A generative deep neural network as an alternative to co-kriging DOI Creative Commons
Herbert Rakotonirina, Paul Honeiné, Olivier Atteia

et al.

Applied Computing and Geosciences, Journal Year: 2024, Volume and Issue: 24, P. 100198 - 100198

Published: Oct. 2, 2024

Language: Английский

Self-sensing joints for in-situ structural health monitoring of composite pipes: A piezoresistive behavior-based method DOI
Riwu Yao,

Zhoutian Ge,

De‐Yi Wang

et al.

Engineering Structures, Journal Year: 2024, Volume and Issue: 308, P. 118049 - 118049

Published: April 12, 2024

Language: Английский

Citations

21
Advances in Electrical Impedance Tomography Inverse Problem Solution Methods: From Traditional Regularization to Deep Learning DOI Creative Commons
Christos Dimas, Vassilis Alimisis,

Nikolaos Uzunoglu

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 47797 - 47829

Published: Jan. 1, 2024

Electrical Impedance Tomography (EIT) has emerged as a valuable medical imaging modality, which visualizes the conductivity distribution of subject by performing multi-electrode impedance measurements. EIT finds applications in monitoring lung and cardiac function, brain detection malignant tissues. Its mobility, outstanding temporal resolution absence ionizing radiation make it particularly suitable for repetitive real-time diagnostics, especially radiation-sensitive populations, such neonates. This paper presents methodological review image reconstruction approaches spanning from traditional linear regularization back-projection to more recent techniques, including deep learning, sparse Bayesian learning non-linear shape-driven reconstruction. Linear are distinguished, well time, frequency difference absolute ones. The exposition includes concise elaboration methodologies' mathematical foundations algorithmic deployment, with particular attention advancements. For each approach, an assessment its merits drawbacks is given, providing implementation considerations, performance relevant applications.

Language: Английский

Citations

10
Progressive Approaches in Oncological Diagnosis and Surveillance: Real‐Time Impedance‐Based Techniques and Advanced Algorithms DOI
Viswambari Devi Ramaswamy, Michael Keidar

Bioelectromagnetics, Journal Year: 2025, Volume and Issue: 46(1)

Published: Jan. 1, 2025

ABSTRACT Cancer remains a formidable global health challenge, necessitating the development of innovative diagnostic techniques capable early detection and differentiation tumor/cancerous cells from their healthy counterparts. This review focuses on confluence advanced computational algorithms with noninvasive, label‐free impedance‐based biophysical methodologies—techniques that assess biological processes directly without need for external markers or dyes. elucidates diverse array state‐of‐the‐art technologies, illuminating distinct electrical signatures inherent to cancer vs tissues. Additionally, study probes transformative potential these modalities in recalibrating personalized treatment paradigms. These offer real‐time insights into tumor dynamics, paving way precision‐guided therapeutic interventions. By emphasizing quest continuous vivo monitoring, herald pivotal advancement overarching endeavor combat globally.

Language: Английский

Citations

1
Evaluation of adjacent and opposite current injection patterns for a wearable chest electrical impedance tomography system DOI Creative Commons
Lin Yang,

Zhijun Gao,

Chunchen Wang

et al.

Physiological Measurement, Journal Year: 2024, Volume and Issue: 45(2), P. 025004 - 025004

Published: Jan. 24, 2024

Abstract Objective. Wearable electrical impedance tomography (EIT) can be used to monitor regional lung ventilation and perfusion at the bedside. Due its special system architecture, amplitude of injected current is usually limited compared stationary EIT system. This study aims evaluate performance injection patterns with various low-amplitude currents in healthy volunteers. Approach. A total 96 test sets measurement was recorded 12 subjects by employing adjacent opposite four amplitudes small (i.e. 1 mA, 500 uA, 250 uA 125 uA). The two evaluated terms signal-to-noise ratio (SNR) thorax impedance, image metrics EIT-based clinical parameters. Main results. Compared injection, had higher SNR ( p < 0.01), less inverse artifacts boundary 0.01) same amplitude. In addition, exhibited more stable parameters across range. For significant differences were found for three 0.05) between group other grou s. Significance. better wearable pulmonary EIT, greater than should one, ensure a high level SNR, quality reconstructed as well reliability

Language: Английский

Citations

4
Measurement of biomechanical properties of transversely isotropic biological tissue using traveling wave expansion DOI
Shengyuan Ma, He Zhao, Runke Wang

et al.

Medical Image Analysis, Journal Year: 2025, Volume and Issue: 101, P. 103457 - 103457

Published: Jan. 9, 2025

Language: Английский

Citations

0
Deep Image Prior based Super Resolution for Fast Electromagnetic Forward Modeling DOI

Min Jiang,

Qingtao Sun, Qing Liu

et al.

IEEE Transactions on Antennas and Propagation, Journal Year: 2025, Volume and Issue: 73(3), P. 1900 - 1905

Published: Jan. 28, 2025

Language: Английский

Citations

0
TransADMM: Transformer enhanced unrolling alternating direction method of multipliers framework for electrical impedance tomography DOI
Zichen Wang, Tao Zhang, Tianchen Zhao

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: 276, P. 127007 - 127007

Published: March 17, 2025

Language: Английский

Citations

0
Deep prior embedding method for Electrical Impedance Tomography DOI
Junwu Wang, Jiansong Deng, Dong Liu

et al.

Neural Networks, Journal Year: 2025, Volume and Issue: unknown, P. 107419 - 107419

Published: March 1, 2025

Language: Английский

Citations

0
Optimization of PET Image Reconstruction for Enhanced Image Quality in Various Tasks Using a Conventional PET Scanner DOI Creative Commons
Zahraa M. Rashid, Zaid H. Al-Sawaff,

Ahmed Sabeeh Yousif

et al.

Journal of Electrical and Computer Engineering, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Positron emission tomography (PET) imaging requires high‐quality yet rapid reconstruction to ensure clinical effectiveness, as these reconstructions enable timely and accurate diagnosis, guide treatment decisions, reduce the risk of delayed interventions in critical settings. This study introduces a deep learning‐based method that employs conditional generative adversarial networks (cGANs) for direct sinogram‐to‐image PET reconstruction. A dual approach was used: simulation experiments with Zubal phantoms, which provided controlled reproducible environment test accuracy robustness, validation real patient datasets, ensuring method’s applicability effectiveness The primary objective evaluate ability cGAN‐based enhance image quality, noise, improve speed compared conventional algorithms, such maximum likelihood expectation maximization (MLEM) total variation (TV). methodology involved training U‐net‐based generator whole‐image discriminator iteratively reconstruct images superior resolution accuracy. Key outcome measures included bias, variance, structural similarity index (SSIM), relative root mean square error (rRMSE), metrics effectively quantify fidelity, noise levels, accuracy, are evaluating reliability precision reconstructed images. results showed proposed achieved significant improvements clarity, suppression, computational efficiency, outperforming traditional techniques. These findings highlight potential improving diagnostic workflow.

Language: Английский

Citations

0
Hyperbolic embedding steered spatiotemporal graph convolutional network for video-based remote heart rate estimation DOI
Hang Shao, Lei Luo, Shuo Chen

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 124, P. 106642 - 106642

Published: June 21, 2023

Language: Английский

Citations

9