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, WQ)/Vantage Orian (Model MRT-1550/ A3, A4, A7, A8) 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 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 gradient system.

The Vantage Orian (Model MRT-1550/ UC, UG, UH, UK, UL, UO, UP, AK, AL, AO, AP, Upgrade only: A3, A4, A7, A8, AC, AD, AG, AH) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. The Vantage Orian models MRT-1550/ UC, UG, UH, UK, UL, UO, UP, Upgrade only: A3, A4, A7, A8 use 1.4 m short and 4.1 tons light weight magnet while the Vantage Orian models MRT-1550/ AK, AL, AO, AP, Upgrade only: AC, AD, AG, AH use 1.4 m short and 3.8 tons light weight magnet. All of the aforementioned models 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, AK, AL, AO, AP includes the XGO gradient system. The Model MRT-1550/ A3, A4, A7, A8, AC, AD, AG, AH include the standard 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 (K222968), cleared October 25, 2022, with the following modifications.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

This table focuses on the specific features detailed in the "Testing" section of the document, as these are the ones with explicit performance criteria and evaluation results.

Feature / Metric	Acceptance Criteria	Reported Device Performance
Exsper 3D (artifact reduction)	Reduction of artifacts caused by unfolding error compared to conventional SPEEDER.	Confirmed that Exsper 3D reduced artifacts caused by unfolding error compared to conventional SPEEDER.
Slice Shim (image quality for off-center slices)	Images with Slice Shim equal to or better than those with Standard Shim, especially for off-center slices.	Confirmed that images with the Slice Shim were equal to or better than those with the Standard Shim especially for off-center slices.
UTE (Ultra Short TE) CG Recon (image resolution & SNR when scan time is reduced)	Better maintenance of both image resolution and image SNR as compared to conventional grid recon when scan time is reduced.	Confirmed CG recon performs better at maintaining both image resolution and image SNR as compared to conventional grid recon when scan time is reduced.
Ringing Correction (ringing artifact reduction)	Reduction of ringing artifacts.	Confirmed Ringing Correction reduced ringing and met predetermined acceptance criteria.
Auto Scan Assist (time and steps for slice positioning)	Less time and fewer steps for slice positioning compared to slice positioning without Auto Scan Assist.	Confirmed the operation of slice positioning utilizing Auto Scan Assist applications (NeuroLine+, SUREVOI Liver, LiverLine+, and W-SpineLine+) resulted in less time and less steps as compared to slice positioning without Auto Scan Assist.
Ceiling Camera (patient orientation & anatomy position detection)	Successful patient orientation detection and cases requiring no correction for successful patient anatomy position detection met predetermined acceptance criteria AND less or comparable patient setting time compared to conventional manual patient setting.	Confirmed the percentage of successful patient orientation detection and cases requiring no correction for successful patient anatomy position detection met predetermined acceptance criteria. Additionally, testing confirmed the ceiling camera resulted in less or comparable patient setting time compared to conventional manual patient setting, regardless of the operator.
PIQE (Precise IQ Engine) - Bench Testing (in-plane matrix, ringing, sharpness, contrast, SNR)	Generates higher in-plane matrix from lower matrix images, contributes to ringing artifact reduction and increase of sharpness, sharper edges, mitigates smoothing and ringing effects, maintains similar or better contrast and SNR.	Confirmed PIQE generates higher in-plane matrix from lower matrix image, PIQE contributes to ringing artifact reduction and increase of sharpness. Comparisons to standard clinical techniques confirmed PIQE generates images with sharper edges while mitigating the smoothing and ringing effects and maintaining similar or better contrast and SNR.
PIQE (Precise IQ Engine) - Clinical Image Review (Likert score for various IQ metrics)	Scores of 3 or above (clinically acceptable) for ringing, sharpness, SNR, overall IQ, and feature conspicuity.	All resulting reconstructions (conventional and new) were scored at, or above, clinically acceptable by three board-certified Radiologists per anatomy. Reviewers exhibited strong agreement at "good" and "very good" level for all IQ metrics. Confirmed: (a) PIQE generates higher spatial in-plane resolution images (up to 3x matrix dimensions in both in-plane directions), (b) PIQE contributes to ringing artifact reduction, denoising and increased sharpness, (c) PIQE accelerates scanning by reducing acquisition matrix while maintaining clinical matrix size and image quality, (d) PIQE benefits obtained on regular clinical protocols.
NeuroLine+ (angular error for slice alignment)	Angular error for slice alignment similar or better as compared to the conventional method.	For the angular error, NeuroLine+ met the acceptance criteria being similar or better as compared to the conventional method.
NeuroLine+ (autopositioning success rate)	Successful scan alignment (offset and angle within acceptable error defined as typical inter-rater variability) greater than 80% of the time.	Yielded 97.5% success, which met the acceptance criteria.
Iterative Motion Correction (IMC) (reduction of motion artifacts)	Effective in reducing motion artifacts with metrics of peak SNR and structural similarity (SSIM).	Demonstrated that IMC is effective in reducing motion artifacts and met predetermined acceptance criteria.
IMC - Clinical Image Review (Likert score for IQ metrics)	Scores of 3 or greater (clinically acceptable) for SNR, tissue contrast, image sharpness, and diagnostic confidence.	Testing confirmed the IMC technique performs as expected, significantly reducing motion artifacts, and improving overall image quality metrics as evaluated via SNR, tissue contrast, image sharpness, and diagnostic confidence. IMC corrected images are the same as, or better than, images without IMC applied.
IMC - Clinical Image Review (diagnostic information)	Diagnostic information in IMC images the same or better than those without IMC applied.	A second clinical image review with patients having pathology and motion further confirmed the diagnostic information in IMC images was the same or better than those without IMC applied.
Free Breathing Dynamic DLR (arterial phase detection success rate)	Automatic arterial phase detection success rate greater than or equal to 80%.	Yielded 90.9% success (automatically proposed phases included the gold standard phase as manually selected by experienced radiologists), which met the acceptance criteria.
Free Breathing Dynamic DLR - Clinical Image Review (Likert score for diagnostic importance)	Average visual scores for overall SNR, overall IQ, feature conspicuity, and diagnostic confidence met acceptance criteria (3 or higher on a 5-point Likert scale).	The average of visual scores for overall SNR, overall IQ, feature conspicuity and diagnostic confidence met the acceptance criteria. The results support the conclusion that Free Breathing Dynamic is a clinically acceptable option for the acquisition of free-breathing contrast enhanced dynamic liver exams providing acceptable diagnostic confidence.

