(115 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 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 update software version, SOMARIS/10 syngo CT VA40 for Siemens SOMATOM Computed Tomography (CT) Scanner Systems with unmodified mobile workflow options. This update also includes optional hardware for CT guided intervention workflow for the X. platform supporting CT Scanner Systems.
SOMATOM go.Platform is comprised of the following 6 CT scanners and optional mobile workflow:
- . SOMATOM go.Up
- SOMATOM go.Now
- SOMATOM go.Top
- SOMATOM go.All ●
- SOMATOM go.Sim ●
- SOMATOM go.Open Pro
- Scan&GO Software (optional mobile workflow component) ●
SOMATOM X. platform is comprised of the following 2 CT scanners and optional mobile workflow:
- SOMATOM X.cite
- SOMATOM X.ceed (new CT Scanner Model)
- Scan&GO Software (optional mobile workflow component) .
The subject device SOMATOM go. platform and SOMATOM X. platform with SOMARIS/10 syngo CT VA40 are Computed Tomography X-ray Systems which feature one continuously rotating tube-detector system and function according to the fan beam principle. The SOMATOM go. platform and SOMATOM X. platform with software SOMARIS/10 syngo CT VA40 produces CT images in DICOM format. These images can be used by trained staff for post-processing applications commercially distributed by Siemens Medical Solutions USA, Inc. and other vendors. These images 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 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 subject device platform CT scanners. Scan&GO can be operated on a Siemens provided various tablet hardware or personal computer that meets certain minimum technical requirements. It allows users to work in close proximity to the scanner and the patient. Specifically Scan&GO allows control/display of the following software interactions via a wireless tablet or personal computer with Wi-Fi connection that meets certain minimum requirements:
- Selection of patients O
- O Selection of pre-defined protocols
- Scan parameter display O
- Patient table position display and gantry tilt parameter display O
- O Tools and instruction message area,
- Patient table position planning area O
- O Physiological data display
- Patient data display (e.g. date of birth, name) O
- Display of acquired topogram and tomogram images O
- Finalization of exam (close patient) O
- Mobile Organizer, O
- O Patient Instruction Language ("API languages")
- Control function for RTP Laser systems O
- O Control of mood light functions
- predefined workflow associated question/answer dialog O
NOTE: Scan&GO does not support storage of images. Additionally, Scan&GO cannot trigger a scan or radiation release.
The software version, syngo CT VA40 (SOMARIS/10 syngo CT VA40), 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 a software plugin interface that allows 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 VA40 (SOMARIS/10 syngo CT VA40) is an update to software version syngo CT VA30A (SOMARIS/10 syngo CT VA30) which was cleared for the primary predicate devices in K200524 and supports the same plugin interfaces for the optional Scan&GO mobile workflow and integration of post-processing tasks as the predicate devices.
The provided text describes a 510(k) premarket notification for Siemens CT scanner systems (SOMATOM go. Platform and SOMATOM X. Platform) with a software update (SOMARIS/10 syngo CT VA40). The document focuses on demonstrating substantial equivalence to a predicate device (SOMATOM X.cite, K200524) rather than presenting a performance study with detailed acceptance criteria and human reader studies for a diagnostic AI.
Therefore, much of the requested information regarding "acceptance criteria and the study that proves the device meets the acceptance criteria" in terms of clinical performance metrics (like sensitivity, specificity, AUC for an AI diagnostic device) and comparative effectiveness studies with human readers is not present in this document. This submission primarily focuses on hardware and software modifications and their impact on safety and technical performance, supported by non-clinical testing and adherence to recognized standards.
However, I can extract information related to the technical acceptance criteria and the non-clinical testing performed to meet them, as implied by the document.
Here's a breakdown of the available information based on your request:
1. Table of acceptance criteria and the reported device performance
The document does not provide a specific table of quantitative clinical acceptance criteria (e.g., specific thresholds for sensitivity, specificity, or AUC) for a diagnostic AI device, nor does it report such performance metrics. This is because the submission is for a CT scanner system with software updates, not a new diagnostic AI algorithm that independently provides a diagnosis.
Instead, the acceptance criteria relate to the technical performance and safety of the CT system and its software. The general statement is: "The test results show that all the software specifications have met the predetermined acceptance criteria."
