Search Results
Found 1 results
510(k) Data Aggregation
(115 days)
TeraRecon Aorta.CT (1.1.0)
TeraRecon Aorta.CT is intended to provide an automatic 3D segmentation and label anatomical landmarks of the Aorta. The results of TeraRecon Aorta.CT are intended to be used in conjunction with other patient information by trained professionals who are responsible for making any patient management decision per the standard of care. TeraRecon Aorta.CT is a software as a medical device (SaMD) deployed as a containerized application. The device inputs are CT Angiography with contrast DICOM images. The device outputs are DICOM result files which may be viewed utilizing DICOM-compliant systems. The device does not alter the original input data and does not provide a diagnosis.
TeraRecon Aorta.CT is indicated to generate results from aortic CT Angiography scans taken of adult patients except patients with pre-existing aortic device, bicuspid aortic valve anomaly, aortic dissection, aortic rupture, and abdominal metallic devices. The device is not specific to any gender, ethnic group, or clinical condition.
The TeraRecon Aorta.CT algorithm is an image processing software device that can be deployed as a containerized application (e.g., Docker container) that runs on off-the-shelf hardware or on a cloud platform.
The device provides an automatic 3D segmentation of the aorta and landmarks of important aortic anatomy. When TeraRecon Aorta.CT results are used in external viewer devices such as TeraRecon's Intuition or Eureka Clinical Al medical devices, all the standard features offered by the external viewer are employed.
The TeraRecon Aorta.CT algorithm is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by individuals that have been trained in the software's function, capabilities, and limitations.
Here's a summary of the acceptance criteria and study details for the TeraRecon Aorta.CT (1.1.0) device:
1. Table of Acceptance Criteria and Reported Device Performance
| Feature | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Lumen Segmentation | Mean DICE score >= 80% | Mean DICE score: 88% (Passed) |
| Aorta Segmentation | Mean DICE score >= 80% | Mean DICE score: 90% (Passed) |
| Landmarking (Overall) | Each of the 22 landmarks independently pass class-specific criteria in 80% of cases. Lower bound of the 95% exact binomial confidence interval >= 70%. | All landmarks passed the acceptance criteria, all 95% confidence intervals were at least 70%. (Passed) |
| Landmarking (Specific Criteria): | ||
| Common Left/Right Iliac Arteries, Left/Right Femoral Arteries (4 landmarks) | Correct identification of the vessel in accordance with ground truth. | Not explicitly stated with individual percentages, but included in the overall "all landmarks passed" statement. |
| Remaining 17 Landmarks (except aortic bifurcation) | Euclidean distance between ground truth annotation and medical device output locations within 5mm. | Not explicitly stated with individual percentages, but included in the overall "all landmarks passed" statement. |
| Aortic Bifurcation (1 landmark) | Euclidean distance between ground truth annotation and medical device output locations within 2cm. | Not explicitly stated with individual percentages, but included in the overall "all landmarks passed" statement. |
2. Sample Size Used for the Test Set and Data Provenance
- Initial Sample Size for Test Set: 170 CTA scans for segmentation and landmarking.
- Adjusted Sample Size for Landmarking: 170 initial studies + 29 supplemental studies = 199 studies (to achieve a target of 70 annotatable landmarks per target).
- Data Provenance: Retrospective cohort study. At least 50% of the ground truth data is from US patients across 3 geographical regions in the United States. The validation data was enriched with data from patients with clinical diagnosis of aortic dilation/aneurysm and/or aortic valve disease. The final manufacturer distribution of scanner types was 77 Siemens, 33 GE, 35 Philips, and 25 Canon.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: Not explicitly stated as a count, but referred to as "annotators" for landmarking and a "US board certified radiologist" for checking collected datasets.
- Qualifications of Experts: The individual who checked collected datasets was a "US board certified radiologist, who is currently practicing in the United States and reads similar scans." The qualifications of the "annotators" for landmarking are not specified beyond their task.
4. Adjudication Method for the Test Set
The document does not explicitly state an adjudication method (e.g., 2+1, 3+1). It implies that ground truth was established by experts (radiologist and annotators) and then compared to the device output. There is no mention of a process for resolving discrepancies among multiple experts or between expert and device output outside of direct comparison.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
No, an MRMC comparative effectiveness study that involves human readers with and without AI assistance was not explicitly described or presented in the provided text. The study focuses on evaluating the standalone performance of the AI device against ground truth.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, a standalone study was performed. The described study evaluates the Aorta.CT device's performance (segmentation DICE scores and landmarking accuracy) directly against expert-established ground truth. There is no mention of human-in-the-loop performance evaluation in this specific study.
7. The Type of Ground Truth Used
- Segmentation (Lumen and Aorta Wall): Expert annotations as described by "Comparison of Aorta lumen segmentation results from the medical device to aorta lumen segmentation from ground truth" and "This aorta wall to wall segmentation includes aorta lumen + wall for the comparison."
- Landmarking: Expert annotations as described by "We will also examine the subject device landmarking locations compared to each ground truth annotation."
8. The Sample Size for the Training Set
The sample size for the training set is not provided in the given text. The document focuses on the validation study and its test set.
9. How the Ground Truth for the Training Set was Established
The method for establishing ground truth for the training set is not provided in the given text. The document only describes how ground truth was established for the retrospective cohort test set.
Ask a specific question about this device
Page 1 of 1