International Research Journal of Education and Technology

Cancer continues to be a major global health challenge, accounting for millions of deaths annually. Early detection significantly improves treatment effectiveness and survival rates. Traditional microscopic examination of cancer cells is manual, time-intensive, and highly dependent on expert interpretation, which may lead to variability and delayed diagnosis. Recent advancements in artificial intelligence, particularly deep learning, have demonstrated promising capabilities in medical image analysis.

This paper presents a web-based cancer cell classification system that employs a Convolutional Neural Network (CNN) to classify microscopic cell images into cancerous and non-cancerous categories. The system integrates a React-based frontend and a Flask backend with TensorFlow/Keras to provide real-time training visualization and instant prediction functionality. Image preprocessing and data augmentation techniques are implemented to enhance model generalization. The trained model is stored locally to support offline prediction without continuous internet connectivity. Experimental evaluation demonstrates effective classification performance, validating the applicability of deep learning in educational and research-based cancer image analysis systems.

Keywords— Cancer Cell Classification, Deep Learning, Convolutional Neural Networks (CNN), Medical Image Analysis, TensorFlow, Image Preprocessing, Data Augmentation, Web-Based AI System, Binary Classification, Computer-Aided Diagnosis (CAD)