(479 days)
CerebralGo Plus is an image processing software package to be used by trained professionals, including, but not limited to physicians and medical technicians. The software runs on standard "off-the-shel" hardware and can be used for image viewing and processing. Data and images are acquired through DICOM compliant imaging devices.
CerebralGo Plus provides viewing and processing capabilities for imaging datasets acquired with adult's CTA (CT Angiography).
CerebralGo Plus is not intended for primary diagnostic use.
CerebralGo Plus is a medical image management and processing software package to be used by trained professionals, including, but not limited to physicians and medical technicians.
The software runs on standard "off-the-shelf" hardware and can be used for image viewing, and processing images of DICOM compliant CTA imaging which, when interpreted by a trained clinician, may yield information useful in clinical decision making.
CerebralGo Plus system provides a wide range of basic image viewing, processing, and manipulation functions, through multiple output formats. The software is used to visualize large vessels from head and neck CTA imaging.
Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria & Reported Device Performance
The document does not explicitly state formal acceptance criteria in a table format with pass/fail thresholds. Instead, it reports performance metrics (Dice Coefficient and 95% Hausdorff Distance) from a verification study. The implied "acceptance" is that these metrics demonstrate the device's efficacy for its intended use, particularly for segmentation tasks (implied by Dice and Hausdorff metrics which are common in image segmentation validation).
| Metric / Parameter | Unit of Measurement | Reported Device Performance |
|---|---|---|
| Dice Coefficient | N/A (unitless, a similarity measure) | 0.942 |
| 95% Hausdorff Distance | Millimeters (implied for medical imaging) | 3.692 |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 141 images.
- Data Provenance: The images were collected from the US and are described as covering different genders, ages, ethnicities, equipment, and CT protocols. It is a retrospective dataset as it was collected for verification of a pre-existing algorithm.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: 3 radiologists.
- Qualifications of Experts: All 3 radiologists were from the US. Their specific experience level (e.g., years of experience, subspecialty) is not explicitly stated in the provided text.
4. Adjudication Method for the Test Set
- Adjudication Method: When the first two radiologists conflicted (presumably in their independent assessments), a third radiologist would arbitrate to generate the reference standard (ground truth). This can be described as a 2+1 adjudication model.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study Done? No, a human-in-the-loop MRMC study comparing human readers with AI assistance versus without AI assistance was not done. The study described is a standalone (algorithm-only) performance evaluation against a consensus ground truth.
- Effect Size of Human Improvement (if applicable): Not applicable, as no MRMC study was conducted.
6. Standalone (Algorithm Only) Performance Study
- Standalone Study Done? Yes. The performance data section explicitly states "Stand-alone software performance testing" and the results are presented for the algorithm itself (Dice Coefficient and Hausdorff Distance).
7. Type of Ground Truth Used
- Type of Ground Truth: The ground truth for the test set was established through expert consensus among 3 radiologists, using a 2+1 adjudication method.
8. Sample Size for the Training Set
- Training Set Sample Size: The exact sample size for the training set is not specified. The document only states that "Algorithm training of CerebralGo Plus has been conducted on images collected from China as training dataset."
9. How the Ground Truth for the Training Set Was Established
- Ground Truth Establishment for Training Set: The document does not provide details on how the ground truth for the training set (images collected from China) was established. It only mentions that these images were used for algorithm training.
§ 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).