(28 days)
The SOMATOM P45 is 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. (*spiral planes: the axial planes resulting from the continuous rotation of detectors and x-ray tube, and the simultaneous translation of the patient.)
The Siemens SOMATOM P45 is a whole body X-ray Computed Tomography System, which features two continuously rotating tube-detector systems and functions according to the fan beam principle. The SOMATOM P45 produces CT images in DICOM format, which can be used by postprocessing applications commercially distributed by Siemens and other vendors. 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 new version of system software, SOMARIS/7 VA44, supports a Windows 7 operating system, additional scanning and evaluation techniques CARE (Combined Application to Reduce Exposure) and FAST (Fully Assisted Scanner Technology), and single click 3D reconstruction of Dual Energy Scans. The computer system delivered with the CT scanner is able to run the post processing applications optionally.
Here's an analysis of the provided Siemens 510(k) submission for the SOMATOM P45 CT system, focusing on acceptance criteria and supporting studies:
This 510(k) submission is for a software update (SOMARIS/7 VA44) to an existing CT system (SOMATOM P45), not for a novel device. The primary argument for substantial equivalence relies on the fact that the changes are not significant in terms of materials, energy source, or technological characteristics compared to predicate devices. This means that extensive clinical studies with new acceptance criteria, as one might expect for a completely new AI algorithm or diagnostic device, are not detailed in this type of submission.
Therefore, many of the typical acceptance criteria and study details requested in your prompt (e.g., number of experts, adjudication methods, MRMC studies, standalone performance with novel AI) are not applicable to this specific 510(k) summary. The "acceptance criteria" here are primarily met through verification and validation of the software changes and phantom testing to ensure the updated system continues to perform as expected and safely.
Here's a breakdown based on your request, with an emphasis on what is and isn't present in this type of 510(k):
1. Table of Acceptance Criteria and Reported Device Performance
Given that this is a 510(k) for a software update to an existing CT system, the "acceptance criteria" revolve around ensuring the updated system maintains the safety and effectiveness of the predicate device and that the new software functions correctly. The submission states:
| Aspect | Acceptance Criteria (Implied / Stated) | Reported Device Performance (Summary) |
|---|---|---|
| Software Functionality | Meet all software specifications for SOMARIS/7 VA44. | "The testing results supports that all the software specifications have met the acceptance criteria." |
| Safety & Effectiveness (Overall System) | Maintain the safety and effectiveness profile of the predicate SOMATOM P45. Ensure no significant changes in materials, energy source, or technological characteristics affecting safety/performance. | "SOMATOM P45 configured with software version SOMARIS/7 VA44 does not have significant changes in materials, energy source, or technological characteristics when compared to the predicate devices. The intended use and fundamental scientific technology are similar to the predicate devices." |
| Risk Mitigation | All identified hazards are controlled; risk analysis completed. | "The risk analysis was completed and risk control implemented to mitigate identified hazards." (for identified risks associated with the modifications). "To minimize electrical, mechanical, and radiation hazards, Siemens adheres to recognized and established industry practice and standards." |
| Compliance with Regulations | Compliance with all applicable regulatory standards and good manufacturing practices. | "Testing for verification and validation of the device was found acceptable to support the claims of substantial equivalence." (implied compliance with an overall regulatory framework). |
| New Features (CARE & FAST) | New features (CARE & FAST, single-click 3D reconstruction of Dual Energy Scans) operate as intended and safely. | The new software "supports ... CARE (Combined Application to Reduce Exposure) and FAST (Fully Assisted Scanner Technology), and single click 3D reconstruction of Dual Energy Scans." The overall verification/validation for the software covers these new features. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified in terms of patient data. The testing mentioned is "non clinical tests" and "phantom testing." This suggests that the "test set" primarily consisted of:
- Software test cases for verification and validation.
- Physical phantoms for image quality and performance assessment.
- Data Provenance: Not applicable in the context of clinical patient data for this submission. The tests are "non clinical" and involve "phantom testing" and internal "verification/validation." There's no mention of human subject data, country of origin, or retrospective/prospective clinical data for this specific 510(k) submission.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Not Applicable: This submission does not describe a clinical study requiring human expert assessment for ground truth. Verification and validation of CT system software and phantom performance typically rely on engineering specifications, physical measurements, and image quality metrics, not expert consensus on diagnostic interpretations of patient data.
4. Adjudication Method for the Test Set
- Not Applicable: Since there's no expert-based ground truth establishment described for patient data, no adjudication method would be presented.
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, not specified and highly unlikely for this type of submission. This 510(k) is for a software update to an existing CT scanner, not a novel AI-driven diagnostic aid that would typically require an MRMC study to demonstrate clinical improvement. The new features (CARE, FAST, single-click 3D) are enhancements to existing CT capabilities, not AI for diagnostic interpretation.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
- Not Applicable for a novel diagnostic algorithm. The "algorithm" here refers to the CT system's operating software for image acquisition, reconstruction, and basic post-processing. Its performance is always "standalone" in the sense that the system itself generates the images, but it's not a standalone diagnostic algorithm in the way a CAD system would be. The focus is on the system's ability to produce images according to specifications, not on its isolated diagnostic performance.
7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)
- Engineering Specifications and Physical Measurements: For the software, the "ground truth" is adherence to its predefined functional and performance specifications. For phantom testing, the "ground truth" would be expected physical measurements, known phantom properties, and established image quality metrics (e.g., spatial resolution, contrast-to-noise ratio, dose efficiency). There is no mention of expert consensus, pathology, or outcomes data, as those are typically relevant for diagnostic interpretation, which is not the focus of this particular 510(k) update.
8. The Sample Size for the Training Set
- Not Applicable: This is not a machine learning or AI algorithm in the contemporary sense that requires a "training set" of data. It's an update to the operating software of a CT scanner. The software would have been developed and tested through traditional software engineering methods.
9. How the Ground Truth for the Training Set Was Established
- Not Applicable: As there's no "training set" in the context of machine learning, there's no ground truth established for one. The "ground truth" for software development would be its design specifications and requirements.
§ 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.