Search Results
Found 1 results
510(k) Data Aggregation
(97 days)
Careverse CoronaryDoc is a web-based software application that is intended to be used by trained medical professionals as an interactive tool for viewing and analyzing cardiac computed tomography (CT) data for determining the presence and extent of coronary plaques (i.e., atherosclerosis) and stenosis in patients who underwent Coronary Computed Tomography Angiography (CCTA) for evaluation of CAD or suspected CAD. This software post processes CT images obtained using any Computed Tomography (CT) scanner. The software provides tools for the measurement and visualization of coronary arteries.
The software is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by people who have been appropriately trained in the software's functions, capabilities and limitations.
Careverse CoronaryDoc is a B/S architecture and is suitable for DICOM medical image viewing, 3D reconstruction and post-processing and stenosis and plaque analysis. Based on the axial image data of coronary computed tomography angiography (CCTA), Careverse CoronaryDoc automatically extracts the coronary region, detects suspected stenosis lesions in this area, and further performs automatic plaque analysis. At the same time, the software can also automatically detect stents and bridges. Users can modify the degree of stenosis, plaque type, stent, and bridge tips to form a structured report to assist physicians in diagnosing coronary heart disease.
The module functions include user login, image list, vascular segmentation and reconstruction, coronary branch naming, coronary stenosis, plaque, stent, myocardial bridge analysis, plaque detailed analysis, editing segmentation, editing blood vessels, editing naming, image operation tools, structured reports, push printing, management configuration, platform management, and transmission queues.
Here's a breakdown of the acceptance criteria and study details for the Careverse CoronaryDoc, based on the provided FDA 510(k) clearance letter:
1. Table of Acceptance Criteria and Reported Device Performance
The clearance letter does not explicitly state the quantitative acceptance criteria for all performance metrics. However, it indicates whether the reported device performance met the acceptable criteria. Where a specific numerical criterion is mentioned, it is included.
| Performance Metric | Acceptance Criteria (explicit if stated) | Reported Device Performance |
|---|---|---|
| Segmentation Performance | ||
| Dice Coefficient | > 0.842 | 0.899 |
| 95% Hausdorff Distance | < 6.46 | 4.366 |
| Labeling Performance | ||
| Case-level Accuracy | Met acceptable criteria | 93.10% |
| Vessel-level Accuracy | Met acceptable criteria | 98.21% |
| Stenosis Performance (Agreement) | Met acceptable criteria | |
| non-stenosis | 98.97% | |
| minor stenosis | 91.25% | |
| minimal stenosis | 87.00% | |
| moderate stenosis | 87.23% | |
| severe stenosis | 83.72% | |
| complete occlusion | 91.18% | |
| Plaque Performance (Pearson Corr.) | Met acceptable criteria | |
| vessel volume | 98.42% | |
| lumen volume | 98.52% | |
| total plaque volume | 96.94% | |
| calcified plaque vol. | 97.92% | |
| non-calcified pv | 95.14% | |
| low-density non-calc | 88.42% | |
| Plaque Performance (Bland-Altman) | Met acceptable criteria | |
| vessel volume | 95.18% | |
| lumen volume | 94.78% | |
| total plaque volume | 95.91% | |
| calcified plaque vol. | 98.00% | |
| non-calcified pv | 95.24% | |
| low-density non-calc | 94.96% |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size:
- For Stenosis Performance: The sample size for each stenosis grade varies, as indicated by the 'n' column in Table 1. The total number of measurements for stenosis is 682 + 160 + 100 + 94 + 86 + 34 = 1116 measurements. It's unclear if this represents unique cases or distinct lesions within cases.
- For Segmentation, Labeling, and Plaque Performance: The exact number of cases or measurements is not explicitly stated in the provided text, beyond the "results are summarized as the following" and the aggregated performance metrics.
- Data Provenance: The ground truth results were "produced by US expert readers." This suggests the test data was composed of CCTA images from patients, and the interpretation was done by experts in the US. It's not explicitly stated whether the data itself was collected retrospectively or prospectively, or its country of origin, only that the ground truth establishment was done by US experts.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: The document states "US expert readers" (plural), but does not specify the exact number of experts.
- Qualifications of Experts: The specific qualifications (e.g., years of experience, subspecialty) of the US expert readers are not detailed.
4. Adjudication Method for the Test Set
The adjudication method is not explicitly stated. The document mentions that ground truth results were "produced by US expert readers," but it doesn't describe how disagreements among multiple experts were resolved (e.g., 2+1, 3+1, majority vote, or a single super-reader).
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done
- No, an MRMC comparative effectiveness study was not explicitly described in this document. The performance data section focuses on the standalone performance of the algorithm compared to a ground truth established by human experts, not on how human readers improve with AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was done
- Yes, a standalone performance study was clearly conducted. The report explicitly states, "the performance of the software was compared to ground truth results produced by US expert readers." This comparison of the device's output against the expert-derived ground truth, without human readers interacting with the AI, is the definition of standalone performance.
7. The Type of Ground Truth Used
- The type of ground truth used is expert consensus / interpretation. The document states that the ground truth results were "produced by US expert readers." This implies that qualified human experts reviewed the CCTA data and made the definitive assessments for segmentation, labeling, stenosis, and plaque parameters.
8. The Sample Size for the Training Set
- The sample size for the training set is not provided in the given FDA 510(k) clearance letter. The document focuses on the performance data of the test set.
9. How the Ground Truth for the Training Set Was Established
- How the ground truth for the training set was established is not provided in the given FDA 510(k) clearance letter. The document only specifies how the ground truth for the test set was established (by US expert readers).
Ask a specific question about this device
Page 1 of 1