Search Results

The NeoCoil 16ch Breast Coils are Magnetic Resonance Imaging (MRI) RF Receive-Only Coils intended for use by trained medical professionals, in combination with and controlled by compatible 1.5T or 3T/3.0T MRI system software.

The NeoCoil 16ch Breast Coils can be used with compatible ancillary components, accessories, and/or devices to provide access to breast anatomy for diagnostic or interventional planning/procedures.

When used as intended, the 16ch Breast Coil provides information used by the MRI system to produce diagnostic and/or interventional planning images of the breast, axilla, and chest wall. The images produced are interpreted by medical professionals as part of clinical decision making.

The NeoCoil 3.0T 16ch Breast Coil is a phased array coil for imaging structures of the breast, axilla and chest wall. The 3.0T 16ch Breast Coil is a three part receive-only coil designed to provide high resolution imaging. The.3.0T 16ch Breast Coil includes a coil support structure, patient support structure, biopsy components, accessories and comfort pads.

The NeoCoil 3.0T 16ch Breast Coil is tuned to receive RF frequency corresponding to the proton precession in a 3 tesla magnetic field, which is governed by the Larmor equation.

The 16ch Breast Coils are intended for use in a manner that is identical to the predicate device and reference device described in this submission 3.0T 16ch Breast Coil, K173377, cleared on 11/28/2017 and 1.5T 16ch Breast Coil, K182958, cleared on 11/16/2018. The 16ch Breast Coil consists of the following arrays available in 1.5T, 3.0T and 3T field strengths:

• Medial Array, Breast Coil
• . Lateral Array Left, Breast Coil
• Lateral Array Right, Breast Coil ●
• . Baseplate Assembly, Breast Coil
• Biopsy Array Left, Breast Coil ●
• Biopsy Array Right, Breast Coil ●

The coils receive magnetic resonance signals generated in hydrogen nuclei (protons) in the Head. Neck and Brachial Plexus anatomy while blocking the high-frequency magnetic field applied by the MRI scanner at specified timings. The received signals are amplified before being transferred to the MRI scanner through the coil's system cable. The amplified signals are processed into tomographic images of the breast, axilla and chest wall anatomy by the MRI scanner. Images are typically generated as axial, sagittal, coronal oblique slices. Accessories associated with the 16ch Breast Coils include biopsy grids and biopsy drapes.

The 1.5T Breast Coil, the 3T 16ch Breast Coil, and the 3.0T 16ch Breast Coil are tuned to receive RF frequency corresponding to the proton precession in a 1.5 tesla and 3.0 tesla magnetic field (respectively), which is governed by the Larmor equation.

The 16ch Breast Coil is intended for use in a manner that is identical to the predicate device described in this submission.

Proposed labeling is documented in the Instructions for Use manual for the 16ch Breast Coil (NC149IFU-en).

The provided text describes the regulatory clearance of NeoCoil's 16ch Breast Coils (K222407) and outlines the testing performed to demonstrate its substantial equivalence to predicate devices. However, the document does not contain information related to an AI/ML powered medical device or a study involving human readers or expert consensus for ground truth establishment. Instead, it focuses on the performance and safety of a physical medical device (an MRI coil).

Therefore, I cannot extract the information required to answer your questions about AI device acceptance criteria, human reader studies, or ground truth establishment based on the provided text. The questions you've asked are typically relevant to the evaluation of AI/ML-driven diagnostic or interpretative tools, which is not what this document addresses.

The document primarily covers non-clinical bench testing for a physical MRI coil, ensuring it meets safety and performance standards comparable to an existing device.

Here's what the document does cover regarding "acceptance criteria" and "study" for the physical device:

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

The document provides a table of "Test Performed" (which serves as acceptance criteria) and the "Results Summary" (reported performance).

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document mentions "Bench Testing" and "MRI scanner test" but does not specify sample sizes for these tests (e.g., number of coils tested, number of scans performed). It also does not provide information on data provenance like country of origin or whether the data was retrospective or prospective, as these are typically considerations for clinical data, which was not gathered for this 510(k).

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)

This is not applicable as the study involves the performance of a physical device against engineering and safety standards, not an AI model requiring human ground truth.

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

Not applicable.

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.

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

This concept is not relevant to the described device. The tests performed are on the physical MRI coil itself.

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

For the physical device, the "ground truth" for the bench tests are the established engineering standards, pre-defined performance criteria (e.g., for electrical safety, temperature limits, B0/B1 field homogeneity), and consensus standards like NEMA MS 6-2008. There is no biological or diagnostic "ground truth" in the way an AI model would require.

8. The sample size for the training set

Not applicable. This is a physical device, not an AI model 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

The 32Ch AIR Open Coil Suite are Magnetic Resonance Imaging (MRI) RF Receive-Only Coils intended to be used by trained medical professionals, for adult patients, in combination with and controlled by 1.5T or 3.0T GE Healthcare MRI system software.

