多尺度ResNeSt-50聚合网络与置信度传播的息肉图像分割  

Polyp image segmentation based on multi-scale ResNeSt-50 aggregation network and message passing

作　　者：夏平[1,2] 张光一 雷帮军[1,2] 邹耀斌[1,2] 唐庭龙 XIA Ping;ZHANG Guangyi;LEI Bangjun;ZOU Yaobing;TANG Tinglong(Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering,Three Gorges University,Yichang 443002,China;College of Computer and Information Technology,Three Gorges University,Yichang 443002,China)

机构地区：[1]三峡大学水电工程智能视觉监测湖北省重点实验室,湖北宜昌443002 [2]三峡大学计算机与信息学院,湖北宜昌443002

出　　处：《光学精密工程》2023年第18期2765-2780,共16页Optics and Precision Engineering

基　　金：国家自然科学基金资助项目(No.U1401252);湖北省重点实验室开放基金资助项目(No.2018SDSJ07).

摘　　要：针对大肠的息肉组织与正常组织间无明显边界,准确定位息肉位置困难的问题,提出了一种多尺度ResNeSt-50聚合网络融合顺序树重加权置信度传播(sequential Tree-Reweighted Message Passing,TRW-S)的息肉图像分割方法。为提高网络对息肉信息的表达能力,构建编码-解码结构的多尺度ResNeSt-50聚合网络,编码器由卷积模块和4级ResNeSt模块级联构建ResNeSt-50骨干网络,实现跨通道信息间的线性整合与连接;ResNeSt-50采用拆分注意力机制加强重要通道组的表现能力,增强了残差模块提取息肉图像信息的能力;解码部分下三层构建多层感受野模块(recep⁃tive field block,RFB)获取多尺度信息,然后用密集聚合模块整合其输出,并以快速解码方式输出解码信息,保证其分割性能的同时减少参数量;其次,生成预测图时采用测试时图像增强(Test-Time Augmentation,TTA)模块提升预测准确度,并增强网络的泛化能力;最后,构建基于马尔科夫随机场的TRW-S算法对输出的预测图进行后处理,以实现分割边缘的连续性和分割区域内部的一致性。对大肠息肉数据集Kvasir-SEG的测试结果表明,本文方法相比于U-Net,UNet++,ResUnet、SFA、PraNet等算法,mDice值达91.6%,mIoU达86.3%,Smeasure达0.921,MAE为0.023,优于其他五种息肉分割算法;在未知数据集ETIS-LaribPolypDB,ColonDB上测试结果表明,相比于PraNet模型,本文模型的mDice值分别提升了14.2%,7.7%;从本文模型在ETIS-LaribPolypDB数据集上的分割表现看,本文算法对微小病变十分敏感;因此,本文算法分割的息肉图像,在分割区域内部的一致性、分割边缘的连续性、轮廓清晰度、捕捉微小病变能力等方面均表现出优良的性能,同时,对未知数据集具有较好的泛化能力。There boundary between colorectal polyps and normal tissues is not typically evident.There⁃fore,accurately locating polyp positions is challenging.This study developed a novel polyp image segmen⁃tation method based on a combination of multiscale ResNeSt-50 aggregation network and sequential tree-reweighted message passing(TRW-S).First,a multiscale ResNeSt-50 aggregation network with an en⁃coding-decoding structure was constructed to improve the expressiveness of the network.The encoder of the network is cascaded by convolution module and four-level ResNeSt module to build the ResNeSt-50 backbone network,which realizes linear integration and communication between cross-channel informa⁃tion,ResNeSt-50 uses split attention to strengthen the performance of important channel groups and en⁃hance the ability of the residual module to extract polyp image information.In the bottom three layers of the decoder,a multilayer receptive field block(RFB)was used to obtain multiscale information.Subse⁃quently,the dense aggregation module was used to integrate the output.The decoding information was output by using a fast decoding method,which ensured consistent segmentation performance and reduced the number of parameters.Second,the test-time augmentation(TTA)module was used to improve the prediction accuracy and enhance the generalization ability of the network when generating predictive imag⁃es.Finally,a sequential tree-reweighted message passing(TRW-S)algorithm based on Markov random fields was constructed to postprocess the predicted image output of the model.This helped achieve conti⁃nuity of the segmentation edge and consistency within the segmentation region.The experimental results on Kvasir-SEG,an open-access dataset for gastrointestinal polyps images,show that our method achieved an mDice value of 91.6%,mIoU of 86.3%,Smeasure of 92.1%,and MAE of 2.3%,which are higher than those of the polyp segmentation algorithms based on U-NET,U-Net++,ResUNet,SFA,and PraNet.Test results on the unknown datasets ETIS-Lar

关 键 词：息肉图像分割 多尺度密集聚合网络 拆分注意力机制 顺序树重加权置信度传播 多尺度感受野 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]