Geng-Shi Jeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Geng-Shi Jeng has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Matthew O'DOnnell
Department of Bioengineering, University of Washington, 3720 15th Ave NE, Seattle, Wa 98195, USA
4 shared publications - Albert J. Sinusas
Yale University School of Medicine
2 shared publications Allen Lu
Department of Biomedical Engineering, Yale University, New Haven, CT, USA
2 shared publications- Bao-Yu Hsieh
Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
2 shared publications Chia-Lun Yeh
Hon Hai Precision Industry, New Taipei City, Taiwan
2 shared publicationsChing-Yao Lu
Institute of Electronics, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
2 shared publications
Latest Publications
- Open Access
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 5, 228-241
Simultaneous Estimation of Blood Pressure and Volume Flow Using Deep Learning- Enhanced Ultrafast Ultrasound
The simultaneous measurement of blood pressure (P) and volume flow rate (Q) is essential for a comprehensive hemodynamic assessment, yet it remains a significant technical challenge. This work presents a novel ultrasound-based system that enables the simultaneous estimation of high-resolution P and Q waveforms at the same vascular location using a single transducer. We propose a system that leverages ultrafast multi-angle plane wave imaging to acquire high-frame-rate B-mode image sequences. A machine learning optical flow model called RAFT was adapted and fine-tuned for ultrasound to perform robust vector flow imaging for Q quantification. Concurrently, an efficient 2-D speckle tracking algorithm tracks vessel wall motion to derive the diameter waveform, from which P is estimated using a calibrated exponential model. The method was evaluated in flow phantom experiments and in vivo on the carotid arteries of healthy subjects. In phantom studies, the proposed method demonstrated high accuracy, with pressure estimates achieving a root-mean-square error of 1.76 mmHg against reference sensors. Crucially, Q estimates showed improved accuracy compared to conventional color Doppler and existing vector flow imaging methods such as blood speckle tracking and multi-angle vector Doppler. In vivo results confirmed that the proposed method provides high-resolution P and Q waveforms, enabling the reliable calculation of hemodynamic energy parameters sensitive to vascular aging. This work introduces a fully ML-driven ultrasound velocimetry method integrated with blood pressure estimation from vessel wall motion, potentially enhancing the diagnosis of cardiovascular and cerebrovascular diseases.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 5, 228-241
Open AccessSimultaneous Estimation of Blood Pressure and Volume Flow Using Deep Learning- Enhanced Ultrafast Ultrasound
The simultaneous measurement of blood pressure (P) and volume flow rate (Q) is essential for a comprehensive hemodynamic assessment, yet it remains a significant technical challenge. This work presents a novel ultrasound-based system that enables the simultaneous estimation of high-resolution P and Q waveforms at the same vascular location using a single transducer. We propose a system that leverages ultrafast multi-angle plane wave imaging to acquire high-frame-rate B-mode image sequences. A machine learning optical flow model called RAFT was adapted and fine-tuned for ultrasound to perform robust vector flow imaging for Q quantification. Concurrently, an efficient 2-D speckle tracking algorithm tracks vessel wall motion to derive the diameter waveform, from which P is estimated using a calibrated exponential model. The method was evaluated in flow phantom experiments and in vivo on the carotid arteries of healthy subjects. In phantom studies, the proposed method demonstrated high accuracy, with pressure estimates achieving a root-mean-square error of 1.76 mmHg against reference sensors. Crucially, Q estimates showed improved accuracy compared to conventional color Doppler and existing vector flow imaging methods such as blood speckle tracking and multi-angle vector Doppler. In vivo results confirmed that the proposed method provides high-resolution P and Q waveforms, enabling the reliable calculation of hemodynamic energy parameters sensitive to vascular aging. This work introduces a fully ML-driven ultrasound velocimetry method integrated with blood pressure estimation from vessel wall motion, potentially enhancing the diagnosis of cardiovascular and cerebrovascular diseases.
