Early Oral Cancer Detection with AI: Design and Implementation of A Deep Learning Image-Based Chatbot

Oral cancer is one of the leading causes of cancer-related deaths worldwide, primarily because the disease is often identified at an advanced stage. Early diagnosis plays a vital role in improving treatment effectiveness, patient survival rates, and overall healthcare outcomes. However, limited awareness, shortage of specialized medical facilities, and delayed clinical consultation continue to create significant challenges, especially in rural and underserved regions. To address these issues, this study proposes an Artificial Intelligence (AI)-based chatbot system for the early detection and preliminary assessment of oral cancer using deep learning and medical image analysis techniques.

The proposed system combines deep learning models, Natural Language Processing (NLP), and conversational healthcare support to create an intelligent and user-friendly screening platform. The chatbot allows users to upload oral cavity images and interact through symptom-based conversations. Multiple Convolutional Neural Network (CNN) architectures, including CNN, DenseNet121, DenseNet169, DenseNet201, and InceptionV3, were implemented and evaluated for oral lesion classification.