The 32Ch AIR Open Coil Suite is intended for use with specified couchtop and patient immobilization devices depending on the region of interest.

When used as intended, the 32Ch AIR Open Coil Suite is used to produce diagnostic images of the head, neck, and brachial plexus structures. The images can be interpreted by medical professionals or facilitate Radiation Therapy (RT) planning.

The 32Ch AIR Open Coil Suite is comprised of MRI receive-only phased array RF coils designed for clinically acceptable signal-to-noise ratio (SNR) and uniform coverage of the Head, Neck and Brachial Plexus anatomy for use with GE Healthcare Magnetic Resonance Imaging (MRI) scanners. The 32Ch AIR Open Coil Suite consists of the following arrays available in 1.5T and 3.0T field strengths:

• AIR Open Head Neck Posterior 9ch
• AIR Open Neck Chest Anterior 7ch
• AIR Open Head Anterior 16ch .

The coils receive magnetic resonance signals generated in hydrogen nuclei (protons) in the Head, Neck and Brachial Plexus anatomy while blocking the high-frequency magnetic field applied by the MRI scanner at specified timings. The received signals are amplified before being transferred to the MRI scanner through the coil's system cable. The amplified signals are processed by the MRI scanner into tomographic images of the Head, Neck and Brachial Plexus anatomy by the MRI scanner. Images are typically generated as axial, sagittal, coronal oblique slices. There are no accessories associated with the 32Ch AIR Open Coil Suite. Depending on the region of interest, the coils may be used in combination with the CIVCO RT Universal Couchtop™ MR Overlay for GE Motus, Kizuna, and GEM as well as the associated patient immobilization devices (e.g., thermoplastic mask, straps provided with the MRI scanner)

The 1.5T 32Ch AIR Open Coil Suite and the 3.0T 32Ch AIR Open Coil Suite are tuned to receive RF frequency corresponding to the proton precession in a 1.5 tesla and 3.0 tesla magnetic field (respectively), which is governed by the Larmor equation.

The 32Ch AIR Open Coil Suite is intended for use in a manner that is identical to the predicate device described in this submission.

Proposed labeling is documented in the Instructions for Use manual for the 32Ch AIR Open Coil Suite (NC139IFU-en).

The provided text describes the acceptance criteria and study proving a medical device, the 32Ch AIR Open Coil Suite, meets these criteria. However, it focuses primarily on bench testing (performance testing) and briefly mentions clinical performance testing without detailing the specifics typically found in studies designed to prove performance against specific clinical acceptance criteria (like diagnostic efficacy, AI algorithm performance, etc.).

The document outlines a 510(k) submission for an MRI RF Receive-Only Coil, which is an imaging accessory, not an AI-powered diagnostic device. Therefore, the common elements of acceptance criteria and study designs for AI/CADe systems (such as sensitivity, specificity, MRMC studies, expert adjudication, ground truth establishment for a diagnostic output) are not directly applicable or present in this document.

The "study" described herein is a series of engineering and safety tests to demonstrate substantial equivalence to a predicate device, as required for a 510(k) clearance, concerning physical and electrical performance, biocompatibility, and image quality (SNR, uniformity). It does not involve an AI algorithm that produces a diagnostic output, nor does it describe a study like a clinical trial for diagnostic performance.

Given this, I will interpret your request keeping in mind the nature of the device and the provided document. I will focus on the acceptance criteria and performance data that are present, and explicitly state where information relevant to AI/CADe validation is not available or not applicable.

Here's an analysis based on the provided text:

Device Name: 32Ch AIR Open Coil Suite (comprising various 1.5T and 3.0T AIR Open Head Neck Posterior, Neck Chest Anterior, and Head Anterior coils).

Device Type: Magnetic Resonance Imaging (MRI) RF Receive-Only Coils. This is a hardware component for MRI systems, not a software-based AI diagnostic tool.

Purpose of Testing: To demonstrate that the device is safe and effective and performs in a manner that demonstrates substantial equivalence to the predicate device (3.0T GEM RT Open Array, K143389).

1. Table of Acceptance Criteria and Reported Device Performance

The document presents a table outlining various bench tests (non-clinical performance testing). These tests are primarily focused on safety, electrical performance, and physical image quality characteristics of the MRI coils.

Note: The document also mentions "Clinical data exhibits a mix of technical factors and anatomy as recommended in FDA guidance; Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices issued November 18, 2016." and "No adverse events were reported during clinical performance testing." However, detailed acceptance criteria for clinical performance (e.g., specific image quality metrics, diagnostic accuracy, etc., that would typically be seen for an AI diagnostic device) are not provided in this regulatory summary. The "clinical performance testing" seems to primarily refer to general image observation to ensure functionality, not a rigorous clinical trial for diagnostic performance.