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

PIQE (Precise IQ Engine):
- Sample Size: 36 unique subjects (patients).
- Data Provenance: Two sites in France.
- Nature of Data: Clinical cases, prospectively collected for the study (scanned to provide test data sets separately from training data).
NeuroLine+:
- Sample Size: 15 clinical cases (4 male, 11 female).
- Data Provenance: France (implied from national identities, although not explicitly stated as collected in France).
- Nature of Data: Clinical images, newly collected, and entirely separate from the training group.
Iterative Motion Correction (IMC):
- Bench Testing: 12 clinical datasets (without subject motion and with mathematically simulated motion added). Data provenance not specified.
- Clinical Image Review (Phase 1): 18 volunteers. Data provenance not specified.
- Clinical Image Review (Phase 2): 49 image volumes from 15 typical clinical patients with pathology and motion. Data provenance not specified.
- Nature of Data:
  - Bench testing: Clinical datasets with simulated motion.
  - Clinical review (Phase 1): Volunteers imaged with and without motion.
  - Clinical review (Phase 2): Clinical patients with pathology and motion.
  - All testing data acquired separately and independently from training data.
Free Breathing Dynamic DLR:
- Arterial Phase Detection: 11 clinical cases (5 male, 5 female, 1 unknown).
- Clinical Image Review: 29 contrast-enhanced Free Breathing Dynamic liver studies from 29 patients (14 male, 14 female, 1 unknown).
- Data Provenance: France and USA for arterial phase detection; United States, France, and Japan for clinical image review.
- Nature of Data:
  - Arterial phase detection: Clinical images from patients receiving clinically indicated contrast.
  - Clinical image review: Contrast-enhanced Free Breathing Dynamic liver studies.
  - All testing data acquired separately and independently from training data.
Exsper 3D, Slice Shim, UTE CG Recon, Ringing Correction, Auto Scan Assist, Ceiling Camera:
- The text states "phantom images" or "clinical images" were used, but specific sample sizes and data provenance for these components (beyond PIQE, NeuroLine+, IMC, and Free Breathing Dynamic DLR, which are highlighted deeper) are not detailed.

