Dong Liu

Dong Liu

Auto-generated profile, based on publicly available information

Dong Liu

School of Biomedical Engineering and Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 January 2019 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
ZWZhun Wei
Zhun Wei
DLDong Liu
Dong Liu
XCXudong Chen
Xudong Chen
Deep learning has recently been applied to electrical impedance tomography (EIT) imaging. Nevertheless, there are still many challenges that this approach has to face, e.g., targets with sharp corners or edges cannot be well recovered when using circular inclusion training data. This paper proposes an iterative-based inversion method and a convolutional neural network (CNN) based inversion method to recover some challenging inclusions such as triangular, rectangular, or lung shapes, where the CNN-based method uses only random circle or ellipse training data. First, the iterative method, i.e., bases-expansion subspace optimization method (BE-SOM), is proposed based on a concept of induced contrast current (ICC) with total variation regularization. Second, the theoretical analysis of BE-SOM and the physical concepts introduced there motivate us to propose a dominant-current deep learning scheme for EIT imaging, in which dominant parts of ICC are utilized to generate multi-channel inputs of CNN. The proposed methods are tested with both numerical and experimental data, where several realistic phantoms including simulated pneumothorax and pleural effusion pathologies are also considered. Significant performance improvements of the proposed methods are shown in reconstructing targets with sharp corners or edges. It is also demonstrated that the proposed methods are capable of fast, stable, and high-quality EIT imaging, which is promising in providing quantitative images for potential clinical applications.

1 February 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
DLDong Liu
Dong Liu
JWJunwu Wang
Junwu Wang
QSQianxue Shan
Qianxue Shan
DSDanny Smyl
Danny Smyl
JDJiansong Deng
Jiansong Deng
JDJiangfeng Du
Jiangfeng Du
Neural networks (NNs) have been widely applied in tomographic imaging through data-driven training and image processing. One of the main challenges in using NNs in real medical imaging is the requirement of massive amounts of training data – which are not always available in clinical practice. In this article, we demonstrate that, on the contrary, one can directly execute image reconstruction using NNs without training data. The key idea is to bring in the recently introduced deep image prior (DIP) and merge it with electrical impedance tomography (EIT) reconstruction. DIP provides a novel approach to the regularization of EIT reconstruction problems by compelling the recovered image to be synthesized from a given NN architecture. Then, by relying on the NN's built-in back-propagation and the finite element solver, the conductivity distribution is optimized. Quantitative results based on simulation and experimental data show that the proposed method is an effective unsupervised approach capable of outperforming state-of-the-art alternatives.

25 September 2017 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Open access
DLDong Liu
Dong Liu
Anil Kumar KhambampatiAnil Kumar Khambampati
Anil Kumar Khambampati
JDJiangfeng Du
Jiangfeng Du
This paper presents an image reconstruction method based on parametric level set (PLS) method using electrical impedance tomography. The conductivity to be reconstructed was assumed to be piecewise constant and the geometry of the anomaly was represented by a shape-based PLS function, which we represent using Gaussian radial basis functions (GRBF). The representation of the PLS function significantly reduces the number of unknowns, and circumvents many difficulties that are associated with traditional level set (TLS) methods, such as regularization, re-initialization and use of signed distance function. PLS reconstruction results shown in this article are some of the first ones using experimental EIT data. The performance of the PLS method was tested with water tank data for two-phase visualization and with simulations which demonstrate the most popular biomedical application of EIT: lung imaging. In addition, robustness studies of the PLS method w.r.t width of the Gaussian function and GRBF centers were performed on simulated lung imaging data. The experimental and simulation results show that PLS method has significant improvement in image quality compared with the TLS reconstruction.

