Chenxi Hu

Chenxi Hu

Auto-generated profile, based on publicly available information

Chenxi Hu

National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 January 2019 in Magnetic Resonance in Medicine
Verified
Journal Article
Closed access
PDF file
CHChenxi Hu
Chenxi Hu
DPDana C. Peters
Dana C. Peters

1 December 2016 in Journal of Cardiovascular Magnetic Resonance
Verified
Journal Article
Open access
PDF file
CHChenxi Hu
Chenxi Hu
Albert SinusasAlbert Sinusas
Albert Sinusas
SHSteffen Huber
Steffen Huber
STStephanie Thorn
Stephanie Thorn
MSMitchel R Stacy
Mitchel R Stacy
DPDana C. Peters
Dana C. Peters
High resolution 3D T1 mapping is important for assessment of diffuse myocardial fibrosis in left atrium or other thin-walled structures. In this work, we investigated a fast single-TI 3D high resolution T1 mapping method that directly transforms a 3D late gadolinium enhancement (LGE) volume to a 3D T1 map. The proposed method, T1-refBlochi, is based on Bloch equation modeling of the LGE signal, a single-point calibration, and assumptions that proton density and T2* are relatively uniform in the heart. Several sources of error of this method were analyzed mathematically and with simulations. Imaging was performed in phantoms, eight swine and five patients, comparing T1-refBlochi to a standard spin-echo T1 mapping, 3D multi-TI T1 mapping, and 2D ShMOLLI, respectively. The method has a good accuracy and adequate precision, even considering various sources of error. In phantoms, over a range of protocols, heart-rates and T1 s, the bias ±1SD was -3 ms ± 9 ms. The porcine studies showed excellent agreement between T1-refBlochi and the multi-TI method (bias ±1SD = −6 ± 22 ms). The proton density and T2* weightings yielded ratios for scar/blood of 0.94 ± 0.01 and for myocardium/blood of 1.03 ± 0.02 in the eight swine, confirming that sufficient uniformity of proton density and T2* weightings exists among heterogeneous tissues of the heart. In the patients, the mean T1 bias ±1SD in myocardium and blood between T1-refBlochi and ShMOLLI was -9 ms ± 21 ms. T1-refBlochi provides a fast single-TI high resolution 3D T1 map of the heart with good accuracy and adequate precision.

2 December 2021 in Journal of Cardiovascular Magnetic Resonance
Verified
Journal Article
Open access
PDF file
RGRicardo A. Gonzales
Ricardo A. Gonzales
FSFelicia Seemann
Felicia Seemann
JLJérôme Lamy
Jérôme Lamy
HMHamid Mojibian
Hamid Mojibian
DADan Atar
Dan Atar
EHEinar Heiberg
Einar Heiberg
Mitral annular plane systolic excursion (MAPSE) and left ventricular (LV) early diastolic velocity (e’) are key metrics of systolic and diastolic function, but not often measured by cardiovascular magnetic resonance (CMR). Its derivation is possible with manual, precise annotation of the mitral valve (MV) insertion points along the cardiac cycle in both two and four-chamber long-axis cines, but this process is highly time-consuming, laborious, and prone to errors. A fully automated, consistent, fast, and accurate method for MV plane tracking is lacking. In this study, we propose MVnet, a deep learning approach for MV point localization and tracking capable of deriving such clinical metrics comparable to human expert-level performance, and validated it in a multi-vendor, multi-center clinical population. The proposed pipeline first performs a coarse MV point annotation in a given cine accurately enough to apply an automated linear transformation task, which standardizes the size, cropping, resolution, and heart orientation, and second, tracks the MV points with high accuracy. The model was trained and evaluated on 38,854 cine images from 703 patients with diverse cardiovascular conditions, scanned on equipment from 3 main vendors, 16 centers, and 7 countries, and manually annotated by 10 observers. Agreement was assessed by the intra-class correlation coefficient (ICC) for both clinical metrics and by the distance error in the MV plane displacement. For inter-observer variability analysis, an additional pair of observers performed manual annotations in a randomly chosen set of 50 patients. MVnet achieved a fast segmentation (<1 s/cine) with excellent ICCs of 0.94 (MAPSE) and 0.93 (LV e’) and a MV plane tracking error of −0.10 ± 0.97 mm. In a similar manner, the inter-observer variability analysis yielded ICCs of 0.95 and 0.89 and a tracking error of −0.15 ± 1.18 mm, respectively. A dual-stage deep learning approach for automated annotation of MV points for systolic and diastolic evaluation in CMR long-axis cine images was developed. The method is able to carefully track these points with high accuracy and in a timely manner. This will improve the feasibility of CMR methods which rely on valve tracking and increase their utility in a clinical setting.

