Search Results

Vantage Galan 3T 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.

The Vantage Galan (Model MRT-30200) is a 3 Tesla Magnetic Resonance Imaging (MRI) System, previously cleared under K203323. This system is based upon the technology and materials of previously marketed Canon Medical Systems and is intended to acquire and display crosssectional, transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body.

The acceptance criteria and study that prove the device meets these criteria are detailed below:

1. Table of Acceptance Criteria & Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Sample Size: 32 studies and 116 scans were used for the human observer study.
• Data Provenance: Not explicitly stated whether the data was retrospective or prospective, nor the country of origin.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three board-certified radiologists per anatomy.
• Qualifications: "Board certified radiologists." No specific years of experience are mentioned.

4. Adjudication Method for Test Set

• The document implies a consensus-based approach for evaluating "clinically-relevant difference in preference" among the radiologists, but a specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated.

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

• A human observer study was conducted comparing images from the predicate device (acceleration factor 2.5) with those from the subject device (higher acceleration factors 3.0 and 4.0). This can be considered a form of MRMC study, as multiple readers (three board-certified radiologists per anatomy) evaluated multiple cases (32 studies, 116 scans).
• Effect Size: The document states that the study demonstrated "no clinically-relevant difference in preference" and "equivalent performance level." This indicates no significant effect size of improvement with the higher acceleration factors (which implies AI processing, though not directly stated as "human readers improve with AI vs without AI assistance"). Instead, it shows that the AI-enhanced acceleration maintains diagnostic quality without degradation and without necessarily improving human reader performance beyond the predicate.

6. Standalone Performance Study (Algorithm Only)

• The document describes a "human observer study," which by its nature involves human readers. It does not explicitly state that a standalone algorithm-only performance study was conducted in terms of diagnostic accuracy or equivalent metrics without human-in-the-loop. The focus is on the human perception of image quality and diagnostic utility.

7. Type of Ground Truth Used

• The ground truth was based on expert consensus/preference from "board certified radiologists." They assessed "clinically-relevant difference in preference" and determined if images were "diagnostic."

8. Sample Size for Training Set

• The document does not specify the sample size used for the training set of the AiCE Reconstruction Processing Unit for MR. This submission is an extension of the maximum acceleration factor, and the AiCE unit itself was part of a previous clearance (K203323).

9. How Ground Truth for Training Set Was Established

• The document does not provide information on how the ground truth for the training set of the AiCE Reconstruction Processing Unit was established.

Ask a specific question about this device

Vantage Galan 3T systems are indicated for use as a diagnostic imaging modality that produces crosssectional 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.

The Vantage Galan (Model MRT-3020) is a 3 Tesla Magnetic Resonance Imaging (MRI) System, previously cleared under K192574. This system is based upon the technology and materials of previously marketed Canon Medical Systems and is intended to acquire and display crosssectional transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body. The AiCE Reconstruction Processing Unit for MR is included with this system for the processing of images for various anatomical regions.

1. Acceptance Criteria and Reported Device Performance

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

The human observer study included 60 subjects and a total of 348 scans. The provenance of this data (e.g., country of origin, retrospective or prospective) is not specified in the provided document.

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

The human observer study involved 15 board-certified radiologists/cardiologists. The document does not explicitly state that these experts established "ground truth" for the test set, but rather that they evaluated the images and demonstrated a statistical preference for AiCE. Their qualifications are listed as "board certified radiologists / cardiologists." No further details on their experience (e.g., 10 years of experience) are provided.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (such as 2+1 or 3+1) for the human observer study. It only states that 15 radiologists/cardiologists provided evaluations leading to a statistical preference.

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

Yes, a multi-reader multi-case (MRMC) comparative effectiveness study was conducted. The study involved 15 board-certified radiologists/cardiologists evaluating images from 60 subjects and 348 scans.

The effect size of how much human readers improve with AI vs. without AI assistance is not explicitly quantified in terms of a specific numerical improvement in accuracy or efficiency. Instead, the study "demonstrated a statistical preference of AiCE when compared to other performance filters," indicating improved perception or diagnostic confidence with AiCE, but without detailing the magnitude of this improvement or the specific metrics used for "preference."

