Deep Learning Based Cell Imaging with Electrical Impedance Tomography
Chen Zhou, Yunjie Yang, Jiabin Jia, Pierre Bagnaninchi
Abstract
Monitoring the 3-D cell culture process or drug responses non-destructively using Electrical Impedance Tomography (EIT) is an emerging topic in biomedical imaging. Significant efforts have been spent on developing EIT image reconstruction algorithms in order to achieve robust and high-quality cell imaging. The considerable computation time and imperfect image quality are the main issues of these conventional methods whereas the emergence of deep learning techniques point out a new direction due to its fast inferences on object detection, image segmentation and classification. In this paper, a novel deep learning architecture is proposed by adding a fully connected layer before a U-Net structure. This new architecture will first generate an initial guess of the conductivity distribution and then feed it to the following denoising model. A novel initialization strategy is also proposed to further help obtain this initial guess. The performance of the method is verified by simulation and experimental data. The results show that the proposed model outperforms the state-of-the-art EIT algorithms and can generalize well to reconstruct unseen cases consisting of human breast cancer cell pellet.