(51 days)
The uCT Computed Tomography X-ray System uCT 520/uCT 528 is a computed tomography X-ray system intended to produce cross-sectional images of the body by computer reconstruction of X-ray transmission data taken at different angles and planes and indicated for the whole body (including head, neck, vascular).
The uCT 520/uCT 528 is a multi-slice X-ray computed tomography scanner which features a continuously rotating tube-detector system and functions according to the fan beam principle. The system provides the filter back-projection (FBP) algorithm to reconstruct images in DICOM format, which can be used by post-processing applications.
The system consists of the Gantry, X-ray System, Data Management System, Patient Table, Console, Power Supply Cabinet, Image Processing Computer, and Software. The system software is a program used for patient management, data management, Xray scan control, image reconstruction, and image archive.
A motorized patient table moves the patient through a circular opening in the Gantry. As the patient passes through the Gantry, a source of x rays rotates around the inside of the circular opening. Detectors on the exit side of the patient record the X rays exiting the section of the patient's body being irradiated as an X-ray "snapshot". Many different "snapshots" (angles) are collected during one complete rotation. The data are sent to a computer to reconstruct all of the individual "snapshots" into a crosssectional image (slice) of the internal organs and tissues for each complete rotation of the source of x rays.
There are two key features of data processing for denoising and reduce metal artifact, which are KARL iterative denoising reconstruction algorithm and MAC Metal artifact correction algorithm.
The provided FDA 510(k) summary (K183143 for uCT 520, uCT 528) describes a computed tomography X-ray system. This submission does not contain information related to an AI/ML device or its performance criteria. The core of the document focuses on demonstrating substantial equivalence to a predicate CT device (uCT 530, uCT 550) based on hardware specifications, application features (some of which are algorithms like iterative noise reduction and metal artifact reduction, but not "AI" in the contemporary sense of machine learning for diagnostic interpretation), and conformance to various medical device standards.
Therefore, I cannot provide acceptance criteria and study details for an AI/ML device's performance as the input document does not pertain to such a device.
Here's an analysis based on the information provided, reinterpreting the request to align with the type of device discussed:
The document focuses on demonstrating substantial equivalence of the uCT 520/uCT 528 Computed Tomography X-ray System to a predicate device (uCT 530/uCT 550). The "acceptance criteria" discussed are primarily related to general CT system performance specifications and safety standards, rather than the diagnostic performance of an AI/ML algorithm.
Acceptance Criteria and Reported Device Performance (Non-AI/ML CT System)
| Criteria Category | Acceptance Criteria (Predicate) | Reported Device Performance (Proposed: uCT 520 / uCT 528) | Remarks |
|---|---|---|---|
| General/Regulatory | Product Code: JAK, Regulation No: 21 CFR 892.1750, Class: II, Intended Use: Same | Same | Same |
| Specifications - Core | Scan Regime: Continuous Rotation, Scan Modes: Scout, Axial, Helical, Detector Material: Solid-state GOS, Z-plane coverage: 22mm, Size of detector element in Z-plane: 0.55mm, Number of element per row: 864, Number of detector row: 40 | Same | Same |
| Specifications - Multi-slice | Maximum slices generated per rotation: 40 for uCT 530, 80 for uCT 550 | 80 for uCT 520, 80 for uCT 528 | Note 1: With a reconstruction process, 40 slices or 80 slices can be achieved from the 40 rows detector. Provides the smaller slice number in one rotation induces longer scanning time for CT imaging, which does not affect safety and effectiveness. (Though uCT 520 now matches uCT 550 at 80 slices). |
| Specifications - X-ray Tube | Tube anode storage capacity: 5.3MHU, Maximum cooling rate: 815 kHU/min | Tube anode storage capacity: 2MHU for uCT 520, 3.5MHU for uCT 528; Maximum cooling rate: 336 kHU/min for uCT 520, 395 kHU/min for uCT 528 | Note 2 & 3: Lower storage capacity and cooling rate affect continuous scan numbers/throughput but not individual scan safety/effectiveness. |
| Specifications - Focal Spot | Focal spot size: 0.5x1.0mm, 1.0x1.0mm | 0.7x0.8mm, 1.2x1.4mm | Note 4: Different focal spot sizes, but image spatial resolution is considered equivalent substantially. |