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (23) , 43256-43266
Design of a Low-Cost, High-Resolution Underwater Acoustic Imager With Integrated Deep Learning Enhancement
- 1 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (23) , 43256-43266
Design of a Low-Cost, High-Resolution Underwater Acoustic Imager With Integrated Deep Learning Enhancement
- 16 July 2025
- Published by Elsevier in Ultrasonics
- Vol. 156, 107760
Confidence-enhanced flow trajectory imaging using speckle tracking with multi-angle plane waves
- 16 July 2025
- Published by Elsevier in Ultrasonics
- Vol. 156, 107760
Confidence-enhanced flow trajectory imaging using speckle tracking with multi-angle plane waves
- Open Access
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 5, 23-32
Contactless Respiratory Waveform Estimation Using Ultrasound Planar Array
Accurate and contactless respiratory monitoring is essential for both clinical diagnostics and home healthcare, offering the potential for continuous, non-invasive observation. Ultrasound-based systems, particularly when integrated into home smart devices, provide a cost-effective solution. However, existing approaches are limited by poor directivity, inadequate clothing penetration, reliance on averaged respiratory rates without waveform details, and the inability to measure range due to continuous-wave Doppler techniques. To address these challenges, this study develops a novel 18-kHz, 16-channel two-dimensional (2-D) ultrasound array system employing adaptive beamforming to enhance sensitivity and accuracy in respiratory waveform detection. The system integrates pulsed and frequency-modulated continuous-wave (FMCW) excitation to improve the signal-to-noise ratio (SNR) by 20 dB, while the 2-D beamforming technique directly estimates delays from respiratory movements, boosting SNR by an additional 8.5 dB and eliminating the need for time-intensive volumetric scanning. Experimental results demonstrate sub-millimeter displacement accuracy in motor-controlled plate tests, surpassing wearable inertial measurement devices, and human trials reveal an average respiratory rate error of 0.13 breaths per minute across various clothing types and distances. The proposed system not only advances remote respiratory monitoring but also paves the way for enhanced health diagnostics in both clinical and home settings.
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 5, 23-32
Open AccessContactless Respiratory Waveform Estimation Using Ultrasound Planar Array
Accurate and contactless respiratory monitoring is essential for both clinical diagnostics and home healthcare, offering the potential for continuous, non-invasive observation. Ultrasound-based systems, particularly when integrated into home smart devices, provide a cost-effective solution. However, existing approaches are limited by poor directivity, inadequate clothing penetration, reliance on averaged respiratory rates without waveform details, and the inability to measure range due to continuous-wave Doppler techniques. To address these challenges, this study develops a novel 18-kHz, 16-channel two-dimensional (2-D) ultrasound array system employing adaptive beamforming to enhance sensitivity and accuracy in respiratory waveform detection. The system integrates pulsed and frequency-modulated continuous-wave (FMCW) excitation to improve the signal-to-noise ratio (SNR) by 20 dB, while the 2-D beamforming technique directly estimates delays from respiratory movements, boosting SNR by an additional 8.5 dB and eliminating the need for time-intensive volumetric scanning. Experimental results demonstrate sub-millimeter displacement accuracy in motor-controlled plate tests, surpassing wearable inertial measurement devices, and human trials reveal an average respiratory rate error of 0.13 breaths per minute across various clothing types and distances. The proposed system not only advances remote respiratory monitoring but also paves the way for enhanced health diagnostics in both clinical and home settings.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 71  (11) , 3312-3323
Coordinate-Independent 3-D Ultrasound Principal Stretch and Direction Imaging
Objective: In clinical ultrasound, current 2-D strain imaging faces challenges in quantifying three orthogonal normal strain components. This requires separate image acquisitions based on the pixel-dependent cardiac coordinate system, leading to additional computations and estimation discrepancies due to probe orientation. Most systems lack shear strain information, as displaying all components is challenging to interpret. Methods: This paper presents a 3-D high-spatial-resolution, coordinate-independent strain imaging approach based on principal stretch and axis estimation. All strain components are transformed into three principal stretches along three normal principal axes, enabling direct visualization of the primary deformation. We devised an efficient 3-D speckle tracking method with tilt filtering, incorporating randomized searching in a two-pass tracking framework and rotating the phase of the 3-D correlation function for robust filtering. The proposed speckle tracking approach significantly improves estimates of displacement gradients related to the axial displacement component. Non-axial displacement gradient estimates are enhanced using a correlation-weighted least-squares method constrained by tissue incompressibility. Results: Simulated and in vivo canine cardiac datasets were evaluated to estimate Lagrangian strains from end-diastole to end-systole. The proposed speckle tracking method improves displacement estimation by a factor of 4.3 to 10.5 over conventional 1-pass processing. Maximum principal axis/direction imaging enables better detection of local disease regions than conventional strain imaging. Conclusion: Coordinate-independent tracking can identify myocardial abnormalities with high accuracy. Significance: This study offers enhanced accuracy and robustness in strain imaging compared to current methods.
