Hongwei Zhang
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
Hongwei Zhang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Dong Zhang
School of Biomedical Engineering, Sun Yat-Sen University, Shenzhen, China
2 shared publications - Heye Zhang
Sun Yat-sen University
2 shared publications - Zhifan Gao
School of Biomedical Engineering, Sun Yat-Sen University, Guangzhou, China
2 shared publications Anbang Wang
School of Biomedical Engineering, Sun Yat-Sen University, Shenzhen, China
1 shared publicationBao-Gen Shen
State Key Laboratory of Magnetism, Institute of Physics and Center for Condensed Matter Physics, Chinese Academy of Sciences, Beijing 100080, People's Republic of China
1 shared publication- Chao Zhang
Department of General Surgery, Xuanwu Hospital of Capital Medical University, Beijing, People's Republic of China; Oncology and Vascular Intervention Center, National Clinical Research Center for Geriatric Diseases, Beijing, People's Republic of China
1 shared publication
Latest Publications
- 23 February 2026
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 37 (5) , 108584
A Deep Learning Model for Artery of Adamkiewicz Detection in Bronchial Artery Embolization: A Multicenter Retrospective Study
- 23 February 2026
- Published by Elsevier in Journal of Vascular and Interventional Radiology
- Vol. 37 (5) , 108584
A Deep Learning Model for Artery of Adamkiewicz Detection in Bronchial Artery Embolization: A Multicenter Retrospective Study
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (12) , 4091-4104
Constraint-Aware Learning for Fractional Flow Reserve Pullback Curve Estimation From Invasive Coronary Imaging
Estimation of the fractional flow reserve (FFR) pullback curve from invasive coronary imaging is important for the intraoperative guidance of coronary intervention. Machine/deep learning has been proven effective in FFR pullback curve estimation. However, the existing methods suffer from inadequate incorporation of intrinsic geometry associations and physics knowledge. In this paper, we propose a constraint-aware learning framework to improve the estimation of the FFR pullback curve from invasive coronary imaging. It incorporates both geometrical and physical constraints to approximate the relationships between the geometric structure and FFR values along the coronary artery centerline. Our method also leverages the power of synthetic data in model training to reduce the collection costs of clinical data. Moreover, to bridge the domain gap between synthetic and real data distributions when testing on real-world imaging data, we also employ a diffusion-driven test-time data adaptation method that preserves the knowledge learned in synthetic data. Specifically, this method learns a diffusion model of the synthetic data distribution and then projects real data to the synthetic data distribution at test time. Extensive experimental studies on a synthetic dataset and a real-world dataset of 382 patients covering three imaging modalities have shown the better performance of our method for FFR estimation of stenotic coronary arteries, compared with other machine/deep learning-based FFR estimation models and computational fluid dynamics-based model. The results also provide high agreement and correlation between the FFR predictions of our method and the invasively measured FFR values. The plausibility of FFR predictions along the coronary artery centerline is also validated.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (12) , 4091-4104
Constraint-Aware Learning for Fractional Flow Reserve Pullback Curve Estimation From Invasive Coronary Imaging
Estimation of the fractional flow reserve (FFR) pullback curve from invasive coronary imaging is important for the intraoperative guidance of coronary intervention. Machine/deep learning has been proven effective in FFR pullback curve estimation. However, the existing methods suffer from inadequate incorporation of intrinsic geometry associations and physics knowledge. In this paper, we propose a constraint-aware learning framework to improve the estimation of the FFR pullback curve from invasive coronary imaging. It incorporates both geometrical and physical constraints to approximate the relationships between the geometric structure and FFR values along the coronary artery centerline. Our method also leverages the power of synthetic data in model training to reduce the collection costs of clinical data. Moreover, to bridge the domain gap between synthetic and real data distributions when testing on real-world imaging data, we also employ a diffusion-driven test-time data adaptation method that preserves the knowledge learned in synthetic data. Specifically, this method learns a diffusion model of the synthetic data distribution and then projects real data to the synthetic data distribution at test time. Extensive experimental studies on a synthetic dataset and a real-world dataset of 382 patients covering three imaging modalities have shown the better performance of our method for FFR estimation of stenotic coronary arteries, compared with other machine/deep learning-based FFR estimation models and computational fluid dynamics-based model. The results also provide high agreement and correlation between the FFR predictions of our method and the invasively measured FFR values. The plausibility of FFR predictions along the coronary artery centerline is also validated.
- 3 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (3) , 864-879
Progressive Perception Learning for Main Coronary Segmentation in X-Ray Angiography
Main coronary segmentation from the X-ray angiography images is important for the computer-aided diagnosis and treatment of coronary disease. However, it confronts the challenge at three different image granularities (the semantic, surrounding, and local levels). The challenge includes the semantic confusion between the main and collateral vessels, low contrast between the foreground vessel and background surroundings, and local ambiguity near the vessel boundaries. The traditional hand-crafted feature-based methods may be insufficient because they may lack the semantic relationship information and may not distinguish the main and collateral vessels. The existing deep learning-based methods seem to have issues due to the deficiency in the long-distance semantic relationship capture, the foreground and background interference adaptability, and the boundary detail information preservation. To solve the main coronary segmentation challenge, we propose the progressive perception learning (PPL) framework to inspect these three different image granularities. Specifically, the PPL contains the context, interference, and boundary perception modules. The context perception is designed to focus on the main coronary vessel based on the semantic dependence capture among different coronary segments. The interference perception is designed to purify the feature maps based on the foreground vessel enhancement and background artifact suppression. The boundary perception is designed to highlight the boundary details based on boundary feature extraction through the intersection between the foreground and background predictions. Extensive experiments on 1085 subjects show that the PPL is effective (e.g., the overall Dice is greater than 95%), and superior to thirteen state-of-the-art coronary segmentation methods.
