Search Results
Found 1 results
510(k) Data Aggregation
(203 days)
Overjet CBCT Assist is a software for the analysis of dental and craniomaxillofacial Cone Beam Computed Tomography (CBCT) images. The software utilizes artificial intelligence/machine learning algorithms to provide automated segmentations, user-delineated or automated measurements, and 2D/3D visualizations. These tools are intended to assist dental professionals in their review and interpretation of CBCT images by facilitating anatomical assessment and supporting their diagnostic and treatment planning process. The device is not intended as a replacement for a complete clinician's review or their clinical judgement.
Overjet CBCT Assist (OCBCTA) is a cloud-based software designed to assist dental professionals in the visualization and assessment of Cone Beam Computed Tomography (CBCT) images. The software enables interactive review of 3D CBCT data through volume rendering and multi-planar reconstruction (MPR) views and provides manual and automated tools to support diagnostic interpretation and treatment planning.
Overjet CBCT Assist uses machine learning-based segmentation algorithms to automatically identify and label anatomical and restorative structures, including permanent teeth, maxillofacial anatomy, and prior dental treatments such as implants, root canal therapy, crowns, and fillings. These outputs support clinical workflows by enhancing visualization and enabling measurement of relevant features.
Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) Clearance Letter for Overjet CBCT Assist:
Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Metric | Predetermined Threshold (Implicit) | Reported Device Performance |
|---|---|---|---|
| Segmentation Accuracy | Instance-level sensitivity for restorative structures | Pass/Exceed threshold | 87.0% with 95% CI (82.3%, 91.2%) - Surpassed required threshold |
| Instance-level sensitivity for dental anatomy | Pass/Exceed threshold | 93.9% with 95% CI (91.7%, 95.9%) - Surpassed required threshold | |
| Dice similarity coefficient for all segmented structures | Individually associated thresholds | Passed individually associated thresholds across all evaluated classes | |
| Measurement Accuracy | Mean Absolute Error (MAE) for automated linear measurements | Target threshold | Met target thresholds for MAE |
| Root Mean Square Error (RMSE) for automated linear measurements | Target threshold | Met target thresholds for RMSE | |
| Tooth Numbering Accuracy | Tooth-level sensitivity for tooth numbering | Implicit target | Met target thresholds |
| Tooth-level accuracy for tooth numbering | Implicit target | Met target thresholds |
Note on "Implicit Thresholds": The document states that the results "met or exceeded all pre-specified performance goals" and "surpassing the required threshold" or "passed their individually associated thresholds." While the exact numerical thresholds are not explicitly provided in this section, the text clearly indicates that such targets were defined and successfully achieved.
Study Details
1. Sample Size and Data Provenance
- Test Set Sample Size: 100 CBCT scans
- Data Provenance: Retrospective. The scans were obtained from a demographically and anatomically diverse patient population in the U.S. (indicated by the use of U.S.-licensed radiologists).
2. Number and Qualifications of Experts for Ground Truth
- Number of Experts: Three (3)
- Qualifications of Experts: U.S.-licensed oral and maxillofacial radiologists and dentists.
3. Adjudication Method for the Test Set
The document states, "Images were independently reviewed and annotated by three U.S.-licensed oral and maxillofacial radiologists and dentists. The resulting segmentations served as the reference standard against which the device's outputs were compared." This implies a consensus-based approach where the collective annotations of the three experts formed the ground truth. The specific adjudication method (e.g., 2+1, 3+1) is not explicitly stated. However, "independently reviewed and annotated" suggests individual contributions were then likely combined to form a final consensus ground truth.
4. MRMC Comparative Effectiveness Study
- Was an MRMC study done? No, based on the provided text. The study evaluated the standalone clinical performance of the device against expert-derived ground truth. There is no mention of human readers evaluating cases with and without AI assistance to measure improvement.
5. Standalone Performance Study
- Was a standalone study done? Yes, explicitly stated: "Additionally, Overjet performed a standalone clinical performance study using retrospective CBCT data to evaluate the accuracy of automated segmentations and measurements."
6. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (annotations generated by licensed oral and maxillofacial radiologists and dentists).
7. Sample Size for the Training Set
- Training Set Sample Size: Not specified in the provided text. The document only details the test set for the performance study.
8. How Ground Truth for the Training Set was Established
- Establishment of Training Set Ground Truth: Not specified in the provided text. While it's implied that AI models require ground truth for training, the methodology for establishing this ground truth is not detailed in this section of the 510(k) summary.
Ask a specific question about this device
Page 1 of 1