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

PIQE (Precise IQ Engine):
- Number of Experts: 6 radiologists (3 per anatomy - brain and knee).
- Qualifications: USA board certified radiologists.
NeuroLine+:
- Number of Experts: 2.
- Qualifications: Experienced ARRT licensed MR technologists (for manual annotation of target planes).
Iterative Motion Correction (IMC):
- Number of Experts: 3.
- Qualifications: US board certified radiologists, specializing in neuro imaging.
Free Breathing Dynamic DLR:
- Arterial Phase Detection: "Experienced radiologists" (number not specified for ground truth selection).
- Clinical Image Review: 2 US board certified radiologists.

4. Adjudication Method for the Test Set

PIQE (Precise IQ Engine): Randomized, blinded to the reviewers. Scored by 3 reviewers per anatomy. The text implies a consensus or averaging approach for reaching conclusions, as it states "all scored at, or above, clinically acceptable by three board-certified Radiologists per anatomy" and "reviewers exhibited a strong agreement".
NeuroLine+: Manual annotation by two experienced ARRT licensed MR technologists. The text implies their annotations served as the reference for accuracy, but does not detail an adjudication process if disagreements occurred.
Iterative Motion Correction (IMC): Randomized and blinded review by 3 US board certified radiologists.
Free Breathing Dynamic DLR:
- Arterial Phase Detection: "Gold standard phase as manually selected by experienced radiologists." (Implies expert consensus or selection, but not specific adjudication).
- Clinical Image Review: 2 US board certified radiologists read and scored the images. The conclusion is based on the "average of visual scores."

5. 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.

Yes, MRMC studies were done for PIQE, IMC, and Free Breathing Dynamic DLR.
- These studies involved multiple readers assessing multiple cases, and comparing images processed with the new AI/DL features (PIQE, IMC, Free Breathing Dynamic DLR) against conventional methods or images without the feature applied.
- **However, these studies were designed as a comparison of image quality from the new AI-enhanced reconstruction/correction methods versus conventional methods, not a comparative effectiveness study measuring human reader improvement with AI assistance vs. without AI assistance (i.e., human-in-the-loop performance). The radiologists were evaluating the reconstructed images themselves, not their diagnostic performance with and without AI tools integrated into their workflow.
- Effect Size: The document does not provide a quantitative effect size in terms of how much human readers improve with AI assistance. Instead, it reports on the quality of the AI-processed images relative to conventional images, often concluding that the AI-processed images are "same or better," "meet acceptance criteria" for clinical acceptability (e.g., Likert scores), or provide "significant reduction" in artifacts.
  - PIQE: "Confirmed PIQE generates higher spatial in-plane resolution images...contributes to ringing artifact reduction, denoising and increased sharpness... is able to accelerate scanning by reducing the acquisition matrix only, while maintaining clinical matrix size and image quality."
  - IMC: "Significantly reducing motion artifacts, and improving overall image quality metrics... IMC corrected images are the same as, or better than, images without IMC applied."
  - Free Breathing Dynamic DLR: "Providing acceptable diagnostic confidence."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

Yes, standalone performance was evaluated for several features, primarily through bench testing and quantitative metrics.
- Exsper 3D: Evaluated using phantom images, confirmed artifact reduction compared to conventional method.
- Slice Shim: Evaluated using clinical images, confirmed image quality equal to or better than standard shim.
- UTE CG Recon: Evaluated using phantom and clinical images, confirmed better maintenance of resolution and SNR.
- Ringing Correction: Evaluated using phantom and clinical images, confirmed ringing reduction.
- PIQE: Underwent performance (bench testing) using ACR phantom images and typical clinical images (brain and knee). Metrics included SNR, signal intensity profiles for ringing and sharpness, Edge Slope Width, Ringing Variable Mean, Signal-to-Noise ratio, and Contrast Change Ratio. This is a clear standalone evaluation of the algorithm's output metrics.
- NeuroLine+: Underwent performance (bench) testing using clinical images. Autopositioning success rate was evaluated against manually annotated ground truth. This is a standalone evaluation of the algorithm's accuracy.
- Iterative Motion Correction (IMC): Underwent performance (bench testing) using clinical datasets with simulated motion. Metrics of peak SNR and structural similarity (SSIM) were used. This is a standalone evaluation of the algorithm's effectiveness.
- Free Breathing Dynamic DLR (Arterial Phase Detection): Underwent performance (bench) testing using clinical images, assessing the success rate of the automatic detection against manually selected gold standard phases. This is a standalone evaluation of the algorithm's accuracy.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

