Hybrid deep learning image reconstruction for photoacoustic
tomography in vivo

Authors: Hengrong Lana,b,c,Daohuai Jianga,b,c, Changchun Yanga,b,c, Feng Gaoa, Fei Gaoa,*


a Hybrid Imaging System Laboratory, Shanghai Engineering Research Center of Intelligent Vision and Imaging, School of Information Science and Technology, ShanghaiTech University, Shanghai 201210, China
b Chinese Academy of Sciences, Shanghai Institute of Microsystem and Information Technology, Shanghai 200050, China
c University of Chinese Academy of Sciences, Beijing 100049, China


Conventional reconstruction algorithms (e.g., delay-and-sum) used in photoacoustic imaging (PAI) provide a fast solution while many artifacts remain, especially for limited-view with ill-posed problem. In this paper, we propose a new convolutional neural network (CNN) framework Y-Net: a CNN architecture to reconstruct the initial PA pressure distribution by optimizing both raw data and beamformed images once. The network combines two encoders with one decoder path, which optimally utilizes more information from raw data and beamformed image. We compared our result with some ablation studies, and the results of the test set show better performance compared with conventional reconstruction algorithms and other deep learning method (U-Net). Both in-vitro and in-vivo experiments are used to validated our method, which still performs better than other existing methods. The proposed Y-Net architecture also has high potential in medical image reconstruction for other imaging modalities beyond PAI.


Hengrong Lan, Daohuai Jiang, Changchun Yang, Feng Gao, Fei Gao, Y-Net: Hybrid deep learning image reconstruction for photoacoustic tomography in vivo,
Photoacoustics, Volume 20, 2020, 100197, ISSN 2213-5979