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

• Test Set (Clinical Data): The document states "Clinical data exhibits a mix of technical factors and anatomy as recommended in FDA guidance." However, specific sample sizes (number of patients/cases), country of origin, or whether the data was retrospective or prospective are not provided in this summary.
• Test Set (Bench Data): For bench testing, the "sample size" is inherently the number of physical coil units tested or the number of experiments performed. This detail is not quantified (e.g., "N=3 coils tested for each parameter").

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

• Not applicable in the context of AI/CADe ground truth: This device is an MRI coil, not a diagnostic AI algorithm that requires expert-established ground truth for diagnostic outputs.
• The "clinical performance testing" would likely involve medical professionals (e.g., radiologists) interpreting images for general quality and usability, but the document does not specify the number or qualifications of experts involved in the "clinical data" review. The stated objective for the device is "to produce diagnostic images of the head, neck, and brachial plexus structures. The interpreted by medical professionals or facilitate Radiation Therapy RT planning." This implies human interpretation.

4. Adjudication Method for the Test Set

• Not applicable in the context of AI/CADe ground truth adjudication: Since this is not an AI diagnostic device, formal adjudication methods for ground truth (like 2+1 or 3+1 consensus) are not described or relevant for the types of tests reported.
• For the "clinical performance testing," the method of image assessment (e.g., unanimous agreement on usability/quality by a panel) is not specified.

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

• No MRMC study was done, nor is it applicable: This type of study (comparing human readers with and without AI assistance for diagnostic performance, or comparing different AI algorithms) is specifically for evaluating the effectiveness of AI-powered diagnostic tools or CADe systems. The 32Ch AIR Open Coil Suite is an MRI hardware component.

6. Standalone Performance (Algorithm Only)

• Not applicable: This is an MRI coil, a hardware component. There is no "algorithm only" performance to evaluate. The device's performance is intrinsically linked to its use with an MRI scanner and subsequent human interpretation of the images it helps acquire.

7. Type of Ground Truth Used

• Not applicable in the context of AI/CADe diagnostic ground truth.
• For the performance testing that was conducted:
  • Bench Tests: The "ground truth" for these tests is defined by established engineering and safety standards (e.g., IEC standards, NEMA MS 6-2008). The criteria are objective measurements against these standards (e.g., temperature limits, signal-to-noise ratio, image uniformity).
  • Clinical Performance: The "ground truth" for assessing image quality and usability in a clinical context would be the subjective and objective assessment by trained medical professionals (e.g., radiologists) determining if the images are diagnostically acceptable and if the coil is usable. No specific details are provided.

8. Sample Size for the Training Set

• Not applicable: This device does not involve a machine learning or AI algorithm that requires a training set.

9. How Ground Truth for the Training Set Was Established

• Not applicable: As there is no AI algorithm and no training set, the establishment of ground truth for a training set is irrelevant for this device.

Summary:

The provided document details a regulatory submission (510(k)) that focuses on demonstrating the substantial equivalence of new MRI coils to a previously cleared predicate device. The "acceptance criteria" and "proof" provided are primarily related to general device safety, electrical performance, and basic image quality metrics as measured by engineering tests. While clinical data is mentioned, it appears to be for general observational assessment of usability and image quality rather than for quantifying diagnostic performance outcomes, which would be the case for an AI-powered diagnostic device. Therefore, many of the questions asked, particularly those pertaining to AI/CADe validation (MRMC studies, expert ground truth establishment, training sets), are not applicable to the nature of the device and the testing described in this document.

Ask a specific question about this device

To be used in conjunction with GEHC 1.5T Magnetic Resonance Scanners to produce diagnostic images of the shoulder that can be interpreted by a trained physician.

To be used in conjunction with GEHC 3.0T Magnetic Resonance Scanners to produce diagnostic images of the shoulder that can be interpreted by a trained physician.

The 1.5T 16ch Shoulder Coil and 3.0T 16ch Shoulder Coil are receive-only phased array RF coils designed for optimum signal-to-noise ratio (SNR) and uniform coverage of the shoulder anatomy for use with GE Healthcare Maqnetic Resonance Imaging (MRI) scanners. The coils receive magnetic resonance signals generated in hydrogen nuclei (protons) in the shoulder while blocking the high-frequency magnetic field applied by the MRI scanner at specified timings.

Images are typically generated as axial, sagittal, coronal oblique slices and include coverage of the Humerus, Humeral Head, Labrum, Labral Tear, Glenoid, Scapula, Clavicle, and Rotator Cuff regions of the shoulder anatomy.

The 1.5T 16ch Shoulder Coil and 3.0T 16ch Shoulder Coil are tuned to receive RF frequency corresponding to the proton precession in a 1.5 tesla and 3.0 tesla magnetic field (respectively), which is governed by the Larmor equation.

This document describes the marketing approval of NeoCoil's 1.5T 16ch Shoulder Coil and 3.0T 16ch Shoulder Coil, which are Magnetic Resonance (MR) diagnostic devices. The acceptance criteria and the study proving the device meets these criteria are primarily based on demonstrating substantial equivalence to a legally marketed predicate device (NeoCoil 3.0T 8-Channel Shoulder Array Coil, K071611).

