Search Results

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

Philips Magnetic Resonance (MR) systems are Medical Electrical Systems indicated for use as a diagnostic device. This MR system enables trained physicians to obtain cross-sectional images and/or spectra of the internal structure of the head, body or extremities, in any orientation, representing the spatial distribution of protons or other nuclei with spin. Image appearance is determined by many different physical properties of the tissue and the anatomy, the MR scan technique applied, and presence of contrast agents for diagnostic imaging applications should be performed consistent with the approved labeling for the contrast agent. The trained clinical user can adjust the MR scan parameters to customize image appearance, accelerate image acquisition. and synchronize with the patient's breathing or cardiac cycle. The systems can use combinations of images to produce physical parameters, and related derived images, spectra, and measurements of physical parameters, when interpreted by a trained physician, provide information that may assist diagnosis and therapy planning. The accuracy of determined physical parameters depends on system and scan parameters, and must be controlled and validated by the clinical user. In addition the Philips MR systems provide imaging capabilities, such as MR fluoroscopy, to guide and evaluate interventional and minimally invasive procedures in the head, body and extremities. MR Interventional procedures, performed inside or adjacent to the Philips MR system, must be performed with R Conditional or MR Safe instrumentation as selected and evaluated by the clinical user for use with the specific MR system configuration in the hospital. The appropriateness and use of information from a Philips MR system for a specific interventional procedure and specific MR system configuration must be validated by the clinical user.

This submission covers the proposed Achieva 1.5T, Achieva 3.0T, and the Intera 1.5T MR Systems R5.6, hereafter to be known as Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems. The proposed Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems are 60 cm bore 1.5 Tesla (1.5T) and 3.0 Tesla (3.0T) Magnetic Resonance Diagnostic Devices. This submission of the proposed Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems contains a description of the software and hardware modifications made since the last 510(k) clearance of the primary predicate Achieva, Intera & Panorama 1.0T R2.5 (K063559, 01/04/2007). The Achieva 1.5T and Intera 1.5T systems differ in outside covers only, both systems function in an identical manner. The proposed Achieva 1.5T, 3.0T and Intera 1.5T MR Systems are substantially equivalent to the primary predicate Achieva, Intera & Panorama 1.0T R2.5 (K063559, 01/04/2007), and the 1st legally marketed reference device Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition (K183063, 02/14/2019) and the 2nd legally marketed reference device Achieva R4 1.5T and Achieva R4 3.0T (aka Ingenia, K110151, 03/22/2011). The proposed Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems are intended to be marketed with the following pulse sequences and coils that were previously cleared by FDA: 1. mDIXON (K102344) 2. SWIp (K131241) 3. mDIXON-Quant (K133526) 4. MRE (K140666) 5. mDIXON XD (K143128) 6. O-MAR (K143253) 7. MultiBand SENSE (K143606) 8. 3D APT (K172920) 9. Achieva and Intera Coils

Here's a breakdown of the acceptance criteria and study information for the Philips Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems, based on the provided text:

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study for a novel device. As such, information typically found in a clinical study report (like detailed statistical methods, effect sizes for human readers with and without AI, or specific ground truth methodologies for a novel algorithm) is not present in this type of submission. The device described is a Magnetic Resonance (MR) system, which is a diagnostic imaging device, not a specific AI-powered diagnostic algorithm.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not applicable. This submission relies on non-clinical verification and validation tests rather than a separate clinical test set with patient data for assessing a new algorithm's performance. The device is an MR system, and the evaluation focuses on its technical performance and safety, not on the diagnostic accuracy of a new AI algorithm processing patient data.
• Data Provenance: Not applicable for a separate clinical test set. The non-clinical tests would involve engineering and performance evaluations in a controlled environment, not patient data from a specific country or collected retrospectively/prospectively for a new algorithm's evaluation.

