Zhangxing Bian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhangxing Bian has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Yihao Liu
Vanderbilt University
7 shared publications - Aaron Carass
Johns Hopkins University
6 shared publications - Jerry L. Prince
Johns Hopkins University
6 shared publications - Shuwen Wei
Johns Hopkins University
6 shared publications Aaron Carass
Johns Hopkins University
5 shared publicationsJerry L. Prince
Johns Hopkins University
5 shared publications
Latest Publications
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP  (02780062) , 1
DSHARP: Deep Incompressible Motion Estimation with Sinusoidal-transformed Harmonic Phase for Tagged MRI
Tagged magnetic resonance imaging (tMRI) is a valuable tool for visualizing and quantifying tissue deformation in vivo. Its use is often hampered, however, by tag fading, long computation times, and the challenge of ensuring diffeomorphic, incompressible motion fields. In this paper, we describe a novel integration of the harmonic phase (HARP) approach to tMRI analysis with an unsupervised deep learning-based registration framework to estimate 2D and 3D motion fields that are diffeomorphic and nearly incompressible. The resulting method, called deep sinusoidally transformed HARP, or DSHARP, enables end-to-end network training by implementing a transformation of the harmonic phase to remove phase-wrapping discontinuities. It produces diffeomorphic motion by estimating a stationary velocity field from which motion is computed using the scaling and squaring technique. Finally, it encourages incompressibility using a novel Jacobian determinant loss term during network training. We evaluated DSHARP on 2D and 3D phantom data with simulated incompressible motions, real 3D human tongue data acquired during speech from both healthy and glossectomy subjects, and cardiac tagged MRI from the public STACOM 2011 benchmark. Our approach outperforms HARP, SinMod, SyN, PVIRA, VoxelMorph, and DeepTag in tracking accuracy, computation speed, and preservation of incompressibility.
- 15 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP  (02780062) , 1
DSHARP: Deep Incompressible Motion Estimation with Sinusoidal-transformed Harmonic Phase for Tagged MRI
Tagged magnetic resonance imaging (tMRI) is a valuable tool for visualizing and quantifying tissue deformation in vivo. Its use is often hampered, however, by tag fading, long computation times, and the challenge of ensuring diffeomorphic, incompressible motion fields. In this paper, we describe a novel integration of the harmonic phase (HARP) approach to tMRI analysis with an unsupervised deep learning-based registration framework to estimate 2D and 3D motion fields that are diffeomorphic and nearly incompressible. The resulting method, called deep sinusoidally transformed HARP, or DSHARP, enables end-to-end network training by implementing a transformation of the harmonic phase to remove phase-wrapping discontinuities. It produces diffeomorphic motion by estimating a stationary velocity field from which motion is computed using the scaling and squaring technique. Finally, it encourages incompressibility using a novel Jacobian determinant loss term during network training. We evaluated DSHARP on 2D and 3D phantom data with simulated incompressible motions, real 3D human tongue data acquired during speech from both healthy and glossectomy subjects, and cardiac tagged MRI from the public STACOM 2011 benchmark. Our approach outperforms HARP, SinMod, SyN, PVIRA, VoxelMorph, and DeepTag in tracking accuracy, computation speed, and preservation of incompressibility.
- 24 November 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 108, 103887
Unsupervised learning of spatially varying regularization for diffeomorphic image registration
- 24 November 2025
- Published by Elsevier in Medical Image Analysis
- Vol. 108, 103887
Unsupervised learning of spatially varying regularization for diffeomorphic image registration
- 19 September 2025
- Published by Springer Nature
- Vol. 15963, 661-671
Unsupervised OCT Image Interpolation Using Deformable Registration and generative models
Optical coherence tomography (OCT) images are often acquired as highly anisotropic volumes, where the scanning step is dense along the fast axis but sparse along the slow axis. This affects image analysis, such as image registration for longitudinal alignment. To create more isotropic volumes, bicubic interpolation can be used along the slow axis, but it generally produces blurry features. Registration-based interpolation can reduce blurriness, but often fails to generate realistic OCT images. Deep generative models can sample realistic images, but lack the structural consistency constraints required for interpolation. In this paper, we propose an unsupervised image interpolation method that combines registration-based interpolation with a deep generative model to overcome their individual limitations and improve the structural accuracy and realism of interpolated OCT images. We compare the proposed method with both bicubic and registration-based interpolation on real OCT datasets, and show that it achieves the best interpolation performance.
