(56 days)
Vantage Orian 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 Orian (Model MRT-1550) is a 1.5 Tesla Magnetic Resonance Imaging (MRI) System. The Vantage Orian uses 1.4 m short and 4.1 tons light weight magnet. It includes the Canon Pianissimo™ and Pianissimo Zen technology (scan noise reduction technology). The design of the gradient coil and the whole body coil of the Vantage Orian provides the maximum field of view of 55 x 55 x 50 cm. The Model MRT-1550/ UC, UD, UG, UH, UK, UL, UO, UP includes the XGO 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 Orian MRI System is comparable to the current 1.5T Vantage Orian MRI System (K202210), cleared September 22, 2020 with the following modifications.
The provided document is a 510(k) Summary for a Magnetic Resonance Imaging (MRI) device, specifically the Vantage Orian 1.5T, MRT-1550, V7.0 with AiCE Reconstruction Processing Unit for MR. This document primarily describes modifications to an existing cleared device and asserts substantial equivalence to a predicate device.
The questions you've posed generally relate to the rigorous evaluation of a new AI-powered diagnostic device, particularly in terms of its clinical performance. This type of detailed clinical study information (e.g., sample size for test sets, data provenance, expert qualifications, HRMR studies, standalone performance with ground truth establishment) is typically found in the clinical validation section of a 510(k) submission for a novel AI/ML device that claims to provide diagnostic information or improve human reader performance.
However, in this specific 510(k) summary, the AiCE (Advanced Intelligent Clear-IQ Engine) is presented as a reconstruction processing unit and its update primarily involves "anatomical region expansion" and "noise estimation improvement." The summary emphasizes that the modifications do not change the indications for use or the intended use of the device. This suggests that the AiCE component, while employing advanced techniques (likely AI-based given the name), functions within the established performance parameters of an MRI reconstruction system and is not being submitted as a standalone diagnostic AI tool requiring a separate, extensive clinical performance study against specific diagnostic criteria.
Given this context, the document focuses on demonstrating that the modified MRI system as a whole remains safe and effective, and substantially equivalent to its predicate. The "acceptance criteria" and "study that proves the device meets the acceptance criteria" are therefore primarily framed around the performance of the MRI system itself and not a new diagnostic AI capability being validated against clinical outcomes or expert consensus on a disease.
Therefore, for many of your specific questions, the information is either not present in this type of 510(k) summary, or the question's premise (e.g., "effect size of how much human readers improve with AI vs without AI assistance") doesn't directly apply to the nature of this submission (a modification to a reconstruction engine for an MRI).
Let's break down what can be extracted or inferred from the provided text against your questions:
1. A table of acceptance criteria and the reported device performance
The document doesn't provide a clear, explicit table of acceptance criteria for diagnostic performance specific to the AiCE component's impact on diagnostic accuracy, because it's framed as an improvement to image reconstruction, not a new diagnostic AI tool.
Instead, the "performance parameters" mentioned are for the overall MRI system:
| Item | Acceptance Criteria (Implied: Same as Predicate) | Reported Device Performance |
|---|---|---|
| Static field strength | 1.5T | 1.5T |
| Operational Modes | Normal and 1st Operating Mode | Normal and 1st Operating Mode |
| Safety parameter display | SAR, dB/dt | SAR, dB/dt |
| Max SAR | 4W/kg for whole body (1st operating mode specified in IEC 60601-2-33) | 4W/kg for whole body (1st operating mode specified in IEC 60601-2-33) |
| Max dB/dt | 1st operating mode specified in IEC 60601-2-33 | 1st operating mode specified in IEC 60601-2-33 |
| Potential emergency shutdown | Shutdown by Emergency Ramp Down Unit for collision hazard for ferromagnetic objects | Shutdown by Emergency Ramp Down Unit for collision hazard for ferromagnetic objects |
| Imaging Performance | No change from previous predicate K202210 | Met, "Image quality testing was completed which demonstrated that the subject device meets predetermined acceptance criteria." |
| Specific AiCE-related | Improved homogeneity, reduced distortion | "Rx/TX Correction Plus increases the homogeneity of the image compared to the image without intensity correction." & "It was confirmed that the distortion due to magnetic field inhomogeneity was reduced by increasing the Exsper acceleration factor." |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: Not explicitly stated in terms of patient cases for clinical performance evaluation. The "testing" section mentions "phantom images" and "volunteer clinical imaging," but does not specify the number of phantoms or volunteers, nor if these were used for a formal test set with ground truth. This is typical for a device primarily undergoing engineering/system validation rather than a clinical diagnostic study.
- Data Provenance: Not specified for any "volunteer clinical imaging." Phantom images are laboratory-based. The device manufacturer is Canon Medical Systems Corporation, Japan, with a U.S. agent.
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 to this submission as it focuses on system performance and image reconstruction quality rather than a diagnostic AI algorithm requiring expert ground truth for clinical diagnostic accuracy studies. The document states, "When interpreted by a trained physician, these images yield information that can be useful in diagnosis," which points to the human reader's role in interpretation of the output, not the AI providing a diagnosis itself.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable, as no multi-reader adjudication process for diagnostic performance is described or implied.
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 is described. This type of study would be performed for a new AI algorithm cleared for diagnostic assistance. The AiCE here is described as a "reconstruction processing unit" aiming to improve image quality characteristics (noise, homogeneity, distortion), which would indirectly benefit interpretation but isn't claimed to be a direct diagnostic aid that would undergo an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
No standalone performance study for the AiCE as a diagnostic algorithm is mentioned. Its function is described as improving image quality, which is intrinsically tied to the overall MRI system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable for a typical "ground truth" used in AI diagnostic performance studies. The "ground truth" for the reconstruction performance would be physical properties of phantoms or established MR physics principles for noise, homogeneity, and distortion measurements.
8. The sample size for the training set
Not present. As a component described as a "reconstruction processing unit" that likely employs AI/ML for image enhancement (implied by "AiCE," "noise estimation improvement"), it's reasonable to assume it has been developed using training data. However, for this type of 510(k) submission for a modification to an existing MRI system's reconstruction software, the details of the training data used for the AiCE component are not disclosed in the summary. The focus is on the safety and effectiveness of the modified system, not the isolated validation of a new AI diagnostic algorithm.
9. How the ground truth for the training set was established
Not present. Similar to #8, these details are not provided in this regulatory summary.
§ 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.