Hybrid CNN Models for Multimodal Synthesis in High-Fidelity Oral Cancer Detection and Characterization
Bibliographic record
Abstract
Cancer is ranked as 2nd life-threatening disease-causing mortality if not diagnosed efficiently.It is quiet challenging to declare a patient cancerous or non-cancerous and this process takes time.There are lots of research conducted over past few years using various deep learning approaches in order to detect oral cancer through lesion and pathological images.Going through some of the studies we came to a fact that the detection could be better with the fusion of both images and clinical data of patients.In this study, the NDB-UFES dataset-comprising 237 samples of histopathological images along with corresponding clinical data-was employed for analysis.This study utilizes the benefit of computer aided detection (CAD) using artificial intelligence, deep learning and the combined dataset resulting in multimodal architecture.The architecture is a custom CNN based where the image feature is extracted and combined with the clinical data for the model training.After the model is trained efficiently its performance is evaluated.The experimental results obtained was ~97% in training and ~93% in testing with a CNN based architecture.The classification included three classes, OSCC, leukoplakia with dysplasia and leukoplakia without dysplasia.Through this study we could conclude that clinical and demographic data may positively influence the performance of deep learning models in classification of oral cancer.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".