Yuantao Huang
Yuantao Huang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Junqing Xu
Department of Radiology, Affiliated Hospital of Guangdong Medical University, Zhanjiang, Guangdong, China
3 shared publications - Xinping Zhang
Department of Radiology, Southern University of Science and Technology Hospital, Shenzhen, Guangdong, China
3 shared publications - Ce Wang
Jiangsu Key Laboratory of Molecular and Functional Imaging, Department of Radiology, Zhongda Hospital, School of Medicine Southeast University Nanjing Jiangsu China
2 shared publications - Baiying Lei
Shenzhen University
1 shared publication Caixue Cheng
Department of Radiology, Southern University of Science and Technology Hospital, Guangdong, China
1 shared publicationCe Wang
Department of Radiology, Southern University of Science and Technology Hospital, Guangdong, China
1 shared publication
Latest Publications
- 18 August 2026
- Published by Springer Nature in The International Journal of Cardiovascular Imaging
- p. 1-13
Deep learning-derived left ventricular circumferential strain for cardiac MRI diagnosis of acute myocarditis with preserved ejection fraction
To evaluate the diagnostic performance of deep learning-derived left ventricular circumferential strain (DL-LVCS), a method that reduces operator dependency and analysis time compared with conventional feature tracking, in patients with acute myocarditis and preserved LVEF (≥ 55%), and to compare it with feature tracking-derived strain (FT-LVCS). This retrospective study, conducted between January 2021 and December 2024, included 142 patients with acute myocarditis, stratified into preserved EF (AMY-pEF, n = 106, mean age, 31 ± 9 years; 80 male) and reduced EF (n = 36, mean age, 33 ± 12 years; 27 male) groups, alongside 106 age- and sex-matched healthy controls (mean age, 32 ± 7 years; 78 male). A deep learning model integrating PPIM-Net (Pyramid Progressive Image Mapping Network) for segmentation and U-Net for motion tracking was developed to compute DL-LVCS. Conventional LVCS was also obtained. Diagnostic performance was evaluated using ROC analysis, and AUCs were compared with the DeLong test. In the AMY-pEF group, both FT-LVCS (-18.4%±1.2 vs. -19.8% ±1.3) and DL-LVCS (-8.0%±1.4 vs. -10.4%±1.8) were significantly impaired versus controls (both P < 0.001). For diagnosing AMY-pEF, FT-LVCS (cutoff=-19.3%) achieved an AUC of 0.806, with 67.2% sensitivity and 84.5% specificity. DL-LVCS (cutoff=-9.2%) demonstrated significantly higher AUC (0.887), sensitivity (85.9%), and specificity (79.2%) (DeLong P < 0.01). DL-LVCS enables quantification of myocardial deformation and demonstrates higher sensitivity than conventional LVCS for discriminating patients with CMR-defined acute myocarditis and preserved LVEF from healthy controls. It may serve as a supplementary CMR biomarker when standard functional metrics are within normal ranges.
- 18 August 2026
- Published by Springer Nature in The International Journal of Cardiovascular Imaging
- p. 1-13
Deep learning-derived left ventricular circumferential strain for cardiac MRI diagnosis of acute myocarditis with preserved ejection fraction
To evaluate the diagnostic performance of deep learning-derived left ventricular circumferential strain (DL-LVCS), a method that reduces operator dependency and analysis time compared with conventional feature tracking, in patients with acute myocarditis and preserved LVEF (≥ 55%), and to compare it with feature tracking-derived strain (FT-LVCS). This retrospective study, conducted between January 2021 and December 2024, included 142 patients with acute myocarditis, stratified into preserved EF (AMY-pEF, n = 106, mean age, 31 ± 9 years; 80 male) and reduced EF (n = 36, mean age, 33 ± 12 years; 27 male) groups, alongside 106 age- and sex-matched healthy controls (mean age, 32 ± 7 years; 78 male). A deep learning model integrating PPIM-Net (Pyramid Progressive Image Mapping Network) for segmentation and U-Net for motion tracking was developed to compute DL-LVCS. Conventional LVCS was also obtained. Diagnostic performance was evaluated using ROC analysis, and AUCs were compared with the DeLong test. In the AMY-pEF group, both FT-LVCS (-18.4%±1.2 vs. -19.8% ±1.3) and DL-LVCS (-8.0%±1.4 vs. -10.4%±1.8) were significantly impaired versus controls (both P < 0.001). For diagnosing AMY-pEF, FT-LVCS (cutoff=-19.3%) achieved an AUC of 0.806, with 67.2% sensitivity and 84.5% specificity. DL-LVCS (cutoff=-9.2%) demonstrated significantly higher AUC (0.887), sensitivity (85.9%), and specificity (79.2%) (DeLong P < 0.01). DL-LVCS enables quantification of myocardial deformation and demonstrates higher sensitivity than conventional LVCS for discriminating patients with CMR-defined acute myocarditis and preserved LVEF from healthy controls. It may serve as a supplementary CMR biomarker when standard functional metrics are within normal ranges.
