(104 days)
MAGiC (MAGnetic resonance image Compilation) is a software option based on a combination and post processing software that is intended for use on GE imaging platforms. MAGiC generates multiple image contrasts from a single acquisition scan. MAGiC enables post-acquisition image contrast adjustment. MAGiC also allows for the generation of parametric maps for further analysis of MRI acquisition data. MAGiC is indicated for head imaging.
When interpreted by a trained physician, MAGiC images can provide information useful in determining diagnosis.
MAGiC (MAGnetic resonance image Compilation) allows the user to generate multiple contrasts in a single scan. MAGiC utilizes a multi-delay, multi-echo acquisition (MDME). The data acquired is processed using a technique to generate multiple image contrasts simultaneously, such as T1, T2, PD and Inversion Recovery (IR) weighted images (including: T1-FLAIR, T2-FLAIR, STIR, Double IR and PSIR weighted images). MAGiC generates all the different image contrasts from the same acquisition, leading to enhanced image slice registration, owing to the absence of inter-acquisition patient movement. MAGiC provides the user the ability to change the contrast of the images after acquisition. This is performed by adjusting the TR, TE, and/or TI parameters post-acquisition, to generate the specific contrast desired. MAGiC also enables users to generate parametric maps, such as T1, T2, R1, R2, PD, for further analysis of MRI acquisition data.
The provided text is a 510(k) Premarket Notification Submission for the MAGiC (MAGnetic resonance image Compilation) device. Based on the document, here's a detailed breakdown of the acceptance criteria and the study conducted:
1. Table of Acceptance Criteria and Reported Device Performance
| Criterion | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Image Quality (Diagnostic Acceptability) | To demonstrate that MAGiC images are of acceptable diagnostic image quality, which is defined as "usable for clinical diagnosis" and equivalent to that of the predicate device. | The study found that MAGiC images are statistically equivalent to the predicate device in terms of diagnostic image quality. Inter-reader agreement between MAGiC and predicate scans was also statistically significant. |
| Radiologic Finding Classes Equivalence | To demonstrate that the radiologic finding classes identified using MAGiC images are equivalent to those identified using images from the predicate device. | The study demonstrated equivalency in radiologic finding classes between MAGiC and predicate device images. |
| Parametric Map Accuracy (T1, T2, PD) | Not explicitly stated as acceptance criteria, but addressed in the study. The study intended to evaluate the accuracy of the quantitative values derived from MAGiC's parametric maps (T1, T2, PD) compared to reference values. | Quantitative values obtained from MAGiC's synthetic images (T1, T2, PD) showed high correlation (R² > 0.98) with reference values, and the differences in these values were within acceptable limits. The parametric measurements were accurate and consistent. |
| Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) in Synthetic Images | Not explicitly stated as acceptance criteria, but mentioned in the study's scope of evaluation. | MAGiC-derived synthetic images demonstrated comparable or improved SNR and CNR values relative to the predicate device's acquired images, particularly for synthetic FLAIR images. This suggests the synthetic images maintain diagnostic utility. |
| Software Compliance & Quality Assurance | Compliance with AAMI/ANSI 62304, AAMI/ANSI ES60601-1, IEC 60601-2-33, and NEMA PS3.1-3.18 (DICOM conformance). Development under quality assurance design controls including Risk Analysis, Requirements Reviews, Design Reviews, Unit/Module Testing, Integration Testing, Performance Testing, Safety Testing, and Simulated Use Testing. | MAGiC is a software-only feature and complies with all listed voluntary standards. All quality assurance measures were applied, and testing was completed with passing results per the defined pass/fail criteria. This supports substantial equivalence. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: The document states that a "reader study was conducted to demonstrate acceptable diagnostic image quality and equivalent radiologic finding classes compared to the predicate device." However, the exact sample size (number of cases/patients) used for this reader study (test set) is not explicitly stated in the provided text.
- Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- The document mentions a "reader study" where images were "interpreted by a trained physician" (in the Indications for Use). However, it does not specify the number of experts who participated in establishing the ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience").
4. Adjudication Method for the Test Set
- The document does not explicitly state the adjudication method used for the reader study (e.g., 2+1, 3+1, none). It only refers to a "reader study."
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- A reader study was performed to compare MAGiC images to the predicate device. This is a form of comparative effectiveness study.
- Effect Size of Human Readers Improvement with AI vs. Without AI Assistance: The document does not report an effect size for how much human readers improve with MAGiC (AI) assistance versus without it. The study's focus was on demonstrating "acceptable diagnostic image quality" and "equivalent radiologic finding classes" compared to the predicate device, implying non-inferiority or equivalence rather than a direct measure of human reader improvement. The device generates images (synthetic contrasts and parametric maps) rather than providing diagnostic assistance in the sense of an CAD system.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- The evaluation of parametric map accuracy (T1, T2, PD) and SNR/CNR in synthetic images could be considered a form of standalone performance evaluation, as it assesses the quantitative outputs and image characteristics of the algorithm itself.
- The document indicates that quantitative values obtained from MAGiC's synthetic images had high correlation (R² > 0.98) with reference values, and differences were within acceptable limits. Also, SNR and CNR values in synthetic images were comparable or improved. This suggests robust standalone performance for these specific aspects.
7. Type of Ground Truth Used
- For the reader study, the ground truth for diagnostic image quality and radiologic finding classes was established through expert interpretation (trained physicians).
- For the evaluation of parametric map accuracy (T1, T2, PD), the ground truth was reference values, implying a comparison against established quantitative measurements (e.g., obtained from standard phantoms or established acquisition sequences).
8. Sample Size for the Training Set
- The document does not provide information on the sample size used for the training set for the MAGiC software or any underlying AI algorithms. It focuses on the validation of the final product.
9. How the Ground Truth for the Training Set Was Established
- Since the document does not mention data used for training or a training set sample size, it consequently does not describe how ground truth for a training set 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.