DefinePK

Abstract

Oral cancer (OC) is a prevalent and complex disease with high severity, posing a major public health concern. Early diagnosis is critical for effective treatment and increased survival rates. In India, oral cancer ranks as the eighth most common cancer, contributing to approximately 130,000 deaths annually. The application of advanced technologies and deep learning algorithms holds significant promise for the early detection and classification of oral cancer. Early identification is essential for improving patient outcomes and saving lives. In recent years, deep learning (DL) has gained momentum as a powerful tool in the early diagnosis of various diseases, including oral cancer. The integration of artificial intelligence (AI) in cancer screening and detection demands a well-structured and strategic approach. This study presents an innovative method for detecting oral cancer using deep learning techniques. The system is built using Python as the main programming language, Flask as the backend framework, and HTML, CSS, and JavaScript for the frontend interface. Two state-of-the-art deep learning architectures, ResNet152V2 and MobileNet, are employed to classify oral images accurately. The ResNet152V2 model achieves impressive training accuracy of 98.00% and validation accuracy of 93.00%, while the MobileNet model achieves a training accuracy of 97.00% and validation accuracy of 92.00%. The findings highlight the efficacy of integrating multiple data modalities for more accurate early detection of potential malignancies compared to using only image data.  The outcomes could pave the way for improved clinical decision-making and patient outcomes