Xinzeng Wang
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
Xinzeng Wang has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Patricia Lan
GE Healthcare, Menlo Park, CA, USA
4 shared publications - Chia-Wei Li
Department of Radiology, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan
2 shared publications - Jingfei Ma
Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA
2 shared publications - Ken-Pin Hwang
Department of Imaging Physics The University of Texas MD Anderson Cancer Center Houston Texas USA
2 shared publications - Nir Stanietzky
The University of Texas, MD Anderson Cancer Center, Department of Abdominal Imaging, Texas, USA
2 shared publications Randy Ernst
Department of Radiology The University of Texas MD Anderson Cancer Center Houston Texas USA
2 shared publications
Latest Publications
- Open Access
- 1 July 2026
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 16 (7) , 537
Impact of deep-learning image reconstruction on multiplexed sensitivity encoding diffusion-weighted imaging in the female pelvis
Background: Diffusion-weighted imaging (DWI) in the female pelvis is degraded by artefacts. The study aimed to evaluate the impact of deep-learning image reconstruction (DLRecon) on the image quality of multiplexed sensitivity encoding (MUSE) DWI in the female pelvis. Methods: Female patients scheduled for pelvic magnetic resonance imaging (MRI) with 2-shot MUSE DWI were prospectively recruited. A subset of patients underwent paired 4-shot MUSE DWI. Images were qualitatively reviewed by two radiologists in terms of overall image quality, artefacts, lesions conspicuity and sharpness using a 5-point scale, with and without DLRecon. Intra-observer and inter-observer agreements were evaluated. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient (ADC) of normal structures and lesions were quantitatively compared between 2-shot MUSE with and without DLRecon. Statistical analyses were performed using Cohen’s kappa, Wilcoxon signed-rank test and paired-sample t-test with Bonferroni correction. Results: Among the 65 female patients evaluated, 27 malignant lesions and 32 benign lesions were detected, while no pathology was found in 6 patients. DLRecon significantly improved the image quality in all aspects evaluated compared to 2-shot MUSE without DLRecon: overall image quality, artefacts, lesions conspicuity and sharpness (N=65, PConclusions: DLRecon improved image quality of MUSE DWI in the female pelvis by reducing impact of artefacts, improving lesion conspicuity and image sharpness, while increasing SNR and CNR but preserving the stability of ADC quantification.
- 1 July 2026
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 16 (7) , 537
Open AccessImpact of deep-learning image reconstruction on multiplexed sensitivity encoding diffusion-weighted imaging in the female pelvis
Background: Diffusion-weighted imaging (DWI) in the female pelvis is degraded by artefacts. The study aimed to evaluate the impact of deep-learning image reconstruction (DLRecon) on the image quality of multiplexed sensitivity encoding (MUSE) DWI in the female pelvis. Methods: Female patients scheduled for pelvic magnetic resonance imaging (MRI) with 2-shot MUSE DWI were prospectively recruited. A subset of patients underwent paired 4-shot MUSE DWI. Images were qualitatively reviewed by two radiologists in terms of overall image quality, artefacts, lesions conspicuity and sharpness using a 5-point scale, with and without DLRecon. Intra-observer and inter-observer agreements were evaluated. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient (ADC) of normal structures and lesions were quantitatively compared between 2-shot MUSE with and without DLRecon. Statistical analyses were performed using Cohen’s kappa, Wilcoxon signed-rank test and paired-sample t-test with Bonferroni correction. Results: Among the 65 female patients evaluated, 27 malignant lesions and 32 benign lesions were detected, while no pathology was found in 6 patients. DLRecon significantly improved the image quality in all aspects evaluated compared to 2-shot MUSE without DLRecon: overall image quality, artefacts, lesions conspicuity and sharpness (N=65, PConclusions: DLRecon improved image quality of MUSE DWI in the female pelvis by reducing impact of artefacts, improving lesion conspicuity and image sharpness, while increasing SNR and CNR but preserving the stability of ADC quantification.
