(129 days)
The system is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission projection data from the same axial plane taken at different angles. The system has the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, liver , kidney, pancreas, etc.. The system may acquire data using Axial, Cine, Helical, Cardiac , and Gated CT scan techniques from patients of all ages. These images may be obtained either with or without contrast. This device may include signal analysis and display equipment, patient and equipment supports, components and accessories.
This device may include data and image processing to produce images in a variety of transaxial and reformatted planes. Further, the images can be post processed to produce additional imaging planes or analysis results
The system is indicated for head, whole body, cardiac, and vascular X-ray Computed Tomography applications.
The device output is a valuable medical tool for the diagnosis of disease, trauma, or abnormality and for planning, guiding, and monitoring therapy.
The Revolution CT is a multi-slice (256 detector row) CT scanner consisting of a gantry, patient table, scanner desktop (operator console), system cabinet, power distribution unit (PDU), and interconnecting cables. The system includes image acquisition hardware, image acquisition and reconstruction software, and associated accessories.
The system generates images through the computer reconstruction of data acquired at different angles and planes of the rotating gantry. The gantry rotates at up to 0.28 seconds per rotation, and can acquire up to 512 slices of image data per rotation with a maximum total coverage of 160 mm in the z direction. The gantry however is designed to be able to rotate at 0.20 second per rotation. The system can be operated in Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisition modes.
The Revolution CT system is a powerful Volume High Definition CT scanner that is designed to provide best-in-class technologies for whole organ coverage, high image quality and responsible dose performance with the following characteristics:
- 160 mm detector coverage
- 140ms temporal resolution (0.28s rot. Speed) combined with intelligent motion correction with SnapShot Freeze for excellent cardiac imaging at any heart rate.
- 0.23 mm spatial resolution
- A wide bore (80-cm bore size) to image all patients allowing better patient positioning & access.
- The next-generation of iterative reconstruction technology, ASiR-V, designed to deliver ultra-low noise levels, improved low contrast detectability and may enable a reduction in dose for all clinical applications
Built upon the existing technologies the Revolution system is designed to use less radiation dose than the previous generation product while maintaining the same diagnostic level of image quality. Further, the fast speed of the scan could potentially reduce contrast volumes. The hardware platform is also capable of supporting Gemstone spectral imaging and 0.2s rotation speed.
Here's a breakdown of the acceptance criteria and study information for the GE Healthcare Revolution CT, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text for the GE Healthcare Revolution CT does not explicitly define quantitative acceptance criteria for specific performance metrics in a readily tabular format. Instead, it states that "The results of this clinical assessment demonstrate the acceptable diagnostic imaging performance of the GE Healthcare Revolution CT scanner." and that the device is "as safe and effective, and performs in a substantially equivalent manner to the predicate device Discovery CT750 HD".
However, the document does list key performance characteristics and areas of evaluation for both non-clinical and clinical testing, which implicitly serve as the basis for "acceptable performance."
| Acceptance Criteria (Implicit) | Reported Device Performance (Summary from submission) |
|---|---|
| Overall Diagnostic Imaging Performance | Demonstrated "acceptable diagnostic imaging performance" as evaluated by multiple qualified radiologists. |
| Image Quality (General) | Excellent image quality at full 160mm coverage. Evaluations included artifacts, scatter, spatial resolution, and low contrast detectability (LCD). |
| Whole Organ Coverage | Achieved with 160mm detector coverage, enabling imaging of whole organs like brain, heart, liver, kidney, pancreas. |
| Temporal Resolution (Cardiac Imaging) | 140ms temporal resolution (0.28s rot. Speed) combined with intelligent motion correction (SnapShot Freeze) for excellent cardiac imaging at any heart rate. |
| Spatial Resolution | 0.23 mm spatial resolution. |
| Dose Performance | Designed to use less radiation dose than the previous generation product while maintaining diagnostic image quality; ASiR-V technology designed to enable reduction in dose for all clinical applications. |
| Low Contrast Detectability (LCD) | Evaluated using a model observer study with the MITA LCD phantom. |
| CT Number Uniformity & Artifacts | Gemstone Clarity detector and 3D collimator minimize scatter artifacts, ensure HU uniformity, and reduce beam hardening artifacts. Volumetric High Definition (VHD) algorithm designed to reduce cone-beam artifacts and maintain CT number uniformity. |
| Scanning Modes | Supports Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisition modes. |
| Wide Bore Size | 80-cm bore size to image all patients, allowing better patient positioning & access. |
| Safety & Effectiveness | Determined to be "as safe and effective, and performs in a substantially equivalent manner to the predicate device." |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 49 subjects.