- 2 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 174
Pyramid progressive image mapping network based on sparse annotations for cardiac segmentation
- 2 January 2026
- Published by Elsevier in Pattern Recognition
- Vol. 174
Pyramid progressive image mapping network based on sparse annotations for cardiac segmentation
- Open Access
- 2 July 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (13) , e032781
Unveiling the Diagnostic Value of Strain Parameters Across All 4 Cardiac Chambers in Patients With Acute Myocarditis With Varied Ejection Fraction: A Cardiovascular Magnetic Resonance Feature‐Tracking Approach
Background: This study assesses the diagnostic utility of strain parameters from cardiovascular magnetic resonance feature tracking across all cardiac chambers in patients with acute myocarditis, stratified by ejection fraction. Methods and Results: Our cohort included 65 patients with acute myocarditis and 25 healthy controls; all underwent cardiac magnetic resonance imaging. Patients were divided into 2 groups based on left ventricular ejection fraction (EF)with a 55% cutoff: acute myocarditis with preserved EF, EF ≥55%, n=48; and acute myocarditis with reduced EF, EF <55%, n=17. The control group matched for age and sex. Cardiovascular magnetic resonance feature tracking evaluated strain parameters across all cardiac chambers. Both acute myocarditis with preserved EF and acute myocarditis with reduced EF groups showed significant decreases in left atrial peak early negative strain rate compared with controls. The acute myocarditis with reduced EF group had significantly reduced left ventricular circumferential strain relative to acute myocarditis with preserved EF and controls. Receiver operating characteristic curve analysis confirmed the diagnostic accuracy in distinguishing patients with acute myocarditis with preserved EF from controls, with left atrial peak early negative strain rate achieving 92.9% specificity, left ventricular circumferential strain demonstrating an area under the curve of 0.832, and similarly effective results for left ventricular longitudinal strain and right ventricular longitudinal strain. Additionally, left atrial peak early negative strain rate and left ventricular circumferential strain showed significant correlations with troponin I levels, indicating myocardial injury. Conclusions: Cardiovascular magnetic resonance feature‐tracking–derived strain parameters, particularly left atrial peak early negative strain rate and left ventricular circumferential strain, effectively diagnose acute myocarditis across different EFs, enhancing diagnostic accuracy and facilitating early detection, notably in patients with preserved EF.
- 2 July 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (13) , e032781
Open AccessUnveiling the Diagnostic Value of Strain Parameters Across All 4 Cardiac Chambers in Patients With Acute Myocarditis With Varied Ejection Fraction: A Cardiovascular Magnetic Resonance Feature‐Tracking Approach
Background: This study assesses the diagnostic utility of strain parameters from cardiovascular magnetic resonance feature tracking across all cardiac chambers in patients with acute myocarditis, stratified by ejection fraction. Methods and Results: Our cohort included 65 patients with acute myocarditis and 25 healthy controls; all underwent cardiac magnetic resonance imaging. Patients were divided into 2 groups based on left ventricular ejection fraction (EF)with a 55% cutoff: acute myocarditis with preserved EF, EF ≥55%, n=48; and acute myocarditis with reduced EF, EF <55%, n=17. The control group matched for age and sex. Cardiovascular magnetic resonance feature tracking evaluated strain parameters across all cardiac chambers. Both acute myocarditis with preserved EF and acute myocarditis with reduced EF groups showed significant decreases in left atrial peak early negative strain rate compared with controls. The acute myocarditis with reduced EF group had significantly reduced left ventricular circumferential strain relative to acute myocarditis with preserved EF and controls. Receiver operating characteristic curve analysis confirmed the diagnostic accuracy in distinguishing patients with acute myocarditis with preserved EF from controls, with left atrial peak early negative strain rate achieving 92.9% specificity, left ventricular circumferential strain demonstrating an area under the curve of 0.832, and similarly effective results for left ventricular longitudinal strain and right ventricular longitudinal strain. Additionally, left atrial peak early negative strain rate and left ventricular circumferential strain showed significant correlations with troponin I levels, indicating myocardial injury. Conclusions: Cardiovascular magnetic resonance feature‐tracking–derived strain parameters, particularly left atrial peak early negative strain rate and left ventricular circumferential strain, effectively diagnose acute myocarditis across different EFs, enhancing diagnostic accuracy and facilitating early detection, notably in patients with preserved EF.