The provided document, however, does not contain a specific table of acceptance criteria with reported quantitative performance metrics for the image quality or diagnostic accuracy studies for a novel AI device. Instead, it details the acceptance criteria met for establishing substantial equivalence for an MRI coil. The studies conducted focus on the safety and effectiveness of the coil itself as a medical device component, not on the performance of an AI algorithm interpreting images.

Therefore, I will interpret the request in the context of demonstrating substantial equivalence for an MRI coil, rather than an AI diagnostic device. The "performance" here refers to the physical and electrical performance of the coil that ensures it can produce diagnostic images, rather than algorithmic performance metrics like sensitivity or specificity.

Here's an analysis of the provided information in the requested format, adapted for an MRI coil rather than an AI diagnostic device:

Acceptance Criteria and Study for NeoCoil 1.5T 16ch Shoulder Coil and 3.0T 16ch Shoulder Coil

The acceptance criteria for these MRI coils are primarily based on demonstrating substantial equivalence to a predicate device (NeoCoil 3.0T 8-Channel Shoulder Array Coil, K071611), ensuring the new coils are safe and effective for their intended use. The performance evaluation includes both non-clinical (bench) and clinical testing.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document provides limited specific detail on the "sample size" in terms of number of patients or scans for the clinical testing. It states: "Clinical data exhibits a mix of technical factors and anatomy as recommended in the FDA guidance, Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices issued November 18, 2016."

• Test Set Sample Size: Not explicitly quantified in terms of number of subjects/scans. The "clinical" section lists examples of sequences tested (e.g., Oblique Axial PD, Oblique Coronal T1). This suggests a limited number of test cases sufficient to demonstrate clinical image interpretability.
• Data Provenance: Not explicitly stated (e.g., country of origin). The studies appear to be prospective or specifically conducted for regulatory submission, given the explicit mention of "Clinical performance testing" and comparison to FDA guidance.

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

This information is not explicitly provided in the document. For an MRI coil, the "ground truth" for diagnostic image quality would typically be judged by trained physicians (e.g., radiologists) interpreting the images. The document states the coils are "to produce diagnostic images of the shoulder that can be interpreted by a trained physician," implying such interpretation was part of the clinical assessment. However, the exact number and qualifications of these interpreting physicians are not detailed.

4. Adjudication Method for the Test Set

Not specified. For an MRI coil that is part of the image acquisition chain, the assessment is more about whether the images produced are diagnostically acceptable and substantially equivalent to images from the predicate device, rather than classifying presence/absence of a condition which would typically require an adjudication process.

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

• No evidence of a formal MRMC study as would be conducted for an AI diagnostic algorithm. The evaluation is focused on the coil's ability to produce diagnostically interpretable images comparable to the predicate. The statement "Clinical testing demonstrates that the differences in the compatible scanners of the devices do not affect the safety and/or the effectiveness of the device when used as labeled" and "Clinical and non-clinical testing demonstrates that the safety and effectiveness of the 1.5T 16ch Shoulder Coil compared to the predicate device is not adversely affected as a result of the differences" suggests a comparative assessment, but not an MRMC study measuring human reader performance with/without AI assistance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Not applicable. This submission is for an MRI coil, which is a physical device component, not an AI algorithm. Its "standalone performance" refers to its physical and electrical characteristics (bench testing) and its ability to produce images, not to interpret them.

7. The Type of Ground Truth Used

• For the non-clinical (bench) testing:
  • Engineering/Physics Measurements: Quantitative measurements (e.g., surface temperature, B1/B0 field distortion, SNR, image uniformity based on NEMA MS 6-2008).
  • Compliance with Standards: Verification against recognized safety and performance standards (e.g., IEC 60601 series).
• For the clinical testing:
  • Clinical Interpretability: The "ground truth" implies that the images produced by the new coils were subjectively assessed as being of sufficient diagnostic quality to be interpreted by a trained physician, in comparison to images from the predicate device. The absence of adverse events further supported the safety and effectiveness.

8. The Sample Size for the Training Set

• Not applicable. This is for an MRI coil, not an AI algorithm that requires a training set.

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

• Not applicable. This is for an MRI coil, not an AI algorithm.

Ask a specific question about this device

To be used in conjunction with GEHC 1.5T Nagnetic Resonance Scanners to produce diagnostic and interventional planning images of the breast that can be interpreted by a trained physician. When used with biopsy accessories, this device permits access to the breast anatomy for interventional procedures that can be performed by a trained physician.

The NeoCoil 1.5T 16ch Breast Coil is a phased array coil for imaging structures of the breast, axilla and chest wall. The 1.5T 16ch Breast Coil is a three part receive-only coil designed to provide high resolution imaging. The 1.5T 16ch Breast Coil includes a coil support structure, patient support structure, biopsy components and comfort pads.

