A systematic review of deep learning based image segmentation to detect polyp

Among the world's most common cancers, colorectal cancer is the third most severe form of cancer. Early polyp detection reduces the risk of colorectal cancer, vital for effective treatment. Artificial intelligence methods such as deep learning have emerged as leading techniques for polyp image segmentation that have gained success in advancing medical image diagnosis. This study aims to provide a review of the most recent research studies that have used deep learning methods and models for polyp segmentation. A comprehensive review of deep learning-based image segmentation models is provided based on existing research studies that are essential for polyp segmentation. Convolutional neural networks, encoder-decoder models, recurrent neural networks, attention-based models, and generative models were the most popular deep learning models which play an essential role in detecting and diagnosing polyp at an early stage. Additionally, this study also aims to provide a detailed classification of prominently used polyp image and video datasets. The evaluation metrics for assessing the effectiveness of different methods, models, and techniques are identified and discussed. A statistical analysis of deep learning models based on polyp datasets and performance metrics is presented, with a discussion of future research trends and limitations.