- Open Access
- 3 March 2026
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 3 (2)
Improved prostate diffusion imaging using deep learning denoising and phase correction with ultra-high-density coil array
Background: MR diffusion-weighted imaging (DWI), especially at high b-value, is a key acquisition to help identify clinically significant prostate cancer; however, it suffers from low signal-to-noise ratio (SNR), high noise floor, and susceptibility artifact. Purpose: To demonstrate the feasibility of improving DWI quality using a novel 50-channel pelvic coil in conjunction with a deep learning (DL)-based phase correction and a DL-denoising algorithm. Methods: In this prospective, single-center study, 24 consecutive men referred for prostate multiparametric MRI over 16 months were enrolled (age 47–79 years; mean, 68.1 years). Axial T2-weighted images and DWI were obtained using a prototype 50‑channel coil and standard clinical phased array (3 T Architect, GE HealthCare, USA). The DWI acquisitions were reconstructed with the vendor’s deep learning denoising algorithm (ARDL). The same raw data were reconstructed offline using an investigational DL Phase Correction algorithm with ARDL (DLPC+ARDL). Two independent readers scored DWI and ADC series using 4 qualitative criteria. SNR and contrast-to-noise ratio (CNR) were measured on b = 1500 s/mm2 images. Combined reader scores were compared using the Wilcoxon matched‑pairs signed‑rank test, inter‑reader variability was assessed using Cohen’s κ, and quantitative SNR/CNR values were compared using 2‑tailed paired t‑tests. Results: Twenty men were analyzable for qualitative and 18 for quantitative metrics (reported as mean ± SD). 50‑channel pelvic coil with DLPC+ARDL produced the highest SNR (99.70 ± 28.50) and CNR (91.68 ± 44.39), exceeding 50‑channel with ARDL alone (SNR 56.44 ± 28.50; CNR 51.11 ± 28.67), 30‑channel anterior array with ARDL (SNR 31.41 ± 13.18; CNR 26.26 ± 13.52), and DLPC + ARDL (SNR 49.4 ± 18.6; CNR 44.7 ± 18.3) (all P < .0001). Reader scores favored DLPC+ARDL in prostate border definition, peripheral/transition zone distinction, lesion conspicuity, and confidence of extraprostatic extension (all P values for DWI at b = 1500 s/mm2 < 0.0001; synthetic DWI at b = 2000 s/mm2: P = 7.5 × 10−7–0.01). Inter‑reader agreement was fair for acquired DWI (quadratic‑weighted κ = 0.34) and lower for synthetic DWI (κ = 0.19). Conclusion: DWI images acquired using the 50‑channel pelvic coil and reconstructed with the DLPC + ARDL pipeline yield the highest image quality compared to ARDL only pipeline and to all 30-channel coil imaging.
- 3 March 2026
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 3 (2)
Open AccessImproved prostate diffusion imaging using deep learning denoising and phase correction with ultra-high-density coil array
Background: MR diffusion-weighted imaging (DWI), especially at high b-value, is a key acquisition to help identify clinically significant prostate cancer; however, it suffers from low signal-to-noise ratio (SNR), high noise floor, and susceptibility artifact. Purpose: To demonstrate the feasibility of improving DWI quality using a novel 50-channel pelvic coil in conjunction with a deep learning (DL)-based phase correction and a DL-denoising algorithm. Methods: In this prospective, single-center study, 24 consecutive men referred for prostate multiparametric MRI over 16 months were enrolled (age 47–79 years; mean, 68.1 years). Axial T2-weighted images and DWI were obtained using a prototype 50‑channel coil and standard clinical phased array (3 T Architect, GE HealthCare, USA). The DWI acquisitions were reconstructed with the vendor’s deep learning denoising algorithm (ARDL). The same raw data were reconstructed offline using an investigational DL Phase Correction algorithm with ARDL (DLPC+ARDL). Two independent readers scored DWI and ADC series using 4 qualitative criteria. SNR and contrast-to-noise ratio (CNR) were measured on b = 1500 s/mm2 images. Combined reader scores were compared using the Wilcoxon matched‑pairs signed‑rank test, inter‑reader variability was assessed using Cohen’s κ, and quantitative SNR/CNR values were compared using 2‑tailed paired t‑tests. Results: Twenty men were analyzable for qualitative and 18 for quantitative metrics (reported as mean ± SD). 50‑channel pelvic coil with DLPC+ARDL produced the highest SNR (99.70 ± 28.50) and CNR (91.68 ± 44.39), exceeding 50‑channel with ARDL alone (SNR 56.44 ± 28.50; CNR 51.11 ± 28.67), 30‑channel anterior array with ARDL (SNR 31.41 ± 13.18; CNR 26.26 ± 13.52), and DLPC + ARDL (SNR 49.4 ± 18.6; CNR 44.7 ± 18.3) (all P < .0001). Reader scores favored DLPC+ARDL in prostate border definition, peripheral/transition zone distinction, lesion conspicuity, and confidence of extraprostatic extension (all P values for DWI at b = 1500 s/mm2 < 0.0001; synthetic DWI at b = 2000 s/mm2: P = 7.5 × 10−7–0.01). Inter‑reader agreement was fair for acquired DWI (quadratic‑weighted κ = 0.34) and lower for synthetic DWI (κ = 0.19). Conclusion: DWI images acquired using the 50‑channel pelvic coil and reconstructed with the DLPC + ARDL pipeline yield the highest image quality compared to ARDL only pipeline and to all 30-channel coil imaging.
