Colorectal Segmentation Using Multiple Encoder-Decoder Network in Colonoscopy Images

Colorectal cancer is the third most common cancer which causes of cancer-related deaths. Therefore, early diagnosis of polyps by colonoscopy could result in successful treatment. Diagnosis of polyps in colonoscopy videos is a challenging task due to variations in the size and shape of polyps. In this paper, we propose a polyp segmentation method based on the encoder-decoder network. Performance of the method is enhanced by two strategies, we perform a novel database augmentation method for colonoscopy images in the training phase. Besides, in the test phase, we perform an effective prediction by combining multi-model to compare the probability of each image that is produced by the network. Evaluation of the proposed method using the ETIS-LariPolypDB database shows that our proposed method outperforms state-of-the-art results.