A polyp is an abnormal tissue growth in the large intestine that is typically benign but can develop into malignant colorectal cancer. Colonoscopy enables endoscopists to identify and assess these polyps for potential removal. However, the accuracy of this procedure depends heavily on the clinician’s expertise, making it prone to human error and variability. Our goal is to build a deep-learning model that detects colorectal polyps in images from colonoscopies to minimize missed lesions and improve patient outcomes.