Automated Segmentation of Graft Material in 1‐Stage Sinus Lift Based on Artificial Intelligence: A Retrospective Study
Bibliographic record
Abstract
OBJECTIVES: Accurate assessment of postoperative bone graft material changes after the 1-stage sinus lift is crucial for evaluating long-term implant survival. However, traditional manual labeling and segmentation of cone-beam computed tomography (CBCT) images are often inaccurate and inefficient. This study aims to utilize artificial intelligence for automated segmentation of graft material in 1-stage sinus lift procedures to enhance accuracy and efficiency. MATERIALS AND METHODS: Swin-UPerNet along with mainstream medical segmentation models, such as FCN, U-Net, DeepLabV3, SegFormer, and UPerNet, were trained using a dataset of 120 CBCT scans. The models were tested on 30 CBCT scans to evaluate model performance based on metrics including the 95% Hausdorff distance, Intersection over Union (IoU), and Dice similarity coefficient. Additionally, processing times were also compared between automated segmentation and manual methods. RESULTS: Swin-UPerNet outperformed other models in accuracy, achieving an accuracy rate of 0.84 and mean precision and IoU values of 0.8574 and 0.7373, respectively (p < 0.05). The time required for uploading and visualizing segmentation results with Swin-UPerNet significantly decreased to 19.28 s from the average manual segmentation times of 1390 s (p < 0.001). CONCLUSIONS: Swin-UPerNet exhibited high accuracy and efficiency in identifying and segmenting the three-dimensional volume of bone graft material, indicating significant potential for evaluating the stability of bone graft material.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".