1 January 2025 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
ZXZhihao Xue
Zhihao Xue
FYFan Yang
Fan Yang
JGJuan Gao
Juan Gao
ZCZhuo Chen
Zhuo Chen
HPHao Peng
Hao Peng
CHChenxi Hu
Chenxi Hu
Three-dimensional coronary magnetic resonance angiography (CMRA) requires reconstruction algorithms that can significantly suppress the artifacts encountered in heavily undersampled acquisitions. While unrolling-based deep reconstruction methods have achieved state-of-the-art performance on 2D image reconstruction, their application in 3D reconstruction is hindered by the large amount of memory required to train an unrolled network. In this study, we propose a memoryefficient deep compressed sensing method that employs a sparsifying transform based on a pre-trained artifact estimation network. The artifact image estimated by a welltrained network is expected to be sparse when the input image is artifact-free and less sparse when the input image has artifacts. Thus, the artifact estimation network can be used as an inherent sparsifying transform. The proposed method, De-Aliasing Regularization-based Compressed Sensing (DARCS), was compared with a patch-based lowrank method, de-aliasing generative adversarial network (DAGAN), 3D model-based deep learning (MoDL), plug-and-play, and AI-assisted compressed sensing (AI-CS) in terms of 3D CMRA acceleration. The results demonstrate that DARCS surpasses the reconstruction quality of the comparison methods, by approximately 2 dB in peak signal-to-noise ratio (PSNR). Furthermore, the proposed method generalizes well to different undersampling rates, patterns, and noise levels, with a memory usage of only 63% of that needed by 3D MoDL. In conclusion, DARCS improves reconstruction quality for 3D CMRA with reduced memory burden.

25 September 2018 in Journal of Magnetic Resonance Imaging
Verified
Journal Article
Closed access
PDF file
CHChenxi Hu
Chenxi Hu
SHSteffen Huber
Steffen Huber
SLSyed R. Latif
Syed R. Latif
GSGuido Santacana‐Laffitte
Guido Santacana‐Laffitte
HMHamid R. Mojibian
Hamid R. Mojibian
DPDana C. Peters
Dana C. Peters

22 November 2023 in Journal of Cardiovascular Magnetic Resonance
Verified
Journal Article
Open access
PDF file
ZCZhuo Chen
Zhuo Chen
SHSha Hua
Sha Hua
JGJuan Gao
Juan Gao
YCYanjia Chen
Yanjia Chen
YGYiwen Gong
Yiwen Gong
CHChenxi Hu
Chenxi Hu
To develop a partially interpretable neural network for joint suppression of banding and flow artifacts in non-phase-cycled bSSFP cine imaging. A dual-stage neural network consisting of a voxel-identification (VI) sub-network and artifact-suppression (AS) sub-network is proposed. The VI sub-network provides identification of artifacts, which guides artifact suppression and improves interpretability. The AS sub-network reduces banding and flow artifacts. Short-axis cine images of 12 frequency offsets from 28 healthy subjects were used to train and test the dual-stage network. An additional 77 patients were retrospectively enrolled to evaluate its clinical generalizability. For healthy subjects, artifact suppression performance was analyzed by comparison with traditional phase cycling. The partial interpretability provided by the VI sub-network was analyzed via correlation analysis. Generalizability was evaluated for cine obtained with different sequence parameters and scanners. For patients, artifact suppression performance and partial interpretability of the network were qualitatively evaluated by 3 clinicians. Cardiac function before and after artifact suppression was assessed via left ventricular ejection fraction (LVEF). For the healthy subjects, visual inspection and quantitative analysis found a considerable reduction of banding and flow artifacts by the proposed network. Compared with traditional phase cycling, the proposed network improved flow artifact scores (4.57 ± 0.23 vs 3.40 ± 0.38, P = 0.002) and overall image quality (4.33 ± 0.22 vs 3.60 ± 0.38, P = 0.002). The VI sub-network well identified the location of banding and flow artifacts in the original movie and significantly correlated with the change of signal intensities in these regions. Changes of imaging parameters or the scanner did not cause a significant change of overall image quality relative to the baseline dataset, suggesting a good generalizability. For the patients, qualitative analysis showed a significant improvement of banding artifacts (4.01 ± 0.50 vs 2.77 ± 0.40, P < 0.001), flow artifacts (4.22 ± 0.38 vs 2.97 ± 0.57, P < 0.001), and image quality (3.91 ± 0.45 vs 2.60 ± 0.43, P < 0.001) relative to the original cine. The artifact suppression slightly reduced the LVEF (mean bias = -1.25%, P = 0.01). The dual-stage network simultaneously reduces banding and flow artifacts in bSSFP cine imaging with a partial interpretability, sparing the need for sequence modification. The method can be easily deployed in a clinical setting to identify artifacts and improve cine image quality.