Super resolution convolutional neural network based pre-processing for automatic polyp detection in colonoscopy images. (March 2021)

• Record Type: Journal Article
• Authors: Taş, Merve; Yılmaz, Bülent
• Is Part Of: Computers & electrical engineering. Volume 90(2021)
• Publication Date: 2021-03
• Subjects: Deep learning -- Convolutional neural networks -- Transfer learning -- Super resolution -- Colonoscopy -- Colon polyp localization; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106959
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Our goal was to develop an effective method for polyp detection system using colonoscopy images that are processed and enhanced in resolution using deep learning techniques. Low-resolution images were converted into high-resolution counterparts by using super resolution convolutional neural networks (SRCNN). These high resolution images were used as the training dataset for automatic polyp detection system. Polyp detection system was based on SSD and Faster RCNN structures that includes feature extractors such as Inception-v2 and ResNet-101. Experimental results indicate that the proposed method can achieve a high detection performance on colonoscopy image datasets. Abstract: Colonoscopy is the most common methodology used to detect polyps on the colon surface. Increasing the image resolution has the potential to improve the automatic colonoscopy based diagnosis and polyp detection and localization. In this study, we proposed a pre-processing approach that uses convolutional neural network based super resolution method (SRCNN) to increase the resolution of the training colonoscopy images before the localization of polyps. We also investigated the use of CNN based models such as the Single Shot MultiBox Detector (SSD) and Faster Regional CNN (RCNN) for real-time polyp detection and localization. Our results showed that using SRCNN method before the training process provides better results in terms of accuracy in both models compared to the low-resolution cases. Furthermore, we reached an F2 score of 0.945 for the correct localization of colon polyps using Faster RCNN with ResNet-101 feature extractor. Graphical abstract: Image, graphical abstract