SAR-CGAN: Improved generative adversarial network for EIT reconstruction of lung diseases. (March 2023)

• Record Type: Journal Article
• Authors: Li, Xiuyan; Zhang, Ruzhi; Wang, Qi; Duan, Xiaojie; Sun, Yukuan; Wang, Jianming
• Is Part Of: Biomedical signal processing and control. Volume 81(2023)
• Publication Date: 2023-03
• Subjects: Electrical impedance tomography -- Image reconstruction -- Generative adversarial network -- Lung disease; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104421
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: The image reconstruction of electrical impedance tomography (EIT) is a nonlinear ill-posed inverse problem, and the reconstructed images tend to have artifacts due to noise in the measurement system. The shallow neural networks are difficult to fully express the nonlinear relationship of the EIT imaging problems. Deep neural networks have demonstrated great potential to remove artifacts from initial conductivity images caused by system noise. In the paper, a novel deep learning method, namely, conditional generative adversarial network with soft-attention gates (AGs) and residual learning (SAR-CGAN), is proposed to solve the above problems of EIT imaging. SAR-CGAN consists of generator and discriminator. Specifically, the AGs are employed by the generator to improve sensitivity and accuracy for lung EIT imaging by suppressing feature activation in irrelevant EIT region. And residual learning framework is introduced in the discriminator to address the problem of model degradation and easily enjoy accuracy gains from greatly increased depth. Extensive confirmatory and comparative experiments with three kinds of lung disease are conducted and compared with CNN, DnCNN, Attention U-Net and CGAN methods. The imaging results indicate that SAR-CGAN method can accurately recover the position and boundaries of lesions in lung images and effective reconstruction can be accomplished for the new conductivity distribution and noisy samples. Highlights: This structure is more interpretable with better contextual feature fusion and selection. Samples in the dataset are based on CT structural information and clinical lung tissue conductivity distribution. This structure can reconstruct detailed features of lesions in Lung EIT imaging task.