Search Results

Advantage Windows /MR Fusion provides an easy means for comparison of three dimensional (3D) images from X-ray angiography (XR: providing anatomical imaging) and Magnetic Resonance (MR: providing anatomical imaging). It allows registration between two volumetric acquisitions, which may come from different acquisition modalities (X-Ray and MR), to help physicians in diagnostic radiology or therapy planning.

The GEMS Advantage Windows X-Ray/MR Fusion software package is an option on Advantage Windows that provides easy comparison of three dimensional (3D) images from X-ray angiography and Magnetic Resonance (MR). It allows 3D registration between two volumer. : acquisitions, which may come from different acquisition modalities, producing fusion of angiographic and other anatomical images.

The provided text is a 510(k) summary for the GE Medical Systems Advantage Windows X-Ray/MR Fusion software package. It focuses on demonstrating substantial equivalence to predicate devices rather than proving a new device's performance against detailed acceptance criteria via a specific study.

Therefore, many of the requested details about acceptance criteria, study specifics, ground truth, and sample sizes for training/test sets are not explicitly present in this type of regulatory submission document.

However, based on the available information, here's what can be inferred and stated:

1. A table of acceptance criteria and the reported device performance

The document doesn't provide a specific table of acceptance criteria with numerical performance metrics. Instead, the acceptance criterion for regulatory clearance in this context is "substantial equivalence" to legally marketed predicate devices.

2. Sample size used for the test set and the data provenance

• Sample size for the test set: Not specified. This document emphasizes equivalence rather than a new de novo performance study with a specific test set.
• Data provenance: Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not specified. (Ground truth establishment for new performance is not the focus of this 510(k) summary.)

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not specified.

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 is not mentioned. This device is for image registration and comparison, not primarily an AI algorithm for diagnostic interpretation in the way that would typically warrant an MRMC study for AI assistance. The focus is on the functional equivalence of the registration capabilities.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• The document implies that the software's functional capabilities (3D registration and comparison) were verified as performing "as well as devices currently on the market." This suggests verification of the algorithm's standalone functionality. However, a specific "standalone study" in the context of clinical performance metrics (e.g., sensitivity, specificity) is not described. The validation mentioned ("Software Development, Validation and Verification Process") would cover the standalone performance to specifications.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Not specified directly regarding a clinical ground truth for a performance study. For software validation, "performance to specifications" and "user requirements" would be the 'ground truth' for the validation process.

8. The sample size for the training set

• Not applicable/Not specified. This is a software package for image fusion, not a machine learning model that typically undergoes a training phase with a distinct training set.

9. How the ground truth for the training set was established

• Not applicable/Not specified, as this isn't a machine learning model with a training set.

Summary of the Study that Proves the Device Meets Acceptance Criteria:

The "study" or justification for meeting acceptance criteria described in this 510(k) summary is based on the concept of substantial equivalence to previously cleared predicate devices.

• Description: GE Medical Systems asserts that its Advantage Windows X-Ray/MR Fusion software package functions are substantially equivalent to:
  • Advantage Windows Fusion (CT/MR Fusion) - K983256
  • Advantage Windows CT/PET Fusion - K010336
• Methodology (implied): The equivalence is primarily argued by comparing the functional features and intended use of the new device with the predicate devices. The new device offers "3D registration of anatomical images from X-Ray with anatomical images from MR," which is functionally similar to what the predicate devices do for CT/MR and CT/PET fusion. The document also states that a "Software Development, Validation and Verification Process" was used to ensure performance to specifications, Federal Regulations, and user requirements, along with adherence to industry and international standards. This process would involve internal testing and validation activities but is not detailed as a clinical "study" in this submission.
• Conclusion: The claim is that the device "does not result in any new potential safety risks and performs as well as devices currently on the market," thereby establishing its equivalence. The FDA concurred with this assessment, granting clearance.

Ask a specific question about this device

AutoAlign software is intended to provide an output registration matrix that may be utilized to align an MRI brain scan to a known and consistent 3-dimensional (3-D) atlas of the human brain. AutoAlign software will be marketed as a software device that can provide improvements to the manual processes of MRI brain image registration.

To be utilized for the registration of brain images for MRI.

The device (software) operates by comparing a subjects' brain MR localizer images to a preexisting atlas of the human brain. The software then calculates a set of coordinates that can be used to align subsequent MRI images to the atlas. The accuracy of the alignment is measured and then programmatically reported. AutoAlign is a software device that provides the following features:

• . Imports MRI brain images
• Calculates and then outputs an optimized 3-D registration matrix that permits . alignment of the brain, regardless of the actual physical position of the subject's head in the image. For instance, in the test alignment:
  • o in the sagittal image, the intra-hemispheric plane is at the center slice of the MRI volume so the anterior & posterior commeasures (ac-pc line) are visible on that slice.
  • in the axial image, the intra-hemispheric plane is parallel to the Y axis. o
  • in the coronal image, the intra-hemispheric plane is parallel to the Y axis. o
• It can provide consistent scan/rescan alignment between separate scanning ● sessions within boundaries established and documented in Product Labeling Instructions.
• This software can be utilized by a MRI scanner original equipment manufacturer ● (OEM) to improve the workflow and automation of MRI brain study acquisitions.
• AutoAlign does not alter or otherwise modify the initial MR localizer image in any way
• The AutoAlign system does not have any adverse affects on health. This tool ● operates as a stand-alone software device, receives the MR scout localizer as input and outputs an optional registration prescription. AutoAlign does not alter or otherwise modify the initial MR localizer image in any way, and Labeling stipulates a review of the output registration by a trained MR operator.

