(210 days)
Quantib™ Brain is a non-invasive medical imaging processing application that is intended for automatic labeling, visualization, and volumetric quantification of segmentable brain structures from a set of magnetic resonance (MR) images. The Quantib™ Brain output consists of segmentations, visualizations and volumetric measurements of grey matter (GM), white matter (WM), and cerebrospinal fluid (CSF). The output also visualizes and quantifies white matter hyperintensity (WMH) candidates. Users need to review and if necessary, edit WMH candidates using the provided tools, before validation of the WMHs. It is intended to provide the trained medical professional with complementary information for the evaluation and assessment of MR brain images and to aid the trained medical professional in quantitative reporting. Quantib™ Brain is a post-processing plugin for the GE Advantage Workstation (AW 4.7) or AW Server (AWS 3.2) platforms.
Quantib™ Brain is post-processing analysis software for the GE Advantage (AW 4.7) or AW Server (AWS 3.2) platforms using Volume Viewer Apps. 12.3 Ext 6. It is intended for automatic labeling, visualization, and volumetric quantification of identifiable brain structures from magnetic resonance images (a 3D T1-weighted MR image, with an additional T2-weighted FLAIR MR image for white matter hyperintensities (WMH) segmentation). The segmentation system relies on a number of atlases each consisting of a 3D T1-weighted MR image and a label map dividing the MR image into different tissue segments. Quantib™ Brain provides quantitative information on both the absolute and relative volume of the segmented regions. The automatic WMH segmentation is to be reviewed and if necessary, edited by the user before validation of the segmentation, after which volumetric information is accessible. It is intended to provide the trained medical professional with complementary information for the evaluation and assessment of MR brain images and to aid the radiology specialist in quantitative reporting.
Here's a breakdown of the acceptance criteria and study details for Quantib™ Brain 1, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state "acceptance criteria" but rather presents a performance study comparing the device's output to manual segmentations. Therefore, the "acceptance criteria" are inferred from the reported performance values that were deemed acceptable for market clearance.
| Metric (Inferred Acceptance Criterion) | Reported Device Performance (Mean ± Standard Deviation) |
|---|---|
| Brain Tissue Segmentation (GM, WM, CSF) | |
| Dice Index for CSF | 0.78 ± 0.05 |
| Dice Index for GM | 0.83 ± 0.02 |
| Dice Index for WM | 0.86 ± 0.02 |
| Absolute Difference of Relative CSF Volume (pp) | 1.6 ± 1.0 |
| Absolute Difference of Relative GM Volume (pp) | 2.8 ± 1.9 |
| Absolute Difference of Relative WM Volume (pp) | 2.6 ± 1.6 |
| ICV Segmentation | |
| Dice Index for ICV | 0.97 ± 0.01 |
| White Matter Hyperintensity (WMH) Segmentation | |
| Dice Index for WMH | 0.61 ± 0.13 |
| Absolute Difference of Relative WMH Volume (pp) | 0.6 ± 0.7 |
Note: The document states that the performance data "shows that Quantib™ Brain is as safe and effective as the predicate device," implying these performance metrics were sufficient to demonstrate substantial equivalence.
2. Sample Size Used for the Test Set and Data Provenance
-
Brain Tissue Segmentation (GM, WM, CSF, ICV):
- Sample Size: 33 T1w MR images with 6 selected slices per scan for comparison.
- Data Provenance: The set was "carefully selected to include data from multiple vendors and a series of representable scan settings." The document does not specify the country of origin or whether the data was retrospective or prospective.
-
White Matter Hyperintensity (WMH) Segmentation:
- Sample Size: 30 3D T1w images with corresponding T2w FLAIR images.
- Data Provenance: This set also "represented various scan settings." The document does not specify the country of origin or whether the data was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts or their qualifications for establishing the ground truth. It simply refers to "manual segmentations" for brain tissues and "manually segmented" WMHs.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method (e.g., 2+1, 3+1) for establishing the ground truth or resolving discrepancies in manual segmentations. It merely states "manual segmentations."
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, the document does not indicate that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done. The study focuses on comparing the algorithm's performance against manual segmentations, not on how human readers improve with or without AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a standalone performance study was done. The reported "Algorithm performance" (Section VII.2) directly compares the Quantib™ Brain's automatic segmentations and volume measurements to manual segmentations for the same scans, without human intervention in the device's output during the test. The "Users need to review and if necessary, edit WMH candidates using the provided tools, before validation of the WMHs" statement in the Indications for Use refers to the intended use case, not the performance validation study's methodology. The study itself assesses the raw algorithmic output.
7. The Type of Ground Truth Used
The ground truth used was expert manual segmentation.
- For brain tissue volumetry (GM, WM, CSF, ICV), the device's relative brain tissue volumes were compared to "relative volumes derived from manual segmentations."
- For WMH, "WMHs were manually segmented on the T2w FLAR images" and compared to the device's automatic segmentation.
8. The Sample Size for the Training Set
The document does not specify the sample size for the training set. It mentions that "The segmentation system relies on a number of atlases each consisting of a 3D T1-weighted MR image and a label map dividing the MR image into different tissue segments," but does not give a number for these atlases or the data used to create them or train the system.
9. How the Ground Truth for the Training Set Was Established
The document does not explicitly state how the ground truth for the training set was established. It mentions that the system "relies on a number of atlases each consisting of a 3D T1-weighted MR image and a label map dividing the MR image into different tissue segments." It can be inferred that these atlases contain expert-defined segmentations (label maps), but the method of their creation (e.g., by how many experts, what qualifications, adjudication) is not detailed.
§ 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).