Advances of deep learning in electrical impedance tomography image reconstruction

Abstract

Electrical impedance tomography (EIT) has been widely used in biomedical research because of its advantages of real-time imaging and nature of being non-invasive and radiation-free. Additionally, it can reconstruct the distribution or changes in electrical properties in the sensing area. Recently, with the significant advancements in the use of deep learning in intelligent medical imaging, EIT image reconstruction based on deep learning has received considerable attention. This study introduces the basic principles of EIT and summarizes the application progress of deep learning in EIT image reconstruction with regards to three aspects: a single network reconstruction, deep learning combined with traditional algorithm reconstruction, and multiple network hybrid reconstruction. In future, optimizing the datasets may be the main challenge in applying deep learning for EIT image reconstruction. Adopting a better network structure, focusing on the joint reconstruction of EIT and traditional algorithms, and using multimodal deep learning-based EIT may be the solution to existing problems. In general, deep learning offers a fresh approach for improving the performance of EIT image reconstruction and could be the foundation for building an intelligent integrated EIT diagnostic system in the future.

Exploratory study of a multifrequency EIT-based method for detecting intracranial abnormalities

“…There has been some progress in image feature recognition in AI technology ( 31 , 32 ). Zhang Tao summarized the application progress of depth learning in EIT image reconstruction from three aspects: single network reconstruction, depth learning combined with traditional algorithm reconstruction, and multi-network hybrid reconstruction ( 33 ). In general, AI technology provides a new method to improve the performance of EIT image reconstruction.…”

Comparison between a novel compressed sensing-based neural network and traditional neural network approaches for electrical impedance tomography reconstruction

“…where 𝑦 𝑖 is expected output value from the training dataset and 𝑦 ̂𝑖 is the NN output value [4,8]. During training, the calculated loss is fed into an optimizer that adjusts the weights in each layer of the NN to minimize loss [7].…”

“…This is mainly due to the ill-posed nature of the EIT inverse problem. With recent advances in computational hardware, deep learning (DL) has been an increasingly attractive approach for EIT reconstruction as it shows potential to enhance reconstruction resolution and quality compared to traditional iterative algorithms, especially for solving nonlinear ill-posed problems [4]. However, one major drawback to DL is the reliance on large amounts of data to successfully generalize the problem at hand.…”

Advances in Electrical Impedance Tomography Inverse Problem Solution Methods: From Traditional Regularization to Deep Learning

“…In geophysical models, on the other hand, there is a lack of a baseline measurement frame that could permit difference-EIT imaging to absorb major modeling errors between the original and the reconstruction models [1]. To address these issues, researchers are attempting to mitigate these challenges with the introduction of more robust DL-based techniques, many of which are focused on specific applications and their unique features [74]. Overall, as in other inverse scattering problems, NN-based learning approaches for EIT can be categorized into three main groups: A) Direct data-based learning, B) post-image reconstruction learning and C) model-based learning [64], [204], [205].…”