- 19 September 2025
- Published by Springer Nature
- Vol. 15963, 661-671
Unsupervised OCT Image Interpolation Using Deformable Registration and generative models
Optical coherence tomography (OCT) images are often acquired as highly anisotropic volumes, where the scanning step is dense along the fast axis but sparse along the slow axis. This affects image analysis, such as image registration for longitudinal alignment. To create more isotropic volumes, bicubic interpolation can be used along the slow axis, but it generally produces blurry features. Registration-based interpolation can reduce blurriness, but often fails to generate realistic OCT images. Deep generative models can sample realistic images, but lack the structural consistency constraints required for interpolation. In this paper, we propose an unsupervised image interpolation method that combines registration-based interpolation with a deep generative model to overcome their individual limitations and improve the structural accuracy and realism of interpolated OCT images. We compare the proposed method with both bicubic and registration-based interpolation on real OCT datasets, and show that it achieves the best interpolation performance.
- 7 August 2025
- Published by Springer Nature
- Vol. 15830, 375-389
Brightness-Invariant Tracking Estimation in Tagged MRI
Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.
- 7 August 2025
- Published by Springer Nature
- Vol. 15830, 375-389
Brightness-Invariant Tracking Estimation in Tagged MRI
Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.
- Open Access
Brightness-Invariant Tracking Estimation in Tagged MRI
Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.
Open AccessBrightness-Invariant Tracking Estimation in Tagged MRI
Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.
- Top Cited Papers
- 10 November 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 100, 103385
A survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond
- 10 November 2024
- Published by Elsevier in Medical Image Analysis
- Vol. 100, 103385
Top Cited PapersA survey on deep learning in medical image registration: New technologies, uncertainty, evaluation metrics, and beyond
- Open Access
Is Registering Raw Tagged-MR Enough for Strain Estimation in the Era of Deep Learning?
Magnetic Resonance Imaging with tagging (tMRI) has long been utilized for quantifying tissue motion and strain during deformation. However, a phenomenon known as tag fading, a gradual decrease in tag visibility over time, often complicates post-processing. The first contribution of this study is to model tag fading by considering the interplay between $T_1$ relaxation and the repeated application of radio frequency (RF) pulses during serial imaging sequences. This is a factor that has been overlooked in prior research on tMRI post-processing. Further, we have observed an emerging trend of utilizing raw tagged MRI within a deep learning-based (DL) registration framework for motion estimation. In this work, we evaluate and analyze the impact of commonly used image similarity objectives in training DL registrations on raw tMRI. This is then compared with the Harmonic Phase-based approach, a traditional approach which is claimed to be robust to tag fading. Our findings, derived from both simulated images and an actual phantom scan, reveal the limitations of various similarity losses in raw tMRI and emphasize caution in registration tasks where image intensity changes over time.Open AccessIs Registering Raw Tagged-MR Enough for Strain Estimation in the Era of Deep Learning?
Magnetic Resonance Imaging with tagging (tMRI) has long been utilized for quantifying tissue motion and strain during deformation. However, a phenomenon known as tag fading, a gradual decrease in tag visibility over time, often complicates post-processing. The first contribution of this study is to model tag fading by considering the interplay between $T_1$ relaxation and the repeated application of radio frequency (RF) pulses during serial imaging sequences. This is a factor that has been overlooked in prior research on tMRI post-processing. Further, we have observed an emerging trend of utilizing raw tagged MRI within a deep learning-based (DL) registration framework for motion estimation. In this work, we evaluate and analyze the impact of commonly used image similarity objectives in training DL registrations on raw tMRI. This is then compared with the Harmonic Phase-based approach, a traditional approach which is claimed to be robust to tag fading. Our findings, derived from both simulated images and an actual phantom scan, reveal the limitations of various similarity losses in raw tMRI and emphasize caution in registration tasks where image intensity changes over time. - 16 September 2023
- Published by Springer Nature
- Vol. 14096, 42-51
Recurrent Self Fusion: Iterative Denoising for Consistent Retinal OCT Segmentation
Optical coherence tomography (OCT) is a valuable imaging technique in ophthalmology, providing high-resolution, cross-sectional images of the retina for early detection and monitoring of various retinal and neurological diseases. However, discrepancies in retinal layer thickness measurements among different OCT devices pose challenges for data comparison and interpretation, particularly in longitudinal analyses. This work introduces the idea of a recurrent self fusion (RSF) algorithm to address this issue. Our RSF algorithm, built upon the self fusion methodology, iteratively denoises retinal OCT images. A deep learning-based retinal OCT segmentation algorithm is employed for downstream analyses. A large dataset of paired OCT scans acquired on both a Spectralis and Cirrus OCT device are used for validation. The results demonstrate that the RSF algorithm effectively reduces speckle contrast and enhances the consistency of retinal OCT segmentation. Keywords Optical coherence tomography Denoise Segmentation
