Image reconstruction for cerebral hemorrhage based on improved densely-connected fully convolutional neural network.
10.7507/1001-5515.202406044
- Author:
Yanyan SHI
1
;
Luanjun WANG
1
;
Yating LI
1
;
Meng WANG
1
;
Bin YANG
2
;
Feng FU
2
Author Information
1. School of Electronic and Electrical Engineering, Henan Normal University, Xinxiang, Henan 453000, P. R. China.
2. Faculty of Biomedical Engineering, Fourth Military Medical University, Xi'an 710032, P. R. China.
- Publication Type:Journal Article
- Keywords:
Cerebral hemorrhage;
Electrical impedance tomography;
Image reconstruction;
Neural network
- MeSH:
Humans;
Cerebral Hemorrhage/diagnostic imaging*;
Neural Networks, Computer;
Electric Impedance;
Image Processing, Computer-Assisted/methods*;
Tomography/methods*;
Brain/diagnostic imaging*;
Phantoms, Imaging;
Convolutional Neural Networks
- From:
Journal of Biomedical Engineering
2024;41(6):1185-1194
- CountryChina
- Language:Chinese
-
Abstract:
Cerebral hemorrhage is a serious cerebrovascular disease with high morbidity and high mortality, for which timely diagnosis and treatment are crucial. Electrical impedance tomography (EIT) is a functional imaging technique which is able to detect abnormal changes of electrical property of the brain tissue at the early stage of the disease. However, irregular multi-layer structure and different conductivity properties of each layer affect image reconstruction of the brain EIT, resulting in low reconstruction quality. To solve this problem, an image reconstruction method based on an improved densely-connected fully convolutional neural network is proposed in this paper. On the basis of constructing a three-layer cerebral model that approximates the real structure of the human head, the nonlinear mapping between the boundary voltage and the conductivity change is determined by network training, which avoids the error caused by the traditional sensitivity matrix method used for solving inverse problem. The proposed method is also evaluated under the conditions with or without noise, as well as with brain model change. The numerical simulation and phantom experimental results show that conductivity distribution of cerebral hemorrhage can be accurately reconstructed with the proposed method, providing a reliable basis for the diagnosis and treatment of cerebral hemorrhage. Also, it promotes the application of EIT in the diagnosis of brain diseases.