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

• Number of Experts/Qualifications: Not applicable. As this involves non-clinical verification and validation testing of an MR system's performance and safety features (e.g., image quality, electromagnetic compatibility, software functionality), the "ground truth" would be established by engineering and quality assurance standards, benchmarks, and regulatory requirements, not by expert interpretation of patient images for diagnostic accuracy.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. Since there's no clinical test set requiring expert interpretation and consensus, there's no need for an adjudication method.

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

• MRMC Study Done: No. An MRMC study is typically performed to evaluate the impact of a new diagnostic algorithm on human reader performance (e.g., radiologists interpreting images with and without AI assistance). This submission pertains to an MR system, which is the imaging hardware and associated software to acquire images. The document explicitly states: "The proposed Achieva 1.5T, 3.0T, and Intera 1.5T MR Systems did not require a clinical study since substantial equivalence to the primary predicate device was proven with the verification/validation testing."
• Effect Size of Human Readers with vs. without AI: Not applicable, as no MRMC study was performed.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• Standalone Study Done: No. The device is an MR imaging system; it is not a standalone AI algorithm designed to provide diagnostic outputs independently. The output of the MR system (images, spectra, measurements) is intended to be interpreted by a trained physician.

7. Type of Ground Truth Used

• Type of Ground Truth: Not applicable in the context of diagnostic accuracy for a specific algorithm. For the non-clinical verification and validation, the ground truth would be defined by engineering specifications, regulatory standards, and established benchmarks for parameters like image quality, signal-to-noise ratio, spatial resolution, gradient linearity, safety limits (e.g., SAR), and software functionality.

8. Sample Size for the Training Set

• Training Set Sample Size: Not applicable. The document describes an MR imaging system, not a machine learning or AI algorithm that would typically require a training set of data. While the system's software components were developed and tested, the information provided does not indicate the use of a data-driven training set in the context of an FDA-cleared AI/ML algorithm.

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

• Ground Truth for Training Set: Not applicable, as there is no mention of a training set or an AI/ML algorithm requiring such.

Ask a specific question about this device

This system is a Magnetic Resonance Medical Electrical Systems indicated for use as a diagnostic device. The system can produce cross-sectional images, spectroscopic images and/or spectra in any orientation of the internal structure of the head, body or extremities.

Magnetic Resonance images represent the spatial distribution of protons or other nuclei with spin. Image appearance is determined by many different physical properties of the tissue and the MR scan technique applied. The image acquisition process can be synchronized with the patient's breathing or cardiac cycle. The systems can use combinations of images to produce physical parameters, and related derived images.

Images, spectra, and measurements of physical parameters, when interpreted by a trained physician, provide information that may assist the diagnosis and therapy planning. The accuracy of determined physical parameters depends on system and scan parameters, and must be controlled and validated by the clinical user. The use of contrast agents for diagnostic imaging applications should be performed consistent with the approved labeling for the contrast agent.

In addition the Philips MR systems provide imaging capabilities, such as MR fluoroscopy, to guide and evaluate interventional and minimally invasive procedures in the head, body and extremities.

MR Interventional procedures, performed inside or adjacent to the Philips MR system, must be performed with MR Conditional or MR Safe instrumentation as selected and evaluated by the clinical user for use with the specific MR system configuration in the hospital. The appropriateness and use of information from a Philips MR system for a specific interventional procedure and specific MR system configuration must be validated by the clinical user.

The proposed Ingenia 1.5T CX and Ingenia 3.0T CX R5.3 with ScanWise Implant and 3D ASL features are provided with a 60 cm magnet. The system and its control software are substantially equivalent to the currently marketed and primary predicate device Achieva R2.5 (K063559, 01/04/2007), enhanced by the digital receive coil architecture as in the currently marketed and reference device Ingenia R4 (K110151, 03/22/2011).

ScanWise Implant functionality enables MR technologists to implement an improved and controlled workflow for MR Conditional implants. The feature consists of an extension to the Patient Registration User Interface where the information relevant to MR Conditional device labeling can be assessed, controlled and reviewed. The ScanWise Implant feature allows the user at the examination level to define restrictions on the 'active fields' generated by the MR system.