- 16 September 2023
- Published by Springer Nature
- Vol. 14096, 42-51
Recurrent Self Fusion: Iterative Denoising for Consistent Retinal OCT Segmentation
Optical coherence tomography (OCT) is a valuable imaging technique in ophthalmology, providing high-resolution, cross-sectional images of the retina for early detection and monitoring of various retinal and neurological diseases. However, discrepancies in retinal layer thickness measurements among different OCT devices pose challenges for data comparison and interpretation, particularly in longitudinal analyses. This work introduces the idea of a recurrent self fusion (RSF) algorithm to address this issue. Our RSF algorithm, built upon the self fusion methodology, iteratively denoises retinal OCT images. A deep learning-based retinal OCT segmentation algorithm is employed for downstream analyses. A large dataset of paired OCT scans acquired on both a Spectralis and Cirrus OCT device are used for validation. The results demonstrate that the RSF algorithm effectively reduces speckle contrast and enhances the consistency of retinal OCT segmentation. Keywords Optical coherence tomography Denoise Segmentation
- Open Access
- 1 September 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10  (05) , 051810-12
Fully automated pipeline for measurement of the thoracic aorta using joint segmentation and localization neural network
Thoracic aortic aneurysm (TAA) is a common disease affecting between 1% and 3% of the United States population over the age of 50, which is characterized by enlargement of the largest artery in the body (i.e., the thoracic aorta) as a result of weakening of the aortic wall.1 TAA is a largely silent disease until potentially fatal complications, such as rupture, occur. Patients with TAA undergo regular surveillance imaging using computed tomography angiography (CTA) to monitor the overall size of their aneurysm and to detect growth, assessments that in turn determine the need for surgical repair.2 Aortic diameter measurements are used to assess TAA, with measurements performed on volumetric CTA imaging data by manual analysts (i.e., technologists or the physicians themselves) using dedicated three-dimensional (3D) image rendering software. Diameter measurements are made in standardized anatomic locations along the length of the aorta to minimize measurement variability and ensure comparability of measurements across time.3,4
- 1 September 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10  (05) , 051810-12
Open AccessFully automated pipeline for measurement of the thoracic aorta using joint segmentation and localization neural network
Thoracic aortic aneurysm (TAA) is a common disease affecting between 1% and 3% of the United States population over the age of 50, which is characterized by enlargement of the largest artery in the body (i.e., the thoracic aorta) as a result of weakening of the aortic wall.1 TAA is a largely silent disease until potentially fatal complications, such as rupture, occur. Patients with TAA undergo regular surveillance imaging using computed tomography angiography (CTA) to monitor the overall size of their aneurysm and to detect growth, assessments that in turn determine the need for surgical repair.2 Aortic diameter measurements are used to assess TAA, with measurements performed on volumetric CTA imaging data by manual analysts (i.e., technologists or the physicians themselves) using dedicated three-dimensional (3D) image rendering software. Diameter measurements are made in standardized anatomic locations along the length of the aorta to minimize measurement variability and ensure comparability of measurements across time.3,4
- Open Access
DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue
Tagged magnetic resonance imaging~(MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available: https://github.com/jasonbian97/DRIMET-tagged-MRI
Open AccessDRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue
Tagged magnetic resonance imaging~(MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. However, this technique faces several challenges such as tag fading, large motion, long computation times, and difficulties in obtaining diffeomorphic incompressible flow fields. To address these issues, this paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI. We introduce two key innovations. First, we apply a sinusoidal transformation to the harmonic phase input, which enables end-to-end training and avoids the need for phase interpolation. Second, we propose a Jacobian determinant-based learning objective to encourage incompressible flow fields for deforming biological tissues. Our method efficiently estimates 3D motion fields that are accurate, dense, and approximately diffeomorphic and incompressible. The efficacy of the method is assessed using human tongue motion during speech, and includes both healthy controls and patients that have undergone glossectomy. We show that the method outperforms existing approaches, and also exhibits improvements in speed, robustness to tag fading, and large tongue motion. The code is available: https://github.com/jasonbian97/DRIMET-tagged-MRI