(119 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. This CT system can be used for low dose lung cancer screening in high risk populations. High risk populations are 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 go. Platform is comprised of 2 Computed Tomography (CT) Scanner Systems, SOMATOM go.Now and SOMATOM go.Up. These CT scanners feature one continuously rotating tube-detector system and function according to the fan beam principle. The system software is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation. The SOMATOM go.Now and SOMATOM go.Up scanners produce CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors as an aid in diagnosis and treatment preparation. The computer system delivered with the CT scanner is able to run optional post processing applications.
The provided document describes the Siemens Somatom Go.up and Somatom Go.now Computed Tomography (CT) systems. The focus of the performance data section is on non-clinical testing, verification and validation of hardware and software modifications, and compliance with various standards. There is no specific study described that establishes detailed acceptance criteria for diagnostic performance outcomes (e.g., sensitivity, specificity for a particular disease) or includes human readers evaluating images from the new CT systems in comparison to ground truth.
Here's the information extracted from the document:
1. A table of acceptance criteria and the reported device performance:
The document does not provide a table with specific acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, accuracy) alongside reported performance values for those metrics. Instead, the acceptance criteria relate to compliance with regulatory standards, successful completion of verification and validation testing, and comparability to predicate devices.
| Acceptance Criteria Category | Reported Device Performance/Findings |
|---|---|
| Non-Clinical Testing | |
| Integration and Functional Testing | Conducted for the SOMATOM go.Now and SOMATOM go.Up during product development. Modifications supported with verification testing. Test results show the subject devices (SOMATOM go.Now and SOMATOM go.Up) are comparable to predicate devices in terms of technological characteristics, safety, and effectiveness. |
| Phantom Tests | Conducted to assess device and feature performance during product development. Analysis of phantom images was performed. |
| Conformance to Performance Standards | Conformance claimed for: ISO 14791, NEMA XR-29, IEC 61223-2-6, IEC 61223-3-5, IEC 62304, NEMA XR-25, and DICOM 3.1-3.20. |
| Electrical Safety & EMC Testing | Conducted in accordance with IEC 60601-1, 60601-2-44, and 60601-1-2. Completed Form FDA 3654 provided. |
| Software Verification & Validation | |
| Documentation Level | Moderate Level of Concern software per FDA's Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005). |
| Conformance with Special Controls | Performance data demonstrates continued conformance with special controls for medical devices containing software. |
| Risk Analysis & Control | Risk analysis completed and risk control implemented to mitigate identified hazards. |
| Software Specifications | Test results show that all software specifications have met the acceptance criteria. |
| Cybersecurity | Conformance with FDA guidance document "Content of Premarket Submissions for Management of Cybersecurity Medical Devices" (Oct 2, 2014) by implementing a process for preventing unauthorized access, modifications, misuse, or unauthorized use of information. |
| Radio Frequency Wireless Technology | Compliance with FDA guidance document "Radio Frequency Wireless Technology in Medical Devices" (Aug 14, 2013) by adhering to EMC and risk-based verification and validation requirements. Complies with 47 CFR part 15 subpart c – Intentional Radiators. FCC ID code on labels. |
| Substantial Equivalence | Testing supports that the device is substantially equivalent to predicate devices. The non-clinical data supports the safety of the device, and hardware/software verification and validation demonstrate intended performance. Data shows comparable performance to predicate devices for the same intended use. |
| Intended Use Support | The National Lung Screening Trial (NLST) is referenced to support the additional lung cancer screening Indications for Use. This trial focused on detecting lung nodules of 4mm diameter or greater using low-dose CT in high-risk populations. (This is supportive data for the indication, not a test of the specific device's diagnostic performance against ground truth for typical clinical use cases.) Note: The NLST was conducted using various CT scanners, not specifically the Siemens Somatom Go.up or Go.now. It is cited to justify the clinical utility of CT for lung cancer screening, to which the new systems are being added. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
- Test Set Sample Size: Not explicitly stated for specific diagnostic performance. The document refers to "phantom tests" and "verification and validation testing" without quantifying these test sets in terms of patient data or number of phantoms used in a way that suggests a diagnostic efficacy study.
- Data Provenance: The document emphasizes non-clinical testing (integration, functional, and phantom tests) and verification and validation of the device's hardware and software. It does not describe a clinical study with a patient test set. The National Lung Screening Trial (NLST) is cited as "Additional Supportive Data" to justify the indication for use for low-dose lung cancer screening, not as a direct performance study of the Somatom Go.up/Go.now CT systems themselves. The NLST was conducted in the USA (National Cancer Institute).
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):
Not applicable. The document describes non-clinical testing and general software/hardware validation. It does not detail a study where expert radiologists established a ground truth for a test set of images acquired by these specific new CT devices for diagnostic performance evaluation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable. No diagnostic performance study with expert adjudication is described for these specific CT systems.
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:
No MRMC study is mentioned. This device is a CT scanner, not an AI-powered CADe/CADx device that assists human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Not applicable. This is a CT scanner, not a standalone AI algorithm. While the device produces images, its performance validation focuses on technical specifications, image quality via phantoms, and substantial equivalence to predicate CT systems, not standalone diagnostic performance of an interpretive algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):
For the core technical and safety validation described:
- Non-clinical testing: Ground truth is against design specifications, physical measurements, and compliance with industry standards.
- Phantom tests: Ground truth is against known phantom characteristics (e.g., density, spatial resolution targets).
- Software V&V: Ground truth is against software specifications and risk analysis.
The NLST, cited for the lung cancer screening indication, relied on biopsy/pathology and clinical follow-up for its ground truth regarding cancer presence. However, this was for the general effectiveness of low-dose CT screening, not a performance evaluation of the specific Siemens devices.
8. The sample size for the training set:
Not applicable. The document describes the marketing clearance for a CT imaging system. CT imaging systems do not typically have "training sets" in the artificial intelligence sense.
9. How the ground truth for the training set was established:
Not applicable.
§ 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.