The information provided does not describe an AI/ML device but rather a Magnetic Resonance Specialty Coil (NeoCoil 1.5T 16ch Breast Coil). Therefore, most of the requested information (such as sample size for test set, data provenance, number of experts, adjudication method, MRMC study, standalone performance, type of ground truth, training set size, and ground truth for training set) is not applicable or cannot be extracted from the given text.

However, I can provide the acceptance criteria and reported device performance from the "Testing" section for the medical device in question.

1. Table of acceptance criteria and the reported device performance:

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

Not applicable/Not provided. The document describes a physical device validation and does not refer to a "test set" in the context of an AI/ML model for data analysis or diagnostic performance. Clinical testing was performed, but specific sample sizes and data provenance details (country of origin, retrospective/prospective) are not mentioned.

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 provided. This device is an MRI coil, not an AI/ML diagnostic algorithm that requires expert-established ground truth for its performance evaluation in the described manner.

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

Not applicable/Not provided.

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/Not provided. 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/Not provided. This is a hardware component (MRI coil).

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

Not applicable/Not provided. The performance testing for this device focuses on physical characteristics, safety (temperature, RF fields), and imaging quality (SNR, uniformity) determined by engineering standards and clinical observation, not diagnostic ground truth as defined for AI/ML algorithms. Clinical testing "demonstrated performance adequate to support the Indications for Use," implying that the images produced were suitable for interpretation by a trained physician, which is the "Indication for Use."

8. The sample size for the training set:

Not applicable/Not provided. This is a hardware device, not an AI/ML algorithm.

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

Not applicable/Not provided. This is a hardware device.

Ask a specific question about this device

The NeoCoil Wireless Audio System is intended to provide entertainment and facilitate patient communication in MRI environments at 3 Tesla field strength and below.

The NeoCoil Wireless Audio System is intended to provide entertainment and facilitate communications between the patient and the operator in a Magnetic Resonance Imaging (MRI) scanner environment. The Wireless Audio System is intended to be used by healthcare professionals.

The NeoCoil Wireless Audio System is a modular system comprised of wireless patient headphones, a remote audio data source unit, and communications infrastructure.

The provided text describes the NeoCoil Wireless Audio System, a device for patient communication and entertainment in MRI environments. It includes details about the device's performance testing and comparison to a predicate device.

Here's an analysis of the acceptance criteria and study information provided:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document mentions "Clinical data submitted exhibits a mix of pulse sequences and imaging options in the axial, sagittal and coronal planes". However, it does not specify the sample size for the test set or the country of origin of the data. It implies the data is prospective clinical performance testing as it refers to "No adverse events were reported during clinical performance testing".

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

The document does not provide information on the number of experts used to establish ground truth for the test set or their qualifications.

4. Adjudication Method

The document does not specify an adjudication method for the test set.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study, nor does it provide an effect size for human readers improving with AI vs. without AI assistance. The device is an audio system, not an AI diagnostic tool.

6. Standalone Performance Study

The document details various standalone performance tests (bench and clinical) of the NeoCoil Wireless Audio System. These tests assess the system's impact on MRI image quality, safety parameters (RF heating, B1 fields), noise reduction, and quality of service for communication. It demonstrates the algorithm's (device's) standalone performance by showing it meets pre-defined acceptance criteria for these aspects.

7. Type of Ground Truth Used for Test Set

For the bench tests, the ground truth appears to be based on pre-defined performance standards and objective measurements (e.g., measuring temperature, SNR, uniformity, noise levels, NRR, quality of service).

For the clinical performance testing, the ground truth seems to be based on the observation that the device "does not adversely affect MR image production in the worst-case environment" and that "No adverse events were reported." This suggests qualitative assessment by clinicians or technicians during actual MRI scans, evaluating image quality and patient safety.

8. Sample Size for the Training Set

The document does not mention a training set size. This device is not an AI/ML model that would typically have a "training set" in the conventional sense.

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

As there is no mention of a training set in the context of an AI/ML device, this information is not applicable and not provided in the document.

Ask a specific question about this device

To be used in conjunction with GEHC 3.0T Magnetic Resonance Scanners to produce diagnostic and interventional planning images of the breast that can be interpreted by a trained physician. When used with biopsy components, this device permits access to the breast anatomy for interventional procedures that can be performed by a trained physician.

The NeoCoil 3.0T 16ch Breast Coil is a phased array coil for imaging structures of the breast, axilla and chest wall. The 3.0T 16ch Breast Coil is a three part receive-only coil designed to provide high resolution imaging. The.3.0T 16ch Breast Coil includes a coil support structure, patient support structure, biopsy components and comfort pads.

The NeoCoil 3.0T 16ch Breast Coil is tuned to receive RF frequency corresponding to the proton precession in a 3 tesla magnetic field, which is governed by the Larmor equation.