- 18 February 2026
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 95 (6) , 3322-3332
Human Brain High‐Resolution Diffusion MRI With Optimized, Slice‐By‐Slice, Zeroth and First Order B0 Shimming in Head‐Only High‐Gradient MRI Systems
Purpose: To propose a brain tissue‐selective, optimized slice‐by‐slice shimming for high‐resolution brain diffusion MRI. Methods: We incorporated actual gradient fields of the , , and imaging gradient coils, which are already designed for fast switching and accessible to any MRI system, in the calculation of the shimming coefficients in dynamic slice‐by‐slice shimming to minimize field inhomogeneity (i.e., ) in deep‐learning segmented brain tissues. Diffusion MRI with oscillating gradient spin echo (OGSE) at 55 Hz and pulsed gradient spin echo (PGSE) (approximated at 0 Hz) were obtained in phantoms and healthy volunteers using a head‐only high‐gradient 3T MRI system. In each diffusion MRI acquisition, standard static volumetric shimming and the proposed shimming were applied separately, and mean/axial/radial diffusivities (MD/AD/RD) and fractional anisotropy (FA) were estimated. Results: Compared to static shimming, dynamic shimming reduced the root‐mean‐square of voxel displacement of each slice by a maximum of 5–10 voxels in single‐shot EPI acquisition at 1–2 mm in‐plane resolution in the phantom, and a maximum of 3 voxels in human brains. Improved accuracy of MD/AD/RD/FA in the frontal lobe, brainstem, and cerebellum was observed by applying dynamic shimming and/or two‐shot EPI acquisition. MD (55 Hz)–MD (0 Hz) showed higher values in FSE hypo‐intensity region by applying dynamic shimming. Furthermore, in phantom, the root‐mean‐square of in areas with high gradient nonlinearity was reduced by 7 Hz when incorporating the actual gradient field in dynamic shimming. Conclusion: Diffusion MRI with brain tissue‐selective, dynamic slice‐by‐slice effectively improves diffusivity characterization in high‐resolution images.
- 18 February 2026
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 95 (6) , 3322-3332
Human Brain High‐Resolution Diffusion MRI With Optimized, Slice‐By‐Slice, Zeroth and First Order B0 Shimming in Head‐Only High‐Gradient MRI Systems
Purpose: To propose a brain tissue‐selective, optimized slice‐by‐slice shimming for high‐resolution brain diffusion MRI. Methods: We incorporated actual gradient fields of the , , and imaging gradient coils, which are already designed for fast switching and accessible to any MRI system, in the calculation of the shimming coefficients in dynamic slice‐by‐slice shimming to minimize field inhomogeneity (i.e., ) in deep‐learning segmented brain tissues. Diffusion MRI with oscillating gradient spin echo (OGSE) at 55 Hz and pulsed gradient spin echo (PGSE) (approximated at 0 Hz) were obtained in phantoms and healthy volunteers using a head‐only high‐gradient 3T MRI system. In each diffusion MRI acquisition, standard static volumetric shimming and the proposed shimming were applied separately, and mean/axial/radial diffusivities (MD/AD/RD) and fractional anisotropy (FA) were estimated. Results: Compared to static shimming, dynamic shimming reduced the root‐mean‐square of voxel displacement of each slice by a maximum of 5–10 voxels in single‐shot EPI acquisition at 1–2 mm in‐plane resolution in the phantom, and a maximum of 3 voxels in human brains. Improved accuracy of MD/AD/RD/FA in the frontal lobe, brainstem, and cerebellum was observed by applying dynamic shimming and/or two‐shot EPI acquisition. MD (55 Hz)–MD (0 Hz) showed higher values in FSE hypo‐intensity region by applying dynamic shimming. Furthermore, in phantom, the root‐mean‐square of in areas with high gradient nonlinearity was reduced by 7 Hz when incorporating the actual gradient field in dynamic shimming. Conclusion: Diffusion MRI with brain tissue‐selective, dynamic slice‐by‐slice effectively improves diffusivity characterization in high‐resolution images.