- 3 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (3) , 864-879
Progressive Perception Learning for Main Coronary Segmentation in X-Ray Angiography
Main coronary segmentation from the X-ray angiography images is important for the computer-aided diagnosis and treatment of coronary disease. However, it confronts the challenge at three different image granularities (the semantic, surrounding, and local levels). The challenge includes the semantic confusion between the main and collateral vessels, low contrast between the foreground vessel and background surroundings, and local ambiguity near the vessel boundaries. The traditional hand-crafted feature-based methods may be insufficient because they may lack the semantic relationship information and may not distinguish the main and collateral vessels. The existing deep learning-based methods seem to have issues due to the deficiency in the long-distance semantic relationship capture, the foreground and background interference adaptability, and the boundary detail information preservation. To solve the main coronary segmentation challenge, we propose the progressive perception learning (PPL) framework to inspect these three different image granularities. Specifically, the PPL contains the context, interference, and boundary perception modules. The context perception is designed to focus on the main coronary vessel based on the semantic dependence capture among different coronary segments. The interference perception is designed to purify the feature maps based on the foreground vessel enhancement and background artifact suppression. The boundary perception is designed to highlight the boundary details based on boundary feature extraction through the intersection between the foreground and background predictions. Extensive experiments on 1085 subjects show that the PPL is effective (e.g., the overall Dice is greater than 95%), and superior to thirteen state-of-the-art coronary segmentation methods.
- 20 June 2009
- Published by China Science Publishing & Media Ltd. in Academic Journal of Second Military Medical University
- Vol. 29 (6) , 637-640
Recombination analysis of full-length genomic sequences of novel influenza virus A/H1N1 in 2009 pandemic
Objective:To analyze the recombination of full-length genomic sequences of novel influenza virus A/H1N1 in 2009 pandemic.Methods:The full-length sequences of the novel A/H1N1 and reference sequences were downloaded from NCBI database.MEGA4.0 software was used to connect,align sequences,and analyze the similarity between the full-length sequences of the novel virus and each of the reference strains.Recombination was analyzed by Simplot software(version 3.5.1).Results:Simplot analysis indicated that the PB1 genes(polymerase B1,PB1)of the novel A/H1N1 viruses might evolve from human H3N2 virus(identity:93.7%);the PB2 genes(polymerase B2,PB2)and the PA genes(polymerase A,PA)might evolve from avian H5N1 viruses(identity:89.0%,89.9%,respectively);the HA genes(hemagglutinin,HA),the NP genes(nucleoprotein,NP)and the NS genes(non-structural protein,NS)showed high similarities with those of swine H1N1 viruses isolated in North America(identity:91.7%,93.1%,and 93.1%,respectively);and the NA genes(neuraminidase,NA)and the MP genes(matrix protein,MP)might evolve from European swine H1N1 viruses(identity:90.5%,95.5%,respectively).The full-length sequence of the novel A/H1N1 viruses had a highest similarities with swine H1N1 viruses isolated in North America(identity:83.9%).Conclusion:The novel influenza virus A/H1N1 is a recombinant virus evolving from human H3N2 viruses,swine H1N1 from North America,swine H1N1 from Europe,and swine H5N1 from Asia.
- 20 June 2009
- Published by China Science Publishing & Media Ltd. in Academic Journal of Second Military Medical University
- Vol. 29 (6) , 637-640
Recombination analysis of full-length genomic sequences of novel influenza virus A/H1N1 in 2009 pandemic
Objective:To analyze the recombination of full-length genomic sequences of novel influenza virus A/H1N1 in 2009 pandemic.Methods:The full-length sequences of the novel A/H1N1 and reference sequences were downloaded from NCBI database.MEGA4.0 software was used to connect,align sequences,and analyze the similarity between the full-length sequences of the novel virus and each of the reference strains.Recombination was analyzed by Simplot software(version 3.5.1).Results:Simplot analysis indicated that the PB1 genes(polymerase B1,PB1)of the novel A/H1N1 viruses might evolve from human H3N2 virus(identity:93.7%);the PB2 genes(polymerase B2,PB2)and the PA genes(polymerase A,PA)might evolve from avian H5N1 viruses(identity:89.0%,89.9%,respectively);the HA genes(hemagglutinin,HA),the NP genes(nucleoprotein,NP)and the NS genes(non-structural protein,NS)showed high similarities with those of swine H1N1 viruses isolated in North America(identity:91.7%,93.1%,and 93.1%,respectively);and the NA genes(neuraminidase,NA)and the MP genes(matrix protein,MP)might evolve from European swine H1N1 viruses(identity:90.5%,95.5%,respectively).The full-length sequence of the novel A/H1N1 viruses had a highest similarities with swine H1N1 viruses isolated in North America(identity:83.9%).Conclusion:The novel influenza virus A/H1N1 is a recombinant virus evolving from human H3N2 viruses,swine H1N1 from North America,swine H1N1 from Europe,and swine H5N1 from Asia.
- 20 January 2006
- Published by IOP Publishing in Journal of Physics D: Applied Physics
- Vol. 39 (3) , 437-440
Effects of annealing on the coercivity of Sm(Co,Fe,Cu,Zr)zribbons and its temperature dependence
- 20 January 2006
- Published by IOP Publishing in Journal of Physics D: Applied Physics
- Vol. 39 (3) , 437-440
Effects of annealing on the coercivity of Sm(Co,Fe,Cu,Zr)zribbons and its temperature dependence