| Specifications - Power | Power: 50kW, mA Range: 10-420mA, kV Settings: 70, 80, 100, 120, 140 | Power: 42kW, mA Range: 10-350mA, kV Settings: 70, 80, 100, 120, 140 | Note 5 & 6: Lower power and mA output might induce higher possibility of photon starvation for high BMI objects, but safety was evaluated by testing. kV settings are the same. |
| Specifications - Rotation | Rotation speed: Up to 0.5 sec per 360° rotation | Up to 0.75 sec per 360° rotation | Note 7: Slower rotation speed induces longer scan time, but does not affect safety and effectiveness. |
| Specifications - Table/Gantry | Scannable range: 1700 mm, Horizontal motion range: 2180 mm, Vertical motion range: 480-950 mm | Scannable range: 1600 mm, Horizontal motion range: 1930 mm, Vertical motion range: 600-950 mm from the floor (Vertical speed: Up to 20 mm/sec vs 40 mm/sec predicate) | Note 8, 9, 10, 11: Differences in ranges and speeds affecting scan coverage, room size, and throughput, but not safety and effectiveness. |
| Image Performance | Image Spatial Resolution: High mode: >20 lp/cm @ MTF 0%, 16.5±1.7 lp/cm @ MTF10%, 11.5±1.2 lp/cm @ MTF50% | High mode: 19 lp/cm @ MTF 0%, 15.6±1.6 lp/cm @ MTF10%, 11.3±1.2 lp/cm @ MTF50% | Note 12: Proposed device has slightly lower spatial resolution (e.g., 0.32mm vs 0.30mm detectability @ MTF10%), but considered equivalent in visual assessment and does not affect safety/effectiveness. |
| Image Noise: 3.0±0.5 HU at 120 kV, 5 mm slice thickness, CTDIvol 28.9 | 3.0±0.5 HU at 120 kV, 5.5 mm slice thickness, CTDIvol 24.32 mGy (uCT 520) & 25.95 mGy (uCT 528) | Note 13: Image noise level considered substantially equivalent, even with slightly different CTDIvol values. | |
| Safety & Compliance | Electrical Safety: Comply with ES60601-1, EMC: Comply with IEC60601-1-2 | Comply with ES60601-1, Comply with IEC60601-1-2, conformity to other relevant medical electrical standards (e.g., IEC 60601-2-44, NEMA XR 25, 28, 29). Biocompatibility: Patient Contact Materials tested for cytotoxicity, irritation and sensitization (ISO 10993-5, 10). Software: Conformance to IEC 62304, NEMA PS 3.1-3.20 (DICOM), FDA guidances on software and cybersecurity. | Demonstrated conformance to listed standards for electrical safety, EMC, radiation protection, biocompatibility, and software development, including cybersecurity. This is the primary "proof" of meeting safety acceptance criteria. |
As this document describes a conventional CT scanner and not an AI/ML diagnostic device, the following points address what would be expected for an AI/ML device but are not present in the provided text.
Information NOT Available for an AI/ML Device:
- Sample sized used for the test set and the data provenance: Not applicable to a non-AI CT system's performance, which is validated through phantom and physical measurements, and clinical image evaluation for quality.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. For fundamental CT image quality, ground truth is often established by physical phantoms and expert human evaluation of image quality rather than diagnostic findings. The document mentions "Clinical Evaluation for sample clinical images evaluation," but provides no details on expert numbers or qualifications.
- Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable to the device type and testing described.
- 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: Not applicable, as this is not an AI-assisted reading device.
- If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device's "performance" is its ability to acquire and reconstruct images, not interpret them diagnostically without human input.
- The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the image quality itself, physical phantom measurements and subjective assessment of clinical images are used. For an AI/ML device, this would refer to the diagnostic truth.
- The sample size for the training set: Not applicable, as this is not an AI/ML device in the context of diagnostic interpretation.
- How the ground truth for the training set was established: Not applicable.
In summary, the provided submission (K183143) is for a conventional CT scanner, and its "acceptance criteria" are demonstrated through engineering specifications, conformance to international standards for safety and performance (e.g., NEMA, IEC), and internal non-clinical performance tests (dosimetry, image performance, AEC, MAC performance evaluation). No AI/ML components requiring diagnostic performance studies, expert ground truth, or human-in-the-loop evaluations are 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.