Yuefu Zhan
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
Yuefu Zhan has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Jianqiang Chen
Department of Radiology, the First Affiliated Hospital of Hainan Medical University, Haikou, China
6 shared publications - Zhenghua Xu
State Key Laboratory of Reliability and Intelligence of Electrical Equipment, School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, China
3 shared publications - Liheng Ma
The First Affiliated Hospital of Guangdong Pharmaceutical University
2 shared publications Ling Chen
The First Affiliated Hospital of Guangdong Pharmaceutical University
2 shared publicationsLingjiang Mo
The First Affiliated Hospital of Guangdong Pharmaceutical University
2 shared publicationsLingling Deng
Department of Radiology, The Second Affiliated Hospital of Nanhua University, Hengyang, China
2 shared publications
Latest Publications
- Open Access
- 20 September 2026
- Published by Springer Nature in Tropical Medicine and Health
- Vol. 54 (1) , 202
Timing of surgery for a melioidosis-associated abdominal aortic pseudoaneurysm: a case report
Melioidosis is a tropical infectious disease caused by Burkholderia pseudomallei. Although vascular involvement is rare, melioidosis-associated abdominal a
- 20 September 2026
- Published by Springer Nature in Tropical Medicine and Health
- Vol. 54 (1) , 202
Open AccessTiming of surgery for a melioidosis-associated abdominal aortic pseudoaneurysm: a case report
Melioidosis is a tropical infectious disease caused by Burkholderia pseudomallei. Although vascular involvement is rare, melioidosis-associated abdominal a
- 18 July 2026
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 201, 575-584
Assessment of glymphatic system function in young major depressive disorder using multimodal MRI
- 18 July 2026
- Published by Elsevier in Journal of Psychiatric Research
- Vol. 201, 575-584
Assessment of glymphatic system function in young major depressive disorder using multimodal MRI
- Open Access
- 2 July 2026
- Published by Springer Nature in Tropical Medicine and Health
- Vol. 54 (1)
Global research trends, knowledge structure, and future directions in melioidosis research: a bibliometric analysis, 1990–2025
Research on melioidosis has expanded steadily over recent decades, but its global research landscape, knowledge structure, collaboration patterns, and thematic evolution remain insufficiently characterized. We searched the Web of Science Core Collection for melioidosis-related Article and Review records published from 1990 to 2025. Bibliometrix-biblioshiny, VOSviewer, CiteSpace, Microsoft Excel, and R were used to analyze publication output, collaboration networks, institutional and author contributions, reference co-citation patterns, keyword co-occurrence, and trend topics. A total of 3973 Article and Review records from 955 sources were included in the final analysis. The annual publication growth rate was 8.42%, and annual output increased from 12 records in 1990 to a peak of 208 records in 2015, with a model-estimated publication peak around 2019.7 (R2 = 0.973). The United States, Thailand, and Australia were the leading contributing countries, while Mahidol University was the most productive institution and CURRIE BJ was the most influential author. Keyword and co-citation analyses showed that melioidosis research was mainly organized around epidemiology and clinical management, virulence and antimicrobial resistance, pathogen identification and typing, immunopathogenesis and vaccine-related studies, and environmental sources and outbreak-related investigations. Recent trend topics increasingly involved antimicrobial resistance, biofilms, outbreak investigation, environmental factors, mortality, and clinical outcomes. Melioidosis research has entered a stage of bibliometric consolidation, characterized by sustained publication output, stable core contributors, and increasingly diversified research themes. The field has shifted from early disease recognition and laboratory detection toward integrated research on clinical management, antimicrobial resistance, pathogen biology, environmental exposure, and outcome-oriented investigation. Strengthening international collaboration and linking molecular, environmental, and clinical data may help advance future melioidosis research and public health practice.
