(15 days)
The MRI Soft Tissue Motion Correction Software is an adjunctive tool to assist radiologists in interpreting magnetic resonance imaging (MRI) studies. The software is intended to be used in dynamic MRI examinations that consist of multiple image volumes where patient motion may have occurred between serial acquisitions.
The MRI Soft Tissue Motion Correction Software performs automatic 2D and/or 3D flexible registration of soft tissue. The registration process enables the correction of motion occuring both within-plane and across planes (3D). By aligning corresponding voxels, the software reduces the impact of patient motion in post-processing techniques including difference (subtraction) images, parametric displays, subtraction volume MIPs and mean-curve analysis.
Patient management decisions should not be made solely on the basis of motion corrected images and should always include review of uncorrected images.
MRI Soft Tissue Motion Correction Software VA10A provides the functionality to correct soft tissue motion of the MRI image volume between scan times. It supports the correction (registration) of one or more volumes relative to an initially supplied reference volume.
The product reduces image deformation and displacement in soft tissues shape and location that may occur due to patient motion in between acquisitions of serial MRJ images. Correction of within imaging plane and across- plane motion is supported.
The software corrects for inter-volume rigid displacement and non-rigid deformation between acquired MRI images. This reduces motion-related artifacts in post-processing techniques that use the corrected images as input, for example subtraction images, subtraction volume MIPs, parametric maps and mean-curve analysis.
MRI Soft Tissue Motion Correction is a plug-in module for Numaris VA21A clinical workstation (K020991) or equivalent, Leonardo 2004 (K040970) or equivalent and MammoReport Plus (K042868) or equivalent. The visualization application invokes the motion correction device, receives and stores the corrected volumes, and displays the results to the user.
MRI Soft Tissue Motion Correction provides both a high quality and a high-speed operational mode. The high-speed mode is optimized for speed, while the high-quality mode is recommended for cases having moderate to large amounts of patient motion between acquisitions and takes longer to complete.
This submission pertains to the "MRI Soft Tissue Motion Correction Software VA10A" by Siemens Medical Solutions USA, Inc., accepted on September 8, 2005.
Here's an analysis of the provided information regarding acceptance criteria and the study conducted:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document, a 510(k) summary, does not explicitly state quantitative acceptance criteria or specific metrics for device performance such as accuracy, sensitivity, or specificity. The submission focuses on demonstrating substantial equivalence to predicate devices rather than meeting pre-defined performance thresholds.
Instead of a table of numerical criteria, the document describes the measures taken during development to ensure quality and performance:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Risk Analysis | Applied |
| Requirements Reviews | Applied |
| Design Reviews | Applied |
| Integration testing (System verification) | Applied |
| Final acceptance testing (Validation) | Applied |
| Performance testing on clinical data sets (Validation) | Applied |
| Overall Conclusion | "The MRI Soft Tissue Motion Correction Software VA10A is as safe, as effective, and performs as well as the predicate devices." |
2. Sample Size Used for the Test Set and Data Provenance
The document states "Performance testing on clinical data sets (Validation)." However, it does not provide any details regarding:
- The specific sample size of the test set (number of cases, number of images).
- The data provenance (e.g., country of origin, whether the data was retrospective or prospective).
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts
The document does not mention using experts to establish ground truth for the test set, nor does it specify the number or qualifications of any such experts. The focus of the validation is on "Performance testing on clinical data sets," but the method of evaluating this performance (e.g., against expert consensus, pathology) is not described.
4. Adjudication Method for the Test Set
Since the document does not specify the use of experts or a method for establishing ground truth, there is no information provided on any adjudication method (e.g., 2+1, 3+1, none) for the test set.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Improvement
The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study. There is no mention of comparing human readers with and without AI assistance, nor any effect size regarding human improvement. The device is described as an "adjunctive tool," suggesting it aids radiologists, but no formal study demonstrating this aid is detailed in the summary.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The 510(k) summary does not explicitly detail a standalone performance study in terms of metrics like accuracy, specificity, or sensitivity. The "Performance testing on clinical data sets" likely served this purpose, demonstrating the algorithm's ability to correct motion, but the specific evaluation methodology and quantitative results are not provided. The phrase "Patient management decisions should not be made solely on the basis of motion corrected images and should always include review of uncorrected images" implies that it is not intended for standalone use in clinical decision-making.
7. The Type of Ground Truth Used
The document does not specify the type of ground truth used for the performance testing. It mentions "clinical data sets" but does not elaborate on how the correctness of the motion correction was evaluated (e.g., against manually corrected images, pathology, or clinical outcomes).
8. The Sample Size for the Training Set
The document does not provide any information regarding the sample size used for the training set for the software.
9. How the Ground Truth for the Training Set Was Established
The document does not provide any information regarding how the ground truth for the training set was established, as details about a training set are not 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.