(139 days)
The Cios Spin is a mobile X-Ray system designed to provide X-ray imaging of the anatomical structures of patient during clinical applications. Clinical applications may include but are not limited to: interventional fluoroscopic, gastro- intestinal, endoscopic, urologic, pain management, orthopedic, neurologic, vascular, cardiac, critical care and emergency room procedures. The patient population may include pediatric patients.
The Cios Spin mobile fluoroscopic C-arm X-ray System designed for the surgical environment. The Cios Spin provides comprehensive image acquisition modes to support orthopedic and vascular procedures. The system consists of two major components:
a) The C-arm with X-ray source on one side and the flat panel detector on the opposite side. The c-arm can be angulated in both planes and be lifted vertically, shifted to the side and move forward/backward by an operator.
b) The second unit is the image display station with a moveable trolley for the image processing and storage system, image display and documentation. Both units are connected to each other with a cable.
This document describes the premarket notification (510(k)) for the Siemens Cios Spin X-ray system. The information provided is primarily focused on demonstrating substantial equivalence to predicate devices, rather than a standalone clinical study with detailed acceptance criteria for a new AI feature.
However, based on the provided text, we can infer acceptance criteria and the studies performed for specific features, particularly those listed under "New Software VA30 due to new functionality."
Summary of Device and Context:
The Cios Spin is a mobile fluoroscopic C-arm X-ray system for imaging anatomical structures during various clinical applications, including interventional, orthopedic, and neurological procedures. The 510(k) submission highlights several modifications and new software functionalities compared to its predicate device, the Cios Alpha.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria in a dedicated section for the new software features. Instead, it relies on comparative equivalence and verification/validation testing against established guidance and predicate device performance. For the detector, quantitative metrics are provided.
| Feature/Metric | Acceptance Criteria (Implied/Direct) | Reported Device Performance |
|---|---|---|
| General Device Safety & Effectiveness | - Compliance with 21 CFR Federal Performance Standards (1020.30, 1020.32, 1040.10). |
- Conformance to FDA Recognized Consensus Standards and Guidance Documents.
- Software specifications meet acceptance criteria.
- Risk analysis completed and controls implemented for identified hazards.
- Safe and effective for intended users, uses, and environments (through design control V&V). | - Complies with 21 CFR 1020.30, 1020.32.
- Certified to comply with AAMI ANSI ES60601-1:2005/(R)2012, IEC 60601-1-2:2014, IEC 60601-1-3:2013, IEC 60601-1-6:2010/A1:2013, IEC 60825-1:2014, IEC 62304:2015, IEC 60601-2-28:2010, IEC 60601-2-43:2017, IEC 60601-2-54:2009/A1:2015, ISO 14971:2007, IEC 62366-1:2015/Cor1:2016.
- Verification and validation testing found acceptable, supporting claims of substantial equivalence.
- All new software functions validated; worked as intended.
- Human Factor Usability Validation showed human factors addressed, with adequate training for employees.
- Cybersecurity statement provided, considering IEC 80001-1:2010. |
| New Software (e.g., Metal Artifact Reduction, Retina 3D, Screw Scout, Target Pointer, High Power 3D, Easy 3D) | - Does not raise any new issues of safety or effectiveness. - Works as intended (for new software functions). | - For Metal Artifact Reduction: The algorithm is unchanged from a previously cleared device (syngo Application Software VD20B, K170747). Improves image quality by reducing artifacts.
- For Retina 3D, Screw Scout, Target Pointer, Cios Open Apps: Non-clinical testing and Software Verification/Validation testing conducted and acceptable per Software Guidance document. Retina 3D has the same reconstruction algorithm as predicate ARTIS Pheno.
- For High Power 3D & Easy 3D: Does not raise any new issues of safety or effectiveness per Software Guidance. |
| CMOS Flat Panel Detector | - Equivalent image quality to a-Si technology detector. - Does not raise any new issues of safety or effectiveness.
- Compliance with "Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices" for performance metrics. | - DQE: 72% (vs. Predicate Cios Alpha 76%, Reference Ziehm Solo FD 70%)
- Dynamic Range: 96dB (vs. Predicate Cios Alpha 94dB, Reference Ziehm Solo FD Equivalent)
- MTF: 58% at 1 lp/mm (large) (vs. Predicate Cios Alpha 55% at 1 Lp/mm, Reference Ziehm Solo FD 4lp/mm)
- Digitization Depth: 16 bit (same as predicates/references)
- Pixel Pitch: 152 μm (vs. Predicate Cios Alpha 194μm, Reference Ziehm Solo FD 100 μm)
- Field of View: 30 cm x 30 cm; 20 cm x 20 cm |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify a "test set" in terms of patient data for evaluating the new software features. The testing mentioned is primarily non-clinical performance testing, software verification and validation (V&V), human factors usability validation, and engineering bench testing.
- Sample Size: Not applicable in the context of patient data for the new software features, as the testing described is primarily technical and comparative against existing standards and predicate devices. For the detector, the metrics (DQE, MTF, etc.) are derived from laboratory measurements, not patient data sets.
- Data Provenance: Not specified as patient data is not the primary focus for the equivalence argument. The testing was conducted by Siemens Healthcare GmbH Corporate Testing Laboratory (for conformance standards) and internally for software V&V. This implies internal company testing, likely in a controlled laboratory environment.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
Given that the testing is primarily non-clinical and focused on technical performance and software functionality, the concept of "ground truth established by experts" for a patient-based test set is not directly applicable in the way it would be for an AI diagnostic algorithm.
- Experts: The "experts" involved are implied to be the engineers and technical specialists responsible for conducting the non-clinical tests, software verification/validation, and human factors evaluations. The approval by the FDA also involves review by regulatory experts.
- Qualifications: While not explicitly stated, these would be Siemens' internal development and quality assurance teams, as well as external certification bodies for standards compliance.
4. Adjudication Method for the Test Set
Not applicable, as there is no mention of a patient-based test set requiring expert adjudication for ground truth.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done for the Cios Spin in this 510(k) submission. The submission focuses on demonstrating substantial equivalence through technological characteristics, non-clinical performance data, and software validation. It does not include an assessment of how human readers improve with or without AI assistance.
6. Standalone (Algorithm Only Without Human-In-The-Loop Performance) Study
The document does not describe a standalone performance study for the software features (e.g., Metal Artifact Reduction, Retina 3D, Screw Scout, Target Pointer) similar to what would be done for a diagnostic AI algorithm. Instead, it states that "All new software functions present in the Subject Device... have been validated through detailed software testing and it was founded they worked as intended." This implies internal functional and performance testing, but not a standalone clinical performance study typically associated with AI algorithms.
7. Type of Ground Truth Used
The "ground truth" for the various new features is established through:
- Engineering specifications and design requirements: For software functionality and hardware performance.
- Compliance with recognized industry standards: (e.g., IEC standards, FDA performance standards)
- Comparison to predicate devices and reference devices: For performance metrics (e.g., DQE, MTF for the detector), where "equivalent" or "comparable" performance serves as the ground truth.
- Expected "working as intended" functionality: For the new software features validated through detailed software testing.
There is no mention of pathology, expert consensus on patient cases, or outcomes data used to establish ground truth for the specific performance of these new features in a clinical setting.
8. Sample Size for the Training Set
Not applicable. The document describes a medical device (X-ray system) with new software features, not a machine learning model that requires a "training set" in the context of AI/ML development. The software validation is based on internal testing against specifications.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no "training set" as understood in machine learning. The "ground truth" for the software validation mentioned in the document is based on meeting pre-defined software specifications and functional requirements through verification and validation testing.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.