• Version
• Download 2
• File Size 294.87 KB
• File Count 1
• Create Date 29 November 2025
• Last Updated 29 November 2025

Oral, Lip and Tongue Cancer Prediction Using Deep Learning

 

 

AG Trishala 1, CT Vidhya 2, G Gokilavani 3, M.Anitha4

1,2,3,4 Department of Computer Science and Engineering, Avinashilingam Institute for Home Science and Higher Education for Women, School of Engineering

E-Mail-ID: vidhya_cse@avinuty.ac.in, gokilavani_cse@avinuty.ac.in, anitha_cse@avinuty.ac.in , 24pea001@avinuty.ac.in

 

 

ABSTRACT
This paper presents a deep learning-based approach for the early prediction of oral, lip, and tongue cancer using medical imaging techniques. These cancers are aggressive and debilitating, contributing to high global mortality rates. The proposed method aims to address the limitations of manual examination, which is often time- consuming, subjective, and error-prone. A convolutional neural network (CNN) model, specifically ResNet50, is fine-tuned and trained on a diverse dataset of oral, lip, and tongue images. Key techniques such as transfer learning, data augmentation, and batch normalization are employed to optimize the model's accuracy and robustness. Experimental results demonstrate the effectiveness of the proposed system in achieving high accuracy for cancer prediction. This approach holds significant potential for assisting clinicians in the early detection and diagnosis of these cancers, improving patient outcomes and reducing mortality rates. Furthermore, the methodology can be extended to other medical imaging applications, representing a valuable contribution to the fields of medical imaging and diagnostics.

Keywords: Preprocessing, Transfer learning, Data augmentation.

Download