Deep Learning Based Teeth Segmentation
Bibliographic record
Abstract
This article discusses the importance of accurate teeth segmentation in dental diagnosis and treatment.Rapid advancements in Artificial Intelligence have led to the development of various approaches for example Res-UNet deep learning architecture.Res-UNet++ has been proposed as a refined version of the Res-UNet architecture to improve teeth segmentation performance.Res-UNet++ integrates three additional elements: squeeze and excitation block, atrous spatial pyramid pooling, and attention block.The purpose of these components is to enhance the performance of Res-UNet by improving the recalibration of features at both the channel and spatial levels, capturing multi-scale contextual information, and prioritizing the relevant regions of interest.Res-UNet++, UNet and Res-UNet were compared on two publicly available dental image datasets using evaluation criteria such as the dice coefficient and mean Intersection over Union (mIoU).The evaluation of these algorithms was implemented under the same experimental settings to statistically assess the significance of the enhancements.The result shows the superiority of Res-UNet++ over UNet and Res-UNet.The effectiveness of Res-UNet++ is demonstrated by its impressive assessment scores: the dice coefficient of 92.91% and 95.58% for the two databases, and the mean Intersection over Union (mIoU) of 88.68% and 88.72%.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".