched on in the SW configuration." |
| CARE kV | Effective mAs settings of low and high kV acquisitions in TwinkV scan adapted by CARE kV to maintain image quality (CNR).
Consistency of image qualities (CNR values) in certain phantoms under different kV settings in "Manual kV" mode.
Consistency of contrast, noise, and CNR values in mix images for all voltage combinations. | "Using CARE kV for TwinkV, contrast, noise, and CNR values in the mix images are consistent for all voltage combinations. In all cases, CNR values do not deviate by more than 10% from the average CNR over the available voltage combinations." |
| Flex 4D Spiral - Neuro/Body | No artifacts should be observed due to missing data, indicating correct trajectory functioning, even with pitch setting changes. | "No artifacts had been observed for any F4DS scan mode due to missing data, indicating that the trajectories work properly in hand. This also accounts for the scenario, where the user may change the pitch setting to get access to another range of scan coverages." |
| Low-Dose Lung Cancer Screening | Technical parameters specific to Low-Dose Lung Cancer Screening comparable to predicate and subject devices. | "It can be concluded that the subject and predicate devices are substantially equivalent for the task of Low-Dose Lung Cancer Screening since the bench test results showed comparable technical parameters." |
2. Sample Size Used for the Test Set and Data Provenance
The document mentions "phantom studies" and "phantom data" for several tests (ZeeFree, Dual Source Dual Energy, CARE kV, Flex 4D Spiral). For FAST 3D Camera, it tested the subject device against the predicate. For myNeedle Guide, it states the algorithm was able to consistently detect needle-tips in "90.76% of cases" over "a wide variety of scans." However,
- Specific sample sizes (N) for phantom studies or "a wide variety of scans" are not provided.
- Data Provenance (e.g., country of origin, retrospective/prospective) is not explicitly stated for these performance tests. Given they are "bench tests" and "phantom studies," they implicitly suggest a controlled laboratory setting (likely at the manufacturing locations in Germany or China) rather than clinical patient data. The reference to the National Lung Screening Trial (NLST) is supportive literature for the additional lung cancer screening Indications for Use, not a test set for the device's technical performance.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Not Provided. The non-clinical tests described in the document appear to be technical performance evaluations, primarily using phantoms and comparing against known technical specifications or established predicate device performance. There is no mention of experts establishing ground truth for these technical tests.
4. Adjudication Method for the Test Set
- Not Provided. This is typically relevant for studies involving human interpretation or clinical outcomes, which are not detailed for the device's technical performance validation.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
- No, an MRMC comparative effectiveness study is not described for the SOMATOM Pro.Pulse's performance relative to its predicate devices. The document focuses on demonstrating comparable technical performance through non-clinical bench testing.
- Effect size of human readers improvement with AI vs. without AI assistance: Not applicable, as no MRMC study comparing human readers with and without AI assistance is detailed.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
- Yes, the described "bench tests" and "phantom studies" are effectively standalone algorithm-only performance evaluations. For example, the ZeeFree reconstruction and myNeedle Detection algorithm evaluations are reported based on their intrinsic technical performance in a controlled setting without human intervention in the loop of image acquisition or primary interpretation for the purpose of the validation described.
7. The Type of Ground Truth Used
The ground truth for the non-clinical tests appears to be:
- Known phantom properties and measurements: For image quality metrics (noise, homogeneity, resolution, CNR, slice thickness).
- Known mechanical or digital parameters: For features like FAST 3D Camera (accuracy of Isocentering, Range, Direction) and Flex 4D Spiral (absence of artifacts due to missing data).
- Predicate device performance: Used as a reference for comparison, implying its performance is considered a benchmark or "ground truth" for equivalence.
- Quantifiable algorithm outputs: For myNeedle Detection, the algorithm's ability to consistently detect needle tips (90.76% accuracy).
8. The Sample Size for the Training Set
- Not Provided. The document describes bench testing for verification and validation, but it does not specify details about the training data used for any machine learning components (such as the optimization of the FAST 3D Camera algorithms or myNeedle Detection, if they involve machine learning).
9. How the Ground Truth for the Training Set Was Established
- Not Provided. Similar to the training set size, the method for establishing ground truth for any potential training data is not detailed in this submission summary.
§ 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.