3D ASL functionality enables MR technologists to assess perfusion in the brain without the usage of contrast agents. The feature consists of an extension to the available scan sequences and image reconstruction algorithms. The proposed Ingenia 1.5T CX and Ingenia 3.0T CX R5.3 with ScanWise Implant and 3D ASL features also consolidate separatelycleared novel functionalities, and minor changes since the clearance of the currently marketed and predicate device, Achieva R2.5 (K063559, 01/04/2007). Following minor changes are covered in this submission: Enhanced Patient Communication User Interface Module, 1. IEC/ISO compliant symbols. 2. New computing platform and peripherals for MR Spectrometer (DDAS). 3. MultiTransmit 4. dStream architecture implementation and commercialize system name as Ingenia CX 5. Planning on cine images. 6. SAR related parameters (SED). Pregnancy status related to Normal Mode. 7. SED limit 8. Parameter optimization for the reconstruction algorithms. 9. Partial NSA algorithm in reconstruction. 10. AutoVoice, using pre-recorded spoken instructions. 11. VCG, optimized electrode placement and enhanced algorithm. 12. ComforTone: mechanical resonance frequency dependent timing adjustments of sequences for lower acoustic noise. 13. Enhanced sequences: a. LIPO b. Black Blood Imaging c. 4D TRAK XD d. Zoom Diffusion Imaging e. 3D Vane XD 4D TRANCE f. g. 3D NerveVIEW h. Fast B1 Mapping and B1 Shading filter i. AutoSpair. TSE flow compensation enhancement 1. k. Optimized 3D TSE flip angle sweeps per anatomy ENCASE: 3D encoding 1. m. CardiacQuant: triggered T1 mapping sequence n. pCASL o. DTI enhancements QA Tool and fMRI stability p.

The provided text describes the Philips Ingenia 1.5T CX and Ingenia 3.0T CX R5.3 MR systems and their features, including "ScanWise Implant" and "3D ASL". However, it does not contain the detailed information required to fully answer all aspects of your request regarding acceptance criteria and a specific study proving those criteria were met.

Specifically, the document states: "The verification and or validation test results, combined with sample clinical images demonstrate that the proposed Ingenia 1.5T CX and Ingenia 3.0T CX R5.3 with ScanWise Implant and 3D ASL features: Complies with the aforementioned international and FDA-recognized consensus standards and Device specific guidance document, entitled “Guidance for the Submission Of Premarket Notifications for Magnetic Resonance Diagnostic Devices – November 14, 1998” Meets the acceptance criteria and is adequate for its intended use."

This indicates that acceptance criteria exist and were met, but the document does not explicitly list the quantitative acceptance criteria themselves, nor does it describe a detailed study that would allow for a precise breakdown of the device's performance against these criteria.

Therefore, much of the requested information cannot be extracted from this document.

Here's what can be answered based on the provided text, and what remains unknown:

1. Table of acceptance criteria and the reported device performance

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

• Unknown. The document states that "Non-Clinical verification and or validation tests have been performed with regards to the intended use, the technical claims, the requirement specifications and the risk management results," and mention "sample clinical images" were used. However, it does not specify the sample size of any test set (e.g., number of patients, number of images), nor its provenance (country, retrospective/prospective).

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)

• Unknown. The document mentions the "interpretation by a trained physician" for general use but does not detail how ground truth was established for any specific test set, nor the number or qualifications of experts.

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

• Unknown. The document does not describe any adjudication method.

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. The document explicitly states: "The proposed Ingenia 1.5T CX and Ingenia 3.0T CX R5.3 with ScanWise Implant and 3D ASL features did not require clinical study since substantial equivalence to the primary currently marketed and predicate device was demonstrated with the following attributes: Design features; Indication for use; Fundamental scientific technology; Non-clinical performance testing; and Safety and effectiveness."
• Furthermore, the document describes the system as a diagnostic device that produces images for physicians to interpret, and features like ScanWise Implant and 3D ASL are described as enabling specific functionalities or workflows. It does not suggest these features involve AI assistance for human readers in the sense of a comparative effectiveness study.

