Optimized YOLOv7 Framework for Skin Cancer Detection using Cuckoo Search and Pelican-Based H yperparameter Tuning
Bibliographic record
Abstract
Skin cancer is among the most common and life-threatening conditions worldwide, and early and correct diagnosis is a major problem in the analysis of medical images. In the present work, automated detection of skin cancer lesions is proposed with the help of the Deep Learning-based method and the YOLOv7 model, which is additionally optimized with the help of hyperparameters to improve performance. Two metaheuristic methods, the Cuckoo Search Optimization (CSO) and the Pelican Optimization Algorithm (POA) are used separately to optimize the YOLOv7 hyperparameters. The algorithms are run 50 times, and the lowest fitness of the run is chosen as the optimized hyperparameter configuration. YOLOv7 is then trained using these optimized hyperparameters, and the performance of the model is measured using accuracy, sensitivity, specificity, precision, and F1 score. The YOLOv7 base model got an accuracy of 89.65, a sensitivity of 85, and a specificity of 91.90. CSO was optimized and then had a performance of 94.1 accuracy, 93.0 sensitivity, 94.8 specificity, 92.5 precision, and F1-score of 92.7. POA had a slightly different improvement, as the accuracy was 93.8, the sensitivity was 92.5, the specificity was 94.5, the precision was 93.2 and the F1 score was 92.8. These findings indicate that CSO and POA applied independently prominently increase the ability of YOLOv7 to detect and classify skin lesions, thus showing the usefulness of metaheuristic hyperparameter optimization of real-time diagnostic systems in dermatology.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".