(14 days)
Imaging of:
- The Whole Body (including head, abdomen, pelvis, limbs and extremities, spine, . neck, TMJ, heart, blood vessels). [Application terms include MRCP (MR Cholangiopancreatography), MR Cisternography, MR Urography, MR Myelography, MR Fluoroscopy, SAS (Surface Anatomy Scan), Dynamic Scan, Cine Imaging and Cardiac tagging. ]
- . Fluid Visualization
- . 2D / 3D Imaging
- MR Angiography / MR Vascular Imaging .
- Blood Oxygenation Level Dependent (BOLD) imaging .
- Perfusion / Diffusion Imaging .
- Proton Spectroscopy .
The EXCELART Vantage Atlas is a 1.5 tesla Magnetic Resonance Imaging (MRI) System. The Atlas has a 1.4 m short magnet (55 cm field of view) and includes Toshiba's Pianissimo™ technology (scan noise reduction technology). The wide bore has a 655 mm opening.
There are two models in the EXCELART Vantage Atlas line as follows:
• EXCELART Vantage Atlas-Z Model No. MRT-1503/S3
• EXCELART Vantage Atlas-X Model No. MRT-1503/S3
The EXCELART Vantage Atlas MRI System is comparable to the EXCELART Vantage ZGV MRI System (K060003, cleared January 18, 2006) with the following modifications:
- . 16 Channel phased array system control
- . CPU performance of the computer system has been enhanced
- The longitudinal movement of the patient couch has been increased
- . Additional table top coil ports
- . Additional RF coils – Atlas SPEEDER Head, Atlas SPEEDER Spine, and Atlas SPEEDER Body)
- SAR limit is 4 W/kg for whole body in conformance with IEC 60601-2-33 (2002)
The provided 510(k) summary for the EXCELART Vantage Atlas MRI system (K063361) indicates that this device is a modification of a previously cleared device, the EXCELART Vantage ZGV MRI System (K060003). Therefore, the submission focuses on demonstrating substantial equivalence to the predicate device rather than presenting a de novo study with specific acceptance criteria and detailed performance metrics comparing it to a ground truth.
Here's an analysis of the provided information concerning acceptance criteria and supporting studies:
1. Table of Acceptance Criteria and Reported Device Performance
The submission does not contain explicit acceptance criteria in the form of quantitative performance targets (e.g., sensitivity, specificity, accuracy, or image quality metrics) against a specific ground truth. Instead, the acceptance is based on demonstrating that the modified device maintains the safety and imaging performance of its predicate device, subject to specific hardware and software changes.
The "performance" is implicitly demonstrated through the declaration that "No changes from the previous submission, K060003" for both "IMAGING PERFORMANCE PARAMETERS" and "INTENDED USE." This means the device is expected to perform at least comparably to the predicate device, which would have had its own performance established during its clearance.
Therefore, a table cannot be directly constructed for acceptance criteria and reported device performance for this specific 510(k) in the way one might for a software algorithm with diagnostic outputs.
The primary change that might be considered an "acceptance criterion" related to safety is:
| Acceptance Criterion (Safety) | Reported Device Performance (K063361) |
|---|---|
| Maximum SAR (Whole Body, 1st operating mode, IEC 60601-2-33 (2002)) | 4 W/kg (This is an increase from the predicate's 3 W/kg, but still within safety standards) |
| Other Safety Parameters (Static Field Strength, Acoustic Noise, dB/dt, Emergency Shutdown, Biocompatibility) | Same as predicate device (EXCELART Vantage ZGV) |
| Imaging Performance Parameters | Same as predicate device (EXCELART Vantage ZGV) |
| Intended Use | Same as predicate device (EXCELART Vantage ZGV) |
2. Sample size used for the test set and the data provenance
The document does not describe a specific test set in terms of patient data or images used to evaluate the new device's imaging performance. The substantial equivalence argument relies on the inherent design and engineering principles, stating "No changes from the previous submission, K060003" for imaging performance. This implies that if any testing was done beyond engineering verification, it would have been at the component or system level, not necessarily on a distinct patient image dataset with a ground truth.
Given the nature of the submission (hardware/software modifications to an existing MRI system), rigorous clinical image-based testing on a test set with human readers is not explicitly detailed. The provenance of such data, if it existed, is not mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
As no specific clinical test set for performance evaluation is described, there is no mention of experts establishing ground truth for such a set within this document.
4. Adjudication method for the test set
Since no specific clinical test set for performance evaluation is described, no adjudication method is mentioned.
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 or reported in this 510(k) submission. This is consistent with the device being a hardware/software update to an MRI system itself, rather than an AI-driven image analysis tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
No standalone algorithm performance study was done or reported. The device is an MRI system, not an independent algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Given the nature of the submission (modifications to an existing MRI machine), the concept of "ground truth" in the diagnostic performance sense is not applicable to this document's scope. The "truth" being established is that the modified system retains the safety and imaging capabilities of the predicate device, which would likely have been verified through engineering tests, phantom studies, and potentially limited clinical scans, rather than large-scale diagnostic accuracy studies.
8. The sample size for the training set
No training set is mentioned or applicable for this device. This is a hardware/software update to a medical imaging device, not a machine learning or AI algorithm that requires a training set.
9. How the ground truth for the training set was established
As there is no training set, this question is not applicable.
In summary, this 510(k) submission is for modifications to a previously cleared MRI system. The "acceptance criteria" and "proof" of meeting them primarily revolve around demonstrating that the changes (increased channel count, CPU enhancement, new coils, increased SAR limit) do not negatively impact the established safety and performance of the predicate device, or that any changes remain within acceptable regulatory limits (e.g., increased SAR is still compliant with IEC standards). There is no indication of a new clinical performance study with a test set, experts, or ground truth establishment as would be typical for a novel diagnostic device or AI algorithm.
§ 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.