- 28 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 71  (11) , 3312-3323
Coordinate-Independent 3-D Ultrasound Principal Stretch and Direction Imaging
Objective: In clinical ultrasound, current 2-D strain imaging faces challenges in quantifying three orthogonal normal strain components. This requires separate image acquisitions based on the pixel-dependent cardiac coordinate system, leading to additional computations and estimation discrepancies due to probe orientation. Most systems lack shear strain information, as displaying all components is challenging to interpret. Methods: This paper presents a 3-D high-spatial-resolution, coordinate-independent strain imaging approach based on principal stretch and axis estimation. All strain components are transformed into three principal stretches along three normal principal axes, enabling direct visualization of the primary deformation. We devised an efficient 3-D speckle tracking method with tilt filtering, incorporating randomized searching in a two-pass tracking framework and rotating the phase of the 3-D correlation function for robust filtering. The proposed speckle tracking approach significantly improves estimates of displacement gradients related to the axial displacement component. Non-axial displacement gradient estimates are enhanced using a correlation-weighted least-squares method constrained by tissue incompressibility. Results: Simulated and in vivo canine cardiac datasets were evaluated to estimate Lagrangian strains from end-diastole to end-systole. The proposed speckle tracking method improves displacement estimation by a factor of 4.3 to 10.5 over conventional 1-pass processing. Maximum principal axis/direction imaging enables better detection of local disease regions than conventional strain imaging. Conclusion: Coordinate-independent tracking can identify myocardial abnormalities with high accuracy. Significance: This study offers enhanced accuracy and robustness in strain imaging compared to current methods.
- 25 July 2022
- Published by AIP Publishing in Applied Physics Letters
- Vol. 121  (4) , 043702
Ultrasound shear-wave computed tomography for elasticity imaging
Shear-wave elasticity imaging (SWEI) has been routinely used for measuring the elastic properties of tissues. It is potentially applicable to three-dimensional (3D) cell culture systems and may outperform existing methods such as atomic force microscopy and shear rheology in terms of being contactless and having higher spatial resolution and penetration. However, applying clinical SWEI to 3D cell culture systems requires the developments of high-frequency SWEI systems operating at >20 MHz that are compatible with the scale of cell culture systems, and C-scan 3D SWEI well suited to such observations. In this study, we implemented a computed tomography (CT) technique for SWEI (called SWCT) by leveraging the scanning scheme used in first-generation x-ray CT systems, that is, translation and rotation of a 20-MHz push probe and a 40-MHz imaging probe to obtain time-of-flight projections for multiple viewing directions. Compared with conventional B-scan SWEI, the proposed reconstruction method allows high-resolution, robust, 3D C-scan imaging of the shear-wave speed distribution. Three phantoms with different inclusions (half circle, thin strip, and cylinder) were imaged using 3D SWCT to a depth of 13 mm. The estimated shear-wave speed for the strip phantom using SWCT was 1.23 ± 0.20 m/s (mean ± standard deviation) in the background and 2.27 ± 0.11 m/s for the inclusion, which suggests the feasibility of SWCT for improving elasticity measurements of cell culture systems.
- 25 July 2022
- Published by AIP Publishing in Applied Physics Letters
- Vol. 121  (4) , 043702
Ultrasound shear-wave computed tomography for elasticity imaging
Shear-wave elasticity imaging (SWEI) has been routinely used for measuring the elastic properties of tissues. It is potentially applicable to three-dimensional (3D) cell culture systems and may outperform existing methods such as atomic force microscopy and shear rheology in terms of being contactless and having higher spatial resolution and penetration. However, applying clinical SWEI to 3D cell culture systems requires the developments of high-frequency SWEI systems operating at >20 MHz that are compatible with the scale of cell culture systems, and C-scan 3D SWEI well suited to such observations. In this study, we implemented a computed tomography (CT) technique for SWEI (called SWCT) by leveraging the scanning scheme used in first-generation x-ray CT systems, that is, translation and rotation of a 20-MHz push probe and a 40-MHz imaging probe to obtain time-of-flight projections for multiple viewing directions. Compared with conventional B-scan SWEI, the proposed reconstruction method allows high-resolution, robust, 3D C-scan imaging of the shear-wave speed distribution. Three phantoms with different inclusions (half circle, thin strip, and cylinder) were imaged using 3D SWCT to a depth of 13 mm. The estimated shear-wave speed for the strip phantom using SWCT was 1.23 ± 0.20 m/s (mean ± standard deviation) in the background and 2.27 ± 0.11 m/s for the inclusion, which suggests the feasibility of SWCT for improving elasticity measurements of cell culture systems.
