K Number
K112989
Device Name
AQUILION CXL
Date Cleared
2012-04-10

(187 days)

Product Code
Regulation Number
892.1750
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Acquisition and display of axial x-ray images of the whole body to include the head.

Device Description

The Aquilion CXL is a whole body multi-slice helical CT System, consisting of a gantry, patient couch and console. The system generates up to 128 slices per rotation using a selectable slice-thickness multi-row detector. Additionally, the Aquilion CXL will utilize the new dose-reduction technologies adopted from Aquilion ONE (currently under FDA review), the system substantially reduces patient exposure dose and improves image quality.

AI/ML Overview
  1. Acceptance Criteria and Reported Device Performance:

The provided document does not explicitly state numerical acceptance criteria in a formal table or a direct comparison of the device's performance against such criteria. Instead, it relies on a statement of "substantial equivalence" to a predicate device and notes that "Testing was conducted utilizing phantoms and accepted image quality metrics. The results of this testing is contained in the user information for the device." This implies that the device's performance was deemed acceptable based on meeting standard image quality metrics in phantom studies, but the specific metrics and their target values are not detailed in this summary.

Therefore, a table cannot be constructed with specific numerical acceptance criteria and reported performance values based solely on the provided text.

  1. Sample Size Used for the Test Set and Data Provenance:

The document mentions that "Testing was conducted utilizing phantoms." This indicates that the "test set" consisted of phantoms, which are artificial objects used to simulate human tissue for imaging purposes. Consequently, there is no human patient data test set.

  • Sample Size for Test Set: Not applicable as real patient data was not used. Instead, phantoms were used for testing. The number or type of phantoms used is not specified.
  • Data Provenance: Not applicable as no human patient data was used.
  1. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:

Not applicable, as phantoms were used for testing, and image quality metrics from these phantoms would be objectively measured rather than requiring expert ground truth establishment in the traditional sense of clinical diagnosis.

  1. Adjudication Method for the Test Set:

Not applicable, as expert adjudication is not relevant for phantom-based image quality testing.

  1. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

No, an MRMC comparative effectiveness study was not done. The document states that "Testing was conducted utilizing phantoms and accepted image quality metrics." This type of testing is focused on the device's technical image quality, not its impact on human reader performance.

  1. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

Yes, a standalone performance assessment was conducted through "Testing... utilizing phantoms and accepted image quality metrics." This evaluated the device's inherent image quality capabilities (such as resolution, contrast, noise reduction) without human intervention in the diagnostic process.

  1. Type of Ground Truth Used:

For the phantom-based testing, the "ground truth" would be the known physical properties and internal structures of the phantoms, against which the reconstructed images' accuracy and quality metrics (e.g., spatial resolution, contrast-to-noise ratio, signal-to-noise ratio) were measured.

  1. Sample Size for the Training Set:

The document does not mention the use of a "training set" in the context of device performance evaluation. This device is a CT scanner, and typical performance evaluation for such devices involves physical and technical testing against established standards and metrics using phantoms, rather than AI model training on a dataset. The "Application of AIDR algorithm" is mentioned as a new feature, suggesting the use of an algorithm, but the document does not provide details about its development or training data.

  1. How the Ground Truth for the Training Set Was Established:

Not applicable, as a training set for an algorithm is not described or detailed in the provided information.

§ 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.