The provided text describes the NeoCoil 3.0T 16ch Breast Coil and its performance testing to support its substantial equivalence to a predicate device. However, it does not describe a study that proves a device meets specific acceptance criteria in the context of an AI/algorithm-driven diagnostic device. The device in question is a magnetic resonance imaging (MRI) coil, which is a hardware component, not an AI or software device.

Therefore, many of the requested categories for AI/algorithm performance and study design are not applicable to the information provided for this hardware device.

Here's an attempt to extract the relevant information and indicate where the requested details are not present due to the nature of the device:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size (Test Set): Not explicitly stated for specific tests. The document mentions "clinical performance testing" but does not quantify the number of patients or images.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). It only mentions "clinical data in this section exhibits a mix of technical factors and anatomy".

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

• Not Applicable. This is a hardware device (MRI coil) and its performance is evaluated based on physical measurements (temperature, RF properties) and image quality metrics (SNR, uniformity) rather than specific diagnostic outcomes requiring expert consensus on a test set of cases. The "Indications for Use" mention interpretation by a "trained physician," but this is for general clinical use, not for establishing ground truth in a performance study of the coil itself.

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

• Not Applicable. See point 3.

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. This is not an AI device.

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

• Not Applicable. This is not an AI device.

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

• Not Applicable in the context of diagnostic accuracy for a specific disease. The "ground truth" for this device's performance involves objective physical measurements and adherence to engineering and imaging standards (e.g., temperature limits, signal-to-noise ratios, image uniformity as per NEMA MS 6-2008).

8. The sample size for the training set:

• Not Applicable. This is not an AI device that requires a training set.

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

• Not Applicable. This is not an AI device.

Ask a specific question about this device

To be used in conjunction with a CT scanner to acquire gated cardiac images. The product is an aid to the acquisition of CT cardiac scans.

The NeoCoil ECG CT Gating Device (ECGD) is a product used to acquire electrocardiogram (ECG) data from a patient and to generate and supply ECG waveform and triggering pulses to the CT scanner to aid in cardiac scanning. The ECGD product includes a Physiologic Acquisition Module (PAM) that connects to the patient using ECG lead wires (Figure 3.), acquires ECG data, processes the ECG data, and wirelessly transmits the data to the Receive Interface Module (RIM). The RIM will wirelessly receive data from the PAM, create analog ECG waveform and trigger pulse mark, and interfaces with the scanner. The ECG waveform and trigger marks can be seen on the scanner console.

The System is compatible with Toshiba Aquilion ONE and Aquilion PRIME CT scanners.

Here's a breakdown of the acceptance criteria and study information for the "ECG CT Gating Device," based on the provided document:

1. Acceptance Criteria and Reported Device Performance

1. Normal Sinus Rhythm
2. Sinus Arrhythmia (heart rate variability)
3. Atrial Fibrillation (AFib)
4. Paroxysmal Supraventricular Tachycardia (PSVT)
5. Bradycardia
6. Second-Degree Atrioventricular block | Identical |
   | Technology Comparison (Trigger Output) | Identical to Predicate: 0V baseline, with +5V trigger, 100ms pulse width | Identical |
   | Technology Comparison (Performance Index) | Provides trigger pulses to the scanner, corresponding with R wave peaks, with an accuracy (performance index) of ≥ 98%. | ≥ 98% |
   | ECG CT Gating Device Compatibility Testing | Gating Device is Compatible with Toshiba Aquilon CT scanners. | Pass |
   | ECG CT Gating Waveforms and Triggers | Device accurately produces waveforms and triggers through specified range and arrhythmias. | Pass |
   | ECG CT Gating Device Interference Testing | Potentially interfering devices in the CT environment do not interfere with the ECG CT Gating Device. | Pass |
   | ECG CT Gating Device Quality of Service | The ECG Gating Device provides a safe and effective wireless quality of service in the CT environment. | Pass |
   | Clinical Performance (No adverse events) | No adverse events were reported during clinical performance testing. | No adverse events |
   | Clinical Performance (Adequate performance for Indications for Use) | The ECG CT Gating Device demonstrated performance adequate to support the Indications for Use. | Demonstrated adequate performance |

Note on Performance Index: The device claims an accuracy of ≥ 98%, which is considered equivalent to the predicate, as the predicate did not make a specific claim for this metric. The document notes that in the rare case of a mistrigger, manual adjustment by the CT scanner operator can be done, similar to the predicate device.

2. Sample Size and Data Provenance for the Test Set

The document mentions "Clinical testing" and "clinical performance testing" but does not specify the sample size for these tests. It also does not explicitly state the country of origin for the data or whether it was retrospective or prospective.

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

The document does not specify the number or qualifications of experts used to establish the ground truth for the test set.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method used for the test set.

