Rafeed RahmanAdrin, Readhwana ReazJunainah, MahmudaChowdhury, AntuSaha, Niladri2025-08-122025-08-1220232023ID 19201034ID 19201060ID 19201077ID 19201078http://hdl.handle.net/10361/26530Cataloged from PDF version of thesis.Includes bibliographical references (pages 65-66).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.A colorectal polyp is a small cell cluster that develops on the lining of the colon. The majority of colon polyps are harmless, but some can develop into tumors later on and can cause colorectal cancer. Though the exact causes of polyp formation are not known, some factors contributing to polyp formation are smoking, excess alcohol consumption, obesity, lack of exercise, consumption of processed food, or having a family history of colorectal polyps. However, if the polyp is detected at an early stage, then it is possible to prevent the tumor or colorectal cancer. In this study, our aim will be to train a CNN model and evaluate its performance. Analysis of medical images using deep learning has been confirmed to be quite successful. CNN showed notably higher accuracy in the domain of medical image classification than traditional machine learning algorithms. CNN is a cutting-edge method of deep learning that is widely used in image or object recognition and classification.66 pagesenBRAC University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Colorectal polypColorectal cancerDeep learningConvolutional Neural Network (CNN)Image recognitionColon (Anatomy)--Cancer.Rectum--Cancer.Neural networks (Computer science).Data mining.Thesis