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance study was done. The document states that "AiCE deep learning reconstruction underwent performance (bench testing) using a model observer study to determine that image low contrast detectability was maintained or improved, accompanied with other bench testing of SNR and contrast performance." This indicates an assessment of the algorithm's intrinsic image quality improvement without direct human interaction at that stage.

7. Type of Ground Truth Used

For the model observer study and bench testing, the ground truth appears to be based on objective image quality metrics such as "low contrast detectability," "SNR," and "contrast performance." These are inherent properties of the reconstructed images.

For the human observer study, the "ground truth" or reference for comparison was the performance of "other performance filters" (implicitly, the images reconstructed with these filters). The observers then indicated a "statistical preference" for AiCE, which served as the outcome measure. It isn't explicitly stated that the cases had a confirmatory diagnostic "ground truth" (e.g., pathology or outcomes data) that the radiologists were evaluating for accuracy. Rather, it focuses on the radiologists' perception and preference for the AiCE reconstructed images.

8. Sample Size for the Training Set

The document does not provide any information about the sample size used for the training set of the AiCE deep learning model.

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

The document does not provide any information on how the ground truth for the training set was established for the AiCE deep learning model.

Ask a specific question about this device

Vantage Galan 3T 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.

The Vantage Galan (Model MRT-3020) is a 3 Tesla Magnetic Resonance Imaging (MRI) System, previously cleared under K181593. This system is based upon the technology and materials of previously marketed Canon Medical Systems and is intended to acquire and display cross-sectional transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body.

AiCE is an optional noise reduction algorithm that improves image quality and reduces thermal noise by employing Deep Convolutional Neural Network methods.

AiCE is designed to remove Gaussian distributed noise in MR images for reducing contributions of thermal noise. In order to train a DCNN that can learn a model that represents thermal noise, the training datasets are created by adding Gaussian noise of different amplitudes to high-SNR images acquired with large number of averages.

The device is targeted for Brain and knee regions.

This software and its associated hardware are used on Canon MRI systems that are designed to communicate with the AiCE Reconstruction Processing Unit for MR.

Here's a breakdown of the acceptance criteria and study information for the Canon Medical Systems Corporation's Vantage Galan 3T, MRT-3020, V6.0 with AiCE Reconstruction Processing Unit for MR, based on the provided document:

Acceptance Criteria and Device Performance

Study Details

1. Sample size used for the test set and the data provenance:

   • Human Observer Study: 160 images.
   • Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective).
   • Model Observer Study: Not specified, but generally involves simulated data or specific phantom images.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Human Observer Study: 6 physicians.
   • Qualifications: Not specified (e.g., years of experience, subspecialty).

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not explicitly stated. The document mentions a "statistical preference," which implies a comparative assessment by the readers, but the method of resolving discrepancies or forming a consensus for ground truth is not detailed.

4. 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, a Human Observer study was conducted with 6 physicians and 160 images.
   • Effect Size: The document states that the study "demonstrated a statistical preference of AiCE when compared to other preferred filters." However, it does not quantify the effect size in terms of human reader improvement with AI vs. without AI assistance (e.g., AUC improvement, sensitivity/specificity increase). The study focused on preference rather than diagnostic accuracy improvement.

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

   • Yes, a "Model Observer study" was conducted to determine if image Low Contrast Detectability was maintained or improved. This is a form of standalone evaluation focusing on image quality metrics.

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

   • Human Observer Study: The "statistical preference" suggests that the physicians were evaluating image quality, and their collective preference served as a form of expert consensus on the perceived image quality rather than a ground truth for a specific pathology.
   • Model Observer Study: Ground truth would typically be established based on known physical properties of the phantoms used or simulated data, where the true low-contrast objects are precisely defined.

7. The sample size for the training set:

   • The document states: "In order to train a DCNN that can learn a model that represents thermal noise, the training datasets are created by adding Gaussian noise of different amplitudes to high-SNR images acquired with large number of averages."
   • The specific number of images or cases in the training set is not provided.

