(406 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 * * 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 SOMATOM Computed Tomography System family scanners are whole body X-ray computed tomography systems which feature a continuously rotating tube-detector system and functions according to the fan beam principle. The SOMATOM Computed Tomography System family scanners vary in configurations from 6 to 192 slices, and are intended to produce cross sectional images of the body by computer reconstruction of x-ray transmission data from either the same axial plane taken at different angles or spiral planes taken at different angles. 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 systems described in this submission provide pre-defined low dose scan modes similar to the modes used for The National Lung Screening Trial (NLST), and the features as recommend by the study. This allows use of these systems for screening in the same way the CT systems were used for NLST. The computer system delivered with the CT scanner is able to run post processing applications optionally.
The provided text describes Siemens' application for expanded indications for use for their SOMATOM Computed Tomography (CT) System family scanners to include low-dose lung cancer screening in high-risk populations. The submission asserts that the devices are substantially equivalent to previously cleared versions and that the new indication does not constitute a new intended use.
Here's a breakdown of the requested information based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The submission does not explicitly state specific quantitative acceptance criteria for performance metrics for the low-dose lung cancer screening indication. Instead, it states that the devices perform "comparably or better than" older devices which were used in the NLST study. The performance characteristics compared are standard CT image quality metrics.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| CT Number Accuracy (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| CT Number Uniformity (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Spatial Resolution (MTF, max in-plane resolution) (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Slice Thickness/Sensitivity Profile (minimum slice width) (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Noise Properties (NPS, Image noise (standard deviation)) (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Contrast to Noise Ratio (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Maximum Scan Speed (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
| Minimum Reconstructed Slice Interval (comparable or better than NLST devices) | "perform comparably or better than the older devices" |
2. Sample Size Used for the Test Set and Data Provenance
The document explicitly states: "Non clinical tests (integration and functional) and phantom testing were conducted for the SOMATOM Computed Tomography System family during product development." It further mentions: "The test results demonstrate that the subject devices perform comparably or better than the older devices. Since the older devices have been identified as suitable for lung cancer screening within the NLST, the respective performance of the subject devices can be regarded as suitable for lung cancer screening as well."
- Sample Size for Test Set: Not specified for new testing. The reliance is on comparability to devices used in the NLST study. The NLST study itself included over 53,000 participants.
- Data Provenance: The new testing focuses on non-clinical phantom testing. The clinical basis for the indication relies on existing clinical literature, specifically referencing the National Lung Screening Trial (NLST) which was a prospective, randomized controlled trial conducted in the United States.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts
The document does not describe the use of human experts to establish ground truth for the non-clinical phantom testing performed for this submission. The "ground truth" for the acceptance of the lung cancer screening application is implicitly tied to the performance characteristics of the devices used in the NLST study and subsequent literature, as defined by professional medical societies.
4. Adjudication Method for the Test Set
Not applicable, as expert adjudication for performance metrics within this submission is not described.
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
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not performed as part of this submission. The devices are CT scanners, not AI-powered diagnostic aids that directly assist human readers. The submission focuses on the performance of the CT system itself for low-dose lung cancer screening.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
This is not applicable as the device in question is a CT scanner, not an algorithm, and it requires clinical interpretation by a trained physician.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the suitability of the CT systems for low-dose lung cancer screening relies on:
- Clinical Literature: Specifically, the results of the National Lung Screening Trial (NLST) which involved clinical outcomes data (lung cancer incidence, mortality).
- Professional Medical Society Definitions: The indications for use explicitly state "As defined by professional medical societies."
- Technical Guidelines: From organizations like the American College of Radiology (ACR) and National Comprehensive Cancer Network (NCCN).
For the non-clinical performance tests conducted for this submission, the ground truth would be based on physical phantom measurements and known parameters of the phantoms.
8. The Sample Size for the Training Set
The document does not describe a training set in the context of an AI/ML algorithm. The devices are CT scanners, and their development and validation involve engineering, physics, and clinical studies (like NLST, which is referenced as foundational for the indication).
9. How the Ground Truth for the Training Set was Established
Not applicable, as no training set for an AI/ML algorithm is 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.