Automatic Segmentation of Colorectal Polyps based on a Novel and Innovative Convolutional Neural Network Approach

Polyp is the name of a colorectal lesion which is created by cells clumping on the lining of the colon.The colorectal polyps can lead to severe illnesses like colon cancer if they are not treated at the early stage oftheir development. In current days, there are very many different polyp detection strategies based on biomedicalimageries such colon capsule endoscopy (CCE) and optical colonoscopy (OC). The CCE imagery is non-invasivebut the quality and resolution of acquired images are low. Moreover, it costs more than OC. So, today OC is themost desired method for detecting colorectal polyps and other lesions besides of its invasiveness. To assistphysicians in detecting polyps more accurately and faster, machine learning with biomedical image processingaspect emerges. One of the most the state-of-the-art strategies for polyp detection based on artificial intelligenceapproach are deep learning (DL) convolutional neural networks (CNNs). As the categorization and grading ofpolyps need significant information about their specular highlights like their exact shape, size, texture and ingeneral heir morphological features, therefore it is very demanded to employ semantic segmentation strategiesfor detecting polyps and discriminating them from the background. According to this fact, a novel and innovativemethod for polyp detection based on their semantic segmentation is proposed in this paper. The proposedsegmentation classifier is in fact a modified CNN network named as U-Net. The proposed U-Net provides anadvanced and developed semantic segmentation ability for polyp detection from OC images. For evaluating theproposed network, accredited and well-known OC image databases with polyps annotated by professionalgastroenterologists known as CVC-ClinicDB, CVC-ColonDB and ETIS-Larib, are employed. The results ofimplementation demonstrate that the proposed method can outperform the other competitive methods for polypdetection from OC images up to an accuracy of 99% which means that the life lasting hopes could be increasedto a considerable ratio.