8. How the ground truth for the training set was established:

   • The training datasets were created by "adding Gaussian noise of different amplitudes to high-SNR images acquired with large number of averages."
   • This implies that the "ground truth" for training the deep convolutional neural network (DCNN) was essentially the original high Signal-to-Noise Ratio (SNR) images before the artificial noise was added. The DCNN was trained to learn how to transform noisy images back to these high-SNR "ground truth" representations.

Ask a specific question about this device

Vantage Galan 3T systems are indicated for use as a diagnostic imaging modality that produces crosssectional 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.

The Vantage Galan (Model MRT-3020) is a 3 Tesla Magnetic Resonance Imaging (MRI) System, previously cleared under K181593. This system is based upon the technology and materials of previously marketed Canon Medical Systems and is intended to acquire and display crosssectional transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body.

The provided text is a 510(k) summary for the Canon Medical Systems Corporation's Vantage Galan 3T, MRT-3020, V6.0 MRI System. This document focuses on demonstrating substantial equivalence to a predicate device, rather than providing a detailed study report with specific acceptance criteria and performance metrics for a novel AI device.

Therefore, the requested information elements (1, 2, 3, 4, 5, 7, 8, 9) regarding acceptance criteria, sample sizes, expert qualifications, ground truth establishment, and MRMC effectiveness studies cannot be fully extracted from this document as it is not a study report for an AI device.

However, based on the information provided regarding the "Compressed SPEEDER" feature, which is a new software functionality, I can deduce some aspects related to its evaluation.

Here's a breakdown of what can be extracted or inferred, and what cannot:

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance

• Sample Size:
  • For technical image quality metrics (SNR, unfolding error, phase encode performance): Phantoms and volunteer images were used. The exact number of phantoms or volunteers is not specified.
  • For clinical image quality assessment by radiologists: Representative images were obtained using the subject device. The exact number of images or cases is not specified.
• Data Provenance: Not explicitly stated, but given it's a medical device submission by a Japanese company with a U.S. agent, the volunteer imaging likely occurred either in Japan or the US. This was a prospective evaluation of the new software feature.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Number of experts: Not explicitly stated, but referred to as "American Board Certified Radiologists" (plural), indicating at least two.
• Qualifications of experts: "American Board Certified Radiologists." No specific experience level (e.g., "10 years of experience") is provided.

4. Adjudication method for the test set

• The document states that reviewers (radiologists) "provided detailed assessments." It does not specify an adjudication method (e.g., 2+1, 3+1, none) for reaching a consensus on the diagnostic quality or other assessments if multiple radiologists were involved. It simply says "reviewed by American Board Certified Radiologists."

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

• No, an MRMC comparative effectiveness study was not explicitly mentioned or performed in the context of human reader improvement with AI assistance. The evaluation focused on the diagnostic quality of images produced by the device's new "Compressed SPEEDER" and "T2 Map" features, reviewed by radiologists, rather than comparing human reader performance with and without AI assistance from these features. The device's features (Compressed SPEEDER) are about image acceleration and quality, not necessarily AI for diagnostic assistance to humans.

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

• Yes, a standalone evaluation of the "Compressed SPEEDER" algorithm's technical performance was done using phantoms and volunteer images to assess SNR, unfolding error artifacts, and performance in all phase encode directions. The algorithm's output (images) was then assessed for diagnostic quality by radiologists. This refers to the algorithm generating the images, which are then interpreted.

7. The type of ground truth used

• For the technical image quality metrics (SNR, unfolding error, phase encode performance), the ground truth was based on known phantom dimensions and electromagnetic properties, along with expected image characteristics from volunteer scans.
• For the clinical assessment by radiologists, the ground truth was expert consensus (implied, as radiologists reviewed and confirmed diagnostic quality). No mention of pathology or outcomes data as ground truth is made.

8. The sample size for the training set

• The document does not specify a training set size or methodology. It is a 510(k) summary for a software update to an MRI system, not a detailed algorithm development report. It is likely that the Compressed SPEEDER algorithm was developed and trained internally by Canon Medical Systems, but details are not provided here.

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

• As the training set itself is not mentioned, the method for establishing its ground truth is not provided in this document.

Ask a specific question about this device