(126 days)
SyMRI is a post-processing software medical device intended for use in visualization of soft tissue. SyMRI analyzes input data from MR imaging systems. SyMRI utilizes data from supported MR sequences to generate parametric maps of R1, R2 relaxation rates, and proton density (PD)
SyMRI is intended for automatic labeling, visualization and volumetric quantification of segmentable brain tissues from a set of MR images. Brain tissue volumes are determined based on modeling of parametric maps from SyMRI.
When interpreted by a trained physician, the parametric maps, tissue maps, and volumetrics from SyMRI can provide information useful in determining diagnosis. SyMRI is indicated for head imaging.
SyMRI can also generate multiple contrast weighted images from the parametric maps generated by post-processing data from M2D-MDME sequence. SyMRI enables post-acquisition image contrasts adjustments from acquisition using M2D-MDME sequence.
When M2D-MDME acquisition data is used as input to SyMRI the synthetic contrast weighted images can also provide information useful in determining diagnosis. SyMRI is intended to be used in combination with at least one other, conventional MR acquisition (e.g. T2-FLAIR).
SyntheticMR's SyMRI is a Class II Magnetic resonance diagnostic device (Requlation # 892.1000) with product code LNH. The device has no components and/or accessories.
SyMRI works by post-processing a multi-delay, multi-echo acquisition into parametric maps. The acquisition is either a multi-slice 2D approach (M2D-MDME), consisting of 4 delays with a short and a long echo time each (8 images per slice), or a 3D approach (3D-QALAS) consisting of 4 delays with a short echo and 1 delay with a long echo time (5 images per slice).
The parametric maps are R1, R2 relaxation rates, and proton density (PD). The inverse relaxation parameters, T1 relaxation time (1/R1), and T2 relaxation time (1/R2) are also provided as parametric maps.
SyMRI enables the users to obtain volumetric information in the head, including white matter (WM), grey matter (GM), cerebrospinal fluid (CSF), Myelin correlated (MyC) partial volume, brain parenchyma (BP) and intracranial cavity (IC). This is accomplished by using tissue definitions based on the parametric maps. The tissue definitions provide tissue partial volume, or tissue fraction, per voxel. SyMRI also provides image processing tools to extract the values of the parametric maps, and tissue partial volume, per individual voxel, per region of interest, or the entire imaging volume.
The parametric maps can also be visualized as contrast weighted MR images, such as T1, T2, PD, and Inversion Recovery (IR) weighted images (including T1-FLAIR, T2-FLAIR, STIR, Double IR, and PSIR weighted images). SyMRI calculates the pixel signal intensity as a function of R1, R2, PD, and desired MR scanner settings, such as echo time (TE), repetition time (TR), and inversion delay time (TI). A number of default settings for TE, TR, and TI are provided, but the user has the ability to change the contrast of the images.
SyMRI generates all the different image contrasts from the same parametric maps, derived from the same acquisition. This leads to enhanced image slice registration, owing to the absence of interacquisition patient movement. SyMRI provides the user the ability to change the contrast of the images after the acquisition. This is performed by adjusting the TE, TR, and/or TI parameters postacquisition, to generate the specific contrast desired.
SyMRI is intended to be used to process data produced by any of the following acquisition sequences:
- M2D-MDME sequence data from GE MAGiC ●
- M2D-MDME sequence data from Philips SyntAc
- . M2D-MDME sequence data from Siemens TSE MDME
- 3D-QALAS sequence data from Philips 3DSyntAc Only 3T .
SyMRI can also create contrast weighted images from 3D-QALAS but these are only available in the product for quality assurance purposes as a risk mitigation related artifacts that could affect quantification and segmentation, and should not be used for clinical purposes.
Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria Category | Acceptance Criteria (from text) | Reported Device Performance (from text) |
|---|---|---|
| Quantification Accuracy | Good correspondence with reference values for R1, R2, and PD measurements, meeting same predefined acceptance criteria as predicate. | "The R1, R2 and PD measurements show a good correspondence with the reference values, and the subject device met the same predefined acceptance criteria as the predicate device. It can be concluded that the accuracy and precision of SyMRI is good." (Comparison to gold standard inversion recovery (R1), CPMG multi-echo (R2), heavy water phantoms (PD) and standard system Model 130 NIST/ISMRM phantom.) |
| Quantification Precision | Good precision for R1, R2, and PD measurements, meeting same predefined acceptance criteria as predicate. | "The R1, R2 and PD measurements show a good correspondence with the reference values, and the subject device met the same predefined acceptance criteria as the predicate device. It can be concluded that the accuracy and precision of SyMRI is good." |
| Segmentation Precision | Within-subject standard deviation on scan-rescan (repeatability) for segmentation volumes should be acceptable. | "The precision of segmentation results was evaluated by scanning healthy volunteers multiple times and analyzing the difference in segmentation volumes. This is evaluated in terms of repeatability as within-subject standard deviation on the scan-rescan on the same model and field strength." (Results implied satisfactory based on overall conclusion of meeting predefined performance criteria.) |
| Volumetric Equivalence (3D-QALAS vs. M2D-MDME) | Segmentation fractions (BPF, MyCPF, WMF, GMF) from SyMRI using 2D and 3D acquisition methods must be statistically equivalent within a clinically determined equivalence margin on both mean difference and slope. | "The performance data show that segmentation fractions BPF, MyCPF, WMF and GMF from SyMRI using 2D or 3D are statistically equivalent within the clinically determined equivalence margin on both mean difference and slope between the two acquisition methods." (Bench test on 45 healthy volunteers.) |
Study Details
-
Sample sizes used for the test set and the data provenance:
- Quantification Accuracy & Precision Test (Phantoms): The text mentions "gold standard inversion recovery (R1), CPMG multi-echo (R2), heavy water phantoms (PD) and standard system Model 130 NIST/ISMRM phantom." No specific number of phantoms or scans is provided.
- Segmentation Precision Test (Healthy Volunteers): "healthy volunteers scanned multiple times." No exact number of subjects or scans is explicitly stated for this particular test, though 45 healthy volunteers were used for the equivalence test.
- Volumetric Equivalence Test (3D-QALAS vs. M2D-MDME): 45 healthy volunteers.
- Data Provenance: Not explicitly stated, but given the mention of "healthy volunteers" and "bench test," it implies a prospective study. The country of origin is not specified.
-
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 ground truth for the test set for quantification or segmentation accuracy/precision. Ground truth for quantification was based on "gold standard" physical measurements (e.g., phantoms) and for segmentation precision, it was based on within-subject variability, which doesn't typically require human expert ground truth review in the same way.
- For the volumetric equivalence study, the ground truth was a statistical comparison between two acquisition methods within the device itself, not against an external expert-derived ground truth.
-
Adjudication method for the test set:
- Not applicable as the ground truth establishment did not involve multiple human experts requiring adjudication.
-
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, nor was there any evaluation of human reader improvement with AI assistance mentioned in the provided text. The study focuses on the technical performance of the device itself (quantification, segmentation, and equivalence between acquisition methods). The device is a "post-processing software medical device intended for use in visualization of soft tissue" and its interpretation is "When interpreted by a trained physician," implying human interpretation, but no study on the impact of the device on physician performance is detailed.
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, the described performance data (Quantification Accuracy & Precision, Segmentation Precision, and Volumetric Equivalence) are all standalone performance evaluations of the SyMRI algorithm. These tests assess the device's technical output (parametric maps, segmentation, volumes) directly, without involving human interpretation as an outcome measure.
-
The type of ground truth used:
- Quantification: "Gold standard" physical measurements, specifically "inversion recovery (R1), CPMG multi-echo (R2), heavy water phantoms (PD) and standard system Model 130 NIST/ISMRM phantom." This represents a form of physical/reference standard ground truth.
- Segmentation Precision: Repeatability (scan-rescan variability) in healthy volunteers. This is an internal consistency/precision ground truth rather than an external anatomical ground truth.
- Volumetric Equivalence: A statistical comparison between the device's outputs from two different acquisition methods (M2D-MDME and 3D-QALAS). The M2D-MDME method effectively serves as a reference within the context of determining equivalence.
-
The sample size for the training set:
- The document does not provide information on the training set used for the SyMRI algorithm. The performance data section focuses solely on verification and validation (testing) and does not disclose details about the development or training phase of the software.
-
How the ground truth for the training set was established:
- Not provided, as information on the training set itself is absent from the text.
§ 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.