(109 days)
icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR images.
icobrain consists of two distinct image processing pipelines: icobrain cross and icobrain long.
Icobrain cross is intended to provide volumes from images acquired at a single timepoint
icobrain long is intended to provide changes in volumes between two images that were acquired on the same scanner, with the same image acquisition protocol and with same contrast at two different timepoints
The results of icobrain cross cannot be compared with the results of icobrain long.
icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR images. This software is intended to automate the current manual process of identifying, labeling and quantifying the volume of segmentable brain structures identified on MR images.
icobrain consists of two distinct image processing pipelines: icobrain cross and icobrain long.
- icobrain cross is intended to provide volumes from images acquired at a single timepoint
- icobrain long is intended to provide changes in volumes between two images that were acquired on the same scanner, with the same image acquisition protocol and with same contrast at two different timepoints
The results of icobrain cross cannot be compared with the results of icobrain long.
As input, icobrain uses TI-weighted and fluid-attenuated inversion recovery (FLAIR) DICOM MR images from a single or from multiple time points. In case of multiple time points, i.e. multiple MRI scans from the same subject, for each time point one FLAIR and one TI image are used as input. During the pre-processing, the scan type (TI, FLAIR) is detected for every input image before it is converted from DICOM format to NIFTI format. The image processing then performs the actual segmentation and calculates the volumes of the brain structures. In case MRI scans subject on multiple time points are available, the changes in volume of the brain structures are calculated as well. Finally, the computed volumes and volume changes (in case of multiple time points) are summarized into an electronic report and (some) segmentations are overlaid on the input images.
The software displays the following volumetric measures:
- normalized volume and volume changes of the whole brain (sum of white and grey matter),
- normalized volume and volume changes of grey matter,
- unnormalized volume and volume changes of FLAIR white matter hyperintensities.
Normalized whole brain and grey matter volumes are corrected for head size and are compared to a healthy population using a statistical model. The reported FLAIR white matter hyperintensities volumes are not normalized since they are not comparable to a reference population.
Here's a breakdown of the acceptance criteria and study information for the icobrain device, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance:
The document broadly mentions acceptance criteria but does not explicitly list them with numerical targets. Instead, it reports aggregated performance metrics.
| Metric | Acceptance Criteria | Reported Device Performance (Averaged over all experiments) |
|---|---|---|
| Pearson Correlation Coefficient (between compared measurements) | Relevant acceptance criteria for each experiment type established through literature review and passed. | 0.90 |
| Intraclass Correlation Coefficient | Relevant acceptance criteria for each experiment type established through literature review and passed. | 0.89 |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: 349 subject datasets in total (encompassing all experiments: accuracy and reproducibility).
- Data Provenance: The document states the subjects include "healthy subjects, Alzheimer's disease patients, multiple sclerosis patients, traumatic brain injury patients, depression patients." It does not specify the country of origin, nor whether the data was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
The document mentions "manually labeled ground truth volume changes" for accuracy experiments but does not specify the number of experts, their qualifications, or how the manual labeling was performed.
4. Adjudication Method for the Test Set:
Not specified in the provided text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Was one done? Not explicitly mentioned. The study focuses on comparing the device's measurements to ground truth or test-retest data, not on human readers' performance with and without AI assistance.
- Effect size of human readers improvement: Not applicable, as an MRMC comparative effectiveness study involving human readers' improvement with AI assistance is not described.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
Yes, the study appears to be a standalone performance evaluation of the icobrain algorithm. It validates the "measured volume changes of the segmentable brain structures for accuracy and reproducibility" by comparing them to "simulated and/or manually labeled ground truth volume changes" and "test-retest image data sets." There is no mention of human-in-the-loop performance in the performance testing section.
7. Type of Ground Truth Used:
- Accuracy Experiments: "Simulated and/or manually labeled ground truth volume changes."
- Reproducibility Experiments: Test-retest image data sets.
8. Sample Size for the Training Set:
Not specified in the provided text. The document focuses on the performance testing dataset (349 subject datasets).
9. How the Ground Truth for the Training Set Was Established:
Not specified in the provided text.
§ 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).