Search Results

MR Elastography is an optional package for Canon Medical Systems magnetic resonance imaging (MRI) systems. This option allows the user to obtain an image that reflects the stiffness, in kPa, of body tissue such as liver and muscle.

MR Elastography is an optional package for Canon Medical Systems magnetic resonance imaging (MRI) system. This option allows the user to obtain an image that reflects the stiffness of body tissue.

MR Elastography consists of Acoustic Driver System including Active Driver, Passive Driver, QA Phantom and Other parts, TTL trigger converter includes AC adaptor, Manuals and Software (License).

By MRI scanning while applying vibration from the Acoustic Driver System, it is possible to obtain an image that reflects the stiffness of the body tissue in kPa. The sequence to be used with Acoustic Driver System is FE2D or SE-EPI2D. The MRI scanner outputs the following images from the acquired phase image and magnitude image.

• · Wave image
• · Stiffness image (capable of registration and display in color image format)
• · Confidence image (capable of superimposing confidence image on the stiffness image)

The provided text describes the 510(k) submission for Canon Medical Systems' MR Elastography (MZEK-001A) device. Here's an analysis of the acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

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

The text states: "The phantoms were scanned 5 times per day, multiple days per scanner, on 2 different 1.5T and 2 different 3T scanners by FE2D and SE-EPI2D techniques."

• Test Set Sample Size: While an exact number of "scans" isn't explicitly given beyond "5 times per day, multiple days per scanner," it indicates a sufficient number of measurements across different scanner types (2x 1.5T, 2x 3T) and scanning techniques (FE2D, SE-EPI2D). The total number of individual phantom measurements would be 5 (scans/day) * X (days) * 4 (scanners) * 2 (techniques). The document implies a robust bench testing setup rather than patient data.
• Data Provenance: The data appears to be from prospective bench testing conducted by Canon Medical Systems, likely in a controlled laboratory environment. The country of origin of the data is not specified, but given the manufacturer is Japan and the US agent is in the US, the testing could have occurred in either location or a combination. The data is synthetic (phantom-based) rather than clinical patient data.

3. Number of Experts Used to Establish Ground Truth and Qualifications

• Number of Experts: Not applicable/not mentioned. The ground truth was established using "Resoundant-provided calibration phantoms having known stiffness values." This indicates a physical phantom with pre-calibrated, known stiffness properties, rather than expert interpretation of images.
• Qualifications of Experts: Not applicable, as expert interpretation was not used for ground truth.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable/not mentioned. Since the ground truth was based on physical phantoms with known stiffness values, there was no need for expert adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• MRMC Study: No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported. The study focused on the device's ability to accurately measure stiffness against known phantom values, not on human reader performance or improvement with AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

• Standalone Performance: Yes, the described testing is akin to a standalone (algorithm only) performance evaluation. The device (hardware and software) outputs stiffness values based on the acquired data, and these values are compared directly against the known stiffness of the phantoms. There is no mention of human interpretation being part of this core performance evaluation. The output stiffness image and confidence image are for user display, but the performance metrics are system-derived.

7. The Type of Ground Truth Used

• Ground Truth Type: The ground truth used was phantom-based with known stiffness values. Specifically, "three Resoundant-provided calibration phantoms having known stiffness values representing the expected clinical range."

8. The Sample Size for the Training Set

• Training Set Sample Size: The document does not provide details on the sample size of any training set. It describes the performance testing of the final device. The software was "based on an estimation algorithm provided by the Mayo Clinic and Resoundant, Inc." and "developed in conjunction with The Mayo Clinic and Resoundant, Inc.," suggesting external development and/or collaboration, but no specifics on training data are given.

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

• Training Set Ground Truth Establishment: The document does not provide details on how the ground truth for any training set was established. Given the software's origin from Mayo Clinic and Resoundant, Inc., it's plausible they used a combination of phantom data and potentially de-identified clinical data with histopathological correlation for development and training, but this is speculative based on common practice for such devices and not explicitly stated in the provided text.

Ask a specific question about this device

The dS FootAnkle 16ch 1.5T and 3.0T MR Coils are intended to be used in conjunction with Philips 1.5T/3.0T Magnetic Resonance Scanners to produce diagnostic images of the foot and ankle anatomy that can be interpreted by a trained physician.

The dS HiRes Hand/Wrist 16ch 1.5T and 3.0T MR Coils are intended to be used in conjunction with Philips 1.5T/3.0T Magnetic Resonance Scanners to produce diagnostic images of the hand and wrist anatomy that can be interpreted by a trained physician.

The dS Small Extremity 16ch 1.5T and 3.0T MR Coils are intended to be used in conjunction with Philips 1.5T/3.0T Magnetic Resonance Scanners to produce diagnostic images of the small extremities anatomy on adult and pediatric patients that can be interpreted by a trained physician.

