ResNet50-Driven Correlated Preference Weighted Features for Accurate Oral Cancer Stage Detection

ResNet50 based Oral Cancer Stage Detection

DOI

10.2991/978-94-6239-693-7_10How to use a DOI?

Keywords

Oral Cancer; Histological Images; Deep Learning; Classification Algorithms; Classification Accuracy; Feature Vector; Convolutional and Pooling Layers; Stage Detection

Abstract

The eighth most frequent disease in the globe in India is oral cancer (OC), which kills 130,000 people every year. Oral cancerous tumors can arise in a variety of locations, such as the tonsils, salivary glands, neck, face, and mouth. Histological pictures are useful for cancer screening because they can find abnormalities and determine their prognosis. It is necessary to reduce the morbidity and mortality caused by mouth cancer, early detection of oral problems that could be cancerous. Misuse or over-reliance on features causes classification algorithms to absorb irrelevant data from images, resulting in inaccurate classifications. The deep learning model takes as input vectors the texture and deep features that are retrieved from these methods. The 50 stackable bottleneck residual pieces used in the ResNet-50 design are the basis of this research. First, the network’s traditional convolutional and pooling layers preprocess the picture before the other blocks do any processing. For precise oral cancer stage detection, this study suggests a ResNet50-based Correlated Preference based Weighted Feature Vector (CPbWFV-SD). Train the model using the weighted feature vector; then, utilize the smallest change in the feature attribute set to determine the disease stage. When it comes to detecting the stage of oral cancer, the proposed model outperforms the conventional methods.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Patibandla Sandhya Krishna
AU  - Subba Rao Peram
PY  - 2026
DA  - 2026/06/16
TI  - ResNet50-Driven Correlated Preference Weighted Features for Accurate Oral Cancer Stage Detection
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 83
EP  - 90
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_10
DO  - 10.2991/978-94-6239-693-7_10
ID  - Krishna2026
ER  -