Robust Dual-Site Cancer Screening via Multi-Scale Vision Transformer and Rapid Recognition Pipeline
Bibliographic record
Abstract
Early detection of skin and oral cancers is essential for improving survival rates and reducing treatment costs, yet conventional diagnostic methods remain resource-intensive and limited in accessibility. This study presents a transformer-based deep learning framework for automated skin and oral cancer detection using models including Multi-ViT, MA-Transformer V2, MobileUNETR, TinyViT, and Xception. Evaluated on the PAD-UFES-20 and Oral Cancer datasets, the proposed multi-ViT achieved high performance, with 99.12% accuracy on the PAD-UFES-20 dataset and 99.37% on the Oral Cancer dataset, while maintaining high F1-scores and AUC-PR values across both datasets. A unified pipeline incorporating targeted preprocessing, model training, and lightweight deployment was developed, enabling real-time screening through a web-based application. This allows users to upload lesion images and receive instant predictions, supporting early intervention without requiring specialized equipment. The proposed system contributes to practical, scalable cancer screening, aiding timely diagnosis and improving healthcare accessibility in diverse clinical and community settings.
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 | 0.002 |
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".