17 December 2015 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Open access
DLDong Liu
Dong Liu
Ville KolehmainenVille Kolehmainen
Ville Kolehmainen
SSSamuli Siltanen
Samuli Siltanen
ALAnne-Maria Laukkanen
Anne-Maria Laukkanen
ASAku Seppanen
Aku Seppanen
Objective: To evaluate the recently proposed nonlinear difference imaging approach to electrical impedance tomography (EIT) in realistic 3-D geometries. Methods: In this paper, the feasibility of nonlinear difference approach-based EIT is tested using simulation studies in 3-D geometries of thorax and larynx, and with an experimental study of a thorax-shaped water tank. All test cases exhibit severe modeling errors due to uncertainty in the boundary shape of the body. Results: In all test cases, the conductivity change reconstructed with nonlinear difference imaging outperforms the conventional reconstructions qualitatively and quantitatively. Conclusion: The results demonstrate that the nonlinear difference reconstructions tolerate geometrical modeling errors at least to the same extent as the conventional linear approach and produce quantitatively more accurate information on the conductivity change. Significance: Physiological processes that produce changes in the electrical conductivity of the body can be monitored with difference imaging based on EIT. The wide popularity of linearized difference imaging in EIT is mainly based on its good tolerance for the ubiquitous modeling errors, which are predominantly caused by inexact knowledge of the body geometry. However, the linearized difference imaging produces only qualitative information on the conductivity change, and the feasibility of the estimates also depends on the selection of the linearization point which ideally should be equal to the conductivity of the initial state. Based on the findings of this paper, these problems can be avoided by nonlinear difference imaging, and potentially the approach can enable quantitative imaging of conductivity change in medical applications.

18 February 2015 in Inverse Problems
Verified
Journal Article
Closed access
DLDong Liu
Dong Liu
Ville KolehmainenVille Kolehmainen
Ville Kolehmainen
SSSamuli Siltanen
Samuli Siltanen
ASAku Seppänen
Aku Seppänen
Electrical impedance tomography (EIT) is highly sensitive to modelling errors that arise from model reductions and inaccurate knowledge of auxiliary model parameters such as electrode positions, contact impedances and boundary shape of the body. In difference imaging , where the objective is to reconstruct change in the conductivity between EIT measurements at two time instants, the traditional way to circumvent modelling errors is to reconstruct the conductivity change using difference of the measurements and a global linearization of the nonlinear forward problem. Recently, a nonlinear reconstruction approach for difference imaging was proposed (Liu et al 2015 Inverse Probl. Imaging 9 , in press). The key feature of the approach is to parameterize the conductivity after the change as a linear combination of the initial conductivity and the conductivity change, and then estimate the initial conductivity and conductivity change by minimizing regularized least squares formulation based on both data sets. This approach allows independently modelling the spatial characteristics of the initial conductivity and the conductivity change by applying separate regularization functionals. In this paper, we investigate how well the nonlinear approach tolerates modelling errors and compare the reconstructions to the results with traditional linearized reconstruction method. The robustness is studied in cases of modelling errors arising from domain truncation, unknown contact impedances, inaccurately known electrode locations and inaccurately known domain boundary using simulated and experimental EIT data.

20 July 2018 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
DLDong Liu
Dong Liu
DSDanny Smyl
Danny Smyl
JDJiangfeng Du
Jiangfeng Du
This paper presents a novel difference imaging approach based on the recently developed parametric level set (PLS) method for estimating the change in a target conductivity from electrical impedance tomography measurements. As in conventional difference imaging, the reconstruction of conductivity change is based on data sets measured from the surface of a body before and after the change. The key feature of the proposed approach is that the conductivity change to be reconstructed is assumed to be piecewise constant while the geometry of the anomaly is represented by a shape-based PLS function employing Gaussian radial basis functions (GRBF). The representation of the PLS function by using GRBF provides flexibility in describing a large class of shapes with fewer unknowns. This feature is advantageous, as it may significantly reduce the overall number of unknowns, improve the condition number of the inverse problem, and enhance the computational efficiency of the technique. To evaluate the proposed PLS-based difference imaging approach, results obtained via simulation, phantom study, and in vivo pig data are studied. We find that the proposed approach tolerates more modeling errors and leads to significant improvement in image quality compared with the conventional linear approach.