期刊
COMPLEX & INTELLIGENT SYSTEMS
卷 -, 期 -, 页码 -出版社
SPRINGER HEIDELBERG
DOI: 10.1007/s40747-023-01049-9
关键词
Feature screening strategy; Multi-dimensional spatial attention; Neural networks
We propose a stereo spatial discoupling network (TSDNets) to leverage the multi-dimensional spatial details of medical images, solve the difficulty of establishing effective spatial associations, and extract similar low-level features, resulting in redundancy of information.
Deep convolutional neural network (CNN) has made great progress in medical image classification. However, it is difficult to establish effective spatial associations, and always extracts similar low-level features, resulting in redundancy of information. To solve these limitations, we propose a stereo spatial discoupling network (TSDNets), which can leverage the multi-dimensional spatial details of medical images. Then, we use an attention mechanism to progressively extract the most discriminative features from three directions: horizontal, vertical, and depth. Moreover, a cross feature screening strategy is used to divide the original feature maps into three levels: important, secondary and redundant. Specifically, we design a cross feature screening module (CFSM) and a semantic guided decoupling module (SGDM) to model multi-dimension spatial relationships, thereby enhancing the feature representation capabilities. The extensive experiments conducted on multiple open source baseline datasets demonstrate that our TSDNets outperforms previous state-of-the-art models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据