Expert Consensus/Annotation:
- PIQE: Clinically relevant categories (ringing, sharpness, SNR, overall IQ, feature conspicuity) scored by board-certified radiologists on a Likert scale, with >=3 considered clinically acceptable.
- NeuroLine+: Manual annotation of angle and position of target planes by experienced ARRT licensed MR technologists.
- IMC: SNR, tissue contrast, image sharpness, and diagnostic confidence scored by board-certified radiologists on a Likert scale.
- Free Breathing Dynamic DLR:
  - Arterial phase detection: "Gold standard phase as manually selected by experienced radiologists."
  - Clinical image review: Overall SNR, overall IQ, feature conspicuity, and diagnostic confidence scored by board-certified radiologists on a Likert scale.
Quantitative/Objective Metrics:
- Exsper 3D: Artifact reduction compared to conventional method.
- Slice Shim: Image quality comparison to standard shim.
- UTE CG Recon: Maintenance of image resolution and SNR.
- Ringing Correction: Reduction of ringing.
- PIQE (bench): SNR, signal intensity profiles for ringing and sharpness, Edge Slope Width, Ringing Variable Mean, Signal-to-Noise ratio, Contrast Change Ratio.
- NeuroLine+ (bench): Angular error and autopositioning success rate (comparison to manual annotations).
- IMC (bench): Peak SNR and structural similarity (SSIM).
- Ceiling Camera: Percentage of successful patient orientation detection and cases requiring no correction.
Pathology/Outcomes Data: Not explicitly mentioned as a direct ground truth for the performance evaluation of these specific software features. The IMC study did use clinical patients with pathology, but the evaluation was still based on image quality and diagnostic information as assessed by radiologists, not a direct comparison to pathology reports or long-term outcomes.

8. The sample size for the training set

The document consistently states for PIQE, NeuroLine+, IMC, and Free Breathing Dynamic DLR that "All testing data were acquired separately and independently from the training data after the machine learning training was completed."
However, the specific sample sizes for the training datasets themselves are not provided in this document.

9. How the ground truth for the training set was established

Again, the document states that training data was used, particularly for features utilizing Deep Learning (e.g., PIQE, IMC, Free Breathing Dynamic DLR, NeuroLine+ via Machine Learning).
However, the document does not detail how the ground truth for these training sets was established. It only clarifies that the test data was independent of the training data.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

April 12, 2024

Canon Medical Systems Corporation % Orlando Tadeo Senior Manager, Regulatory Affairs Canon Medical Systems, USA 2441 Michelle Drive Tustin, California 92780

Re: K240238

Trade/Device Name: Vantage Fortian/Orian 1.5T, MRT-1550, V9.0 with AiCE Reconstruction Processing Unit for MR Regulation Number: 21 CFR 892.1000 Regulation Name: Magnetic resonance diagnostic device Regulatory Class: Class II Product Code: LNH Dated: January 29, 2024 Received: January 29, 2024

Dear Orlando Tadeo:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

{1}------------------------------------------------

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

{2}------------------------------------------------

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

D. Ray Kennedy

Daniel M. Krainak, Ph.D. Assistant Director DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Ouality Center for Devices and Radiological Health

Enclosure

{3}------------------------------------------------

Indications for Use

510(k) Number (if known) K240238

Device Name

Vantage Fortian/Orian 1.5T. MRT-1550, V9.0 with AiCE Reconstruction Processing Unit for MR

Indications for Use (Describe)

·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.

Type of Use (Select one or both, as applicable)
☒ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{4}------------------------------------------------

510(k) SUMMARY

This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of Safe Medical Device Act 1990 and 21 CFR § 807.92.

1. CLASSIFICATION and DEVICE NAME

Classification Name:	Magnetic Resonance Diagnostic Device
Regulation Number:	90-LNH (Per 21 CFR § 892.1000)
Trade Proprietary Name:	Vantage Fortian / Orian 1.5T, MRT-1550, V9.0 with AiCEReconstruction Processing Unit for MR
Model Number:	MRT-1550

2. SUBMITTER'S NAME

Canon Medical Systems Corporation 1385 Shimoishigami Otawara-Shi, Tochigi-ken, Japan 324-8550

3. OFFICIAL CORRESPONDENT

Naofumi Watanabe Senior Manager, Regulatory Affairs and Vigilance Canon Medical Systems Corporation

4. CONTACT PERSON, U.S. AGENT and ADDRESS

Contact Person

Janine Reyes Manager, Regulatory Affairs Canon Medical Systems USA, Inc. 2441 Michelle Drive, Tustin, CA 92780 Phone: (714) 669-7853 Fax: (714) 730-1310 E-mail: jfreyes@us.medical.canon

