Search Results

Vantage Fortian/Orian 1.5T systems are indicated for use as a diagnostic imaging modality that produces cross-sectional transaxial, coronal, sagittal, and oblique images that display anatomic structures of the head or body. Additionally, this system is capable of non-contrast enhanced imaging, such as MRA.

MRI (magnetic resonance imaging) images correspond to the spatial distribution of protons (hydrogen nuclei) that exhibit nuclear magnetic resonance (NMR). The NMR properties of body tissues and fluids are:

Proton density (PD) (also called hydrogen density)
Spin-lattice relaxation time (T1)
Spin-spin relaxation time (T2)
Flow dynamics
Chemical Shift

Depending on the region of interest, contrast agents may be used. When interpreted by a trained physician, these images yield information that can be useful in diagnosis.

Device Description

The Vantage Fortian (Model MRT-1550/WK, WM, WO, WQ)/Vantage Orian (Model MRT-1550/U3, U4, U7, U8) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. These Vantage Fortian/Orian models use 1.4 m short and 4.1 tons light weight magnet. They include the Canon Pianissimo™ Sigma and Pianissimo Zen technology (scan noise reduction technology). The design of the gradient coil and the whole-body coil of these Vantage Fortian/Orian models provide the maximum field of view of 55 x 55 x 50 cm and include the standard (STD) gradient system.

The Vantage Orian (Model MRT-1550/ UC, UD, UG, UH, UK, UL, UO, UP) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. The Vantage Orian models use 1.4 m short and 4.1 tons light weight magnet. They include the Canon Pianissimo™ and Pianissimo Zen technology (scan noise reduction technology). The design of the gradient coil and the whole-body coil of these Vantage Orian models provide the maximum field of view of 55 x 55 x 50 cm. The Model MRT-1550/ UC, UD, UG, UH, UK, UL, UO, UP includes the XGO gradient system.

This system is based upon the technology and materials of previously marketed Canon Medical Systems MRI systems and is intended to acquire and display cross-sectional transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body. The Vantage Fortian/Orian MRI System is comparable to the current 1.5T Vantage Fortian/Orian MRI System (K240238), cleared April 12, 2024, with the following modifications.

AI/ML Overview

Acceptance Criteria and Study for Canon Medical Systems Vantage Fortian/Orian 1.5T with AiCE Reconstruction Processing Unit for MR

This document outlines the acceptance criteria and the study conducted to demonstrate that the Canon Medical Systems Vantage Fortian/Orian 1.5T with AiCE Reconstruction Processing Unit for MR (V10.0) device meets these criteria, specifically focusing on the new features: 4D Flow, Zoom DWI, and PIQE.

The provided text focuses on the updates in V10.0 of the device, which primarily include software enhancements: 4D Flow, Zoom DWI, and an extended Precise IQ Engine (PIQE). The acceptance criteria and testing are described for these specific additions.

1. Table of Acceptance Criteria and Reported Device Performance

The general acceptance criterion for all new features appears to be demonstrating clinical acceptability and performance that is either equivalent to or better than conventional methods, maintaining image quality, and confirming intended functionality. Specific quantitative acceptance criteria are not explicitly detailed in the provided document beyond qualitative assessments and comparative statements.

Feature	Acceptance Criteria (Implied from testing)	Reported Device Performance
4D Flow	Velocity measurement with and without PIQE of a phantom should meet the acceptance criteria for known flow values. Images in volunteers should demonstrate velocity stream lines consistent with physiological flow.	The testing confirmed that the flow velocity of the 4DFlow sequence met the acceptance criteria. Images in volunteers demonstrated velocity stream lines.
Zoom DWI	Effective suppression of wraparound artifacts in the PE direction. Reduction of image distortion level when setting a smaller PE-FOV. Accurate measurement of ADC values.	Testing confirmed that Zoom DWI is effective for suppressing wraparound artifacts in the PE direction; setting a smaller PE-FOV in Zoom DWI scan can reduce the image distortion level; and the ADC values can be measured accurately.
PIQE (Bench Testing)	Generate higher in-plane matrix images from low matrix images. Mitigate ringing artifacts. Maintain similar or better contrast and SNR compared to standard clinical techniques. Achieve sharper edges.	Bench testing demonstrated that PIQE generates images with sharper edges while mitigating the smoothing and ringing effects and maintaining similar or better contrast and SNR compared to standard clinical techniques (zero-padding interpolation and typical clinical filters).
PIQE (Clinical Image Review)	Images reconstructed with PIQE should be scored clinically acceptable or better by radiologists/cardiologists across various categories (ringing, sharpness, SNR, overall image quality (IQ), and feature conspicuity). PIQE should generate higher spatial in-plane resolution images from lower resolution images (e.g., triple matrix dimensions, 9x factor). PIQE should contribute to ringing artifact reduction, denoising, and increased sharpness. PIQE should be able to accelerate scanning by reducing acquisition matrix while maintaining clinical matrix size and image quality. PIQE benefits should be obtainable on regular clinical protocols without requiring acquisition parameter adjustment. Reviewer agreement should be strong.	The resulting reconstructions were scored on average at, or above, clinically acceptable. Exhibiting a strong agreement at the "good" and "very good" level in the IQ metrics, the Reviewers' scoring confirmed all the specific criteria listed (higher spatial resolution, ringing reduction, denoising, sharpness, acceleration, and applicability to regular protocols).

