AI-Based Detection and Classification of Impacted Wisdom Teeth Using Deep Learning on Panoramic Dental X-Rays
Bibliographic record
Abstract
Convolutional neural networks (CNNs) cover established great potential in the pasture of dental diagnostics, especially when it comes to the processing of panoramic X-rays for the purpose of early dental pathology identification and classification. ResNet-101 is unique among CNN architectures because of its deep structure and effective feature extraction capabilities, which make it ideal for challenging image-based tasks. In order to identify and classify wisdom tooth inclination assessment in panoramic X-rays by Winter's classification, here using ResNet-18, 50, and 101 as feature extractors to assess the concert of three top deep learning entity finding models:, SDD, YOLO V2, and Quicker R-CNN X. During training and testing, the ResNet-50 architecture offered a strong compromise between accuracy and processing requirements efficiency thanks to its depth-efficient design and bottleneck residual blocks. Four angle groups were identified from our dataset, which included 644 panoramic dental X-rays: distoangular, vertical, mesioangular, and horizontal. When paired with ResNet-101, YOLO V2 demonstrated high accuracy, with testing performance up to 99 %. These results demonstrate how well CNN-based object detection frameworks especially those driven by ResNet-101 support accurate and automated dental diagnostics. By emphasizing how deep CNN architectures improve dental imaging processing, this work advances clinical decision-making.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".