Dual convolutional neural network framework for segmenting dental caries in panoramic radiographs
Bibliographic record
Abstract
STATEMENT OF PROBLEM: Dental caries, a widespread chronic disease, has been difficult to detect, especially in posterior proximal regions. Conventional diagnostic methods, such as visual inspection and radiography, are subjective and inconsistent across clinicians. PURPOSE: The purpose of this study was to develop and evaluate a deep learning-based method for automated detection and segmentation of dental caries in panoramic radiographs. MATERIAL AND METHODS: A deep learning pipeline combining Faster Regions based Convolutional Neural Networks (R-CNN) and U-Net architectures was developed. The Faster R-CNN model was used to detect tooth regions, and the U-Net model segmented carious areas within these regions. Performance differences against comparative models were evaluated for statistical significance using paired t tests (α=.05). RESULTS: The proposed method achieved an intersection over union of 0.6075, a dice coefficient of 0.7429, a recall of 0.7309, and a precision of 0.7881. This performance represented an improvement in intersection over union, dice coefficient, and recall over conventional segmentation models, with the difference being statistically significant (P<.05). CONCLUSIONS: The results indicated that the proposed deep learning method was effective in detecting and segmenting dental caries in panoramic radiographs and showed potential for improving diagnostic accuracy.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".