Official Correspondent/U.S. Agent

Paul Biggins Senior Director, Regulatory Affairs Canon Medical Systems USA, Inc. 2441 Michelle Drive, Tustin, CA 92780 Phone: (714) 730-7808 Fax: (714) 730-1310 E-mail: pbiggins@us.medical.canon

{5}------------------------------------------------

1. MANUFACTURING SITE Canon Medical Systems Corporation 1385 Shimoishigami Otawara-shi, Tochigi 324-8550, Japan
1. ESTABLISHMENT REGISTRATION 9614698
1. DATE PREPARED January 29, 2024

8. DEVICE NAME

Vantage Fortian/Orian 1.5T, MRT-1550, V9.0 with AiCE Reconstruction Processing Unit for MR

9. TRADE NAME

Vantage Fortian/Orian 1.5T, MRT-1550, V9.0 with AiCE Reconstruction Processing Unit for MR

10. CLASSIFICATION NAME

Magnetic Resonance Diagnostic Device (MRDD)

11. CLASSIFICATION PANEL

Radiology

12. DEVICE CLASSIFICATION

Class II (per 21 CFR 892.1000, Magnetic Resonance Diagnostic Device)

13. PRODUCT CODE

90-LNH

14. PREDICATE DEVICE

Predicate Device: Vantage Fortian/Orian 1.5T, MRT-1550, V8.0 with AiCE Reconstruction Processing Unit for MR (K222968)

Reference Device: Vantage Galan 3T, MRT-3020, V9.0 with AiCE Reconstruction Processing Unit for MR (K230355)

	Predicate Device	Reference Device
System	Vantage Fortian/Orian 1.5T, MRT-1550, V8.0 withAiCE Reconstruction Processing Unit for MR	Vantage Galan 3T, MRT-1550, V9.0 with AiCEReconstruction Processing Unit for MR
Marketed By	Canon Medical Systems USA, Inc.	Canon Medical Systems USA, Inc.
510(k) Number	K222968	K230355
Clearance Date	October 25, 2022	August 30, 2023

15. REASON FOR SUBMISSION

Modification of a cleared device

16. SUBMISSION TYPE

Traditional 510(k) Premarket Notification

{6}------------------------------------------------

Image /page/6/Picture/0 description: The image shows the logo for Canon Medical Systems USA, INC. The word "Canon" is in red, and the rest of the text is in black. The text is left-aligned and the font is sans-serif. The logo is simple and professional.

17. DEVICE DESCRIPTION

18. SUMMARY OF CHANGE(S)

This submission is to report the following changes:

Summary of Software Changes:

. Exsper: Exsper has been updated to support 3D encoding sequences. FASE2D/3D, FE3D, FFE2D/3D, and SSFP2D/3D have been also supported.
. Slice shimming: When performing the multi-slice image acquisition, parameters for magnetic field homogeneity are corrected per slice.
. Iterative Motion Correction (IMC): IMC has been updated to utilize Deep Learning based methods in addition to traditional model-based methods.
. Free Breathing Dynamic: Free Breathing Dynamic is contrast enhanced dynamic imaging technique. Utilizing Deep Learning reconstruction, Free Breathing Dynamic enables a single continuous scan to aid patients who have difficulty holding their breath.
. UTE imaging: UTE imaging has been updated to support CG-Recon to reduce the scan time while maintaining resolution and SNR.
Precise IQ Engine (PIQE): PIQE is Deep Learning based technique that generates higher inplane matrix images from low matrix images while mitigating the ringing artifact. PIQE is targeted for brain and knee regions.
. Auto Protocol Brain Application: Auto Protocol Brain Application allows to automatically proceed with examination according to a pre-defined scenario.

{7}------------------------------------------------

ICAL SYSTEMS USA, INC.

Made For life

Auto Consult Brain Package: Auto Consult performs the examinations for brain region all the ● way from patient setting down to the scan and check.
NeuroLine+: NeuroLine+ has been updated to utilize Machine Learning based method.
. Auto Scan Assist: Auto Scan Assist takes away the variability and helps operators improve workflow with automatic slice alignment, standardizing workflow with automatic positioning. Planning of re-scan which is based on the result of image analysis are also available.
Ringing correction: Ringing Correction detects areas in the image that contain truncation artifacts and then reduces or eliminates the artifacts by applying minute subpixel shifting to the pixels in those areas of the image. Ringing correction is targeted for head imaging.

