Search Results

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, spectroscopic 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 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 Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems R5.7 with MultiBand SENSE software feature are provided on the 60 cm and 70 cm bore 1.5 Tesla (1.5T) and 3.0 Tesla (3.0T) Magnetic Resonance Diagnostic Devices.

Hereafter Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems R5.7 with MultiBand SENSE software feature will be referred to as the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems in this submission.

This bundled abbreviated 510(k) submission will include software modifications to the following legally marketed MR systems: Ingenia 1.5T, Ingenia 1.5T S, Ingenia 3.0T, Ingenia 1.5T CX, Ingenia 3.0T CX, Ingenia Elition S, Ingenia Elition X, Ingenia Ambition S and Ingenia Ambition X (K183063, 02/14/2019) and Achieva 1.5T, Achieva 3.0T, Intera 1.5T (K190461, 06/04/2019).

All of the aforementioned legally marketed systems will be brought up to the new baseline software R5.7. This submission addresses only software modifications, there are no hardware modifications made to any of the above legally marketed systems.

In this 510(k) submission, Philips Medical Systems Nederland B.V. will be addressing modifications to MultiBand SENSE and one labeling change to the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems:

• Removal of contra-indication statement of Compressed SENSE with Gd contrast agent

This 510(k) submission will also address minor software enhancements contained in software R5.7 for the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems since the clearance of the last submission for each of the systems:

1. 4D FreeBreathing
2. MR Elastography Extension
3. EPIC Brain
4. LOVA ADC
5. Computed DWI
6. SmartShim
7. VitalScreen
8. Extended Functionality Options

The proposed Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition 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. mDIXON XD (K143128)
5. O-MAR K143253
6. 3D APT (K172920)
7. Ingenia Coils

The proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems are substantially equivalent to the legally marketed predicate device Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems (K183063, 02/14/2019).

In addition, the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems is substantially equivalent to the following legally marketed reference devices: MultiBand SENSE software application (K162940, 12/30/2016), to support MultiBand SENSE for 1.5T and to support diffusion body imaging on 1.5T and 3.0T.Ingenia 1.5T, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T CX, and Ingenia 3.0T CX R5.4 K173079, 04/04/2018, to support the removal of the contra-indication of the compatibility of Compressed SENSE with (dynamic) Gadolinium contrast-enhanced imaging.

The provided text is a 510(k) Summary for Philips MR Systems, primarily addressing software modifications and enhancements. It focuses on demonstrating substantial equivalence to previously cleared devices rather than presenting a novel AI/CAD device. Therefore, much of the requested information regarding acceptance criteria specifically for AI/CAD performance, MRMC studies, and detailed ground truth establishment for a test set as typically seen for AI algorithm validation is not explicitly detailed in this document.

However, based on the non-clinical performance data section, we can infer some information about "acceptance criteria" in the context of demonstrating equivalence for the software modifications.

Here's an attempt to extract and present the information based on the provided text:

Device: Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems (with software modifications R5.7, including MultiBand SENSE and Compressed SENSE with contrast among other enhancements).

Study Goal: To demonstrate substantial equivalence of the modified MR systems to legally marketed predicate devices, particularly regarding the performance of the software features.

Acceptance Criteria and Reported Device Performance

The document doesn't present a specific table of acceptance criteria with numerical performance targets typical for AI/CAD devices (e.g., sensitivity, specificity, AUC). Instead, the acceptance criteria are implicitly performance characteristics demonstrating equivalence to the predicate device and proper functioning of the new features.

Study Details

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

   • For Compressed SENSE with Contrast:
     • "Bench test results (Shelley phantom)" - number of phantom acquisitions not specified.
     • "Retrospectively and prospectively sub-sampled data" - not specified if this refers to phantom or human data for prospectively sub-sampled.
     • "Data from retrospective sub-sampled CE-angio data, on 3 human subjects."
     • "Clinical data for brain perfusion in tumor classification was provided." (Number of subjects not specified, but this refers to another retrospective subsampling approach.)
   • For other features, the document states "Non-Clinical verification and or validation tests have been performed on all of the software modifications" but does not specify sample sizes for test images or subjects.
   • Data Provenance: Not explicitly stated regarding country of origin. The data appears to be retrospective (e.g., "retrospective sub-sampled CE-angio data"). It's a non-clinical submission, so no large-scale clinical trial data is expected.

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

   • No information provided regarding experts establishing ground truth for a test set. This submission focuses on demonstrating substantial equivalence based on technical and performance characteristics of the MR sequences, not on diagnostic accuracy of an AI interpreting images for specific conditions. The "ground truth" here is implied to be the established performance of the predicate device (non-accelerated acquisition) or physical properties measured by phantoms.
   • The document implies that "interpreted by a trained physician" is crucial for clinical use, but this is not about ground truth for the device's performance testing.

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

   • Not applicable/Not specified. This type of submission does not detail an adjudication process for a diagnostic interpretative task.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • No. An MRMC comparative effectiveness study was not performed and is not described in this 510(k) summary. This submission pertains to modifications of the MR scanner's acquisition capabilities, not an AI or CAD system that assists human readers with diagnostic interpretation.

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

   • The studies mentioned (bench tests, subsampled data comparisons) were essentially "standalone" evaluations of the image reconstruction algorithms' technical performance (e.g., temporal and spatial resolution, contrast appearance, robustness) against a reference (fully sampled or non-accelerated data). No specific metrics like sensitivity/specificity for a diagnostic task are provided, as the device is the scanner itself, not an interpretative AI.

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

   • The "ground truth" for the technical performance evaluations appears to be:
     • Phantom data: For assessing properties like time-intensity behavior (Shelley phantom).
     • Fully sampled (non-accelerated) MR acquisition data: Used as a reference for comparison with accelerated acquisition (Compressed SENSE) to assess image quality, spatial/temporal resolution, and contrast appearance.
     • Implied clinical utility/diagnostic information: The "clinical data for brain perfusion in tumor classification" might have relied on clinical diagnosis or other established medical information for the "tumor classification" aspect, but the primary comparison was the technical quality of the MR images generated by the new sequence versus the predicate.

7. The sample size for the training set:

   • Not applicable/Not specified. This document describes improvements to existing MR sequences and software, not a de novo AI model that requires a distinct "training set." The development of the algorithms would have involved internal testing and validation, but not in the sense of a machine learning training dataset for a specific diagnostic task from a large, labeled dataset.

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

   • Not applicable, as no external "training set" in the context of machine learning model development is described.

Ask a specific question about this device