(90 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 Single source CT system NAEOTOM Alpha.Prime and a new Dual Source CT system NAEOTOM Alpha.Pro based on the SOMARIS/10 software platform.
Siemens also intends to market updated software version, SOMARIS/10 syngo CT VB20, for the new NAEOTOM CT scanner systems and for the NAEOTOM Alpha cleared in K233657 (clearance date March 28th, 2024). The updated software version SOMARIS/10 syngo CT VB20 incorporates mainly features for radiotherapy planning support.
With the new software version SOMARIS/10 syngo CT VB20, the trade name of NAEOTOM Alpha cleared in K233657 has been changed to NAEOTOM Alpha.Peak for ex-factory systems. Systems already installed will receive the software update without change of the trade name. The system label keeps the product name NAEOTOM Alpha. System label information and UDI are not changed and remain the same as the original submitted.
For simplicity, the product name of NAEOTOM Alpha will be used throughout this submission instead of the trade name NAEOTOM Alpha.Peak.
The subject devices NAEOTOM Alpha (trade name ex-factory CT systems: NAEOTOM Alpha.Peak) and NAEOTOM Alpha.Pro with software version SOMARIS/10 syngo CT VB20 are Computed Tomography X-ray systems which feature two continuously rotating tube-detector systems, denominated as Aand B-systems respectively (dual source NAEOTOM CT scanner system).
The subject device NAEOTOM Alpha.Prime with software version SOMARIS/10 syngo CT VB20 is a Computed Tomography X-ray system which features one continuously rotating tube-detector systems, denominated as A-system (single source NAEOTOM Alpha CT scanner system).
The detectors' function is based on photon-counting technology.
In this submission, the above-mentioned CT scanner systems are jointly referred to as subject devices by "NAEOTOM CT scanner systems".
The NAEOTOM CT scanner systems with SOMARIS/10 syngo CT VB20 produce CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors. The CT images 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. The radiation therapy planning support includes, 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 NAEOTOM CT scanner systems is syngo CT VB20 (SOMARIS/10 syngo CT VB20). 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.
Software version syngo CT VB20 (SOMARIS/10 syngo CT VB20) is a modified software version of the primary predicate device NAEOTOM Alpha, syngo CT VB10 (SOMARIS/10 syngo CT VB10) cleared in K233657.
Software version SOMARIS/10 syngo CT VB20 will be offered ex-factory and as optional upgrade for the existing NAEOTOM Alpha systems.
The bundle approach is feasible for this submission since the subject devices have similar technological characteristics, software operating platform, and supported software characteristics. 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 document is a 510(k) summary for the Siemens NAEOTOM CT Scanner Systems, specifically addressing the updated software version SOMARIS/10 syngo CT VB20 and new system configurations (NAEOTOM Alpha.Pro and NAEOTOM Alpha.Prime).
The document does not contain a multi-reader, multi-case (MRMC) comparative effectiveness study with human readers improving with AI vs. without AI assistance. The device described is a Computed Tomography (CT) X-ray system, which is a medical imaging hardware device, not an AI software intended for image interpretation assistance to human readers in the way an MRMC study would typically evaluate. The software features described primarily relate to system control, image reconstruction, and workflow efficiency, some of which are automated ("FAST" technologies) but do not indicate an "AI assistance" that augments a human reader's diagnostic performance in a comparative study design. Therefore, the questions related to MRMC studies and human reader improvement are not applicable to the information provided in this 510(k) summary.
Additionally, the document describes non-clinical performance testing (bench testing), which evaluates the technical performance of the device and its features, rather than a clinical study evaluating diagnostic accuracy against a ground truth from expert readers or pathology. The performance data presented is based on phantom tests and technical assessments rather than a clinical study. Therefore, several of the requested elements (number of experts, adjudication methods, type of ground truth for test sets/training sets, sample sizes for training/test sets as they pertain to clinical data) are not directly addressed in the context of a clinical performance study as typically understood for AI/CADe devices.
The acceptance criteria and reported device performance are generally stated in terms of comparable or improved accuracy to predicate devices and successful completion of verification and validation testing against internal specifications and recognized standards.
Here's an attempt to answer the questions based on the provided document, noting the limitations regarding the type of device and performance data presented:
Acceptance Criteria and Device Performance Study Summary
The device in question is a Computed Tomography (CT) X-ray System (NAEOTOM CT Scanner Systems) with software version SOMARIS/10 syngo CT VB20. The performance data provided are primarily from non-clinical bench testing to demonstrate the device's technical capabilities and comparability to predicate devices. The focus is on functionality verification and image quality evaluation, particularly for new and modified features.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not provide a specific, quantifiable table of "acceptance criteria" for features in the typical sense of a clinical trial (e.g., sensitivity/specificity thresholds). Instead, "acceptance criteria" are referenced as being "related to the corresponding requirements" for various verification and validation tests. The reported performance is generally qualitative, stating that features meet expectations or are comparable/improved to predicate devices.