Summary of Accessory Changes:

. Tablet UX: Tablet UX has been updated so that display movie from patient camera can be displayed on tablet, voice communication with a patient to be available and scan control to be possible.
10GbE High-speed reconstruction kit: This kit increases the communication speed of the AiCE reconstruction processing unit for MR.
. Ceiling camera: Position calculation method for some body regions have been updated.

Item	Subject Device:Vantage Fortian/Orian 1.5T,MRT-1550, V9.0with AiCE ReconstructionProcessing Unit for MR	Predicate Device:Vantage Fortian/Orian 1.5T,MRT-1550, V8.0with AiCE ReconstructionProcessing Unit for MR	Notes
Static field strength	1.5T	1.5T	Same
Operational Modes	Normal and 1st Operating Mode	Normal and 1st Operating Mode	Same
i. Safety parameterdisplay	SAR, dB/dt	SAR, dB/dt	Same
ii. Operating mode access requirements	Allows screen access to 1st level operating mode	Allows screen access to 1st level operating mode	Same
Maximum SAR	4W/kg for whole body (1stoperating mode specified in IEC60601-2-33:2010+A1:2013+A2:2015)	4W/kg for whole body (1stoperating mode specified in IEC60601-2-33:2010+A1:2013+A2:2015)	Same
Maximum dB/dt	1st operating mode specified in IEC60601-2-33:2010+A1:2013+A2:2015	1st operating mode specified in IEC60601-2-33:2010+A1:2013+A2:2015	Same
Potential emergencycondition and meansprovided for shutdown	Shutdown by Emergency RampDown Unit for collision hazard forferromagnetic objects	Shutdown by Emergency RampDown Unit for collision hazard forferromagnetic objects	Same

19. SAFETY PARAMETERS

20. IMAGING PERFORMANCE PARAMETERS

No change from the previous predicate submission, K222968.

{8}------------------------------------------------

21. INDICATIONS FOR USE

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.

22. SUMMARY OF DESIGN CONTROL ACTIVITIES

Risk Management activities for this modification are included in this submission. The test methods used are the same as those submitted in the previously cleared submission of the predicate device, Vantage Fortian/Orian 1.5T, MRT-1550, V8.0 with AiCE Reconstruction Processing Unit for MR (K222968). A declaration of conformity with design controls is included in this submission.

23. SAFETY

This device is designed and manufactured under the Quality System Regulations as outlined in 21 CFR § 820 and ISO 13485 Standards.

This device is based upon the same technologies, materials and software as the predicate device. Risk activities were conducted in concurrence with established medical device development standards and guidance. Additionally, testing was done in accordance with applicable recognized consensus standards published by the International Electrotechnical Commission (IEC) for medical devices and the National Electrical Manufacturers Association (NEMA):

LIST OF APPLICABLE STANDARDS

ANSI AAMI ES60601-1:2005/(R)2012 ● and A1:2012, C1:2009/(R)2012 and A2:2010/(R)2012 (Cons. Text) [Incl. AMD2:2021]
IEC60601-1:2005, A1:2012, A2:2020 ●
. IEC60601-1-2:2014+A1:2020
IEC60601-1-6 (2010), Amd.1 (2013), Amd.2 (2020)
IEC60601-2-33 (2010), Amd.1 (2013), Amd.2 (2015)
IEC60825-1 (2007, 2014) ●
IEC62304 (2006), Amd.1 (2015) ●
IEC62366-1 (2020)
ISO 10993-1 (2018) ●
NEMA MS 1:2008 (R2020)
NEMA MS 2:2008 (R2020) ●
NEMA MS 3:2008 (R2020) ●
NEMA MS 4 (2010)
NEMA MS 5 (2010, 2018) ●

{9}------------------------------------------------

24. TESTING

Risk analysis and verification/validation testing conducted through bench testing are included in this submission which demonstrate that the system requirements have been met. Additionally, image quality testing was completed which demonstrated that the subject device meets predetermined acceptance criteria.

Exsper 3D was evaluated utilizing phantom images. Testing confirmed that Exsper 3D reduced artifacts caused by unfolding error compared to conventional SPEEDER.

Slice Shim was evaluated using clinical images. Testing confirmed that images with the Slice Shim were equal to or better than those with the Standard Shim especially for off-center slices.

UTE (Ultra Short TE) CG Recon was evaluated utilizing both phantom and clinical images. Testing confirmed CG recon performs better at maintaining both image resolution and image SNR as compared to conventional grid recon when scan time is reduced.

Ringing Correction was evaluated utilizing both phantom and clinical images. Testing confirmed Ringing Correction reduced ringing and met predetermined acceptance criteria.