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

• While "Non-Clinical verification and or validation tests" were performed, and software/algorithms are integral to the system's function (e.g., image reconstruction algorithms, ASL processing), the document does not describe a standalone algorithm performance study separate from the overall system performance verification. The device is an MRI system, and its performance would be evaluated as a complete system, not just individual algorithms in isolation.

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

• Unknown. The document vaguely mentions "sample clinical images" in the context of verification/validation, but does not specify the method for establishing ground truth for these images.

8. The sample size for the training set

• Not applicable / Unknown related to specific AI training. The document describes a medical device (MRI system) with advanced features (ScanWise Implant, 3D ASL) and various software enhancements. It does not explicitly state that these features were developed using machine learning or AI that required a distinct "training set" in the modern sense of AI/ML development. The document predates the widespread regulatory focus on AI/ML training data. It refers to "image reconstruction algorithms" but does not detail their development process.

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

• Not applicable. As above, the document does not mention a "training set" in the context of modern AI/ML.

Ask a specific question about this device

MultiBand SENSE is a software option intended for use on Achieva and Ingenia 1.5T & 3.OT MR Systems. It's indicated for use in magnetic resonance imaging of the brain for BOLD fMRI. MultiBand SENSE consists of an acquisition and reconstruction technique allowing simultaneous excitation of multiple volumes to accelerate imaging acquisition times or increasing coverage or resolution without increasing scan time.

The MultiBand SENSE technique enables simultaneous excitation and acquisition of multiple volumes or slices for the purpose of speeding up acquisition times or increasing coverage or resolution at constant scan time. The simultaneous excitation is done using a multi-band radiofrequency pulse. The unfolding of the simultaneously acquired volumes is done using the SENSE algorithm. The unfolding process (solving the linear equation of the SENSE algorithm) is improved by introducing a linear phase over k-space in the volume direction resulting in a spatial shift of the aliased pixels. The phase shift is applied by additional blip-gradients in the slice direction or switching between different RF pulses, and compensated for in reconstruction by a translation of the coil sensitivity data before the SENSE unfolding. The feature consists of:

• Modulated RF pulses exciting 2 or more slices
• Blip-gradients to introduce a phase shift for improved unfolding ●
• New parameterization of the SENSE calculations ●
• Shifting coil sensitivities in reconstruction to correct for linear phase shift. ●

MultiBand SENSE is supported on the following systems:

• . 3.0T Ingenia
• 3.0T Achieva ●
• 1.5T Ingenia ●
• . 1.5T Achieva

The functionality is supported on all available gradient performance levels. Optimized protocols will be provided for the different performance points. MultiBand SENSE is supported on the centralized data acquisition systems of the Achieva systems as well as the digitally networked data acquisition system of the Ingenia systems. The data acquisition system is fully transparent to the MultiBand SENSE pulse sequences and reconstructions.

The main functional units in the software are:

• Methods (acquisition of MR signals by means of MR pulse sequences) -
• Reconstruction (transforming the MR signals to images) -
• -Patient Administration (storing of the images in the database and providing access)
• Viewing (display of images) -

The technical impact of the feature MultiBand SENSE comprises:

• -Methods: Introduction of a modulated RF pulse. Apply blipped gradients. Provide new parameterization for SENSE reconstruction.
• Reconstruction: Read new parameterization of SENSE calculations. Shift coil sensitivities before SENSE calculations.

No off-the-shelf software is used for the feature MultiBand SENSE. The off-the-shelf software used in the basic MR system is cleared. MultiBand SENSE is not designed to be connected to an external network.

MultiBand SENSE does not require any change of the hardware platform. The extension introduced by Multiband SENSE, are in methods pulse sequence code, and in reconstruction only for a new parameterization of a cleared SENSE unfolding calculation. Those run on the host computer characteristics :

• Manufacturer: HP; Model: Z420; Processor clock: 3.5 GHz; RAM: 64 GB RAM; -Processors: six core with hyper threading
• Operating system: Windows 7, 64 bits -

The only new element for the operator of the Multiband SENSE feature in this clinical routine workflow is:

• Protocol selection: The operator selects an ExamCard with Multiband SENSE protocols -
• Planscan phase: Optionally the operator may want to change the predefined Multiband acceleration factor.