Here's an inferred table based on the non-clinical testing described:
| Acceptance Criteria (Inferred from Testing Objectives) | Reported Device Performance (Summary) |
|---|---|
| For MyNeedle Laser: | |
| Accuracy of simulated clinical workflow | Defined accuracy level achieved. |
| Reduction in workflow steps | Reduction in steps demonstrated. |
| For UHR imaging-Ultra High Resolution: | |
| High Resolution across the whole FoV | Met the predetermined acceptance criteria. |
| For Cardiac CT imaging - Motion artifact reduced ECG-gated imaging: | |
| Support clinical claims (via phantom testing) | Performed to demonstrate support of clinical claims. |
| For Motion Artifact Reduced Non-Gated Imaging: | |
| Support clinical claims (via phantom testing) | Completed to support the clinical claims. |
| For Cardiac BestPhase: | |
| Automatic calculation of cardiac reconstruction phase with minimized visible motion | Demonstrated the feature met the requirements. |
| For Equivalence of essential image quality parameters (SOMATOM X.ceed vs. SOMATOM X.cite): | |
| Image contrast values | Substantial equivalence demonstrated. |
| Image noise | Substantial equivalence demonstrated. |
| Contrast to noise ratio (CNR) | Substantial equivalence demonstrated. |
| Noise power spectra | Substantial equivalence demonstrated. |
| For Lung Cancer Screening: | |
| Technological Parameters Comparison to support Indications for Use | Completed and supports the indications for use. |
| Overall Software Performance: | |
| All software specifications | Met the predetermined acceptance criteria. |
| Verification and validation of hardware and software | Demonstrates the systems perform as intended. |
| Risk control | Implemented to mitigate identified hazards. |
2. Sample size used for the test set and the data provenance
- Sample Size: The document does not specify exact sample sizes (e.g., number of images or patients) for the non-clinical testing. It refers to "phantom tests" and "bench tests." For the lung cancer screening indication, it references the National Lung Screening Trial (NLST), which is a large prospective clinical trial, but the submission itself did not conduct a new clinical trial for this specific device. The NLST is cited as supportive literature for the clinical utility of low-dose CT in lung cancer screening, not data directly generated by this device for its performance.
- Data Provenance:
- Country of Origin: The non-clinical tests were conducted internally by Siemens, likely at their manufacturing and development sites, which include Germany and China (as per manufacturing site listings).
- Retrospective or Prospective: The non-clinical tests (phantom and bench testing) are inherently prospective in nature because they are controlled experiments performed during product development and verification. The NLST, referenced for lung cancer screening, was a prospective clinical trial.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not applicable and therefore not provided in this document in the context of diagnostic AI acceptance criteria. The tests performed are non-clinical (phantom, bench tests) and mechanical/software verification, not human-in-the-loop diagnostic studies requiring expert ground truth labeling.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not applicable as it pertains to establishing ground truth for diagnostic interpretation, which was not the focus of this non-clinical testing.
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
An MRMC study was not conducted for this submission. This is not a submission for a new AI diagnostic algorithm but rather for updates to a CT scanner system and its core operating software. The mention of "Scan&GO Software" refers to a mobile workflow control software, not an AI diagnostic assistant.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone performance study for an AI diagnostic algorithm was not done. The "software" being updated is the CT scanner's operating system (SOMARIS/10 syngo CT VA40) and command-based program, along with a mobile workflow control application (Scan&GO). These are not presented as standalone AI tools that provide diagnostic output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the non-clinical testing described:
- Phantom measurements/simulations: The "ground truth" or reference for these tests would be the known physical properties and configurations of the phantoms, or scientifically established benchmarks for image quality parameters.
- Simulated clinical workflow: For things like "MyNeedle Laser," the "accuracy" is likely judged against pre-defined engineering specifications for precision and workflow efficiency.
- Bench testing: Involves controlled experiments against pre-determined requirements and specifications.
- Reference to NLST: For the lung cancer screening indication for use, the ground truth for the clinical utility of low-dose CT screening itself came from the NLST study, which used clinical outcomes (e.g., reduction in mortality from lung cancer) as its primary endpoint. However, this is for the indication, not performance of this specific device's new features.
8. The sample size for the training set
This document does not refer to a training set in the context of an AI algorithm. The software update is for the CT system's operating and control software, not a machine learning model that requires a training set.
9. How the ground truth for the training set was established
This is not applicable as no AI training set is discussed or implied by the nature of the software update described.
§ 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.