融合Transformer和线索交叉聚合的结直肠息肉分割方法  

Colorectal polyp segmentation method fusing Transformer and cross-cue fusion

作　　者：梁礼明 李俞霖 金家新 何安军 夏雨辰 LIANG Liming;LI Yulin;JIN Jiaxin;HE Anjun;XIA Yuchen(School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou,Jiangxi341000,China;Software Department,Jiangxi Communication Terminal Industry Technology Research InstituteCo.,LTD,Ji′an,Jiangxi 343000,China)

机构地区：[1]江西理工大学电气工程与自动化学院,江西赣州341000 [2]江西省通讯终端产业技术研究院有限公司软件部,江西吉安343000

出　　处：《光电子.激光》2025年第2期136-145,共10页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(51365017,61463018);江西省自然科学基金面上项目(20192BAB205084);江西省教育厅科学技术研究重点项目(GJJ170491,GJJ2200848)资助项目。

摘　　要：针对结直肠息肉图像分割时动态信息处理和边缘细节捕捉能力不足,导致边界信息损失和错误分割等问题,本文提出一种建立在Swin Transformer框架上的线索交叉聚合(cross-cue fusion,CCF)结肠息肉分割方法。该方法首先通过Transformer编码器对图像的病变特征进行逐级提取。其次利用改进的二阶通道注意力(second-order channel attention,SOCA)机制增强跨层级信息交互能力,有效提取丰富的多尺度上下文特征信息。再次采用反向通道频率注意力(reverse channel frequency attention,RCFA)机制中的离散余弦变换(discrete cosine transform,DCT),突出多尺度上下文信息的通道特征。最后通过CCF模块从动态和静态深度两个层面增强图像特征,进而提升动态信息处理和细节捕捉能力。在数据集CVC-ClinicDB、Kvasir、CVC-ColonDB和ETISLaribPolypDB上进行测试,Dice指数分别为0.942、0.924、0.800和0.774。MI o U指数分别为0.896、0.878、0.726和0.697。实验数据表明,本文提出的方法能有效分割结直肠息肉图像,为结直肠息肉的诊断提供了新思路。In order to solve the problems of insufficient dynamic information processing and edge detail capture in colorectal polyp image segmentation,such as boundary information loss and wrong segmentation,this paper proposes a colorectal polyp segmentation method based on Swin Transformer framework.Firstly,Transformer encoder is used to extract the pathological features of the image step by step.Secondly,the improved second-order channel attention(SOCA)mechanism is used to enhance cross-level information interaction ability and effectively extract rich multi-scale context feature information.Furthermore,the discrete cosine transform(DCT)in the attention mechanism of reverse frequency channel is used to highlight the channel characteristics of multi-scale context information.Finally,the image features are enhanced from both dynamic and static depth through the cross-cue fusion(CCF)module to improve the dynamic information processing and detail capture capabilities.When tested on the datasets CVC-ClinicDB,Kvasir,CVC-ColonDB,and ETIS-LaribPolypDB,Diceindices are 0.942,0.924,0.800and 0.774,respectively.The MIoUindices are 0.896,0.878,0.726and 0.697,respectively.The experimental data show that the proposed method can effectively segment colorectal polyp images and provide a new idea for the diagnosis of colorectal polyp.

关 键 词：图像分割 结直肠息肉 TRANSFORMER 线索交叉聚合(CCF)模块 反向通道频率注意力(RCFA)模块 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]