The Philips Orthopedic MR Coils are designed for use with Magnetic Resonance Imaging (MRI) systems. The coils are designed to work in unison with the Body Coil of the MRI system, which will transmit the radio frequency (RF) signals, so that the coil may receive the resultant RF signal from the excited nuclei.

The subject devices have 16-elements and are for use with Philips Ingenia 1.5T and 3.0T MR Systems with dStream interface (K193215). The devices are designed for optimum coverage and high-resolution visualization of detailed cartilage structures of the body anatomy (foot/ankle, hand/wrist, small extremity). The coil is used independently and cannot be combined with any other coils. The coils are available in both 1.5T and 3.0T magnetic strengths.

The provided text outlines the performance testing for the Philips Orthopedic MR Coils, but it does not contain details on acceptance criteria or performance data as would be found in a study proving a device meets specific acceptance criteria in the context of an AI/ML diagnostic device regulatory submission. The document is a 510(k) summary for magnetic resonance coils, which are hardware components, not artificial intelligence software.

Therefore, I cannot fulfill your request for details regarding:

• A table of acceptance criteria and reported device performance (in the context of AI/ML diagnostic output).
• Sample sizes for test sets or data provenance (as there's no AI algorithm being tested).
• Number of experts or their qualifications, or adjudication methods (as this pertains to evaluating AI output against ground truth).
• MRMC comparative effectiveness studies.
• Standalone algorithm performance.
• Type of ground truth used.
• Training set information.

The document focuses on the substantial equivalence of the MR coils to predicate devices based on:

• Physical characteristics (design, material, chemical composition, energy source).
• Adherence to recognized standards for MR coil performance (e.g., NEMA MS 1, 3, 9, IEC 62464-1 for image quality; ANSI/AAMI ES 60601-1, NEMA MS 14 for surface heating).
• General electrical/mechanical safety (IEC 60601-2-33, AAMI/ANSI ES 60601-1).
• Biocompatibility (ISO 10993 series).

The closest mention of "image quality assessment by a U.S. Board Certified radiologist" just confirms that the images produced were "sufficient quality for diagnostic use," but this is a general statement and not a quantitative performance metric against specific acceptance criteria for a diagnostic algorithm.

Ask a specific question about this device

The dS Head 32ch 3.0T MR Coil is intended to be used in conjunction with a Philips 3.0T Magnetic Resonance Scanner to produce diagnostic images of the head on adult and pediatric patients that can be interpreted by a trained physician.

The subject dS Head 32ch 3.0T Coil is a receive-only, phased-array radiofrequency (RF) coil designed for high-resolution head examinations on adult and pediatric patients. The coil is intended for use with Philips magnetic resonance (MR) scanners with a 3.0 tesla magnetic field strength.

The provided text describes the 510(k) summary for the Philips dS Head 32ch 3.0T MR Coil. This document focuses on the safety and performance criteria for the device itself (a medical imaging coil), not on the performance of an AI algorithm interpreting images produced by the device.

Therefore, the information typically requested for AI/algorithm performance (e.g., sample size for test set, number of experts for ground truth, MRMC study, standalone performance) is not applicable or not provided in this document as it's not a submission for an AI/ML powered device.

However, I can extract the relevant information regarding the device's acceptance criteria and the study proving it meets those criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The study proving the device meets the acceptance criteria is detailed under "Summary of Non-Clinical and Clinical Performance Data":

The subject dS Head 32ch 3.0T Coil met all safety and performance criteria outlined in the FDA guidance "Magnetic Resonance (MR) Receive-only Coil – Performance Criteria for Safety and Performance Based Pathway" issued December 11, 2020.

The specific tests performed include:

• Image Signal to Noise and Image Uniformity characterization (NEMA MS 1, 3, 9 and IEC 62464-1)
• Surface heating (ANSI/AAMI ES 60601-1 and NEMA MS 14)
• Acquired Image quality assessment by a U.S. Board Certified radiologist
• Confirmation of the presence of decoupling mechanisms
• EMC – Immunity, electrostatic discharge (IEC 60601-1-2)
• General electrical/mechanical safety (IEC 60601-2-33 and AAMI/ANSI ES 60601-1)
• Biocompatibility evaluation (ISO 10993 series)

Regarding the specific questions about an AI study (which are not directly applicable to this device submission as it's not an AI device):

2. Sample size used for the test set and the data provenance: Not applicable. This submission is for an MR coil and focuses on its physical and imaging performance, not an AI algorithm's diagnostic performance on a test set.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable for an AI algorithm test set. For the device's image quality assessment, it states "Acquired Image quality was assessed by a U.S. Board Certified radiologist." It does not specify the number beyond "a" radiologist.

4. Adjudication method for the test set: Not applicable for an AI algorithm test set.

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 not an AI-assisted device.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an AI algorithm.

7. The type of ground truth used: For the device's performance, physical measurements and adherence to engineering standards (NEMA, IEC, ANSI/AAMI, ISO) served as ground truth for technical performance aspects. For diagnostic utility, the "U.S. Board Certified radiologist" assessment of image quality serves as the ground truth (expert opinion) that the images produced are suitable for diagnostic use.

