Search Results

The MRI system is indicated for use as a diagnostic imaging modality that produces crosssectional transaxial, coronal, sagittal, and oblique images that display anatomic structures of the head or body. In addition, this system supports non-contrast 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
  Contrast agent use is restricted to the approved drug indications. When interpreted by a trained physician, these images yield information that can be useful in diagnosis.

The new Vantage Titan (Model MRT-1504/U4) MRI System is comparable to the current 1.5T Vantage Titan MRI System. The Vantage Titan uses the same magnet as the current Vantage Titan (K080038). However, the following modifications have been added: a redefinition of gradient strength, magnet cover and cabinet's configuration changes. In addition, two applications software: Diffusion Tensor Tractography (DTT), and PaceMaker.

This 510(k) premarket notification describes modifications to an existing MRI system (Vantage Titan) rather than a new AI medical device requiring extensive performance studies. The "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context refer to demonstrating substantial equivalence to predicate devices and adherence to established safety and performance standards for MRI systems, rather than clinical performance metrics for an AI algorithm.

Here's a breakdown of the provided information, framed to address your questions where possible:

Acceptance Criteria and Reported Device Performance

Study Information (as applicable to this device modification):

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

   • Test Set: Not applicable in the sense of a clinical trial with patient data to evaluate an AI algorithm's performance. The "testing" referred to in this submission is related to engineering verification and validation of hardware and software changes, and demonstrating compliance with safety and performance standards. This would involve internal testing, phantom studies, and potentially a limited number of human scans to confirm functionality and safety, but not a large-scale clinical test set for diagnostic accuracy.
   • Data Provenance: Not specified for a clinical test set. The validation would have been performed by Toshiba Medical Systems Corporation, likely in Japan (manufacturing site).

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

   • Not applicable as this is not a study establishing ground truth for a diagnostic AI algorithm. The safety and performance evaluations would involve engineers and potentially clinical experts to review images and system functionality, but not in the capacity of creating a "ground truth" for a diagnostic accuracy study.

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

   • Not applicable for the type of submission. Adjudication methods are typically for clinical trials assessing diagnostic accuracy, which is not the focus here.

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. This submission is for modifications to an MRI scanner and the addition of specific imaging sequences (DTT, PaceMaker), not for an AI-assisted diagnostic tool requiring a MRMC study.

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

   • No. The "applications software" (DTT and PaceMaker) are features of the MRI system, designed to aid in image acquisition and processing, not standalone diagnostic algorithms.

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

   • Not applicable in the context of diagnostic "ground truth." For hardware and software functionality, ground truth would be established through engineering specifications, phantom measurements, and known physical principles. For the new software features (DTT, PaceMaker), ground truth would relate to their ability to correctly perform their intended function (e.g., generate diffusion tensor tracts, accurately gate cardiac images) as measured against established technical benchmarks and clinical expectations.

7. The sample size for the training set:

   • Not applicable. This device is not an AI algorithm that learns from a training set of labeled data in the conventional sense. The "training" for the software applications would be their development and optimization by engineers.

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

   • Not applicable, as there isn't a "training set" in the context of an AI algorithm learning from data. The functionality of DTT and PaceMaker would be based on well-established MR physics and clinical needs.

Ask a specific question about this device