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

There is no indication that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was conducted with human readers or AI assistance. The device is an ECG CT Gating Device, which is an accessory to a CT scanner, not an AI-powered diagnostic tool for interpretation.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance assessment was effectively conducted. The "Performance Index" of ≥ 98% for trigger pulse accuracy is a direct measure of the device's algorithmic performance in identifying R wave peaks and generating triggers. The "ECG CT Gating Waveforms and Triggers" test also assesses the device's standalone capability to accurately produce waveforms and triggers.

7. Type of Ground Truth Used

The type of ground truth used for performance assessment appears to be based on:

• Engineering/Technical Specifications: For criteria like heart rate range, trigger output, and accuracy of waveforms/triggers.
• Clinical Observation: For confirming the absence of adverse events and adequate performance for its intended use in generating cross-sectional cardiac images.

For the Performance Index, the ground truth would likely be established by comparing the device's generated trigger pulses against a "true" R-wave peak derived from a precise, independent ECG measurement or a known simulated ECG waveform.

8. Sample Size for the Training Set

The document does not provide information on a training set sample size. This device is not described as an AI/machine learning device that would typically have a distinct training set. Its functionality appears to be based on established physiological signal processing, rather than learned patterns.

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

As there is no mention of a training set, there is no information on how its ground truth might have been established.

Ask a specific question about this device

To be used in conjunction with Toshiba 3T Magnetic Resonance Scanners with ODU connectors to produce diagnostic images of the upper and lower extremities, chest, abdomen, pelvis, head, neck and spine that can be interpreted by a trained physician.

The NeoCoil 3T 16ch Flex SPEEDER Coils are a receive-only phased array coil system designed to provide high resolution imaging for the upper and lower extremities, chest. abdomen, pelvis, head, neck, and spine. The system is compatible with 2D, 3D, parallel and isotropic imaging, as well as, coil signal intensity correction. The system consists of:

• Two formable, flexible and detachable antennae of different size that can be . wrapped or orientated flat, in order to accommodate various anatomic shapes and sizes.
• . Optional accessories designed for patient comfort and reduced motion artifacts.
  The NeoCoil 3T 16ch Flex SPEEDER Coils are tuned to receive RF frequency corresponding to the proton precession in a 3 tesla magnetic field, which is governed by the Larmor equation.

Here's a breakdown of the acceptance criteria and study information for the NeoCoil 3T 16ch Flex SPEEDER Coils, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

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

The document does not explicitly state the numerical sample size for the "test set" in terms of number of patients or images. It mentions "Clinical data in this section exhibits a mix of technical factors and anatomy in the axial, sagittal and coronal planes." This suggests a varied, but unspecified, sample for clinical testing.

The data provenance is not explicitly stated as 'country of origin' or 'retrospective/prospective'. However, given that it's a 510(k) submission for a device to be marketed in the USA, and the testing involves compliance with standards like NEMA MS 6-2008, it's highly likely that the testing was conducted prospectively to demonstrate performance for regulatory clearance, primarily in a research or clinical setting relevant to MRI device evaluation.

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

The document does not specify the number of experts used or their qualifications for establishing ground truth in the clinical performance testing. It simply states that the images "can be interpreted by a trained physician," which is a general statement about the intended use of the diagnostic images rather than the ground truth establishment process for the study itself.

4. Adjudication Method for the Test Set:

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for the clinical performance test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of AI Improvement:

An MRMC comparative effectiveness study was not done. This device is an MRI coil, not an AI-powered diagnostic algorithm. The testing focuses on the physical performance and imaging capabilities of the hardware. Therefore, there is no mention of AI assistance or its effect size on human readers.

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

This question is not applicable. The device is an MRI coil, which is hardware, not a software algorithm. Therefore, "standalone (algorithm only)" performance is not relevant.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.):

For the clinical performance testing, the "ground truth" implicitly relies on the ability of the images generated by the coil to be "interpreted by a trained physician" for diagnostic purposes. This suggests that the ground truth would be based on clinical interpretation by physicians, likely in comparison to established diagnostic standards or findings from other imaging modalities if specific pathologies were being assessed. However, the document does not explicitly detail the method for establishing "ground truth" beyond meeting diagnostic quality for interpretation. The primary focus of the performance tests (SNR, image uniformity, B1 field distortion) is on the physical imaging capabilities of the coil.

8. The Sample Size for the Training Set:

This question is not applicable. The NeoCoil 3T 16ch Flex SPEEDER Coils are hardware (an MRI coil), not a machine learning or AI algorithm that requires a "training set."

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

This question is not applicable as there is no training set for an MRI coil.

Ask a specific question about this device

The NeoColl PCE system is intended to provide audio entertainment and facilitate patient communication in MBL environments at 3 tesla field strength and below.

The NeoCoil Patient Communication and Entertainment (PCE) System is intended to provide audio entertainment and facilitate communications between the patient and the operator in a Magnetic Resonance Imaging (MRI) scanner environment. The PCE System is intended to be used by healthcare professionals.

The NeoCoil Patient Communication and Entertainment System is a modular system comprised of wireless patient headphones, a remote audio data source unit, patient alert, and communications infrastructure.