8. The sample size for the training set: Not applicable. This device does not use an AI algorithm that requires a training set.

9. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

Elekta Unity using Magnetic Resonance Imaging is indicated for radiation therapy treatments and stereotactic radiation treatments of malignant and benign diseases anywhere in the body as determined by a licensed medical practitioner in accordance with a defined treatment plan.

Elekta Unity is intended for use with compatible Treatment Planning and Oncology Information Systems. The Elekta Unity 1.5T MR scanner is a magnetic resonance imaging system that produces cross-sectional images in any orientation of the internal structure of the whole body before, during, and after the radiotherapy treatment.

When interpreted by a trained physician magnetic resonance images acquired before, during, and after the radiotherapy treatment yield information that can be useful in diagnosis and may assist therapy planning, patient positioning and treatment delivery related to radiation oncology.

Elekta Unity is a multifunctional digital linear accelerator designed to assist licensed medical practitioners in the delivery of ionizing radiation to defined volumes (e.g. malignant and benign tumors). Elekta Unity is capable of both intensity modulated radiation therapy (IMRT) and image guided radiation therapy (IGRT).

The Elekta Unity 1.5T MRI scanner is a magnetic resonance imaging sub-system that produces cross-sectional images in any orientation of the internal structure of the whole body before, during, and after the radiotherapy treatment.

When interpreted by a trained physician the images acquired before, during, and after the radiotherapy treatment yield information that can be useful in diagnosis and may assist therapy planning, patient positioning and treatment delivery related to radiation oncology.

In addition to the MRI sequences cleared with the predicate device, the subject device Elekta Unity configuration has the ability to generate images using following techniques, before, during or after treatment:

Introduce 3D Vane
3D Vane XD is a free breathing acquisition method that can be used to compensate for respiratory motion and peristalsis in 3D/FFE and 3D/TFE body imaging.

Introduce CS-Sense - compressed images
Compressed SENSE is an acceleration technique that is less sensitive to noise allowing increased resolution and/or coverage without a scan time penalty.

Introduce Breath Hold (BH) .
Breath-hold is a technique where an image is acquired when a patient holds their breath in a defined phase of the breathing cycle.

The Elekta Unity device mentioned in the document is a medical charged-particle radiation therapy system. However, the provided document does not contain information about specific acceptance criteria or a dedicated study proving device performance against such criteria for AI/ML components.

The document primarily focuses on demonstrating substantial equivalence of the overall device (Elekta Unity with new imaging options) to a predicate device (Elekta Unity K192482). It lists performance testing for the overall system based on design verification, risk management, software verification, and conformance to recognized consensus standards.

Here's a breakdown of why the requested information cannot be fully provided based on the given text, and what information is available:

Missing Information (Specific to AI/ML acceptance criteria and performance study):

• No explicit acceptance criteria for an AI/ML component: The document introduces new imaging options (3D Vane XD, CS-Sense, Breath Hold) but does not frame these as AI/ML applications requiring specific performance metrics like sensitivity, specificity, or AUC against a ground truth. They are described as "additional imaging options" or "acceleration techniques."
• No dedicated study proving AI/ML device performance: There is no study described that evaluates the performance of any AI/ML algorithm within the Elekta Unity against a defined ground truth, nor are there details about sample size, expert readers, or adjudication methods for such a study.
• No MRMC comparative effectiveness study for AI assistance: The document does not describe any study where human readers' performance with and without AI assistance was compared.
• No standalone algorithm-only performance study: No study detailing the performance of an algorithm without human involvement is mentioned.
• No details on ground truth for AI/ML training or testing: Since no specific AI/ML component is detailed with its own performance study, there's no information about the ground truth used for training or testing such components.
• No sample size for training sets of AI/ML components: This information is not present.

What is available regarding overall device testing and compliance:

The document states broader performance testing was conducted for the Elekta Unity system, but these are general engineering and safety tests rather than AI/ML specific performance evaluations.

• Design verification and performance testing: Carried out in accordance with FDA's Quality System Regulation (21 CFR §820.30), ISO 13485, ISO 14971, and IEC 62304.
• Software verification testing: Conducted and documented in accordance with FDA guidance for devices that pose a major level of concern (Class C per IEC 62304).
• Basic safety and essential performance: Satisfied through conformance with device-specific recognized consensus standards (listed in a table).

However, none of this directly answers the AI/ML-specific questions in your prompt. The "new imaging options" are presented as new functionalities of the MR system rather than intelligent algorithms for interpretation or decision support.

Therefore, a table of acceptance criteria and reported device performance for an AI/ML component cannot be created from the provided text. The document focuses on demonstrating that the device as a whole with its new MR imaging sequences maintains safety and effectiveness comparable to its predicate, largely through non-clinical engineering and software testing and adherence to general medical device standards.

Ask a specific question about this device