(187 days)
This system is a Magnetic Resonance Medicated for use as a diagnostic device. The system can produce cross-sectional images 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, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T, and Ingenia 3.0T CX R5.4 with Compressed SENSE feature is applicable for the 60 cm (CX) and 70 cm magnet systems. The systems and control software are substantially equivalent to the legally marketed primary predicate device Ingenia 1.5T, Ingenia 1.5T S and Ingenia 3T R5.3 (K163116, 01/06/2017).
The proposed Ingenia 1.5T, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T, and Ingenia 3.0T CX R5.4 with the Compressed SENSE feature also includes minor software changes since the clearance of the legally marketed primary predicate device, Ingenia 1.5T, Ingenia 1.5T S and Ingenia 3T R5.3 (K163116, 01/06/2017).
The following modifications are covered in this submission:
- Upgrade software platform to Windows 10
- Compressed SENSE feature allows ultra-high acceleration factors for shorter scan times and higher resolution in 2D and 3D imaging based on the principle of Compressed sensing in combination with SENSE.
- PerformanceBridge Protocol Manager Release 1.0 offering intended to help customers increase collaboration within a healthcare facility group. Customers will enter the Protocol Manager cloud functionality via the PerformanceBridge portal. Protocol Manager is a subscription service to a cloud based protocol repository that will allow a user to standardize protocols over the various connected MRI systems, enable editing of protocols and scan parameters and make central protocols available for use on local MRI systems.
The proposed Ingenia 1.5T, Ingenia 1.5T S and Ingenia 3.0T, Ingenia 1.5T CX, and Ingenia 3.0T CX R5.4 with Compressed SENSE feature is intended to be marketed with the following pulse sequences and coils that were previously cleared by FDA:
The Philips Ingenia 1.5T, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T, and Ingenia 3.0T CX R5.4 with the Compressed SENSE feature did not involve an AI algorithm in the typical sense of machine learning for diagnosis or prediction. Instead, "Compressed SENSE" refers to an image acquisition and reconstruction technique for Magnetic Resonance Imaging (MRI) that uses compressed sensing principles to achieve faster scan times and/or higher resolution. Therefore, the device's performance acceptance criteria and study design are related to image quality and system functionality rather than AI diagnostic performance.
Here's an analysis of the provided information based on your request, with the understanding that the "device" in question is an MRI system with an advanced imaging feature:
Acceptance Criteria and Reported Device Performance
The document does not explicitly present a table of numerical acceptance criteria for a "device performance" in terms of diagnostic accuracy, sensitivity, or specificity, as would be expected for an AI-powered diagnostic tool. Instead, the acceptance criteria are generally stated as compliance with regulatory standards and the demonstration of substantial equivalence to a predicate device. The performance is assessed based on a comparison of images produced by the new feature to those from the predicate device and established imaging principles.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Regulatory Compliance | Complies with IEC60601-1-2 Edition 3, IEC60601-1-6 Edition 3, IEC62366 (2015), IEC60601-1-8 Edition 2, IEC60601-2-33 Edition 3, IEC 62304 (2006), ISO 14971 (2007), Device specific guidance document ("Guidance for the Submission Of Premarket Notifications for Magnetic Resonance Diagnostic Devices – November 18, 2016"), "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (May 11, 2005), "Applying Human Factors and Usability Engineering to Medical Devices" (February 3, 2016), and "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" (October 2, 2014). |
| Functional Equivalence | The new device with Compressed SENSE feature is substantially equivalent to the legally marketed primary predicate device Ingenia 1.5T, Ingenia 1.5T S and Ingenia 3T R5.3 (K163116, 01/06/2017) in terms of design features, fundamental scientific technology, indications for use, and safety and effectiveness. |
| Intended Use Adequacy | The verification and validation test results, combined with sample clinical images, demonstrate that the proposed device: "Meets the acceptance criteria and is adequate for its intended use." This intended use is: "a Magnetic Resonance Medical Electrical System 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. Images, spectra, and measurements of physical parameters, when interpreted by a trained physician, provide information that may assist the diagnosis and therapy planning." Compressed SENSE enables scan time reduction or improved spatial resolution. |
| Safety and Effectiveness | The device does not raise "different questions of safety and effectiveness" compared to the predicate device. Non-clinical performance (verification and validation) tests demonstrated compliance with requirements. |
Study Details:
-
Sample size used for the test set and the data provenance:
- The document states that "sample clinical images" were used. However, it does not specify a numerical sample size for a test set in the context of an analytical or clinical performance study.
- Data provenance: Not explicitly stated, but given Philips' global operations, it's likely a combination of internal data or data from clinical sites where their systems are installed. The study is described as "non-clinical verification and or validation tests" combined with sample clinical images, suggesting a retrospective evaluation of existing images or images acquired during validation protocols.
-
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, as the submission focuses on the technical equivalence and safety of the MRI system and its new imaging feature (Compressed SENSE), rather than a diagnostic performance study requiring expert ground truth establishing for a specific pathology. The "ground truth" for an MRI system's image reconstruction capability is typically evaluated against physical phantoms (known objects) and expert review of image quality (e.g., signal-to-noise ratio, spatial resolution, artifact levels, anatomical depiction) by MR physicists and radiologists.
-
Adjudication method for the test set:
- This information is not applicable/provided as there was no formal diagnostic performance study described that would require an adjudication method for ground truth establishment by multiple experts.
-
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 done. The document explicitly states: "The proposed Ingenia 1.5T, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T, and Ingenia 3.0T CX R5.4 with the Compressed SENSE feature did not require a clinical study since substantial equivalence to the legally marketed predicate device was proven with the verification/validation testing."
- Furthermore, the "Compressed SENSE" feature is an imaging technique, not an AI diagnostic tool, so improving human readers with AI assistance is not the objective here. The goal is to produce images of comparable diagnostic quality with faster acquisition or higher resolution.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable in the context of an AI diagnostic algorithm. The "Compressed SENSE" is an image reconstruction algorithm that operates intrinsically within the MRI system to produce images for interpretation by a human. Its performance is effectively its ability to produce diagnostically acceptable images.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the technical validation of Compressed SENSE, the "ground truth" would likely involve:
- Physical phantoms: Objects with known properties used to objectively measure image quality metrics (e.g., spatial resolution, signal-to-noise ratio, uniformity).
- Comparison to gold standard MRI sequences: Images acquired with conventional, fully sampled sequences (considered the "gold standard" for image quality, though slower) would serve as a reference for images reconstructed using Compressed SENSE.
- Expert review of image quality: Radiologists and MR physicists would qualitatively assess the images for diagnostic acceptability, presence of artifacts, depiction of anatomical structures, and comparability to predicate device images.
- The document mentions "sample clinical images" were part of the validation, implying expert review of these images for diagnostic acceptability.
- For the technical validation of Compressed SENSE, the "ground truth" would likely involve:
-
The sample size for the training set:
- Not applicable/provided. Compressed SENSE, while employing sophisticated mathematics (compressed sensing), is primarily a signal processing and image reconstruction technique rather than a machine learning algorithm that requires a separate "training set" for diagnostic classification. The parameters for compressed sensing reconstruction are typically derived from theoretical principles and validated through experimentation, rather than trained from a large labeled dataset in the same way a deep learning model would be.
-
How the ground truth for the training set was established:
- Not applicable/provided as there was no distinct "training set" in the context of an AI diagnostic model. The development of Compressed SENSE relies on mathematical principles and engineering validation.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.