(58 days)
Vantage Fortian 1.5T systems are indicated for use as a diagnostic imaging modality that produces cross-sectional transaxial, coronal, sagittal, and oblique images that display anatomic structures of the head or body. Additionally, this system is capable of non-contrast enhanced imaging, such as MRA.
MRI (magnetic resonance imaging) images correspond to the spatial distribution of protons (hydrogen nuclei) that exhibit nuclear magnetic resonance (NMR). The NMR properties of body tissues and fluids are:
·Proton density (PD) (also called hydrogen density)
·Spin-lattice relaxation time (T1)
·Spin-spin relaxation time (T2)
·Flow dynamics
·Chemical Shift
Depending on the region of interest, contrast agents may be used. When interpreted by a trained physician, these images yield information that can be useful in diagnosis.
The Vantage Fortian (Model MRT-1550) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. The Vantage Fortian uses 1.4 m short and 4.1 tons light weight magnet. It includes the Canon Pianissimo™ Σ and Pianissimo Zen technology (scan noise reduction technology). The design of the gradient coil and the whole body coil of the Vantage Fortian provides the maximum field of view of 55 x 55 x 50 cm. The Model MRT-1550/ WK, WM, WO, WQ includes the standard gradient system.
This system is based upon the technology and materials of previously marketed Canon Medical Systems MRI systems and is intended to acquire and display cross-sectional transaxial, coronal, sagittal, and oblique images of anatomic structures of the head or body. The Vantage Fortian MRI System is comparable to the current 1.5T Vantage Orian MRI System (K211633), cleared July 22, 2021 with the following modifications.
The provided text describes a 510(k) premarket notification for a new MRI system, the Vantage Fortian 1.5T, MRT-1550, V8.0 with AiCE Reconstruction Processing Unit for MR. This submission seeks to demonstrate substantial equivalence to a previously cleared predicate device.
The document primarily focuses on changes to hardware and software features of the MRI system and the safety and performance testing conducted for these changes. It does not contain information about a study proving the device meets acceptance criteria for an AI-specific application in the manner typically expected for a diagnostic AI device (e.g., a multi-reader, multi-case study comparing human performance with and without AI assistance).
Instead, the information provided for the AI-related features (pCASL, mART EXP, IMC, RDC DWI, sureVOI Liver, LiverLine+, ProstateLine+, W-SpineLine+) focuses on their functional validation and improvement of image quality/workflow, rather than a comparative diagnostic performance study with human readers.
However, based on the information provided regarding the evaluation of the new software features, here's an attempt to answer the questions within the given constraints.
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of quantitative acceptance criteria for each software feature in the format of "metric > threshold" along with a "reported performance" value. Instead, it describes qualitative or general statements of acceptance.
| Acceptance Criteria (from text) | Reported Device Performance (from text) |
|---|---|
| SureVOI Liver, LiverLine+, ProstateLine+, W-SpineLine+: These features worked as intended, the images were of diagnostic quality, and the test results met predetermined acceptance criteria. | "It was confirmed that these features worked as intended, the images were of diagnostic quality, and the test results met predetermined acceptance criteria." |
| Exsper in FSE2D: Exsper reduces artifacts caused by unfolding errors, compared to traditional SPEEDER. | "It was confirmed that Exsper reduces artifacts caused by unfolding errors, compared to traditional SPEEDER." |
| mART EXP: mART EXP can reduce distortion artifacts in the readout direction like mART+ and can also reduce distortion artifacts in the slice direction more than mART+. | "Testing verified mART EXP can reduce distortion artifacts in the readout direction like mART+ and can also reduce distortion artifacts in the slice direction more than mART+." |
| IMC (Iterative Motion Correction): IMC is effective in reducing motion artifacts. | "Testing confirmed that IMC is effective in reducing motion artifacts." |
| RDC DWI: The distortion in phase encoding direction was reduced by RDC DWI as compared to conventional images without RDC DWI in SEEPI2D sequence. | "It was confirmed that the distortion in phase encoding direction was reduced by RDC DWI as compared to conventional images without RDC DWI in SEEPI2D sequence." |
| pCASL (pseudo-continuous ASL): CBF values via pCASL met predetermined acceptance criteria. | "Testing confirmed CBF values via pCASL met predetermined acceptance criteria." |
2. Sample sizes used for the test set and the data provenance
- Sample Size:
- SureVOI Liver, LiverLine+, ProstateLine+, W-SpineLine+: "volunteer images" (specific number not provided).
- Exsper in FSE2D: "phantom images" (specific number not provided).
- mART EXP: "phantom images" (specific number not provided).
- IMC: "volunteer images" (specific number not provided).
- RDC DWI: "phantom images" (specific number not provided).
- pCASL: "phantom images" (specific number not provided).
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective). The use of "volunteer images" for some tests implies prospective acquisition, but details are not given.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not mention the use of experts to establish a "ground truth" for the test set in the context of diagnostic performance evaluation. The "ground truth" for these performance tests appears to be defined by the expected functional behavior and image characteristics, likely assessed by engineers and imaging scientists rather than clinical experts for diagnostic consensus.
4. Adjudication method for the test set
Not applicable. The document describes functional and image quality evaluations rather than diagnostic performance evaluations requiring adjudication of expert interpretations.
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, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not conducted or reported in this document. The evaluations described are primarily focused on the technical performance, artifact reduction, and workflow assistance of the new features.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the testing described appears to be primarily standalone (algorithm only) performance, assessing the direct output of the new software features in terms of image quality, artifact reduction, or automated functionality (e.g., sureVOI Liver, LiverLine+). Human assessment of the "diagnostic quality" of images produced by these features is mentioned, but it's not a formal diagnostic performance study.
7. The type of ground truth used
The "ground truth" used for these tests appears to be:
- Pre-determined functional expectations/specifications: For features like sureVOI Liver, LiverLine+, ProstateLine+, W-SpineLine+, the confirmation that they "worked as intended" and "met predetermined acceptance criteria" suggests this.
- Comparison to existing methods/undesirable conditions: For Exsper (reduces unfolding errors compared to traditional SPEEDER), mART EXP (reduces distortion more than mART+), IMC (effective in reducing motion artifacts), and RDC DWI (reduces distortion compared to conventional images).
- Quantitative measurements against expected values: For pCASL, "CBF values via pCASL met predetermined acceptance criteria" implies quantitative comparison to established values or ranges.
8. The sample size for the training set
The document does not provide information on the sample size of the training set used for the AI-related features (e.g., LiverLine+, ProstateLine+, W-SpineLine+). These are described as "Machine Learning based detection technology," implying a training phase, but details are not given.
9. How the ground truth for the training set was established
The document does not provide information on how the ground truth for the training set (if applicable to features like LiverLine+ which use machine learning) was established.
§ 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.