The NeoCoil Patient Communication and Entertainment (PCE) System is intended to provide audio entertainment and facilitate communications between the patient and the operator in a Magnetic Resonance Imaging (MRI) scanner environment. The device's performance meets the requirements of pre-defined acceptance criteria and intended uses.

Acceptance Criteria and Reported Device Performance

Study Details

• Sample size used for the test set and the data provenance: The document mentions "clinical performance testing" and indicates that "No adverse events were reported during clinical performance testing." However, it does not specify the exact sample size for the test set or the country of origin of the data. It implies a prospective or at least observed clinical use during testing to ensure no adverse effects.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: This information is not provided in the document.
• Adjudication method for the test set: This information is not provided in the document.
• 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: An MRMC comparative effectiveness study was not conducted, as this device (Patient Communication and Entertainment System) is not an AI-driven diagnostic or interpretative tool for medical images, but rather a patient comfort and communication system during MRI.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The device is a system involving hardware and interaction with human operators and patients. Therefore, a standalone algorithm-only performance assessment is not applicable.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): The ground truth for this device's performance is based on fulfilling pre-defined engineering and safety standards related to MRI compatibility, communication quality, and noise reduction. It's not a diagnostic device, so ground truth like pathology or expert consensus on image interpretation is not relevant. The clinical performance testing focused on ensuring the device "does not adversely affect MR image production in the worst-case environment" and that "no adverse events were reported."
• The sample size for the training set: This is not applicable, as this is not a machine learning or AI-driven device requiring a training set.
• How the ground truth for the training set was established: This is not applicable.

Ask a specific question about this device

To be used in conjunction with Siemens 1.5T MAGNETOM MRI scanners to produce diagnostic images of the upper and lower extremities, chest, abdomen, pelvis and spine that can be interpreted by a trained physician.

The NeoCoil 1.5T 16-Channel Flex Coils for Siemens is a system of phased array, receiveonly coils. The system consists of:

• Two formable, flexible and detachable antennae of different size that can be . wrapped or orientated flat, in order to accommodate various anatomic shapes and sizes.
• Optional accessories designed for patient comfort and reduced motion artifacts. .
  The NeoCoil 1.5T 16-Channel Flex Coils for Siemens are tuned to receive RF frequency corresponding to the proton precession in a 1.5 testa magnetic field, which is governed by the Larmor equation.

The provided text describes the 510(k) summary for the NeoCoil 1.5T 16-Channel Flex Coils. This device is a magnetic resonance specialty coil, not an AI/ML powered device, therefore the information requested for AI/ML powered devices, e.g. sample sizes for test and training sets, number of experts used for ground truth, adjudication method, MRMC studies, and standalone performance data, are not applicable or provided in the submission.

However, the document does detail the acceptance criteria and study results for this specific medical device.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not explicitly stated with a specific number of cases or patients. The document mentions "clinical data submitted exhibits a mix of scanner configurations, pulse sequences, imaging options, field of view and anatomy in the axial, sagittal and coronal planes."
• Data Provenance: Not explicitly stated (e.g., country of origin). The testing included "clinical performance testing," which implies prospective data collection, but it does not specify whether it was retrospective or prospective.

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

• This information is not provided as the device is an MRI coil, not an AI/ML algorithm. Ground truth, in the context of diagnostic image interpretation, is typically established by trained physicians interpreting the images produced by the device, as mentioned in the Indications for Use ("...images...that can be interpreted by a trained physician."). The document does not specify the number or qualifications of these physicians for the performance testing.

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

• This information is not applicable and therefore not provided for this type of medical device (MRI coil). Adjudication methods are typically relevant for studies evaluating human interpretation or AI algorithm performance against a consensus 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:

• No MRMC comparative effectiveness study was done, as this device is an MRI coil, not an AI-assisted diagnostic tool. Therefore, the effect size of human readers improving with or without AI assistance is not applicable and not provided.

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

• A standalone performance assessment in the context of an AI algorithm is not applicable to this MRI coil. The performance assessment focused on the coil's physical, electrical, and imaging characteristics.

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

• For the bench performance tests, the "ground truth" was based on pre-defined performance standards (e.g., maximum temperature, adequate RF decoupling, meeting Siemens performance requirements for B1 field, and NEMA MS 6-2008 standards for SNR and Image Uniformity).
• For the clinical performance testing, the "ground truth" was the ability of the coil to produce diagnostic images that could be interpreted by a trained physician, as per the stated Indications for Use. No specific "expert consensus," "pathology," or "outcomes data" are explicitly mentioned as ground truth for this device's performance evaluation beyond the general statement of "performance adequate to support the Indications for Use."

8. The sample size for the training set:

• This information is not applicable and not provided as the device is an MRI coil, not an AI/ML powered device that requires a training set.

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

• This information is not applicable and not provided as the device is an MRI coil, not an AI/ML powered device.

Ask a specific question about this device