A Two-Stage Deep Learning Method for Robust Shape Reconstruction With Electrical Impedance Tomography
- 20 November 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 69 (7) , 4887-4897
Abstract
As a non-invasive and radiation-free imaging modality, electrical impedance tomography (EIT) has attracted much attention in the last two decades and owns many industry and biomedical applications. However, due to the nonlinearity and ill-posedness of its inverse problem, the EIT images always suffer from low spatial resolution and are sensitive to the modelling errors. To achieve high resolution and modelling error robust EIT image, a two-stage deep learning (TSDL) method is proposed. The proposed method consists of a pre-reconstruction block and a convolutional neural network (CNN). The pre-reconstruction block learns the regularization pattern from the training data set and provides a rough reconstruction of the target. The CNN post-processes the pre-reconstruction result in a multi-level feature analysis strategy, and eliminates the modelling errors with prior information of the observation domain shape. The pre-reconstruction and CNN blocks are trained together by using a minimum square approach. To evaluate the performance of the TSDL method, the lung EIT problem was studied. The training data set is calculated from more than 100 thousand EIT simulation models generated from CT scans across 792 patients. Lung injury, measurement noise and model errors are randomly simulated during the model generation process. The trained TSDL model is evaluated with simulation testes, as well as the experimental tests from a laboratory setting. According to the results, the TSDL method could achieve high accuracy shape reconstructions and is robust against measurement noise and modelling errors.Keywords
Funding Information
- National Natural Science Foundation of China (61971304, 81827806)
- Natural Science Foundation of Tianjin (17JCQNJC03500)
This publication has 32 references indexed in Scilit:
- Deep learningNature, 2015
- The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information RepositoryJournal of Digital Imaging, 2013
- Integral equation methods for the inverse obstacle problem with generalized impedance boundary conditionInverse Problems, 2012
- Design of Parallel Electrical Resistance Tomography System for Measuring Multiphase FlowChinese Journal of Chemical Engineering, 2012
- The detection of pleural effusion using a parametric EIT techniquePhysiological Measurement, 2009
- Subspace-Based Optimization Method in Electric Impedance TomographyJournal of Electromagnetic Waves and Applications, 2009
- Level set reconstruction of conductivity and permittivity from boundary electrical measurements using experimental dataInverse Problems in Science and Engineering, 2006
- A neural network image reconstruction technique for electrical impedance tomographyIEEE Transactions on Medical Imaging, 1994
- NOSER: An algorithm for solving the inverse conductivity problemInternational Journal of Imaging Systems and Technology, 1990
- Generalized Procrustes AnalysisPsychometrika, 1975