<p>Colon cancer is a type of cancer caused by polyps that become malignant within the colon or rectum. Dealing with colon cancer effectively requires the diagnosis of the cancer at an early stage, which is of vital importance. Computer-aided diagnostic systems are being developed to ensure the accurate and rapid diagnosis of cancer in its early stages. In this paper, deep learning approaches that segment polyps from colorectal polyp images have been reviewed, and a detailed analysis is presented. Firstly, deep learning approaches for polyp segmentation from colorectal polyp images were categorized into three categories. The categories include conventional convolutional neural networks, attention-based models, and transformer architectures. A detailed analysis of the approaches grouped under each category has been conducted. This review provides a summary of current deep learning architectures used in colorectal polyp images, detailing which dataset methods were utilized, preferred performance metrics, challenges encountered, and the hardware and software infrastructure. It is hoped that this study will be beneficial for researchers who wish to use deep learning techniques to segment colorectal polyp images in diagnosing colon cancer.</p>