- 16 September 2025
- Published by Elsevier in European Journal of Radiology
- Vol. 193, 112419
Deep learning based multi-shot breast diffusion MRI: Improving imaging quality and reduced distortion
- 16 September 2025
- Published by Elsevier in European Journal of Radiology
- Vol. 193, 112419
Deep learning based multi-shot breast diffusion MRI: Improving imaging quality and reduced distortion
- Open Access
- 20 February 2025
- Published by Wiley in Journal of Applied Clinical Medical Physics
- Vol. 26 (5) , e70031
T2‐weighted imaging of rectal cancer using a 3D fast spin echo sequence with and without deep learning reconstruction: A reader study
Purpose: To compare image quality and clinical utility of a T2‐weighted (T2W) 3‐dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional reconstruction for rectal magnetic resonance imaging (MRI).Methods: The study included 50 patients with rectal cancer who underwent rectal MRI consecutively between July 7, 2020 and January 20, 2021 using a T2W 3D FSE sequence with DLR and conventional reconstruction. Three radiologists reviewed the two sets of images, scoring overall SNR, motion artifacts, and overall image quality on a 3‐point scale and indicating clinical preference for DLR or conventional reconstruction based on those three criteria as well as image characterization of bowel wall layer definition, tumor invasion of muscularis propria, residual disease, fibrosis, nodal margin, and extramural venous invasion.Results: Image quality was rated as moderate or good for both DLR and conventional reconstruction for most cases. DLR was preferred over conventional reconstruction in all of the categories except for bowel wall layer definition.Conclusion: Both conventional reconstruction and DLR provide acceptable image quality for T2W 3D FSE imaging of rectal cancer. DLR was clinically preferred over conventional reconstruction in almost all categories.
- 20 February 2025
- Published by Wiley in Journal of Applied Clinical Medical Physics
- Vol. 26 (5) , e70031
Open AccessT2‐weighted imaging of rectal cancer using a 3D fast spin echo sequence with and without deep learning reconstruction: A reader study
Purpose: To compare image quality and clinical utility of a T2‐weighted (T2W) 3‐dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional reconstruction for rectal magnetic resonance imaging (MRI).Methods: The study included 50 patients with rectal cancer who underwent rectal MRI consecutively between July 7, 2020 and January 20, 2021 using a T2W 3D FSE sequence with DLR and conventional reconstruction. Three radiologists reviewed the two sets of images, scoring overall SNR, motion artifacts, and overall image quality on a 3‐point scale and indicating clinical preference for DLR or conventional reconstruction based on those three criteria as well as image characterization of bowel wall layer definition, tumor invasion of muscularis propria, residual disease, fibrosis, nodal margin, and extramural venous invasion.Results: Image quality was rated as moderate or good for both DLR and conventional reconstruction for most cases. DLR was preferred over conventional reconstruction in all of the categories except for bowel wall layer definition.Conclusion: Both conventional reconstruction and DLR provide acceptable image quality for T2W 3D FSE imaging of rectal cancer. DLR was clinically preferred over conventional reconstruction in almost all categories.
- 3 August 2023
- Published by International Society for Magnetic Resonance in Medicine (ISMRM)
3D T2-Weighted Rectal Cancer Imaging using a 3D Fast Spin Echo Sequence with Deep Learning Reconstruction
Multiplanar high resolution T2-weighted (T2W) imaging with a 2D fast spin echo (FSE) sequence is currently an essential component of rectal cancer MRI. In this work, we performed T2W imaging of rectal cancer with a 3D FSE sequence and evaluated the quality and potential clinical value of the images after applying a postprocessing deep learning reconstruction (DLR) algorithm. We found that DLR images are non-inferior to conventional images and there are fair-moderate inter-reader agreements in a large majority of the categories evaluated for image quality and clinical usefulness.