- 2 July 2026
- Published by Springer Nature in Tropical Medicine and Health
- Vol. 54 (1)
Open AccessGlobal research trends, knowledge structure, and future directions in melioidosis research: a bibliometric analysis, 1990–2025
Research on melioidosis has expanded steadily over recent decades, but its global research landscape, knowledge structure, collaboration patterns, and thematic evolution remain insufficiently characterized. We searched the Web of Science Core Collection for melioidosis-related Article and Review records published from 1990 to 2025. Bibliometrix-biblioshiny, VOSviewer, CiteSpace, Microsoft Excel, and R were used to analyze publication output, collaboration networks, institutional and author contributions, reference co-citation patterns, keyword co-occurrence, and trend topics. A total of 3973 Article and Review records from 955 sources were included in the final analysis. The annual publication growth rate was 8.42%, and annual output increased from 12 records in 1990 to a peak of 208 records in 2015, with a model-estimated publication peak around 2019.7 (R2 = 0.973). The United States, Thailand, and Australia were the leading contributing countries, while Mahidol University was the most productive institution and CURRIE BJ was the most influential author. Keyword and co-citation analyses showed that melioidosis research was mainly organized around epidemiology and clinical management, virulence and antimicrobial resistance, pathogen identification and typing, immunopathogenesis and vaccine-related studies, and environmental sources and outbreak-related investigations. Recent trend topics increasingly involved antimicrobial resistance, biofilms, outbreak investigation, environmental factors, mortality, and clinical outcomes. Melioidosis research has entered a stage of bibliometric consolidation, characterized by sustained publication output, stable core contributors, and increasingly diversified research themes. The field has shifted from early disease recognition and laboratory detection toward integrated research on clinical management, antimicrobial resistance, pathogen biology, environmental exposure, and outcome-oriented investigation. Strengthening international collaboration and linking molecular, environmental, and clinical data may help advance future melioidosis research and public health practice.
- 14 May 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 123
HGR-DiffSeg: Hybrid-guided robust diffusion model for medical image segmentation
- 14 May 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 123
HGR-DiffSeg: Hybrid-guided robust diffusion model for medical image segmentation
- Open Access
- 6 February 2026
- Published by Frontiers Media SA in Frontiers in Bioengineering and Biotechnology
- Vol. 14
Correction: Cerium oxide nanoparticles for enhanced healing of diabetic foot ulcers
- 6 February 2026
- Published by Frontiers Media SA in Frontiers in Bioengineering and Biotechnology
- Vol. 14
Open AccessCorrection: Cerium oxide nanoparticles for enhanced healing of diabetic foot ulcers
- Top Cited PapersOpen Access
- 12 January 2026
- Published by Frontiers Media SA in Frontiers in Bioengineering and Biotechnology
- Vol. 13, 1695821
Cerium oxide nanoparticles for enhanced healing of diabetic foot ulcers
One of the main complications of diabetes is diabetic foot ulcers (DFUs), which have a substantial global impact on morbidity, medical expenses, and lower limb amputations. A complicated microenvironment—characterized by bacterial infections, chronic inflammation, oxidative stress, and poor angiogenesis impedes the healing process of DFUs. Cerium oxide nanoparticles (CeO 2 nanoparticles), owing to their antibacterial, anti-inflammatory, and antioxidant properties, have emerged as a promising treatment. These nanoparticles can scavenge reactive oxygen species (ROS), reduce inflammation, and stimulate tissue regeneration by modulating macrophage polarization and promoting angiogenesis. However, limitations such as poor biocompatibility, aggregation, and dose-dependent toxicity hinder their clinical application. Recent advances in coating strategies—including polymeric, natural biomolecule, and hybrid coatings have improved the stability, targeting, and controlled release of CeO 2 nanoparticles. This review discusses the design, therapeutic mechanisms, and safety considerations of coated CeO 2 nanoparticles in DFU treatment, with emphasis on combination therapies and smart-responsive coatings. Clinical translation challenges and future research directions are also addressed.
- 12 January 2026
- Published by Frontiers Media SA in Frontiers in Bioengineering and Biotechnology
- Vol. 13, 1695821
Top Cited PapersOpen AccessCerium oxide nanoparticles for enhanced healing of diabetic foot ulcers
One of the main complications of diabetes is diabetic foot ulcers (DFUs), which have a substantial global impact on morbidity, medical expenses, and lower limb amputations. A complicated microenvironment—characterized by bacterial infections, chronic inflammation, oxidative stress, and poor angiogenesis impedes the healing process of DFUs. Cerium oxide nanoparticles (CeO 2 nanoparticles), owing to their antibacterial, anti-inflammatory, and antioxidant properties, have emerged as a promising treatment. These nanoparticles can scavenge reactive oxygen species (ROS), reduce inflammation, and stimulate tissue regeneration by modulating macrophage polarization and promoting angiogenesis. However, limitations such as poor biocompatibility, aggregation, and dose-dependent toxicity hinder their clinical application. Recent advances in coating strategies—including polymeric, natural biomolecule, and hybrid coatings have improved the stability, targeting, and controlled release of CeO 2 nanoparticles. This review discusses the design, therapeutic mechanisms, and safety considerations of coated CeO 2 nanoparticles in DFU treatment, with emphasis on combination therapies and smart-responsive coatings. Clinical translation challenges and future research directions are also addressed.