All other steps are not changed. The generated image types can be viewed, post-processed, printed and archived as any other image type.

This document is a 510(k) Summary for the Philips MultiBand SENSE device, a software option for MRI systems. It focuses on demonstrating substantial equivalence to a predicate device. The information provided is primarily related to verification and validation, rather than a detailed comparative effectiveness study with specific acceptance criteria and statistical analysis as might be found in a clinical trial report.

Here's an analysis of the provided text in relation to your questions, noting where information is explicitly stated, implied, or absent:

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

The document does not present a formal table of quantitative acceptance criteria and corresponding device performance metrics in the way a statistically powered study might. Instead, it describes general successful outcomes of verification and validation testing.

Ask a specific question about this device

mDIXON XD is a software option intended for use on Achieva, Ingenia 1.5T & 3T MR Systems. It is indicated for use in Magnetic Resonance Imaging of the human body. mDIXON XD is an enhanced 2-point fat-free mDIXON technology, available for gradient echo and spin echo acquisitions. mDIXON XD enables the combination of a fat-free technology with the MultiVane XD motion-free technique for anatomies such as head. mDIXON XD also enables subtractionless MR Angiography in areas of the body where exogenous contrast media has been approved for MR imaging.

mDIXON XD provides an improved water/fat reconstruction algorithm (7-peak fat modeling, B0correction and fat-shift correction). mDIXON XD relies on the 2-point mDIXON fat-free technology making use of unrestricted echo times and is capable of generating four image contrasts (Water, Fat, In-Phase, Out-Phase) in one scan. mDIXON XD can be used with the following:

• Multivane XD (motion correction) for the head
• MR Angiography (subtractionless MRA), removes the need for the subtraction of the pre-● and post-contrast enhanced images.
• Gradient echo (FFE Fast Field Echo) and turbo spin echo (TSE) sequences to achieve ● efficient fat-free scanning compatibility, even at large FOV or sub-millimetric resolutions
  mDIXON XD is supported on the following systems:
• 3.0T Ingenia
• 3.0T Achieva ●
• 1.5T Ingenia
• 1.5T Achieva ●
  The functionality is supported on all available gradient performance levels. Optimized protocols will be provided for the different performance points. mDIXON XD is supported on the centralized data acquisition systems of the Achieva systems as well as the digitally networked data acquisition system of the Ingenia systems. The data acquisition system is fully transparent to the pulse sequences and mDIXON XD reconstructions.

The provided text is a 510(k) summary for the Philips Medical Systems' mDIXON XD device. It describes the device, its intended use, and provides a brief summary of nonclinical and clinical tests. However, it does not contain specific acceptance criteria, detailed study designs, or quantitative performance metrics as requested in the prompt.

Therefore, I cannot provide a table of acceptance criteria and the reported device performance, nor can I answer questions about sample sizes for test/training sets, data provenance, number/qualifications of experts, or adjudication methods, as this information is not present in the provided document.

Here's what can be extracted based on the document:

1. Table of Acceptance Criteria and Reported Device Performance:

• Acceptance Criteria: Not explicitly stated as quantitative metrics. The document broadly states that the device was "successful" and "passed" clinical user needs.
• Reported Device Performance:
  • For total body and head/neck examinations: Image Quality, fat suppression, and fat suppression over large FOV were similar or better with mDIXON XD compared to e-Thrive.
  • For cardiac examinations: Image quality and fat suppression were better with mDIXON XD.
  • For MultiVane XD in combination with mDIXON TSE: Motion related artifacts were reduced compared to mDIXON TSE alone.
  • MultiVane XD with mDIXON XD can be used with T2 in head imaging.

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

• Sample Size for Test Set: Not specified.
• Data Provenance: Not specified (e.g., country of origin, retrospective/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. The term "clinical user needs" suggests clinical evaluation, but details on expert involvement are absent.