2. Sample Size Used for the Test Set and Data Provenance

4D Flow & Zoom DWI: Evaluated utilizing phantom images and "representative volunteer images." Specific numbers for volunteers are not provided.
PIQE Clinical Image Review Study:
- Subjects: A total of 75 unique subjects.
- Scans: Comprising a total of 399 scans.
- Reconstructions: Each scan was reconstructed multiple ways with or without PIQE, totaling 1197 reconstructions for scoring.
- Data Provenance: Subjects were from two sites in USA and Japan. The study states that although the dataset includes subjects from outside the USA, the population is expected to be representative of the intended US population due to PIQE being an image post-processing algorithm that is not disease-specific and not dependent on factors like population variation or body habitus.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

PIQE Clinical Image Review Study:
- Number of Experts: 14 USA board-certified radiologists/cardiologists.
- Distribution: 3 experts per anatomy (Body, Breast, Cardiac, Musculoskeletal (MSK), and Neuro).
- Qualifications: "USA board-certified radiologists/cardiologists." Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set

PIQE Clinical Image Review Study: The study describes a randomized, blinded clinical image review study. Images reconstructed with either the conventional method or the new PIQE method were randomized and blinded to the reviewers. Reviewers scored the images independently using a modified 5-point Likert scale. Analytical methods used included Gwet's Agreement Coefficient for reviewer agreement and Generalized Estimating Equations (GEE) for differences between reconstruction techniques, implying a statistical assessment of agreement and comparison across reviewers rather than a simple consensus adjudication method (e.g., 2+1, 3+1).

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Yes, an MRMC comparative effectiveness study was done for PIQE.
Effect Size of Human Readers' Improvement with AI vs. Without AI Assistance: The document states that "the Reviewers' scoring confirmed that: (a) PIQE generates higher spatial in-plane resolution images from lower resolution images (with the ability to triple the matrix dimensions in both in-plane directions, i.e. a factor of 9x); (b) PIQE contributes to ringing artifact reduction, denoising and increased sharpness; (c) PIQE is able to accelerate scanning by reducing the acquisition matrix only, while maintaining clinical matrix size and image quality; and (d) PIQE benefits can be obtained on regular clinical protocols without requiring acquisition parameter adjustment."
- While it reports positive outcomes ("scored on average at, or above, clinically acceptable," "strong agreement at the 'good' and 'very good' level"), it does not provide a quantitative effect size (e.g., AUC difference, diagnostic accuracy improvement percentage) of how much human readers improve with AI (PIQE) assistance compared to without it. The focus is on the quality of PIQE-reconstructed images as perceived by experts, rather than the direct impact on diagnostic accuracy or reader performance metrics. It confirms that the performance is "similar or better" compared to conventional methods.

6. Standalone (Algorithm Only) Performance Study

Yes, standalone performance was conducted for PIQE and other features.
- 4D Flow and Zoom DWI: Evaluated using phantom images, which represents standalone, objective measurement of the algorithm's performance against known physical properties.
- PIQE: Bench testing was performed on typical clinical images to evaluate metrics like Edge Slope Width (sharpness), Ringing Variable Mean (ringing artifacts), Signal-to-Noise ratio (SNR), and Contrast Ratio. This is an algorithmic-only evaluation against predefined metrics, without direct human interpretation as part of the performance metric.

7. Type of Ground Truth Used

4D Flow & Zoom DWI:
- Phantom Studies: Known physical values (e.g., known flow values for velocity measurement, known distortion levels, known ADC values).
PIQE:
- Bench Testing: Quantitative imaging metrics derived from the images themselves (Edge Slope Width, Ringing Variable Mean, SNR, Contrast Ratio) are used to assess the impact of the algorithm. No external ground truth (like pathology) is explicitly mentioned here, as the focus is on image quality enhancement.
- Clinical Image Review Study: Expert consensus/opinion (modified 5-point Likert scale scores from 14 board-certified radiologists/cardiologists) was used as the ground truth for image quality, sharpness, ringing, SNR, and feature conspicuity, compared against images reconstructed with conventional methods. No pathology or outcomes data is mentioned as ground truth.

8. Sample Size for the Training Set

The document explicitly states that the 75 unique subjects used in the PIQE clinical image review study were "separate from the training data sets." However, it does not specify the sample size for the training set used for the PIQE deep learning model.

9. How the Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for the training set for PIQE was established. It only mentions that the study test data sets were separate from the training data sets.

Ask a Question

Ask a specific question about this device

Page 1 of 1