(104 days)
The ECHELON Oval System is an imaging device and is intended to provide the physician with physiological and clinical information, obtained non-invasively and without the use of ionizing radiation. The MR system produces transverse, coronal, sagittal, oblique, and curved cross-sectional images that display the internal structure of the head, body, or extremities. The images produced by the MR system reflect the spatial distribution of protons (hydrogen nuclei) exhibiting magnetic resonance. The NMR properties that determine the image appearance are proton density, spin-lattice relaxation time (T1), spin-spin relaxation time (T2) and flow. When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination.
The ECHELON OVAL is a Magnetic Resonance Imaging System that utilizes a 1.5 Tesla superconducting magnet in a gantry design. The design was based on the ECHELON MRI system. The ECHELON OVAL has been designed to enhance clinical utility as compared to the ECHELON by taking advantage of open architecture.
This request is asking for a detailed breakdown of the acceptance criteria and the study used to validate the ECHELON Oval V5.0 MRI system, based on the provided FDA 510(k) summary.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria in a traditional table format for performance metrics. Instead, the acceptance is based on qualitative assessments and comparisons to the predicate device.
| Testing Type | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Performance Testing - Clinical | Acceptable image quality for clinical use. | "A radiologist validated that the clinical images have acceptable image quality for clinical use." |
| Performance Testing - Bench | New features perform as intended for diagnostic use. | "We confirmed that each new feature performs as intended for diagnostic use." Specifically for each new feature: |
- ASL-Perfusion: "Test results confirm ASL-Perfusion acquires perfusion images using labeled blood flowing into the brain tissue without Contrast-Enhanced both in phantom simulations and clinical results."
- Beam Sat VASC-ASL: "Test results confirm Beam Sat improves the visibility of the portal vein in making MIP images both in phantom simulations and clinical results."
- Breast MRS: "Test results from phantom simulations and clinical results confirm MRS (Magnetic Resonance Spectroscopy) acquires the magnetic resonance signal of in vivo metabolites through chemical shift phenomenon and can detect Choline as metabolite in the breast area."
- Enhanced PC: "Test results from phantom simulations and clinical results indicate a reduction in scan time of phase contrast (PC) sequence in 2D and 3D by shorting the TR by optimizing velocity encode gradient and applied parallel imaging (RAPID). As a result of this improvement, we can shorten scan time of '4D flow' which is time-resolved (CINE) three-dimensional (3D) spatial encoding combined with three-directional velocityencoded phase contrast MRI."
- Fat and water separation scan (FSE, RSSG, GE): "Test results from phantom simulations and clinical results indicate reliable and uniform fat suppression by utilizing the difference between resonant frequencies due to chemical shift of water protons and fat protons to obtain a water image and a fat image. The chemical shift of a water signal and a fat signal receives two echo signals at the timing which becomes an in-phase and an out-of-phase. By adding and subtracting it, a water image and a fat image are simultaneously acquirable."
- k-RAPID: "Test results from phantom simulations and clinical results indicate that k-space parallel imaging technique accelerates the scan by acquiring k-space data with skipped phase encoding and skipped position which is filled with estimated data by the interpolation of neighboring data."
- Multi b and DKI: "Test results from phantom simulations and clinical results confirm Multi b DKI images can be acquired in one scan utilizing Tensor 15 and Tensor 30 being added to the number of MPG Axes. Diffusion Kurtosis Imaging (DKI) is the diffusion-weighted imaging technique in restriction."
- opFSE / opFIR: "Test results from phantom simulations and clinical results confirm by deriving opFSE and opFIR sequence from the primeFSE and primeFIR image quality is improved."
- PBSG: "Test results from phantom simulations and clinical results confirm PBSG which is a sequence based on BASG sequence improves to mitigate the dark band artifact which is unique to BASG sequence. The PBSG sequence makes it possible to acquire BASG images under the condition of inhomogeneous magnetic field with less band artifact."
