(154 days)
The OASIS MRI 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 (T), 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 OASIS is a Magnetic Resonance Imaging System that utilizes a 1.2 Tesla superconducting maqnet in a qantry design.
The provided document is a 510(k) Premarket Notification from Hitachi Healthcare Americas for their OASIS MRI System. It primarily focuses on demonstrating substantial equivalence to a previously cleared predicate device (OASIS MRI System K202030) rather than presenting a detailed clinical study with acceptance criteria for a new device's performance.
Therefore, the document does not contain details about acceptance criteria or a study that specifically proves the device meets those criteria in the way typically expected for an AI/ML medical device.
However, I can extract information related to performance evaluation and testing that was conducted to support the substantial equivalence claim.
Here's an analysis based on the provided text:
No specific acceptance criteria and detailed study proving direct device performance against those criteria are provided in the document. The document primarily focuses on demonstrating substantial equivalence to a predicate device by evaluating changes and ensuring they do not affect safety or effectiveness.
Here's what can be extracted regarding the type of performance evaluation done:
1. Table of Acceptance Criteria and Reported Device Performance
As noted above, no explicit table of acceptance criteria with corresponding device performance metrics is provided in the document for the new features. The evaluation is primarily framed in terms of demonstrating that new features perform as intended and do not raise new questions of safety or effectiveness compared to the predicate device.
The document states:
- "Performance bench testing was conducted on the applicable new features. Test data confirmed that each new feature perform as intended for diagnostic use."
- "Clinical image examples are provided for each applicable new feature and or coil that we judged to be sufficient to evaluate clinical usability."
- "Clinical images were collected and analyzed, to ensure that images from the new feature meet user needs."
These are qualitative statements about performance rather than quantitative acceptance criteria.
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not specified. The document states "Clinical image examples are provided for each applicable new feature..." This suggests a qualitative review of examples rather than a statistically powered study with a defined sample size.
- Data Provenance: Not specified. The context implies these are images generated by the OASIS MRI system itself, but no details about the patient population, imaging sites, or whether the data is retrospective or prospective are given.
3. Number of Experts Used to Establish Ground Truth and Qualifications of Experts
- Number of Experts: Not specified. The evaluations were "judged to be sufficient to evaluate clinical usability" and to "meet user needs," implying expert review, but the number or specific roles of these experts are not detailed.
- Qualifications of Experts: Not specified. The indications for use state that "When interpreted by a trained physician, these images provide information that can be useful in diagnosis determination." This indirectly suggests that the "judges" and "users" are likely trained physicians or radiologists, but their specific qualifications (e.g., years of experience, subspecialty) are not mentioned.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified. Given the qualitative nature of the review ("judged to be sufficient," "meet user needs"), it's likely a consensus-based or individual expert assessment rather than a formal adjudicated process (e.g., 2+1, 3+1).
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
- MRMC Study: No, an MRMC comparative effectiveness study was not explicitly mentioned or described. The document focuses on demonstrating that the device (i.e., the MRI system itself) with new features is substantially equivalent to the predicate, not on how human readers' performance improves with or without AI assistance. The OASIS MRI System is an imaging device, and the changes described (coils, software functions) are enhancements to image acquisition and processing, not an AI-assisted diagnostic tool.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done
- Standalone Performance: The described device (OASIS MRI System) is an imaging system, not an algorithm intended for standalone diagnostic output. Therefore, a standalone performance evaluation in the context of an "algorithm only" is not applicable or described. The performance testing conducted for the new software functions (IP-Recon, IP-Scan, AutoPose Spine, AutoClip) would relate to their intended function within the MRI system (e.g., image reconstruction accuracy, scan automation effectiveness), not as standalone diagnostic algorithms.
7. The Type of Ground Truth Used
- Ground Truth Type: Not explicitly stated as "ground truth." The evaluation seems to rely on clinical usability and meeting user needs as assessed by qualified individuals (implicitly, physicians/radiologists). This would fall under a form of expert consensus/opinion regarding the quality and utility of the images produced by the new features. There's no mention of pathology, outcomes data, or other objective sources of ground truth.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable/not specified. The document describes an MRI system and its software/hardware enhancements. It does not mention a "training set" in the context of machine learning model development. The software functions like IP-Recon, IP-Scan, AutoPose Spine, and AutoClip are likely rule-based or optimized algorithms, not necessarily deep learning models requiring a distinct "training set" in the common sense.
9. How the Ground Truth for the Training Set was Established
- Ground Truth Establishment for Training Set: Not applicable/not specified, as no training set for a machine learning model is mentioned.
§ 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.