首页|基于高低频特征分解的深度多模态医学图像融合网络

基于高低频特征分解的深度多模态医学图像融合网络

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
多模态医学图像融合旨在利用跨模态图像的相关性和信息互补性,以增强医学图像在临床应用中的可读性和适用性.然而,现有手工设计的模型无法有效地提取关键目标特征,从而导致融合图像模糊、纹理细节丢失等问题.为此,提出了一种新的基于高低频特征分解的深度多模态医学图像融合网络,将通道注意力和空间注意力机制引入融合过程,在保持全局结构的基础上保留了局部纹理细节信息,实现了更加细致的融合.首先,通过预训练模型VGG-19提取两种模态图像的高频特征,并通过下采样提取其低频特征,形成高低频中间特征图.其次,在特征融合模块嵌入残差注意力网络,依次从通道和空间维度推断注意力图,并将其用来指导输入特征图的自适应特征优化过程.最后,重构模块形成高质量特征表示并输出融合图像.实验结果表明,该算法在Harvard公开数据集和自建腹部数据集峰值信噪比提升 8.29％,结构相似性提升 85.07％,相关系数提升 65.67％,特征互信息提升46.76％,视觉保真度提升80.89％.
Deep multimodal medical image fusion network based on high-low frequency feature decomposition
Multimodal medical image fusion aims to enhance the interpretability and applicability of medical images in clinical settings by leveraging correlations and complementary information across different imaging modalities.However,existing manually designed models often fail to effectively extract critical target features,resulting in issues such as blurred fusion images and loss of textural details.To address this,a novel deep multimodal medical image fusion network based on high-low frequency feature decomposition was proposed.This approach incorporated channel attention and spatial attention mechanisms into the fusion process,allowing for a more intricate fusion of high-low frequency features while preserving both global structure and local textural details.Firstly,the high-frequency features of two modal images were extracted using the pre-trained model VGG-19,and their low-frequency features were extracted through downsampling to form intermediate features between high and low frequencies.Secondly,a residual attention network was embedded in the feature fusion module to sequentially infer attention maps from independent channels and spatial dimensions.These maps were then employed to guide the adaptive feature optimization of input feature maps.Finally,the reconstruction module fused high-low frequency features and output the fusion image.Experimental results on both the Harvard open dataset and a self-created abdominal dataset demonstrated that compared to the source image,the fusion image produced by the proposed method achieved an 8.29％improvement in peak signal-to-noise ratio,85.07％in structural similarity,65.67％in correlation coefficient,46.76％in feature mutual information,and 80.89％in visual fidelity.

multi-modal medical image fusionpre-trained modeldeep learninghigh-low frequency feature extractionresidual attention network

王欣雨、刘慧、朱积成、盛玉瑞、张彩明

展开 >

山东财经大学计算机科学与技术学院,山东 济南 250014

山东省数字媒体技术重点实验室,山东 济南 250014

山东第一医科大学第一附属医院,山东 济南 250014

山东大学软件学院,山东 济南 250014

展开 >

多模态医学图像融合 预训练模型 深度学习 高低频特征提取 残差注意力网络

国家自然科学基金项目国家自然科学基金项目中央引导地方科技发展项目山东省泰山学者特聘专家计划项目

62072274U22A2033YDZX2022009tstp20221137

2024

10.11996/JG.j.2095-302X.2024010065

图学学报
中国图学学会

图学学报

CSTPCD北大核心
影响因子：0.73
ISSN：2095-302X
年,卷(期)：2024.45(1)
  • 33