基于自注意力机制优化的AtG-DeepLab V3+内窥图像增强算法  

AtG-DeepLab V3+ Endoscopic Image Enhancement Algorithm Based on Self-attention Mechanism Optimization

作　　者：陈家俊 李开祥 李仁剑 邵春蕾 李贵叶 陈玲玲 CHEN Jiajun;LI Kaixiang;LI Renjian;SHAO Chunlei;LI Guiye;CHEN Lingling(College of Health Science and Environmental Engineering,Shenzhen Technology University,Shenzhen 518118,China;College of Electronic Information Engineering,Beijing University of Aeronautics and Astronautics,Beijing 100191,China)

机构地区：[1]深圳技术大学健康与环境工程学院,深圳518118 [2]北京航空航天大学,电子信息工程学院,北京100191

出　　处：《光子学报》2023年第8期183-193,共11页Acta Photonica Sinica

基　　金：国家自然科学基金(No.52270008);深圳市科技计划基础研究项目(No.JCYJ20190813102005655);深圳技术大学自制仪器项目(No.2020XZY003)。

摘　　要：基于自注意力机制和DeepLab V3+网络联合构建了AtG-DeepLab V3+开源算法进行内窥图像增强处理,并采集测试靶和生物组织图像进行训练和测试。实现了内窥成像畸变和蜂窝状栅格结构的同时去除并能高清还原更多图像细节,对比现有的内窥图像重建网络U2-Net、Attention U-net和GARNN等算法,在峰值信噪比(提升66.4%,51.9%,154.6%)、结构相似度(提升55.6%,45.9%,231.5%)等量化指标上均实现了较大幅度的提高。该算法为光学内窥图像处理提供了一个新的高效处理方案。The optical endoscope imaging technology based on fiber bundle has the advantages of strong flexibility,no radiation and ease of integration.However,the structural characteristics of the fiber bundle inherently cause the honeycomb grid artefacts.In addition,the endoscope microlens introduces image distortion and low numerical aperture.As a result,there is a substantial decrease in the image quality for such endoscopic systems.In order to address this challenge,tremendous efforts have been made and a number of algorithms have been developed,such as spatial/frequency domain filtering,interpolation,etc.,to successfully eliminate the image grid artefacts introduced by fiber bundle.Nevertheless,the image quality has not been substantially improved especially in terms of reduced spatial resolution and image distortion.In recent years,the image recognition and enhancement capabilities of Deep Learning(DL) have been significantly improved and thus,DL has been explored to apply for the reconstruction of endoscopic images,for example,using U2-Net,Attention U-net,and GARNN models.While the image quality could be improved to some extent,it remains challenging in the restoration of fine details.More importantly,until now,there has been no research on the utilization of DL to eliminate image distortion introduced by microlens in the endoscopic image.In order to address this challenge,we develop a new open source algorithm AtG-DeepLab V3+ by effectively integrating the self-attention mechanism and the DeepLab V3+ network for the enhancement processing of endoscopic images.This developed model adapts the coding-decoding network as a whole architecture and uses the ResNet101network to extract features.Encoding context information by probing incoming features at multiple rates and multiple valid horizons or merging operations allows high-level abstract features to be extracted and clearer objects to be captured by progressively recovering spatial information.The self-attention gate integrated with the model decoder can effectively

关 键 词：内窥图像 深度学习 图像增强 注意力门 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]