Polyp Segmentation From Colonoscopy Image Using DeepLabV3+

Abstract

Colorectal cancer is one of the most common cancers in the world, and it is also one of the leading causes of mortality from cancer. Over time, polyp development on the inner lining of the colon or rectum may progress to cancer. Due to the differences in size, shape, and color, this is a difficult undertaking polyp texture and differences between several forms of hard polyps mimics. Colonoscopy is the most effective way to detect polyps. Screening and detection are possible, but they are operator-dependent, time-consuming, and prone to errors. Polyp segmentation method based on the convolutional neural network is developed and to enhance the performance of the method. In this study, polyp segmentation algorithm was developed using Python as the main programming language which was applied with TensorFlow and OpenCV on Kvasir-SEG datasets. DeepLabv3+ model was used to train the filters and pooling operations were applied to images to segment the polyps. The data obtained was further analysed and evaluated the performance analysis. As a result, the developed algorithm was tested and shows an average accuracy 0.7215 and average IoU score 0.7240 for 20 epochs. As a conclusion, the algorithm developed is able to segment the polyps and it can be further developed with large number of data to improve the accuracy.