- Data Provenance:
- Country of Origin: United States.
- Retrospective or Prospective: Prospective. The text states, "Sample clinical data was collected from 49 subjects at one site in the US... Patients were selected for potential recruitment to meet these needs. Any patient who met these criteria stated in the Protocol and who voluntarily signed the Informed Consent Form was recruited."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not explicitly state that "ground truth" was established by experts in a specific, annotated sense. Instead, it describes a clinical assessment of image quality and diagnostic performance.
- Number of Experts: "multiple readers." A specific number is not provided.
- Qualifications of Experts: "qualified radiologists at different institutions in the United States of America." Further details on their years of experience or subspecialty are not provided.
4. Adjudication Method for the Test Set
The document describes the evaluation being done by "multiple readers" who are "qualified radiologists" using a "5 point Likert scale." It does not specify if there was a formal adjudication method (e.g., 2+1, 3+1 consensus process) for disagreeing interpretations among these readers or how their individual Likert scale ratings were combined or adjudicated to reach the overall conclusion of "acceptable diagnostic imaging performance." It simply states "The results of this clinical assessment demonstrate the acceptable diagnostic imaging performance."
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size
While "multiple readers" were involved in the clinical assessment, it was not a comparative effectiveness study pitting human readers with AI assistance versus without AI assistance. The study evaluated the Revolution CT scanner's performance (which incorporates advanced algorithms like ASiR-V and SnapShot Freeze as integral parts of its image reconstruction), but there is no mention of comparing human readers' performance with and without these specific AI-driven features as a standalone intervention. Therefore, no effect size of human readers improving with AI vs. without AI assistance is reported.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, in a sense. The document describes extensive Non-Clinical Testing where various mathematical, physics, and statistical analyses were performed using phantoms and clinical datasets to verify and substantiate performance specifications. This includes evaluation of temporal resolution, dose performance, and image quality metrics like artifacts, scatter, spatial resolution, and low contrast detectability (using a model observer study with the MITA LCD phantom). These evaluations assess the device's technical performance, including its algorithms, without direct human interpretation of clinical images for diagnosis.
7. The Type of Ground Truth Used
The concept of "ground truth" for the clinical study is implicitly the radiologists' assessment of the diagnostic quality and clinical acceptance of the images. It's a form of expert consensus/assessment of image quality and diagnostic utility, rather than comparison to a definitive, independent "ground truth" like pathology for specific disease detection. The radiologists evaluated images using a 5-point Likert scale for "clinical acceptance and image quality."
8. The Sample Size for the Training Set
The document does not provide a specific sample size for a "training set" for the Revolution CT's algorithms (like ASiR-V or VHD). It describes the algorithms as new technologies (e.g., "ASiR-V, the next generation of GE's ASiR iterative recon technology") and states they were "designed" to address specific challenges (e.g., "Volumetric High Definition (VHD) has been designed specifically to reduce cone-beam artifacts"). This suggests they are developed and refined through engineering, physics, and potentially extensive internal datasets, but the specific training set size is not disclosed in this 510(k) summary.
9. How the Ground Truth for the Training Set Was Established
Since a specific training set or its "ground truth" establishment isn't detailed in this summary, it can only be inferred:
- For reconstruction algorithms like ASiR-V and VHD, ground truth would typically involve physics-based simulations, phantom data (with known properties), and potentially large datasets of clinical images used for iterative refinement and validation of noise reduction, artifact suppression, and image quality metrics. This process would rely on engineering specifications, known physics of CT image formation, and expert review of image characteristics.
- The document states, "The software user interface has been redesigned to provide more simplified workflow and user experience," implying a focus on usability, which would involve user feedback and design principles rather than a traditional "ground truth" for a diagnostic algorithm.
In summary, the 510(k) focuses on demonstrating "substantial equivalence" to a predicate device through engineering verification, adherence to standards, and a clinical assessment of image quality and diagnostic acceptability by qualified radiologists, rather than a detailed breakdown of acceptance criteria and ground truth for individual AI/algorithmic components.
§ 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.