IJETEV1I1A007 – DEEPINSIGHT: ENDOSCOPIC IMAGE-BASED COLORECTAL CANCER CLASSIFICATION USING SEQUENTIAL CNN ARCHITECTURE 

ABSTRACT – Colorectal cancer (CRC) is one of the most common and life-threatening cancers worldwide, where early detection significantly improves survival rates. Conventional diagnostic approaches such as colonoscopy and histopathological examination rely heavily on manual interpretation by clinicians, making the process time-consuming. This paper presents an artificial intelligence–based computeraided diagnosis (CAD) system for automated colorectal cancer classification using endoscopic images. The proposed system employs a Sequential Convolutional Neural Network (CNN) architecture to classify colorectal images into normal, polyp, and cancerous categories. Image preprocessing techniques such as resizing, noise removal, normalization, and data augmentation are applied to enhance feature learning and improve model performance. Experimental results demonstrate improved classification accuracy, reduced false detection rates, and real-time diagnostic support