Auto Scan Assist was evaluated utilizing clinical images. Testing confirmed the operation of slice positioning utilizing Auto Scan Assist applications NeuroLine+, SUREVOI Liver, LiverLine+, and W-SpineLine+ resulted in less time and less steps as compared to slice positioning without Auto Scan Assist.

Ceiling Camera patient orientation and patient anatomy position detection method was evaluated using clinical images. Testing confirmed the percentage of successful patient orientation detection and cases requiring no correction for successful patient anatomy position detection met predetermined acceptance criteria. Additionally, testing confirmed the ceiling camera resulted in less or comparable patient setting time compared to conventional manual patient setting, regardless of the operator.

PIQE (Precise IQ Engine) for MR underwent performance (bench testing) using ACR phantom images. Using metrics of SNR and signal intensity profiles for ringing and sharpness, testing confirmed PIQE generates higher in-plane matrix from lower matrix image and PIQE contributes to ringing artifact reduction and increase of sharpness. The bench testing also included evaluation in typical clinical images of brain and knee, the metrics of Edge Slope Width (to evaluate image sharpness), Ringing Variable Mean (to evaluate ringing artifacts), Signal-to-Noise ratio, and Contrast Change Ratio. Comparing images with PIQE at various scaling factors to standard clinical techniques such as zeropadding interpolation and GA filter, confirmed that PIQE generates images with sharper edges while mitigating the smoothing and ringing effects and maintaining similar or better contrast and SNR.

Additionally, a randomized, blinical image review study was conducted with 6 USA board certified radiologists (3 per anatomy). Using the conventional method (i.e., matrix expansion with Fine Reconstruction and processing with GA Filter) as a reference, the images reconstructed with either the conventional method or the new method PIQE were randomized, blinded to the reviewers, and scored by the 3 reviewers per anatomy in various clinically-relevant categories (including ringing, sharpness, SNR, overall IQ, and feature conspicuity) using a modified 5-point Likert scale, where 3 or above is considered clinically acceptable. A total of 36 unique subjects, from two sites in France, were scanned in

{10}------------------------------------------------

brain or knee to provide the test data sets separately from the training data sets using Vantage Orian or Fortian 1.5T and anatomy-appropriate coils, comprising a total of 252 scans (neuro and knee), in multiple orientations (axial, sagittal and coronal), and multiple contrast weightings (T1-/T2-/PDweighted with/without Fat saturation) within the FSE2D family of pulse sequences. The resulting reconstructions (conventional and new) were all scored at, or above, clinically acceptable by three board-certified Radiologists per anatomy. The reviewers exhibited a strong agreement at the "good" and "very good" level for all IQ metrics such as SNR, image sharpness, image ringing, overall IQ and feature conspicuity. In conclusion, Testing confirmed (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, (d) PIQE benefits can be obtained on regular clinical protocols without requiring acquisition parameter adjustment.

NeuroLine+ underwent performance (bench) testing using clinical images. Testing of NeuroLine+ was conducted with an independent group of patients, newly collected, and entirely separate from the training group. The data, comprising 15 clinical cases (4 male, 11 female, height = 166±7, weight = 73±17, BMI = 27±6, Age = 52±21, national identities include France), were acquired with the typical localizer imaging condition of Fast Field Echo 3D sequence (TR/TE = 3.7/1.3 [ms], Matrix = 128 x 128 x 128 x 128, Spatial resolution = 2.5 [mm] isotropic) on the Vantage Orian 1.5T System. The acceptance criterion was a successful scan alignment (i.e., offset and angle within acceptable error defined as typical inter-rater variability) greater than 80% of the time. To assess the accuracy of the auto-detected angle or center position of the target planes, the angle and position of the target planes were manually annotated by two experienced ARRT licensed MR technologists. For the angular error, NeuroLine+ met the acceptance criteria being similar or better as compared to the conventional method. For the autopositioning, NeuroLine+ vielded 97.5% success which met the acceptance criteria. The results support the conclusion that NeuroLine+ is a clinically acceptable option for the slice-alignment procedure in head examination.

lterative Motion Correction (IMC) underwent performance (bench testing) using clinical datasets (12) without subject motion and with mathematically simulated motion added. Using the metrics of peak SNR and structural similarity (SSIM), testing demonstrated that IMC is effective in reducing motion artifacts and met predetermined acceptance criteria.

