文献类型：期刊文献

英文题名：Automatic Polyp Detection by Combining Conditional Generative Adversarial Network and Modified You-Only-Look-Once

作者：Qian, Zhiqin[1];Jing, Weiji[1];Lv, Yi[1];Zhang, Wenjun[2]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Complex & Intelligent Syst Res Lab CISRL, Shanghai 200237, Peoples R China;[2]Univ Saskatchewan, Dept Mech Engn, Saskatoon, SK S7N 5A9, Canada

年份：2022

卷号：22

期号：11

起止页码：10841

外文期刊名：IEEE SENSORS JOURNAL

收录：;EI(收录号：20221912092259);WOS:【SCI-EXPANDED(收录号:WOS:000804789800084)】；

基金：This work was supported by the Science and Technology Commission of Shanghai Municipality (STCSM) through Shanghai International Science and Technology Cooperation Fund Project under Grant 12410709900. The associate editor coordinating the review of this article and approving it for publication was Prof. Shih-Chia Huang.

语种：英文

外文关键词：Convolution; Computer architecture; Training; Sensors; Generative adversarial networks; Image edge detection; Convolutional neural networks; Polyp detection; convolutional neural network; generative adversarial network; YOLO; CVC-ClinicDB; CVC-ColonDB

摘要：Recent years have seen deep learning algorithms such as Convolutional Neural Networks (CNNs) and their variants achieving competitive performance in the application of medical image processing. Yet their shortcomings are: (i) the need of a large collection of annotated data, and (ii) the involvement of careful design of CNN layers. In this paper, we presented a novel polyp detection architecture based on two ideas: (i) to use Conditional Generative Adversarial Network (CGAN) to expand the training datasets, specifically the Generator takes advantage of the Efficient Spatial Pyramid (ESP) and the Discriminator is based on the PatchGAN; (ii) to modify the architecture of YOLOv4 using dilated convolution and skip connections. Experiments were performed using three publicly available datasets, i.e., CVC-ClinicDB, CVC-ColonDB, and ETIS-Larib Polyp DB. Experimental results showed that our generative network outperformed U-Net and can synthesize more realistic polyp images. The modified YOLOv4 significantly improved the performance of polyp detection using the expanded dataset, with an accuracy of 92.37% and a detection rate of 17.2 frames per second.