YLYuehong Liu

Yuehong Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuehong Liu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Association Between Thrombus Signal Intensity and Pulmonary Embolism in Patients With Proximal Deep Vein Thrombosis: A Magnetic Resonance Imaging Study

    by Xinyu Wang, Congrui Sun, Yuehong Liu, Yichen Tang, Chen Zhang, Alto Stemmer, Jiajia Zhang, Guoxi Xie, Chunmin Li, Qi Yang

    BACKGROUND: Approximately 50% of deep vein thrombosis (DVT) occurrences in the lower extremity proximal veins are associated with pulmonary embolism (PE). The progression of proximal DVT is critical in PE development, as reflected by thrombus composition. Magnetic resonance black-blood thrombus imaging can identify venous thrombus components by displaying thrombus signal intensity variations. This study investigated the association between thrombus signal intensity and PE in patients with proximal DVT. METHODS: A total of 126 patients with proximal DVT were recruited, and all underwent magnetic resonance black-blood thrombus imaging examination. The patients were divided into 2 groups: DVT-only and DVT with PE. The whole thrombus signal intensity ratio, proximal thrombus signal intensity ratio, distal thrombus signal intensity ratio, and thrombus volume were assessed. Histological analysis was performed to characterize the thrombus content. Logistic regression models were performed to evaluate the relationship between thrombus signal intensity and PE. RESULTS: Of the 126 eligible patients, 73 (58%) patients were in the DVT with PE group. Both proximal thrombus signal intensity ratio and whole thrombus signal intensity ratio were lower in the DVT with PE group compared with the DVT-only group (1.92±0.54 versus 1.31±0.42, P P =0.034). The percentage of fibrin area (13.99±1.56% versus 7.51±1.25%, P =0.0087) and red blood cells area (49.65±18.8% versus 13.41±4.74%, P =0.0012) were higher in DVT with PE than DVT-only group. Univariate and multivariate logistic regression analysis showed that proximal thrombus signal intensity ratio remained statistically significant (odds ratio, 0.21 [95% CI, 0.12–0.39]; P <0.001). CONCLUSIONS: The proximal thrombus signal intensity ratio of the thrombus was independently associated with acute PE in patients with proximal lower extremity DVT, suggesting that thrombus components may be important in PE occurrence. These findings could provide novel insights for understanding DVT evolution.


  • Quantitative Ischemic Lesions of Portable Low–Field Strength MRI Using Deep Learning–Based Super-Resolution

    by Yueyan Bian, Long Wang, Jin Li, Xiaoxu Yang, Erling Wang, Yingying Li, Yuehong Liu, Lei Xiang, Qi Yang

    BACKGROUND: Deep learning–based synthetic super-resolution magnetic resonance imaging (SynthMRI) may improve the quantitative lesion performance of portable low–field strength magnetic resonance imaging (LF-MRI). The aim of this study is to evaluate whether SynthMRI improves the diagnostic performance of LF-MRI in assessing ischemic lesions. METHODS: We retrospectively included 178 stroke patients and 104 healthy controls with both LF-MRI and high–field strength magnetic resonance imaging (HF-MRI) examinations. Using HF-MRI as the ground truth, the deep learning–based super-resolution framework (SCUNet [Swin-Conv-UNet]) was pretrained using large-scale open-source data sets to generate SynthMRI images from LF-MRI images. Participants were split into a training set (64.2%) to fine-tune the pretrained SCUNet, and a testing set (35.8%) to evaluate the performance of SynthMRI. Sensitivity and specificity of LF-MRI and SynthMRI were assessed. Agreement with HF-MRI for Alberta Stroke Program Early CT Score in the anterior and posterior circulation (diffusion-weighted imaging–Alberta Stroke Program Early CT Score and diffusion-weighted imaging–posterior circulation Alberta Stroke Program Early CT Score) was evaluated using intraclass correlation coefficients (ICCs). Agreement with HF-MRI for lesion volume and mean apparent diffusion coefficient (ADC) within lesions was assessed using both ICCs and Pearson correlation coefficients. RESULTS: SynthMRI demonstrated significantly higher sensitivity and specificity than LF-MRI (89.0% [83.3%–94.6%] versus 77.1% [69.5%–84.7%]; P P P P 0.85, r >0.78) than LF-MRI (ICC>0.45, r >0.35). Furthermore, for lesions during various poststroke phases, SynthMRI exhibited significantly higher agreement with HF-MRI than LF-MRI during the early hyperacute and subacute phases. CONCLUSIONS: SynthMRI demonstrates high agreement with HF-MRI in detecting and quantifying ischemic lesions and is better than LF-MRI, particularly for lesions during the early hyperacute and subacute phases.


  • Exploring Prolonged Efficacy of Ferumoxytol‐Enhanced Whole‐Body MR Angiography: A Preliminary Study in Healthy Male Subjects

    by Guangxiang Si, Yuehong Liu, Jingyi Sheng, Gao Ma, Zhenyue Gao, Zhenyu Li, Zhaochen Jia, Jinling Xue, Dan Mu, Bin Sun, et al.


  • Deep Learning Algorithm Enables Cerebral Venous Thrombosis Detection With Routine Brain Magnetic Resonance Imaging

    by Xiaoxu Yang, Pengxin Yu, Haoyue Zhang, Rongguo Zhang, Yuehong Liu, Haoyuan Li, Penghui Sun, Xin Liu, Yu Wu, Xiuqin Jia, et al.

    Background: Cerebral venous thrombosis (CVT) is a rare cerebrovascular disease. Routine brain magnetic resonance imaging is commonly used to diagnose CVT. This study aimed to develop and evaluate a novel deep learning (DL) algorithm for detecting CVT using routine brain magnetic resonance imaging. Methods: Routine brain magnetic resonance imaging, including T1-weighted, T2-weighted, and fluid-attenuated inversion recovery images of patients suspected of CVT from April 2014 through December 2019 who were enrolled from a CVT registry, were collected. The images were divided into 2 data sets: a development set and a test set. Different DL algorithms were constructed in the development set using 5-fold cross-validation. Four radiologists with various levels of expertise independently read the images and performed diagnosis within the test set. The diagnostic performance on per-patient and per-segment diagnosis levels of the DL algorithms and radiologist’s assessment were evaluated and compared. Results: A total of 392 patients, including 294 patients with CVT (37±14 years, 151 women) and 98 patients without CVT (42±15 years, 65 women), were enrolled. Of these, 100 patients (50 CVT and 50 non-CVT) were randomly assigned to the test set, and the other 292 patients comprised the development set. In the test set, the optimal DL algorithm (multisequence multitask deep learning algorithm) achieved an area under the curve of 0.96, with a sensitivity of 96% (48/50) and a specificity of 88% (44/50) on per-patient diagnosis level, as well as a sensitivity of 88% (129/146) and a specificity of 80% (521/654) on per-segment diagnosis level. Compared with 4 radiologists, multisequence multitask deep learning algorithm showed higher sensitivity both on per-patient (all P P <0.001). Conclusions: The CVT-detected DL algorithm herein improved diagnostic performance of routine brain magnetic resonance imaging, with high sensitivity and specificity, which provides a promising approach for detecting CVT.