Search Results
Found 1 results
510(k) Data Aggregation
(146 days)
The syngo.CT Lung CAD device is a Computer-Aided Detection (CAD) tool designed to assist radiologists in the detection of solid and subsolid (part-solid and ground glass) pulmonary nodules during review of multi-detector computed tomography (MDCT) from multivendor examinations of the chest. The software is an adjunctive tool to alert the radiologist to regions of interest (ROI) that may otherwise be overlooked.
The syngo. CT Lung CAD device may be used as a concurrent first reader followed by a full review of the case by the radiologist or as second reader after the radiologist has completed his/her initial read.
The software device is an algorithm which does not have its own user interface component for displaying of CAD marks. The Hosting Application incorporating syngo.CT Lung CAD is responsible for implementing a user interface.
Siemens Healthcare GmbH intends to market the syngo.CT Lung CAD which is a medical device that is designed to perform CAD processing in thoracic CT examinations for the detection of solid pulmonary nodules (between 3.0 mm and 30.0mm) and subsolid (partsolid and ground glass) nodules (between 5.0 mm and 30.0mm) in average diameter. The device processes images acquired with multi-detector CT scanners with 16 or more detector rows.
The syngo.CT Lung CAD device supports the full range of nodule locations (central, peripheral) and contours (round, irregular).
The syngo.CT Lung CAD sends a list of nodule candidate locations to a visualization application, such as syngo MM Oncology, or a visualization rendering component, which generates output images series with the CAD marks superimposed on the input thoracic CT images to enable the radiologist's review. syngo MM Oncology (FDA clearance K191309) is deployed on the syngo.via platform (FDA clearance K191040), which provides a common framework for various other applications implementing specific clinical workflows (but are not part of this clearance) to display the CAD marks. The syngo.CT Lung CAD device may be used either as a concurrent first reader, followed by a review of the case, or as a second reader only after the initial read is completed
The subject device and predicate device have the same basic technical characteristics. This does not introduce new types of safety or effectiveness concerns as demonstrated by the statistical analyses and results of the reader study and additional evaluations results documented in the Statistical Analysis.
Here's a breakdown of the acceptance criteria and the study proving the device's performance, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance:
The document primarily focuses on demonstrating the improvement of the new VD20 version over the predicate VC30, rather than explicitly listing fixed "acceptance criteria" with numerical targets in a single table. However, based on the statistical analysis summary and the comparison tables, we can infer the performance goals and the reported outcomes:
| Feature/Metric | Acceptance Criteria (Inferred) | Reported Device Performance (VD20) |
|---|---|---|
| Detection Target | Extension to subsolid (part-solid and ground glass) pulmonary nodules, in addition to solid nodules. | Device successfully assists in detecting solid and subsolid (part-solid and ground glass) pulmonary nodules. |
| Nodule Size Range | Solid: Up to 30mm; Subsolid: Up to 30mm | Solid: ≥ 3mm and ≤ 30mm; Subsolid: ≥ 5mm and ≤ 30mm. |
| Reader Workflow | Support for concurrent first reader workflow in addition to second reader. | Device supports both concurrent first reader and second reader workflows. |
| Multi-vendor Compatibility | Support for multi-vendor CT scanners. | Supports Siemens, GE, Philips, and Toshiba MDCT scanners. |
| Detector Rows | Recommended 16 or more detector rows. | Recommendation to use 16 or more detector rows included, matching FDA recommendation. |
| Voltage | Expanded range (implied). | 100-140 kVp. |
| Slice Thickness | Up to 2.5mm, with recommendation for ≤ 1.25mm for smaller nodules. | Up to and including 2.5mm; recommended that ≤ 1.25mm be used for detection of smaller nodules (e.g., 3.0mm). |
| Slice Overlap | 0-50% | 0-50%. |
| Kernels | Expanded range of supported kernels. | Consistent with thoracic CT protocols and patient safety guidelines. Typical kernels: Smooth, Medium, Sharp groups validated. |
| Dose | Consistent with diagnostic and screening protocols. | CTDIvol < 8.0 mGy (diagnostic) and 3.0 mGy (screening) for standard-sized patients, with adjustments for patient size. |
| Diagnostic Accuracy (MRMC Study) | Demonstrate significant improvement in reader accuracy with CAD assistance. | All readers showed a significant improvement for the detection of pulmonary nodules (solid, part-solid, and ground glass) with both reading workflows (second reader and concurrent first reader). |
| Safety and Effectiveness | No new safety or effectiveness concerns compared to predicate. | No unmitigated safety risks; demonstrated as safe and effective as the predicate. |
| Standalone Performance (Mark Overlap) | Marks generated by VD20 and VC30 are reasonably consistent. | Standalone analysis demonstrated that the marks generated by the two devices are reasonably consistent. This also validated the post-filtering module and bug fixes. |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: 232 cases.
- Data Provenance: The study was retrospective. The document does not explicitly state the country of origin of the data, but it can be inferred that it involves multi-vendor examinations, suggesting a broader base.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:
- Number of Experts: Five expert radiologists.
- Qualifications: The document indicates they were "expert radiologists." No further specific details (e.g., years of experience, subspecialty certification) are provided in the excerpt.
4. Adjudication Method for the Test Set:
- Adjudication Method: "Reader majority (three out of five) followed by expert adjudication, as needed." This means if at least three of the five experts agreed on a finding, it was considered true. If there was no clear majority or disagreement, further expert adjudication was used to resolve discrepancies.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Was it done?: Yes, an MRMC reader study was conducted.
- Effect Size (Improvement with AI vs. without AI assistance): The document states: "All readers showed a significant improvement for the detection of pulmonary nodules (solid, part-solid and ground glass) with both reading workflows." While it confirms a significant improvement, it does not provide a specific quantitative effect size (e.g., percentage improvement in sensitivity or specificity, or a numerical change in AUC).
6. Standalone (Algorithm-Only) Performance:
- Was it done?: Yes, "standalone Mark Overlap evaluations" were performed.
- Purpose: These evaluations specifically demonstrated "that the marks generated by the two devices are reasonably consistent," validating the post-filtering module and bug fixes in VD20. However, specific performance metrics for this standalone evaluation (like sensitivity, specificity, FROC curves) are not provided in this summary.
7. Type of Ground Truth Used:
- Type of Ground Truth: The primary ground truth for the MRMC study was established through expert consensus/adjudication (reader majority of five expert radiologists, followed by further expert adjudication if needed).
8. Sample Size for the Training Set:
- The document does not provide the sample size of the training set. It mentions that the algorithm is based on Convolutional Neural Networks (CNN) and that VD20 introduces "new AI models for Candidate Generation and Classification components to support the extension of the claims," but gives no details about the data used to train these models.
9. How the Ground Truth for the Training Set was Established:
- The document does not specify how the ground truth for the training set was established.
Ask a specific question about this device
Page 1 of 1