一种基于局部通道注意力的可信息肉分割方法  

Reliable Polyp Segmentation Based on Local Channel Attention

作　　者：许建[1,2] 王若涵 Xu Jian;Wang Ruohan(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,Jiangsu,China;Jiangsu Key Laboratory of Big Data Security and Intelligent Processing(Nanjing University of Posts and Telecommunications),Nanjing 210023,Jiangsu,China)

机构地区：[1]南京邮电大学计算机学院,江苏南京210023 [2]江苏省大数据安全与智能处理重点实验室(南京邮电大学),江苏南京210023

出　　处：《激光与光电子学进展》2025年第2期264-272,共9页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62202241,62372244);江苏省重点研发计划项目(BE2021093)。

摘　　要：为了进一步提高现有息肉分割技术的准确性和可信性,提出了一种基于局部通道注意力的可信息肉分割方法。首先,该方法利用改进的金字塔视觉Transformer编码器提取息肉区域特征,解决传统卷积神经网络特征提取能力不足的问题;然后,利用局部通道注意力机制来融合级联的特征,在精确定位息肉的前提下,逐步恢复边缘细节信息,提升模型的整体表征能力;最后,基于主观逻辑证据理论构建可信的息肉分割模型,推导出息肉分割问题的概率和不确定性,对分割结果进行可信性度量。利用多个公开数据集进行了大量实验,实验结果表明,与现有典型方法相比,本文方法具有更好的准确性、鲁棒性和泛化性,并且可以得到较为可信的息肉分割结果。To enhance the accuracy and credibility of existing polyp segmentation methods,this study proposes a reliable segmentation technique that uses local channel attention.First,the improved pyramid vision transformer is employed to extract polyp region features,thereby addressing the insufficient feature extraction capabilities of traditional convolutional neural networks.In addition,a local channel attention mechanism is applied to fuse cascade features,and the edge detail information is gradually recovered to enhance the overall representational capability of the model while ensuring accurate polyp localization.Finally,a trusted polyp segmentation model is developed based on subjective logic evidence to derive the probability and uncertainty of the polyp segmentation problem,and a plausibility measure is applied to the segmentation results.Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art polyp segmentation techniques in terms of accuracy,robustness,and generalization,leading to more reliable polyp segmentation results.

关 键 词：图像处理 息肉分割 局部通道注意力 不确定性估计 主观逻辑证据理论 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]