- 3 August 2023
- Published by International Society for Magnetic Resonance in Medicine (ISMRM)
3D T2-Weighted Rectal Cancer Imaging using a 3D Fast Spin Echo Sequence with Deep Learning Reconstruction
Multiplanar high resolution T2-weighted (T2W) imaging with a 2D fast spin echo (FSE) sequence is currently an essential component of rectal cancer MRI. In this work, we performed T2W imaging of rectal cancer with a 3D FSE sequence and evaluated the quality and potential clinical value of the images after applying a postprocessing deep learning reconstruction (DLR) algorithm. We found that DLR images are non-inferior to conventional images and there are fair-moderate inter-reader agreements in a large majority of the categories evaluated for image quality and clinical usefulness.
- Open Access
- 26 October 2020
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 85 (4) , 2136-2144
Combining inhomogeneous magnetization transfer and multipoint Dixon acquisition: Potential utility and evaluation
Purpose The recently introduced inhomogeneous magnetization transfer (ihMT) method has predominantly been applied for imaging the central nervous system. Future applications of ihMT, such as in peripheral nerves and muscles, will involve imaging in the vicinity of adipose tissues. This work aims to systematically investigate the partial volume effect of fat on the ihMT signal and to propose an efficient fat‐separation method that does not interfere with ihMT measurements. Methods First, the influence of fat on ihMT signal was studied using simulations. Next, the ihMT sequence was combined with a multi‐echo Dixon acquisition for fat separation. The sequence was tested in 9 healthy volunteers using a 3T human scanner. The ihMT ratio (ihMTR) values were calculated in regions of interest in the brain and the spinal cord using standard acquisition (no fat saturation), water‐only, in‐phase, and out‐of‐phase reconstructions. The values obtained were compared with a standard fat suppression method, spectral presaturation with inversion recovery. Results Simulations showed variations in the ihMTR values in the presence of fat, depending on the TEs used. The IhMTR values in the brain and spinal cord derived from the water‐only ihMT multi‐echo Dixon images were in good agreement with values from the unsuppressed sequence. The ihMT–spectral presaturation with inversion recovery combination resulted in 24%‐35% lower ihMTR values compared with the standard non‐fat‐suppressed acquisition. Conclusion The presence of fat within a voxel affects the ihMTR calculations. The IhMT multi‐echo Dixon method does not compromise the observable ihMT effect and can potentially be used to remove fat influence in ihMT.
- 26 October 2020
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 85 (4) , 2136-2144
Open AccessCombining inhomogeneous magnetization transfer and multipoint Dixon acquisition: Potential utility and evaluation
Purpose The recently introduced inhomogeneous magnetization transfer (ihMT) method has predominantly been applied for imaging the central nervous system. Future applications of ihMT, such as in peripheral nerves and muscles, will involve imaging in the vicinity of adipose tissues. This work aims to systematically investigate the partial volume effect of fat on the ihMT signal and to propose an efficient fat‐separation method that does not interfere with ihMT measurements. Methods First, the influence of fat on ihMT signal was studied using simulations. Next, the ihMT sequence was combined with a multi‐echo Dixon acquisition for fat separation. The sequence was tested in 9 healthy volunteers using a 3T human scanner. The ihMT ratio (ihMTR) values were calculated in regions of interest in the brain and the spinal cord using standard acquisition (no fat saturation), water‐only, in‐phase, and out‐of‐phase reconstructions. The values obtained were compared with a standard fat suppression method, spectral presaturation with inversion recovery. Results Simulations showed variations in the ihMTR values in the presence of fat, depending on the TEs used. The IhMTR values in the brain and spinal cord derived from the water‐only ihMT multi‐echo Dixon images were in good agreement with values from the unsuppressed sequence. The ihMT–spectral presaturation with inversion recovery combination resulted in 24%‐35% lower ihMTR values compared with the standard non‐fat‐suppressed acquisition. Conclusion The presence of fat within a voxel affects the ihMTR calculations. The IhMT multi‐echo Dixon method does not compromise the observable ihMT effect and can potentially be used to remove fat influence in ihMT.