4. Adjudication method for the test set:

• Not specified.

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 involving human readers and AI assistance is described. The comparison is between mDIXON XD and existing technologies (e-Thrive, mDIXON TSE alone).

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

• The testing described is on the "device" as a whole, which is a software option for MR systems. It's an "algorithm only" performance in the sense that it evaluates the output of the software. However, it's not a standalone AI device in the modern sense of a diagnostic AI assisting or replacing a human. The clinical validation assesses image quality and artifact reduction.

7. The type of ground truth used:

• The "ground truth" implicitly used is expert judgment and assessment of "Image Quality," "fat suppression," and "motion related artifacts" as perceived by "clinical user needs." It's based on subjective clinical assessment rather than objective pathology or outcomes data.

8. The sample size for the training set:

• Not specified. The document describes verification and validation but does not detail a separate training set, suggesting this is a software update/feature validation rather than a deep learning algorithm that requires a distinct training phase.

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

• Neither a training set nor its ground truth establishment is mentioned.

Ask a specific question about this device

MR Elastography is a software option intended for use on Achieva and Ingenia 1.5T and 3.0T MR Systems for producing images representing tissue stiffness of the abdomen area such as liver and muscle. MR Elastography applies an MR acquisition sequence synchronized with an external source of vibration to produce images representing tissue stiffness (in kiloPascals, kPa). The stiffness image production technique also creates an overlay representing the reliability of the stiffness image production algorithm.

The MR Elastography feature consists of a specialized acquisition: a source of acoustic frequency vibration and means to impart that vibration to the scan subject: an image processing step to produce stiffness maps, confidence maps, and wave images; and an analysis tool to evaluate the parametric images created.

The acquisition is based on the Phase Contrast FFE sequence acquired while imparting a known frequency of vibration into the patient. A set of images with controlled phase differences between the acquisition and the mechanical oscillation is created by synchronizing the mechanical driver with the acquisition at different time delays. The vibration source and connecting equipment are provided by Resoundant Inc. as a complete set. Elasticity images are created from the image data generated by this acquisition strategy using an algorithm developed by Resoundant Inc. and The Mayo Clinic. In addition, wave images and confidence overlays are also produced to provide data quality assurance.

The Philips MR Elastography software option is intended for use on Achieva and Ingenia 1.5T and 3.0T MR Systems to produce images representing tissue stiffness of the abdomen area (e.g., liver and muscle). It utilizes an MR acquisition sequence synchronized with an external vibration source to generate stiffness images (in kiloPascals, kPa) and an overlay indicating the reliability of the stiffness image production algorithm.

The acceptance criteria for the device are not explicitly quantified with specific performance metrics in the provided document. Instead, the document describes the successful completion of verification activities to demonstrate functionality and substantial equivalence to predicate devices.

Here's an analysis of the provided information:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify the sample size used for the test set. It mentions "sample images" and "confidence studies" but does not provide details on the number of subjects or images included in these tests. The data provenance is also not explicitly stated in terms of country of origin or whether the studies were retrospective or prospective.

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

This information is not provided in the document. The document mentions an "algorithm developed by Resoundant Inc. and The Mayo Clinic" and that the "MR Elastography software post-processing package was based on an estimation algorithm provided by The Mayo Clinic and Resoundant, Inc." but does not detail the specific involvement of experts in establishing ground truth for testing, nor their qualifications.

4. Adjudication Method for the Test Set

The adjudication method used for the test set is not described in the provided document.

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

No MRMC comparative effectiveness study is mentioned or referenced in the provided text. The document focuses on demonstrating substantial equivalence to predicate devices and fulfilling functionality and safety requirements.

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

The document describes the "MR Elastography" feature as consisting of hardware and software elements, including an "image processing step to produce stiffness maps, confidence maps, and wave images" and an "analysis tool." The "confidence studies" seem to be related to the algorithm's performance in producing repeatable results and differentiating tissue stiffness, which implies a standalone evaluation of the algorithm's output. However, it's not explicitly stated as a formal "standalone" study to evaluate algorithmic performance against a definitive ground truth in a clinical context.

