(124 days)
Vitrea Software Toshiba Package is an application package developed for use on Vitrea®, a medical diagnostic system that allows the processing, review, analysis, communication and media interchange of multi-dimensional digital images acquired from a variety of imaging devices. Vitrea has the following additional indications:
The CT/XA Cerebral Artery Morphological Analysis application is intended to facilitate the extraction and segmentation of user identified aneurysms on the cerebral arteries. The software can be used as an adjunct to diagnosis for the purposes of measurement of size and aspect ratio.
The MR Wall Motion Tracking application is intended to assist physicians with performing cardiac functional analysis based upon magnetic resonance images. It provides measurements of global and regional myocardial function that is used for patients with suspected heart disease.
The MR Coronary Tracking application is intended to assist physicians with performing coronary artery analysis for MR heart images which are intended for the qualitative and quantitative analysis of coronary arteries.
The SUREVolume Synthesis application is intended to load volume images acquired by whole-body X-ray CT scanners, X-ray angiography systems, and MRI systems and displays fusion images.
The Angio Viewer application displays image data acquired using an X-ray angiography system. It supports cine display, subtraction, and distance measurement.
The US Cardiac Fusion application enables fusion display of the analysis results obtained using the US 3D Wall Motion Tracking application and the CT Coronary Artery Analysis application.
Vitrea Software Toshiba Package, VSTP-001A, an application package developed for use on Vitrea, a medical image processing software, marketed by Vital Images, Inc. Vitrea Software Toshiba Package, VSTP-001A, currently includes three post processing applications, CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, and MR Coronary Tracking which use brain and cardiac image data, obtained from CT/XA/MR systems, to assist physicians in performing specialized measurements and analysis.
The provided document describes the Vitrea Software Toshiba Package, VSTP-001A, which includes several applications. The information regarding acceptance criteria and studies is provided for the new applications being submitted: SUREVolume Synthesis, US Cardiac Fusion, and Angio Viewer.
Here's a breakdown of the requested information based on the provided text:
1. Table of acceptance criteria and the reported device performance
| Application | Acceptance Criteria (Implied from Study Objectives/Outcomes) | Reported Device Performance |
|---|---|---|
| SUREVolume Synthesis | Able to successfully fuse various combinations of data sets at an acceptable level. Automatic alignment is desirable; manual alignment should be successful if automatic fails. | Successfully fused various combinations of data sets at an acceptable level. In cases where automatic alignment was not obtainable, manual alignment was successful on all cases. |
| US Cardiac Fusion | Successful alignment of CCTA images and 3D Wall motion tracking images. Automatic alignment is desirable; manual alignment should be successful if automatic fails. | Automatic alignment success: 74% (64 to 89%). Successful manual adjustment: 90% (86 to 93%). |
| Angio Viewer | Replicate image measurements from the predicate device within a stated tolerance (implied to be ≤ 1%). | Possible to replicate image measurements from the predicate device within the stated tolerance of less than or equal to 1%, demonstrating successful integration of the INFX-8000F software to the VSTP-001A application. |
| CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking | (Not explicitly stated for these applications, as they were previously cleared and unchanged. Bench testing mentioned for accuracy of extraction/display of aneurysm shaped regions, and measurement calculations, cardiac function, and strain.) | Bench studies were conducted using numerical phantoms to analyze the accuracy of extraction/display of aneurysm shaped regions as well as measurement calculations and to analyze cardiac function and strain. (Specific acceptance criteria or performance numbers are not detailed for these previously cleared features in this submission.) |
2. Sample size used for the test set and the data provenance
- SUREVolume Synthesis & US Cardiac Fusion:
- Sample size: Not explicitly stated as a number of cases or images. The text mentions "various combinations of data sets" for SUREVolume Synthesis and "CCTA images and 3D Wall motion tracking images" for US Cardiac Fusion.
- Data provenance: Not explicitly stated (e.g., country of origin). The studies were described as "clinical evaluations conducted at clinical sites" for both. The text does not specify retrospective or prospective.
- Angio Viewer:
- Sample size: Not explicitly stated. The text mentions "repeated measurements."
- Data provenance: Not explicitly stated. The evaluation was "conducted head on against the predicate device at the design site." Implies retrospective use of existing data for comparison.
- CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking:
- Sample size: Not explicitly stated. The text mentions "numerical phantoms."
- Data provenance: Not explicitly stated. These were "bench studies."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- SUREVolume Synthesis & US Cardiac Fusion: The text states, "In both studies users of varying levels of experience reviewed all images and performed manual alignments as required." It does not specify the exact number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience").
- Angio Viewer, CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking: Not specified for these applications.
4. Adjudication method for the test set
- SUREVolume Synthesis & US Cardiac Fusion: For these clinical evaluations, "users of varying levels of experience" performed manual alignments when automatic alignment was not successful. This implies that the initial "ground truth" for success/failure of automatic alignment might have been based on their interpretation, and their subsequent manual alignments formed a manual "ground truth" for comparison. An explicit adjudication method like 2+1 or 3+1 is not mentioned.
- Angio Viewer: The evaluation involved "repeated measurements" against a predicate device. This suggests a direct comparison rather than an adjudication process by multiple experts.
- CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking: These involved bench studies with numerical phantoms. Adjudication by experts is not applicable here.
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 MRMC comparative effectiveness study, evaluating human reader improvement with or without AI (or in this case, the software applications), is described in the provided text. The studies primarily focused on the performance of the software applications themselves, or direct comparison against a predicate device, rather than a reader study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- SUREVolume Synthesis & US Cardiac Fusion: The studies mention "automatic alignment success" which represents a standalone algorithm performance metric. However, it also clarifies that "users of varying levels of experience" performed manual alignments when automatic alignment failed, indicating that human-in-the-loop performance (manual adjustment) was also evaluated as a fallback.
- Angio Viewer: The "bench testing at the design site against its predicate device" and replicating measurements implies a standalone comparison of the software's measurement capabilities.
- CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking: Bench studies using "numerical phantoms to analyze the accuracy of extraction/display... as well as measurement calculations" clearly represent standalone algorithm performance.
7. The type of ground truth used
- SUREVolume Synthesis & US Cardiac Fusion: The ground truth for fusion success and alignment appears to be based on the assessment of "users of varying levels of experience" at clinical sites. This would fall under an expert consensus/assessment type of ground truth, though the number of experts and their specific consensus method are not detailed.
- Angio Viewer: The ground truth for measurement accuracy was the "predicate device" (Infinix Celeve-I: INFX-8000F) based on measurements obtained from it.
- CT/XA Cerebral Artery Morphological Analysis, MR Wall Motion Tracking, MR Coronary Tracking: The ground truth for these bench studies was "numerical phantoms" and "measurement calculations," implying a precisely defined, known truth.
8. The sample size for the training set
The provided document does not mention the sample size used for the training set for any of the applications. It focuses on the validation/verification studies.
9. How the ground truth for the training set was established
The provided document does not mention how the ground truth for the training set was established, as it does not discuss the training process.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).