Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K192574
    Date Cleared
    2020-03-09

    (172 days)

    Product Code
    Regulation Number
    892.1000
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K181593

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    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.

    Device Description

    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.

    AI/ML Overview

    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

    Acceptance CriteriaReported Device Performance
    Maintained or improved Low Contrast Detectability (LCD)Performance (bench testing) using a Model Observer study determined that image Low Contrast Detectability was maintained or improved.
    Statistical preference for AiCE images compared to other preferred filtersA Human Observer study demonstrated a statistical preference of AiCE when compared to other preferred filters.
    Overall safety and effectiveness for intended useConcluded that the subject device is safe and effective for its intended use based on bench testing, phantom imaging, volunteer clinical imaging, successful completion of software validation, and application of risk management and design controls.

    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 Question

    Ask a specific question about this device

    K Number
    K182282
    Date Cleared
    2018-10-19

    (57 days)

    Product Code
    Regulation Number
    892.1000
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K181593

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Vantage 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 Orian (Model MRT-1550) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. The Vantage Orian uses 1.4 m short and 3.8 tons light magnet. It includes the Canon Pianissimo™ and Pianissimo Zen technology (scan noise reduction technology). The design of the gradient coil and the whole body coil of the Vantage Orian provides the maximum field of view of 55 x 55 x 50 cm. The Model MRT-1550/AC, AD, AG, AH includes the standard gradient system and Model MRT-2020/AK, AL, AO, AP 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.

    AI/ML Overview

    The provided text is a 510(k) summary for the Vantage Orian 1.5T, MRT-1550, V4.5 Magnetic Resonance Imaging (MRI) System. It details changes to an existing, cleared MRI system and asserts its substantial equivalence to predicate devices. However, this document does not describe a study that establishes acceptance criteria for specific device performance metrics in terms of diagnostic outcomes (e.g., sensitivity, specificity, accuracy) using a clinical test set with ground truth established by experts.

    Instead, the document focuses on:

    • Hardware and Software Changes: It lists modifications made to the previous MRI system, such as new cover design, optional table, RF system changes, increased gradient strength, changes in maximum slew rate and rise time, and additional software functionalities (e.g., DSD filter, MultiBand SPEEDER, KneeLine+, k-t SPEEDER, R-wave Monitoring, SpineLine+, WFS DIXON, Quick Star, Fast 3D Mode, 2D-RMC for EPI).
    • Safety and Performance Parameters: It compares safety parameters (static field strength, operational modes, maximum SAR, maximum dB/dt, emergency shutdown) to the predicate device and states they are "Same." It also notes "No change from the previous predicate submission, K170412" for imaging performance parameters.
    • Compliance with Standards: It states that the device is designed and manufactured under Quality System Regulations (21 CFR § 820 and ISO 13485) and lists applicable IEC and NEMA standards.
    • Testing for Substantial Equivalence: It mentions that bench testing, phantom imaging, and volunteer clinical imaging were conducted to demonstrate that modifications result in performance "equal to or better than the predicate system" and to evaluate established PNS limits. It also states software validation and application of risk management and design controls were completed.
    • Intended Use: The indications for use are exactly the same as the predicate device, focusing on producing cross-sectional images of anatomic structures for diagnosis when interpreted by a trained physician.

    Therefore, many of the requested categories cannot be directly addressed from the provided text because the study described is not a clinical performance study with predefined acceptance criteria for diagnostic accuracy metrics typically seen in AI/CAD device submissions.

    However, based on the information provided, here's what can be extracted and inferred:

    **No information available or directly applicable to the specific request for acceptance criteria and a study proving device performance in terms of diagnostic outcomes (e.g., sensitivity, specificity, accuracy) with a clinical test set, expert ground truth, and statistical analysis.**
    
    The provided document describes a 510(k) submission for an MRI system, focusing on hardware and software modifications and demonstrating substantial equivalence to a predicate device through engineering and safety testing, not a clinical performance study measuring diagnostic accuracy against a ground truth.
    

    Here's an attempt to populate the table and answer the questions based only on the provided content, explicitly stating when information is not available:


    1. Table of acceptance criteria and the reported device performance

      The document does not specify acceptance criteria in terms of diagnostic accuracy metrics (e.g., sensitivity, specificity, AUC) for the overall device or its new functionalities, nor does it report performance against such criteria. The "performance" described is largely related to engineering specifications and compliance with safety standards, and comparative performance against the predicate is stated as "equal to or better than".

      Acceptance Criteria (Diagnostic Performance)Reported Device Performance (Diagnostic Performance)
      Not specified (for diagnostic performance)Not reported (for diagnostic performance)

      However, for Safety Parameters, the acceptance criterion is effectively "Same as predicate" and the performance meets this:

      Acceptance Criteria (Safety Parameters, e.g., Max SAR, Max dB/dt)Reported Device Performance (Safety Parameters)
      Same as predicate (Vantage Titan 1.5T, K170412)Meets "Same as predicate"
    2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

      The document mentions "A volunteer study was conducted to evaluate the established PNS limits" and "Sample clinical images were included in the determination of substantial equivalence."

      • Test Set Sample Size: Not explicitly stated for specific imaging tasks/functionalities. The "volunteer study" sample size is not provided. The number of "sample clinical images" is not specified.
      • Data Provenance: The country of origin and whether the data was retrospective or prospective are not specified.
    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

      Not applicable/Not mentioned. The document describes a general-purpose MRI system. "Ground truth" in the context of diagnostic accuracy established by expert consensus is not part of the described testing strategy in this 510(k) summary. The statement "When interpreted by a trained physician, these images yield information that can be useful in diagnosis" refers to the intended use of MRI generally, not a specific ground truth for the device's performance evaluation in this submission.

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

      Not applicable/Not mentioned, as there is no described clinical test set with expert-established ground truth.

    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

      Not applicable. This is an MRI system, not an AI/CAD-assisted diagnostic device where human reader improvement with AI would typically be evaluated. The "improvements" mentioned are technical enhancements of the MRI system for image acquisition (e.g., speed, noise reduction, motion correction) and workflow (e.g., automatic positioning), not AI assistance for diagnostic interpretation.

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

      Not applicable. This device is an imaging modality. Its output (images) is intended to be interpreted by a human physician, not to provide a standalone diagnostic interpretation. Some software functionalities mentioned (like SpineLine+ or surevol Knee) do involve automated processing to aid workflow but are not standalone diagnostic algorithms.

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

      Not applicable. No formal clinical ground truth (like expert consensus, pathology, or outcomes data) for diagnostic accuracy metrics is described as being used in the performance evaluation presented in this 510(k) summary. The evaluation focuses on technical performance and safety.

    8. The sample size for the training set

      Not applicable/Not mentioned. The document does not describe a machine learning algorithm that would require a distinct "training set" for diagnostic performance evaluation. The software enhancements are integrated features of the MRI system, and their development likely involved internal data for quality assurance and algorithm development, but this is not termed a "training set" in the context of a performance study shown here.

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

      Not applicable/Not mentioned, as no training set for a diagnostic algorithm is described.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1