信息与控制2024，Vol.53Issue(5)：673-688,16.DOI:10.13976/j.cnki.xk.2024.3203
结合多分支纹理特征提取和注意力机制的肝脏肿瘤自动分割方法
Automatic Liver Tumor Segmentation Method Integrating Multi-branch Texture Feature Extraction and Attention Mechanism
摘要
Abstract
To address the issues of fuzzy boundaries,diverse tumor types,low contrast with surrounding tissues in computerized tomography(CT)images,as well as insufficient utilization of texture infor-mation in existing networks for medical images,an automatic liver tumor segmentation method that combines multi-branch texture feature extraction and attention mechanism is proposed.Firstly,a parallel convolutional encoder is designed to replace the dual convolutional modules in the U-Net baseline network,aiming to extract superficial features under two different receptive fields.Sec-ondly,a texture feature extraction network is introduced in the skip-connection part of the U-Net to extract deep texture information of liver tumors at multiple scales.Finally,a channel attention module with a residual path is incorporated in the decoding stage to effectively capture inter-chan-nel dependencies and enhance the relevant features for liver tumor segmentation tasks.The proposed method is evaluated on the LiTS2017 and 3DIRDCADb-01 liver tumor segmentation datasets.Experimental results demonstrate superiority of the proposed method in terms of evaluation metrics and visualizations in comparison with the baseline methods,which shows advantages in segmenting small-sized and blurry boundary tumors,providing promising insights for liver tumor screening.关键词
图像处理/肝脏肿瘤/U-Net/并行卷积/纹理特征/注意力机制Key words
image processing/liver tumor/U-Net/parallel convolution/texture feature/attention mechanism分类
信息技术与安全科学引用本文复制引用
邱云飞,王月洋..结合多分支纹理特征提取和注意力机制的肝脏肿瘤自动分割方法[J].信息与控制,2024,53(5):673-688,16.基金项目
国家自然科学基金(62173171,61404069) （62173171,61404069）
辽宁省自然科学基金(2015020095) （2015020095）
辽宁省教育厅科学技术研究项目(LJYL051) （LJYL051）
