(53 days)
The DIGITAL RADIOGRAPHY CXDI-Elite / E1 provides digital image capture for conventional film/screen radiographic examinations. This device is intended to capture, for display, radiographic images of human anatomy, and to replace radiographic film/screen systems in all general purpose diagnostic procedures. This device is not intended for mammography applications.
The DIGITAL RADIOGRAPHY CXDI-Elite, also called the DIGITAL RADIOGRAPHY E1, (hereinafter referred to as CXDI-Elite) is a solid-state x-ray imager using TFT (thin-film transistor) arrays. The CXDI-Elite is a series of detectors, currently consisting of the CXDI-720C Wireless detector unit, also called the AR- E3543W detector. The detector intercepts x-ray photons, and the Cesium-Iodide scintillator emits visible spectrum photons that illuminate an array of photodetectors that create electrical signals. After the electrical signals are generated, the signals are converted to a digital image, and the images will be displayed on monitors. The digital image can be communicated to the operator console via a wired or wireless connection.
The monitors used with the CXDI-Elite are not a part of this submission.
The CXDI Control Software is updated from V2.16 to V3.10 in this submission. The update to the software includes bug fixes, modification to check-in function, modification to communication with X-ray emission devise, calibration support, addition of the Intelligent NR function (previously cleared under K212269), and the addition of Standard Synchronization Mode with Built in AEC Assistance.
The provided document K213780 is a 510(k) Pre-market Notification for a digital radiography device, the Canon DIGITAL RADIOGRAPHY CXDI-Elite / E1. This document establishes substantial equivalence to a predicate device, and as such, does not contain the detailed acceptance criteria for an AI/ML algorithm or the specific study that would prove the device meets such criteria.
The document makes a brief reference to an "Intelligent NR function (previously cleared under K212269)" in the section "Device Description," indicating that this specific function (likely an AI/ML noise reduction feature) has been previously cleared. However, the current 510(k) submission (K213780) is focused on the overall digital radiography system and its hardware/software updates, not specifically on the detailed performance of the "Intelligent NR function."
Therefore, based solely on the provided text, it is not possible to answer the requested questions about acceptance criteria and study details for an AI/ML device/algorithm, as this document does not provide that specific information.
To address the prompt, I will explain why the information cannot be extracted from this document:
- A table of acceptance criteria and the reported device performance: Not present. This document is for a general digital radiography system, not specifically an AI/ML diagnostic or assistive algorithm. The "Intelligent NR function" is briefly mentioned as having been "previously cleared," meaning its performance data and acceptance criteria would be in the K212269 submission, not this one.
- Sample sizes used for the test set and the data provenance: Not present. The document states "Clinical testing is not necessary for the current submission, based on the minor differences from the predicate device. Adequate detector bench testing should be sufficient to demonstrate that the subject detector CXDI-Elite / E1 works as intended." This indicates that the substantial equivalence was based on bench testing and comparisons with predicate devices, not a clinical test set with human subject data for an AI/ML algorithm.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not present, as no clinical test set for an AI/ML algorithm is described.
- Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present, as no clinical test set for an AI/ML algorithm is 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 present. The document explicitly states "Clinical testing is not necessary."
- If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not present. The focus is on the complete system and its hardware.
- The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not present, as no clinical test set for an AI/ML algorithm is described.
- The sample size for the training set: Not present.
- How the ground truth for the training set was established: Not present.
In summary, the provided document (K213780) is a 510(k) Pre-market Notification for a general digital radiography system. It establishes substantial equivalence based on hardware and software updates, and bench testing, not on clinical performance studies of an AI/ML algorithm. While an "Intelligent NR function" (likely an AI/ML feature) is mentioned as previously cleared, the details of its specific acceptance criteria and the study proving it meets those criteria are not included in this particular submission.
§ 892.1680 Stationary x-ray system.
(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. 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). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary 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.