- Open Access
- 31 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40  (9) , 2233-2245
Learning-Based Regularization for Cardiac Strain Analysis via Domain Adaptation
Reliable motion estimation and strain analysis using 3D+ time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions. However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates. In this work, we incorporated the notion of domain adaptation into a supervised neural network regularization framework. We first propose a semi-supervised Multi-Layered Perceptron (MLP) network with biomechanical constraints for learning a latent representation that is shown to have more physiologically plausible displacements. We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation. We validated the semi-supervised regularization method on in vivo data with implanted sonomicrometers. Finally, we showed the ability of our semi-supervised learning regularization approach to identify infarct regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.
- 31 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40  (9) , 2233-2245
Open AccessLearning-Based Regularization for Cardiac Strain Analysis via Domain Adaptation
Reliable motion estimation and strain analysis using 3D+ time echocardiography (4DE) for localization and characterization of myocardial injury is valuable for early detection and targeted interventions. However, motion estimation is difficult due to the low-SNR that stems from the inherent image properties of 4DE, and intelligent regularization is critical for producing reliable motion estimates. In this work, we incorporated the notion of domain adaptation into a supervised neural network regularization framework. We first propose a semi-supervised Multi-Layered Perceptron (MLP) network with biomechanical constraints for learning a latent representation that is shown to have more physiologically plausible displacements. We extended this framework to include a supervised loss term on synthetic data and showed the effects of biomechanical constraints on the network's ability for domain adaptation. We validated the semi-supervised regularization method on in vivo data with implanted sonomicrometers. Finally, we showed the ability of our semi-supervised learning regularization approach to identify infarct regions using estimated regional strain maps with good agreement to manually traced infarct regions from postmortem excised hearts.
- 29 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 68  (7) , 2496-2506
Laser-Generated Leaky Acoustic Wave Imaging for Interventional Guidewire Guidance
Ultrasound (US) is widely used to visualize both tissue and the positions of surgical instruments in real time during surgery. Previously we proposed a new method to exploit US imaging and laser-generated leaky acoustic waves for needle visualization. Although successful, that method only detects the position of a needle tip, with the location of the entire needle deduced from knowing that the needle is straight. The purpose of the current study was to develop a beamforming-based method for the direct visualization of objects. The approach can be applied to objects with arbitrary shapes, such as the guidewires that are commonly used in interventional guidance. With this method, illumination by a short laser pulse generates photoacoustic waves at the top of the guidewire that propagate down its metal surface. These waves then leak into the surrounding tissue, which can be detected by an US array transducer. The time of flight consists of two parts: (1) the propagation time of the guided waves on the guidewire and (2) the propagation time of the US that leaks into the tissue. In principle, an image of the guidewire can be formed based on array beamforming by taking the propagation time on the metal into consideration. Furthermore, we introduced directional filtering and a matched filter to compress the dispersion signal associated with long propagation times. The results showed that guidewires could be detected at depths of at least 70 mm. The maximum detectable angle was 56.3°. Leaky acoustic wave imaging with a 1268-mm long guidewire was also demonstrated. The proposed method has considerable potential in new clinical applications.
- 29 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 68  (7) , 2496-2506
Laser-Generated Leaky Acoustic Wave Imaging for Interventional Guidewire Guidance
Ultrasound (US) is widely used to visualize both tissue and the positions of surgical instruments in real time during surgery. Previously we proposed a new method to exploit US imaging and laser-generated leaky acoustic waves for needle visualization. Although successful, that method only detects the position of a needle tip, with the location of the entire needle deduced from knowing that the needle is straight. The purpose of the current study was to develop a beamforming-based method for the direct visualization of objects. The approach can be applied to objects with arbitrary shapes, such as the guidewires that are commonly used in interventional guidance. With this method, illumination by a short laser pulse generates photoacoustic waves at the top of the guidewire that propagate down its metal surface. These waves then leak into the surrounding tissue, which can be detected by an US array transducer. The time of flight consists of two parts: (1) the propagation time of the guided waves on the guidewire and (2) the propagation time of the US that leaks into the tissue. In principle, an image of the guidewire can be formed based on array beamforming by taking the propagation time on the metal into consideration. Furthermore, we introduced directional filtering and a matched filter to compress the dispersion signal associated with long propagation times. The results showed that guidewires could be detected at depths of at least 70 mm. The maximum detectable angle was 56.3°. Leaky acoustic wave imaging with a 1268-mm long guidewire was also demonstrated. The proposed method has considerable potential in new clinical applications.