With scanning protocols typically employed clinically for brain and cervical spine, 18 volunteers were imaged at 1.5T in the head and neck coil with various orientations and weightings using the FSE 2D family of sequences. Two acquisitions of each image type and orientation were acquired, one with subject motionless, the other with subject moving as instructed. From the two acquisitions, three reconstructions were performed. The motion free acquisition was reconstructed using typical clinical routine, and the image acquired during the subject motion was reconstructed in two ways: once without IMC applied and again with IMC applied. In total, there were 300 image volumes (100 per group). The image review using the randomized and blinded 300 image volumes was performed. Three US board certified radiologists, specializing in neuro imaging, read and scored the images in various clinically relevant categories (such as SNR, tissue contrast, image sharpness, and diagnostic confidence) based on a pre-determined 5-point modified Likert scale, where a value of 3 or greater was considered clinically acceptable. Testing confirmed the IMC technique performs as expected, significantly reducing

{11}------------------------------------------------

Image /page/11/Picture/0 description: The image shows the logo for Canon Medical Systems USA, INC. The word "Canon" is in red, and the rest of the text is in black. The text is aligned to the left.

Made For life

motion artifacts, and improving overall image quality metrics as evaluated via SNR, tissue contrast, image sharpness, and diagnostic confidence. IMC corrected images are the same as, or better than, images without IMC applied.

Another clinical image review was performed by the three US board certified radiologists using an additional 49 image volumes in brain or cervical spine acquired, at 1.5T, from 15 typical clinical patients with pathology and motion. This study further confirmed the diagnostic information in IMC images was the same or better than those without IMC applied. All testing data were acquired separately and independently from the training data after the machine learning training was completed.

Free Breathing Dynamic DLR. The automatic arterial phase detection feature of Free Breathing Dynamic DLR underwent performance (bench) testing using clinical images from patients receiving clinically indicated contrast. Firstly, testing of the arterial phase detection was conducted with 11 clinical cases (5 male, 5 female, 1 unknown, age = 61±11, height = 173±13 years, weight = 78±15 kg, BMI = 26±4, national identities include France and USA), and yielded 90.9% success (i.e., the automatically proposed phases included the gold standard phase as manually selected by experienced radiologists) which met the acceptance criteria (greater than or equal to 80%). Additionally, a clinical image review was conducted with 2 US board certified radiologists who read and scored a total of 29 (14 male, 14 female, 1 unknown, age = 63±12, national identities include United States, France and Japan) contrast enhanced Free Breathing Dynamic liver studies (50 slices per study, repeated for 23 dynamic phases) acquired using either Galan 3T or Orian 1.5T scanner. Based on a modified 5-point Likert scale in categories of diagnostic importance, a score of 3 or higher was considered clinically acceptable. The average of visual scores for overall SNR, overall IQ, feature conspicuity and diagnostic confidence met the acceptance criteria. All testing data were acquired separately and independently from the training data after the machine learning training was completed. The results support the conclusion that Free Breathing Dynamic is a clinically acceptable option for the acquisition of free-breathing contrast enhanced dynamic liver exams providing acceptable diagnostic confidence.

Software Documentation for a Basic Documentation Level, per the FDA guidance document, "Content of Premarket Submissions for Device Software Functions" issued on June 14, 2023, is included in this submission. This documentation includes justification for the Basic Documentation Level determination as well as testing which demonstrates that the verification requirements have been met.

Cybersecurity documentation, per the FDA cybersecurity premarket guidance document "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" issued on September 27, 2023, is also included as part of this submission.

25. SUBSTANTIAL EQUIVALENCE

Canon Medical Systems Corporation believes that the Vantage Fortian/Orian 1.5T, MRT-1550, V9.0, Magnetic Resonance Imaging (MRI) System with AiCE Reconstruction Processing Unit for MR, is substantially equivalent to the previously cleared predicate device referenced in this submission.

Canon Medical Systems Corporation believes that the changes incorporated into the Vantage Fortian/Orian 1.5T, MRT-1550, V9.0, Magnetic Resonance Imaging (MRI) System with AiCE Reconstruction Processing Unit for MR, are substantially equivalent to the previously cleared predicate device.

{12}------------------------------------------------

Made For life

26. CONCLUSION

The modifications incorporated into the Vantage Fortian/Orian 1.5T, MRT-1550, V9.0, Magnetic Resonance Imaging (MRI) System with AiCE Reconstruction Processing Unit for MR, do not change the indications for use or the intended use of the device. Based upon bench testing, successful completion of software validation, and application of risk management and design controls, it is concluded that the subject device is safe and effective for its intended use.

Regulation Number and Section

§ 892.1000 Magnetic resonance diagnostic device.

(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.