The provided text does not contain detailed acceptance criteria or a study that explicitly proves the device meets such criteria. It outlines the intended use, device description, and acknowledges that "Final Verification and Validation of the software has not been completed" and will be notified to the FDA upon completion. It mentions "Performance Testing: AutoAlign will successfully complete testing as detailed in the Clinical Performance Summary," but this summary is not provided in the excerpt.

Therefore, I cannot fulfill your request for a table of acceptance criteria, reported device performance, sample sizes, expert qualifications, adjudication methods, MRMC study details, standalone performance, or ground truth details.

The document is an Abbreviated 510(k) Summary and a subsequent FDA clearance letter. It serves to explain the device's purpose and its substantial equivalence to predicate devices, rather than providing a detailed clinical performance study report.

Key information from the document related to performance (but not meeting your request for detailed study results):

• Intended Use: "AutoAlign software is intended to provide an output registration matrix that may be utilized to align an MRI brain scan to a known and consistent 3-dimensional (3-D) atlas of the human brain. AutoAlign software will be marketed as a software device that can provide improvements to the manual processes of MRI brain image registration."
• Device Description (related to performance): "The accuracy of the alignment is measured and then programmatically reported." And, "It can provide consistent scan/rescan alignment between separate scanning sessions within boundaries established and documented in Product Labeling Instructions."
• Performance Testing: "AutoAlign will successfully complete testing as detailed in the Clinical Performance Summary." (This summary is missing).
• Regulatory Status: The FDA's clearance letter indicates the device is cleared for marketing based on substantial equivalence, with the expectation that verification and validation will be completed.

Without the "Clinical Performance Summary" or similar documentation, it's impossible to provide the requested details about acceptance criteria and the study that proves the device meets them.

Ask a specific question about this device

Fusion7D registers pairs of anatomical and functional volumetric images (e.g. MRI-SPECT, MRI-PET, CT-SPECT, CT-PET), or pairs of anatomical volumetric images (e.g. MRI-MRI, CT-CT and MRI-CT) as a means to ease the comparison of image volume data by the clinician. The result of the registration operation aims to help the clinician obtain a better understanding of the joint information that would otherwise have to be compared visually. This is useful for a wide range of clinical and therapeutic applications. It is important to note that the clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard procedures including visual comparison of the separate unregistered images. Fusion7D is a complement to these standard procedures.

Fusion7D is a software program running on a PC platform, which brings into alignment (registers) pairs of images from different imaging modalities. Fusion7D also includes functionality to read, display, and save the original volumetric data and the results of the registration operation by means of a graphic user interface that includes visualization, file browsing and control of input and output as described in the following text.

The provided text describes Fusion7D, a software program for registering and fusing medical images. However, it does not include detailed acceptance criteria or a study that specifically proves the device meets such criteria in terms of quantitative performance metrics, sample sizes, expert involvement, or statistical analysis.

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to predicate devices, rather than providing a detailed performance study with acceptance criteria.

Therefore, the following information cannot be extracted from the provided text:

• A table of acceptance criteria and the reported device performance: This information is not present. The document describes the device's capabilities and intended use but does not quantify performance against specific criteria.
• Sample size used for the test set and the data provenance: No performance study details are given.
• Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
• Adjudication method for the test set: Not mentioned.
• If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance: This type of study is not described. The device is a registration tool, not an AI diagnostic aid in the sense of improving human reader performance on a diagnostic task, although it aims to "ease the comparison of image volume data."
• If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not explicitly stated or quantified in terms of performance. The document implies automated registration capabilities but doesn't provide a standalone performance evaluation against a gold standard.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not mentioned.
• The sample size for the training set: No training data or set is mentioned, as this is more a description of the final device functionality rather than its development.
• How the ground truth for the training set was established: Not applicable, as no training set is described.

Summary of what can be inferred about "acceptance criteria" and "study" implicitly from the document:

The "acceptance criteria" for Fusion7D, as implied by the 510(k) process, primarily revolve around demonstrating substantial equivalence to legally marketed predicate devices in terms of intended use, technological characteristics, and safety/effectiveness. The "study" largely consists of the submission itself, detailing the device's functionality and comparing it to existing, approved devices.

The document states:

• "Fusion7D is a software program running on a PC platform, which brings into alignment (registers) pairs of images from different imaging modalities."
• It supports "manual," "semi-automatic," and "automatic" registration, limited to "rigid body deformation."
• It provides "standard visualization facilities" and allows "registration results to be displayed in a variety of ways."
• Intended Use: "Fusion7D registers pairs of anatomical and functional volumetric images... as a means to ease the comparison of image data."

The FDA's approval letter confirms that the device was found "substantially equivalent" based on its comparison to the predicate devices listed (K010336, K983256, K992654). This substantial equivalence is the de facto "acceptance criteria" for this 510(k) submission, and the "study" is the submission argument itself.

Ask a specific question about this device