首页|多尺度注意力融合与视觉Transformer方法优化的电阻抗层析成像深度学习方法

多尺度注意力融合与视觉Transformer方法优化的电阻抗层析成像深度学习方法

扫码查看
原文链接
  • 万方数据
  • 维普
电阻抗层析成像(EIT)具有显著的可视化和非侵入性等特点，在工业和生物医学工程领域展现了其广阔的应用潜力。由于其逆问题存在高度非线性和病态性特点，导致了数值成像方法在空间分辨率上的局限性，尤其是在多相介质分布情况下，现有EIT技术在成像过程中出现边界失真和电导率误差，从而影响最终的成像精度。本文提出了一种基于卷积注意力机制的U型深度成像方法——MAT-UNet，将卷积块注意力模块(CBAM)与U-Net结构相结合，在特征提取与融合过程中嵌入卷积块注意力模块，以增强模型的注意力定向和特征表征能力，同时跳跃连接引入了压缩-激励(SE)注意力机制与视觉Transformer(ViT)来优化全局特征的学习，使用多头交叉注意力模块(MHCA)实现编码器与解码器的多尺度信息融合。MAT-UNet通过大量的仿真数据训练获得最优模型参数，并在多样化复杂形状和肺部仿真模型进行了实验验证。定量评估指标表明，该方法在重建图像中的均方根误差(RMSE)结果为2。315 6，结构相似性指数(SSIM)结果为0。943 7，可视化结果与真实分布和边界具有很好的一致性。实验结果表明，本文提出的MAT-UNet模型展现出良好的鲁棒性和泛化能力，相较于传统的单一卷积结构，集成Transformer结构提供了更精准的EIT图像重建效果，在无损测量与检测应用中存在很大的潜力和价值。
Optimized learning method for electrical impedance tomography with multi-scale attention fusion and vision transformer
Considering the advantage of visualization and non-invasiveness of electrical impedance tomography(EIT),it's broadly applied in industrial and biomedical fields.However,due to the highly nonlinear and ill-posed nature of inverse problem,numerical imaging methods face spatial resolution limitations.These limitations are especially evident in multiphase media distributions,where current EIT technology encounters boundary distortions and conductivity errors,thereby affecting the final imaging accuracy.To address mentioned issues,this paper introduces a learning-based model for EIT reconstruction,referred as MAT-UNet,which is mainly composed of U-shaped backbone and optimized multi-head attention block.The MAT-UNet integrates convolutional block attention module(CBAM)in the Encoders for feature extraction to construct the spatial and channel latent feature.In addition,the Squeeze-and-Excitation Vision Transformer(SE-ViT)is introduced in the skip connection between Encoder and Decoder,which optimizes the global feature learning.Also,the Multi-Head Cross-Attention(MHCA)module facilitates multi-scale information fusion between the encoder and decoder.MAT-UNet is trained on extensive simulation data to obtain optimal model parameters and is experimentally validated on diverse complex shapes and lung simulation models.The quantitative evaluation metrics indicate that this method achieves a Root Mean Square Error(RMSE)of 2.315 6 and a Structural Similarity Index(SSIM)of 0.943 7 in reconstructed images.The visualized results closely match the true distribution and boundaries.Experimental outcomes demonstrate that the proposed MAT-UNet model exhibits robust performance and generalization capability.Compared to traditional single convolution structures,the integration of the Transformer structure provides more accurate EIT image reconstruction,presenting significant potential and value in non-destructive measurement and detection applications.

electrical impedance tomographyconvolutional attention mechanismSE-ViT connectionmulti-head cross-attention mechanismU-shaped convolutional networknon-destructive measurement

王琦、张涛、徐超炜、卢梦凡、王子辰

展开 >

天津工业大学电子与信息工程学院 天津 300387

天津市光电检测技术与系统重点实验室 天津 300387

电阻抗层析成像 卷积注意力机制 SE-ViT连接 多头交叉注意力模块 U型卷积网络 无损测量

国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金

62072335620713286187226961903273

2024

10.19650/j.cnki.cjsi.J2412698

仪器仪表学报
中国仪器仪表学会

仪器仪表学报

CSTPCD北大核心
影响因子：2.372
ISSN：0254-3087
年,卷(期)：2024.45(7)