基于混合域注意力ResNeSt的结肠息肉分割模型  

Colon Polyp Segmentation Model Based on Mixed-domain Attention ResNeSt

作　　者：周孟然[1] 刘思怡 卞凯 王宁 高立鹏 ZHOU Mengran;LIU Siyi;BIAN Kai;WANG Ning;GAO Lipeng(School of Electrical and Information Engineering,Anhui University of Science and Technology,Anhui Huainan 232001,China)

机构地区：[1]安徽理工大学电气与信息工程学院,安徽淮南232001

出　　处：《重庆工商大学学报(自然科学版)》2025年第1期85-93,共9页Journal of Chongqing Technology and Business University:Natural Science Edition

基　　金：安徽省科技重大专项项目(201903A07020013);教育部产学研创新基金(2019ITA01010);安徽理工大学引进人才科研启动基金项目(2022YJRC43).

摘　　要：目的针对因息肉大小不一,边界不清,光线影响,在图片中所占比例较小导致的分割精度不高的问题,提出了一种改进的U型结构网络BMR-Net。方法该模型的框架为编码器-解码器形式,在编码器部分采用ResNeSt提取特征,在计算成本增加很少的情况下改善了特征提取效果;在编码器和解码器之间设计边界预测生成模块(BPGM)来聚合高层特征并加入改良空间金字塔池化模块,在其中引入注意力机制,提升多尺度信息融合效果,获得更精确的全局特征图表示;针对不清晰的边缘部分采用反向注意力模块,删除已预测区域,校正边界信息。结果在CVC-ClinicDB、Kvasir-SEG、CVC-ColonDB、ETIS-Larib、EndoScene数据集上进行测试,mDice值分别达到了0.930、0.903、0.743、0.712、0.874。结论该方法分割性能和泛化性能均优于其他的先进方法,并且可以更加精确和完整地分割出小尺寸息肉,可以为结肠息肉患者提供早期预后信息。Objective To address the challenges posed by polyps of varied sizes,unclear boundaries,lighting effects,and their relatively small proportions in images that result in lower segmentation accuracy,an improved U-shaped network structure,BMR-Net,was proposed.Methods The model adopted an encoder-decoder architecture.The encoder partially utilized ResNeSt for feature extraction,enhancing the feature extraction performance with only a slight increase in computational cost.Between the encoder and the decoder,a boundary prediction generation module(BPGM)was designed to aggregate high-level features and incorporate a modified spatial pyramid pooling module,in which an attention mechanism was introduced.This promoted multi-scale information fusion,obtaining a more accurate global feature map representation.For unclear edge areas,a reverse attention module was applied to remove previously predicted areas and correct the boundary information.Results Tests were conducted on the CVC-ClinicDB,Kvasir-SEG,CVC-ColonDB,ETIS-Larib,and EndoScene datasets,with mDice values reaching 0.930,0.903,0.743,0.712,and 0.874,respectively.Conclusion This method outperforms other advanced methods in terms of segmentation performance and generalization ability.Furthermore,it can segment small-sized polyps more precisely and completely,providing early prognosis information for patients with colon polyps.

关 键 词：图像分割 结肠息肉 ResNeSt 编解码网络 注意力机制 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]