摘要
为了有效利用少量的医学图像标签数据和大量的无标签数据,提出了一种基于半监督学习和生成对抗网络的医学图像融合算法。所提生成对抗网络融合架构包含1个生成器网络和2个判别器网络。采用半监督学习策略对所提网络进行训练,主要包括监督训练、无监督训练、参数微调等3个阶段。此外,生成器由面向融合任务的U-Net和squeeze and excitation通道注意力模块组成,而判别器含有3层卷积层、1层全连接层及sigmoid激活输出层。在各种不同模态医学图像上的实验结果表明,与现有的6种基于深度学习的算法相比,所提算法的主观视觉效果和客观性能指标都有一定竞争力。相关消融实验也验证了半监督学习策略能强化生成网络的性能,提高融合图像的质量。
To efficiently employ a small amount of labeled data,a medical image fusion network based on semisupervised learning and a generative adversarial network is developed.The developed fusion network comprises one generator and two discriminators.A semisupervised learning scheme is developed to train the network,including the supervisedtraining,unsupervised training,and parameters fine-tuning phases.Furthermore,the generator is constructed using a fusion inspired U-Net,squeeze and excitation attention modules.The discriminator contains three convolution layers,one fully connected layer,and a sigmoid activation function.The experimental findings on different multimodal medical images exhibit the proposed approach is competitive with six existing deep-learning based approaches in terms of visual effects and objective indexes.Moreover,the ablation investigations show the effectiveness of a semisupervised learning scheme that can enhance the quality of fused images.
作者
尹海涛
岳勇赢
Yin Haitao;Yue Yongying(College of Automation&College of Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210023,Jiangsu,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第22期237-246,共10页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61971237)。
关键词
机器视觉
生成对抗网络
半监督学习
医学图像融合
注意力机制
machine vision
generate adversarial network
semisupervised learning
medical image fusion
attention mechanism