7. The Type of Ground Truth Used

The type of ground truth used is not explicitly specified. The document states that "confidence studies prove that MR Elastography produces repeatable results and can reliably differentiate between tissues of different stiffness," suggesting that some form of reference independent of the device was used to confirm stiffness differentiation, potentially phantoms with known stiffness or other established methods. However, the specific type (e.g., pathology, outcomes data) is not detailed.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set. It mentions that the algorithm was "developed by Resoundant Inc. and The Mayo Clinic" and that the software was developed "in conjunction with The Mayo Clinic and Resoundant, Inc.," but does not elaborate on the data used during development.

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

This information is not provided in the document.

Ask a specific question about this device

The Ingenia 1.5T and Ingenia 3.0T are magnetic resonance diagnostic devices that produce cross-sectional images, spectroscopy images and/or spectra in any orientation of the internal structure of the whole body. These images when interpreted by a trained physician, yield information that may assist in diagnosis.

In addition, the Ingenia 1.5T and Ingenia 3.0T devices provide capabilities to perform interventional procedures in the head, body and extremities, which may be facilitated by MR techniques, such as real time imaging. Such procedures must be performed with MR compatible instrumentation as selected and evaluated by the clinical user.

The 510(k) subject devices are magnetic resonance coil is designed and intended for use with Philips 1.5T & 3.0T Magnetic Resonance Imaging (MRI) systems. The MR Coil devices work in unison with the Body Coil of the MRI system, which will transmit the radio frequency (RF) signals, so the coil may receive the resultant RF signal from the excited nuclei. The coil is designed as receive only for high resolution diagnostic imaging of internal body structures.

The provided text is a 510(k) Summary of Safety and Effectiveness for Philips Ingenia MRI coils. It outlines the device description, indications for use, and claims substantial equivalence to a predicate device.

Crucially, this document focuses on demonstrating substantial equivalence based on design similarities and identical indications for use, without presenting data from
clinical performance testing or algorithm-based performance studies.

Therefore, based solely on the provided text, it is not possible to describe the acceptance criteria and the study that proves the device meets the acceptance criteria in the manner requested (i.e., with performance metrics, sample sizes for test/training, expert and ground truth details, MRMC studies, etc.).

The regulatory submission explicitly states:

"The scope of this Special 510(k) is supplemental labeling to allow the MRI coil accessory devices to be packaged and labeled at another facility owned by Philips. There are no changes to the electrical or mechanical design of the MRI coil devices and no changes to the indications for use. The new labeling does not supplant any of the labeling for the MRI system as described in K110151."

This indicates that the submission is a "Special 510(k)" for a change in manufacturing location/labeling, not a submission for a new device requiring extensive performance validation for software or AI components. The MR coils themselves are hardware accessories to an MRI system.

Therefore, I cannot populate the requested table or answer the detailed questions about acceptance criteria verification studies because the provided document does not contain such information for performance metrics.

If this were a typical AI/software device submission, the provided document would be insufficient. The information usually found in such submissions (and required to answer your questions) would include:

• Acceptance Criteria for Performance: Quantifiable metrics (e.g., sensitivity, specificity, AUC, FROC, agreement rates) with predefined thresholds.
• Study Design: Details of a performance study (e.g., diagnostic accuracy study, reader study).
• Test and Training Data Provenance: Sources, characteristics, and acquisition methods of the data.
• Ground Truth Establishment: How the true status of cases was determined (e.g., multi-expert consensus, biopsy, clinical follow-up).
• Expert Qualifications and Adjudication: Details on the radiologists/experts involved in ground truth and study reading.
• Statistical Analysis Plan: Methods for evaluating the results.

In summary, the provided K123492 document is a regulatory submission for a change in manufacturing/labeling of an MRI coil, not a performance study for an AI-based diagnostic device. As such, the requested information on acceptance criteria and proof of performance (in the context of AI/software algorithm evaluation) is not present.

Ask a specific question about this device