| Feature/Non-clinical Supportive Testing | Acceptance Criteria (Implicit from text) | Reported Device Performance |
|---|---|---|
| Direct i4D | The functionality should enable acquisition of a complete breathing cycle at every planned position, even with changing respiratory rates during data acquisition, successfully avoiding interpolation artifacts seen in conventional 4DCT. | "The test results show that with Direct i4D it is possible to acquire data for a full breathing cycle at every position of the patient even if the respiratory rate changes during the data acquisition. Compared to the conventional 4DCT scan mode interpolation artifacts (which occur because not for every position a complete breathing cycle could be acquired) can successfully be avoided with Direct i4D." |
| DirectBreathhold | The functionality should correctly trigger a spiral scan automatically from an external respiratory gating device, ensuring the scan remains unchanged and the object is accurately depicted. | "The test results show that using the Direct Breathhold functionality, a spiral scan can automatically be triggered from an external respiratory gating device. The actual scan remains unchanged, and the object is correctly depicted in the resulting image." |
| Recon&GO – RT planning | The introduction of RTP scan protocols should enable time and imaging dose savings by allowing spectral post-processing to provide task-specific images, eliminating the need for additional Single Energy scan ranges. | "The bench test underpins the possibility that with the introduction of the RTP scan protocols in the subject devices NAEOTOM CT scanner systems with syngo CT VB20, time and imaging dose can be saved, since each RTP scan range allows for spectral post-processing to provide task-specific images for an end-to-end radiotherapy workflow and thus no additional scan range with Single Energy is needed." |
| FAST 3D Camera/FAST Integrated Workflow | The optimized sub-features (Isocentering, Range, Direction) should demonstrate comparable or better accuracy for adults and adolescents as the predicate device for adults. | "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." (Specific improvements for adolescents and maintained accuracy for adults) |
| Flex 4D Spiral | The functionality should demonstrate proper function and assess the image quality of Flex 4D Spiral with NAEOTOM CT scanners. | "The performed bench test report describes the technical background of Flex 4D Spiral and its functionalities with NAEOTOM CT scanners, demonstrate the proper function of those, and assess the image quality of Flex 4D Spiral." (No specific quantifiable results given in summary, just that a report describes and assesses). |
| FAST Planning | The algorithm should have a high fraction (percentage) of correct ranges that can be applied without change and meet interactive speed requirements for 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." (Meets objective for reducing editing actions and meeting speed requirements). |
| Low-Dose Lung Cancer Screening (NAEOTOM Alpha.Pro & Alpha.Prime) | Technical parameters specific to Low-Dose Lung Cancer Screening should be comparable to predicate 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 "test set" in this context refers to phantom test data used for non-clinical bench testing.
- Sample Size: Not explicitly quantified as a number of "cases" or "patients" in the way a clinical study would. The descriptions indicate testing was performed on "a dynamic phantom" for Direct i4D, and "additional data from adults and adolescence patients" for FAST 3D Camera accuracy (though this data was for optimizing the feature, not for an independent test set as typically understood for a clinical performance evaluation). For FAST Planning, testing was done on "patient data" but no sample size is given. For Low-Dose Lung Cancer Screening, "technical parameters" were compared, implying phantom or engineering data. The overall testing framework includes "System Validation test" and "System Verification test" with various activities, but no specific human subject test set is detailed.
- Data Provenance: The data is from non-clinical bench testing and internal verification/validation activities. There is no mention of data origin in terms of "country of origin" as it is not a clinical study involving patient data from specific geographical locations. The testing is described as part of product development, implying internal company testing. It is inherently retrospective in the sense that it's testing a developed product against its specifications.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not provided as the performance data is from non-clinical bench testing, not from a clinical study with a ground truth established by medical experts interpreting images. The "ground truth" for these tests would be the pre-defined technical specifications and expected physical behavior of the system, verified by engineering and quality assurance personnel.
4. Adjudication Method for the Test Set
Since there is no clinical test set involving human expert interpretations and potential discrepancies, an "adjudication method" is not applicable. The "acceptance criteria" for the non-clinical tests are against internal requirements and performance metrics (e.g., accuracy against a known phantom truth, successful triggering of functions).
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, an MRMC comparative effectiveness study was not done according to the provided information. This submission is for a CT scanner system (hardware and associated control/reconstruction software), not an AI software intended to assist human readers in image interpretation. The performance data focuses on the technical capabilities of the CT system itself.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
The "performance data" section describes the technical performance and functionality of various software and hardware features, which can be considered "standalone" in the sense of evaluating the algorithm/system's output against a known input (e.g., phantom data). For instance:
- Direct i4D: Performance evaluated based on data acquisition and artifact avoidance.
- FAST Planning: Assessed the algorithm's ability to calculate ranges correctly and its speed.
- Low-Dose Lung Cancer Screening: Compared technical parameters.
However, this is not a "standalone performance" measure for diagnostic accuracy of an AI algorithm in the context of interpreting medical images compared to a clinical ground truth, but rather the technical performance of the imaging device and its embedded functionalities.
7. The Type of Ground Truth Used
For the non-clinical testing, the "ground truth" is technical/physical ground truth based on phantom properties, defined test conditions, and engineering specifications. For instance:
- For Direct i4D, the ground truth is the "breathing pattern of a thorax phantom."
- For FAST 3D Camera, the ground truth for accuracy would be the known physical position/orientation relative to the scanner.
- For FAST Planning, the ground truth involves "correct" calculated ranges based on anatomical rules or system design.
There is no mention of ground truth established via expert consensus, pathology, or outcomes data, as these are non-clinical hardware/software performance tests.
8. The Sample Size for the Training Set
The document does not provide information on a "training set" in the context of machine learning or AI models with labelled clinical data. The software features described are primarily rule-based or optimized algorithms, not deep learning models that require large labelled training datasets. While some features like FAST 3D camera were "optimized using additional data," this refers to data used for algorithm refinement (development/internal testing) and not a distinct "training set" for an AI model that would then be tested on an independent "test set."
9. How the Ground Truth for the Training Set was Established
Since no explicit "training set" for AI/ML algorithms is described in the provided context, this question is not applicable. The development and optimization of the system's features rely on engineering specifications, physical models, and potentially iterative refinement using internal test data (phantoms, potentially anonymized patient data for feature optimization) where the "truth" is either known by design or derived from highly controlled measurements.
§ 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.