Shape Reconstruction With Multiphase Conductivity for Electrical Impedance Tomography Using Improved Convolutional Neural Network Method
Shape Reconstruction With Multiphase Conductivity for Electrical Impedance Tomography Using Improved Convolutional Neural Network Method
复制标题
DOI：
10.1109/jsen.2021.3050845
复制
发表时间：
2021-04
影响因子：
4.3
通讯作者：
Yang Wu;Bai Chen;Kai Liu;Chengjun Zhu;Huaping Pan;J. Jia;Hongtao Wu;Jiafeng Yao
中科院分区：
文献类型：
--
作者：
Yang Wu;Bai Chen;Kai Liu;Chengjun Zhu;Huaping Pan;J. Jia;Hongtao Wu;Jiafeng Yao
电阻抗层析成像（EIT）图像重构是一个高度非线性的不适定反问题，对测量噪声和模型误差很敏感。提出了一种改进的卷积神经网络（CNN）方法用于EIT肺成像。该方法基于视觉几何组（VGG）模型进行优化，增加了批归一化（BN）层、ELU激活函数、全局平均池化（GAP）层和径向基函数（RBF）神经网络。这些优化有助于加快网络收敛速度，提高重构的准确性和鲁棒性。利用60例患者胸部CT图像生成的近1万个EIT仿真模型进行网络训练。在模型生成过程中随机模拟胸部变形、肺过度扩张和肺不张。训练后的方法通过一系列仿真数据和实验模型进行了验证。通过计算均方根误差（RMSE）和图像相关系数（ICC）对重建质量进行定量比较。实验结果表明，该方法平均RMSE为0.082，ICC为0.892。该方法可实现高分辨率和鲁棒性的多相电导率肺成像，特别是在存在测量噪声和干扰的情况下。该方法有望为潜在的临床应用提供定量图像，如人体胸腔成像。
Image reconstruction of Electrical Impedance Tomography (EIT) is a highly nonlinear ill-posed inverse problem, which is sensitive to the measurement noise and model errors. An improved Convolutional Neural Network (CNN) method is proposed for the EIT lung imaging. The proposed method is optimized based on the Visual Geometry Group (VGG) model, adding the batch normalization (BN) layer, ELU activation function, global average pooling (GAP) layer, and radial basis function (RBF) neural network. These optimizations help speed up network convergence, and improve reconstruction accuracy and robustness. Nearly 10 thousand EIT simulation models generated from chest CT images of 60 patients are used for the network training. The chest deformation, lung hyperdilation and atelectasis are randomly simulated during the model generation process. The proposed method after training is tested through a series of simulation data and experimental models. The reconstruction quality is quantitatively compared by calculating the root mean square error (RMSE) and image correlation coefficient (ICC). On average, the proposed method achieves 0.082 RMSE and 0.892 ICC through experimental results. The proposed method achieves high-resolution and robust shape reconstructions with multiphase conductivity for EIT lung imaging, especially in the presence of the measurement noise and interference. The proposed method is promising in providing quantitative images for potential clinical applications, such as human thorax imaging.