Optimizing Hyperparameters with Pelican Algorithm for Deep Learning–based Oral Cancer Detection
Bibliographic record
Abstract
This paper presents a comprehensive study on oral cancer segmentation using deep learning techniques, focusing on the U-Net and DenseNet architectures. U-Net, designed for biomedical image segmentation, leverages its encoder-decoder framework to produce high-resolution outputs critical for identifying tumor boundaries in oral cancer cases. DenseNet, recognized for its densely connected layers, improves feature reuse and mitigates the vanishing gradient issue, thereby enhancing overall model performance. The combined use of these models demonstrates the effectiveness of deep learning in medical image analysis, supporting early detection and treatment planning. The study highlights the significance of annotated datasets specific to oral cancer segmentation, which serve as the ground truth for training and validation. Given the limited availability of such datasets, data augmentation techniques are applied to expand the training samples and improve the generalization capability of the models. The optimization of hyperparameters using the Pelican Optimization Algorithm further refines model accuracy and performance. Results indicate improved segmentation outcomes compared to traditional approaches. This research underscores the value of combining robust architecture with intelligent optimization strategies in the context of oral cancer detection.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".