- Open Access
- 29 January 2021
- Published by Springer Nature in Nature Communications
- Vol. 12  (1) , 1-12
Real-time interleaved spectroscopic photoacoustic and ultrasound (PAUS) scanning with simultaneous fluence compensation and motion correction
For over two decades photoacoustic imaging has been tested clinically, but successful human trials have been limited. To enable quantitative clinical spectroscopy, the fundamental issues of wavelength-dependent fluence variations and inter-wavelength motion must be overcome. Here we propose a real-time, spectroscopic photoacoustic/ultrasound (PAUS) imaging approach using a compact, 1-kHz rate wavelength-tunable laser. Instead of illuminating tissue over a large area, the fiber-optic delivery system surrounding an US array sequentially scans a narrow laser beam, with partial PA image reconstruction for each laser pulse. The final image is then formed by coherently summing partial images. This scheme enables (i) automatic compensation for wavelength-dependent fluence variations in spectroscopic PA imaging and (ii) motion correction of spectroscopic PA frames using US speckle tracking in real-time systems. The 50-Hz video rate PAUS system is demonstrated in vivo using a murine model of labelled drug delivery.
- 29 January 2021
- Published by Springer Nature in Nature Communications
- Vol. 12  (1) , 1-12
Open AccessReal-time interleaved spectroscopic photoacoustic and ultrasound (PAUS) scanning with simultaneous fluence compensation and motion correction
For over two decades photoacoustic imaging has been tested clinically, but successful human trials have been limited. To enable quantitative clinical spectroscopy, the fundamental issues of wavelength-dependent fluence variations and inter-wavelength motion must be overcome. Here we propose a real-time, spectroscopic photoacoustic/ultrasound (PAUS) imaging approach using a compact, 1-kHz rate wavelength-tunable laser. Instead of illuminating tissue over a large area, the fiber-optic delivery system surrounding an US array sequentially scans a narrow laser beam, with partial PA image reconstruction for each laser pulse. The final image is then formed by coherently summing partial images. This scheme enables (i) automatic compensation for wavelength-dependent fluence variations in spectroscopic PA imaging and (ii) motion correction of spectroscopic PA frames using US speckle tracking in real-time systems. The 50-Hz video rate PAUS system is demonstrated in vivo using a murine model of labelled drug delivery.
- Top Cited Papers
- 28 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39  (11) , 3379-3390
Deep-Learning Image Reconstruction for Real-Time Photoacoustic System
Recent advances in photoacoustic (PA) imaging have enabled detailed images of microvascular structure and quantitative measurement of blood oxygenation or perfusion. Standard reconstruction methods for PA imaging are based on solving an inverse problem using appropriate signal and system models. For handheld scanners, however, the ill-posed conditions of limited detection view and bandwidth yield low image contrast and severe structure loss in most instances. In this paper, we propose a practical reconstruction method based on a deep convolutional neural network (CNN) to overcome those problems. It is designed for real-time clinical applications and trained by large-scale synthetic data mimicking typical microvessel networks. Experimental results using synthetic and real datasets confirm that the deep-learning approach provides superior reconstructions compared to conventional methods.
- 28 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39  (11) , 3379-3390
Top Cited PapersDeep-Learning Image Reconstruction for Real-Time Photoacoustic System
Recent advances in photoacoustic (PA) imaging have enabled detailed images of microvascular structure and quantitative measurement of blood oxygenation or perfusion. Standard reconstruction methods for PA imaging are based on solving an inverse problem using appropriate signal and system models. For handheld scanners, however, the ill-posed conditions of limited detection view and bandwidth yield low image contrast and severe structure loss in most instances. In this paper, we propose a practical reconstruction method based on a deep convolutional neural network (CNN) to overcome those problems. It is designed for real-time clinical applications and trained by large-scale synthetic data mimicking typical microvessel networks. Experimental results using synthetic and real datasets confirm that the deep-learning approach provides superior reconstructions compared to conventional methods.