- RADAR-GE/TOF: "Test results from phantom simulations and clinical results confirm the RADAR measurement feature is functioning with the GE and TOF sequence."
- T2 RelaxMap:* "Test results from phantom simulations and clinical results confirm that T2* relaxation time can be mapped on morphological image in color by using T2* RelaxMap function. The T2* RelaxMap function consists of (a) acquisition of multi-echo images (up to 32) and (b) analysis of T2* relaxation time." |
| Substantial Equivalence | Hardware, coils, and functionality are substantially equivalent to the predicate device in design features, fundamental scientific technology, indications for use, and safety and effectiveness. | "based on a thorough analysis and comparison of the functions, scientific concepts, physical and performance characteristics, performance comparison and technological characteristics, the proposed ECHELON Oval V5.0 MRI is considered substantially equivalent to the currently marketed predicate device (ECHELON Oval MRI System (K113145)) in terms of design features, fundamental scientific technology, indications for use, and safety and effectiveness." |
2. Sample Size Used for the Test Set and Data Provenance
The document states:
- "Clinical images were collected and analyzed, to ensure that images from the new features meet user needs."
- "We provide clinical image examples for each new feature..."
However, the specific sample size (number of images or patients) used for the clinical test set is not provided in the document.
The data provenance is also not explicitly stated in terms of country of origin or whether it was retrospective or prospective. It only mentions "clinical images were collected," implying real patient data, but without further detail.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: "A radiologist" (singular) validated the clinical images.
- Qualifications of Experts: The document specifies "a radiologist." No further details on their experience (e.g., "10 years of experience") are provided.
4. Adjudication Method for the Test Set
The document mentions "a radiologist validated" the images. This suggests a single expert review. There is no mention of an adjudication method such as 2+1, 3+1, or any multi-reader consensus process for the clinical images.
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, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not done or reported in this submission. This submission is for a software update to an MRI system itself, not an AI-assisted diagnostic tool for readers. The "AI" features (like k-RAPID for image acceleration or certain processing tasks) are integrated into image acquisition and reconstruction, not designed to directly assist human interpretation in a comparative effectiveness study setting mentioned in the question.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
The "Performance Evaluation" section indicates that both "Performance Testing - Clinical" and "Performance Testing - Bench" were conducted for the new features.
- Bench tests involved "phantom simulations," which represents an algorithm-only evaluation for the technical performance of specific sequences.
- Clinical tests involved collecting and analyzing clinical images, and "a radiologist validated" them. While a human reviewed the output, the core algorithms for the new features (e.g., ASL-Perfusion generating perfusion images, T2* RelaxMap creating maps) operate in a standalone manner to produce these outputs before human interpretation.
Therefore, standalone performance tests were conducted for the new features on phantoms, and the resulting clinical images were then validated by a radiologist. The focus was on the technical and image quality output of the new algorithms, not diagnostic accuracy in a standalone AI context compared to a ground truth.
7. The Type of Ground Truth Used
- For the bench tests (phantom simulations), the "ground truth" would be the known physical properties and configurations of the phantom, allowing for objective measurement of parameters like signal-to-noise ratio, geometric distortion, etc.
- For the clinical validation, the ground truth appears to be expert consensus or opinion from "a radiologist" who validated the "acceptable image quality for clinical use." There is no mention of pathology, outcomes data, or a multi-expert consensus forming the ground truth.
8. The Sample Size for the Training Set
The document does not describe the development or training of new algorithms in a way that suggests a "training set" in the context of machine learning. The enhanced features are described as software updates and new pulse sequences. Therefore, there is no information provided regarding a training set size. This submission focuses on the performance verification and validation of the software update, not the development process of, for example, a deep learning model.
9. How the Ground Truth for the Training Set was Established
Since no training set is mentioned in the context of machine learning algorithm development, this information is not applicable and not provided in the document. The document describes system updates and their performance validation.
§ 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.