- Open Access
- 1 December 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (12) , 12561-12581
Early identification of abnormal pulmonary infectious diseases using unsupervised anomaly detection
Original Article Early identification of abnormal pulmonary infectious diseases using unsupervised anomaly detection Rong Liu, Yuhe Zhu, Zhangwen Lyu, Yite Gao, Yinwei Zhan, Yuefu Zhan
- 1 December 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (12) , 12561-12581
Open AccessEarly identification of abnormal pulmonary infectious diseases using unsupervised anomaly detection
Original Article Early identification of abnormal pulmonary infectious diseases using unsupervised anomaly detection Rong Liu, Yuhe Zhu, Zhangwen Lyu, Yite Gao, Yinwei Zhan, Yuefu Zhan
- Open Access
- 10 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Pixel level deep reinforcement learning for accurate and robust medical image segmentation
Existing deep learning methods have achieved significant success in medical image segmentation. However, this success largely relies on stacking advanced modules and architectures, which has created a path dependency. This path dependency is unsustainable, as it leads to increasingly larger model parameters and higher deployment costs. To break this path dependency, we introduce deep reinforcement learning to enhance segmentation performance. However, current deep reinforcement learning methods face challenges such as high training cost, independent iterative processes, and high uncertainty of segmentation masks. Consequently, we propose a Pixel-level Deep Reinforcement Learning model with pixel-by-pixel Mask Generation (PixelDRL-MG) for more accurate and robust medical image segmentation. PixelDRL-MG adopts a dynamic iterative update policy, directly segmenting the regions of interest without requiring user interaction or coarse segmentation masks. We propose a Pixel-level Asynchronous Advantage Actor-Critic (PA3C) strategy to treat each pixel as an agent whose state (foreground or background) is iteratively updated through direct actions. Our experiments on two commonly used medical image segmentation datasets demonstrate that PixelDRL-MG achieves more superior segmentation performances than the state-of-the-art segmentation baselines (especially in boundaries) using significantly fewer model parameters. We also conducted detailed ablation studies to enhance understanding and facilitate practical application. Additionally, PixelDRL-MG performs well in low-resource settings (i.e., 50-shot or 100-shot), making it an ideal choice for real-world scenarios.
- 10 March 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-18
Open AccessPixel level deep reinforcement learning for accurate and robust medical image segmentation
Existing deep learning methods have achieved significant success in medical image segmentation. However, this success largely relies on stacking advanced modules and architectures, which has created a path dependency. This path dependency is unsustainable, as it leads to increasingly larger model parameters and higher deployment costs. To break this path dependency, we introduce deep reinforcement learning to enhance segmentation performance. However, current deep reinforcement learning methods face challenges such as high training cost, independent iterative processes, and high uncertainty of segmentation masks. Consequently, we propose a Pixel-level Deep Reinforcement Learning model with pixel-by-pixel Mask Generation (PixelDRL-MG) for more accurate and robust medical image segmentation. PixelDRL-MG adopts a dynamic iterative update policy, directly segmenting the regions of interest without requiring user interaction or coarse segmentation masks. We propose a Pixel-level Asynchronous Advantage Actor-Critic (PA3C) strategy to treat each pixel as an agent whose state (foreground or background) is iteratively updated through direct actions. Our experiments on two commonly used medical image segmentation datasets demonstrate that PixelDRL-MG achieves more superior segmentation performances than the state-of-the-art segmentation baselines (especially in boundaries) using significantly fewer model parameters. We also conducted detailed ablation studies to enhance understanding and facilitate practical application. Additionally, PixelDRL-MG performs well in low-resource settings (i.e., 50-shot or 100-shot), making it an ideal choice for real-world scenarios.
- Open Access
- 1 January 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (1) , 1-14
High performance of the diffusion magnetic resonance imaging biomarker diffusion-derived ‘vessel density’ (DDVD) for separating placentas associated with pre-eclampsia from placentas in normal pregnancy
Background: Diffusion-derived ‘vessel density’ (DDVD) is a surrogate of the area of micro-vessels per unit tissue. DDVD is calculated according to: DDVD (b0b50) = Sb0/ROIarea0 − Sb50/ROIarea50, where Sb0 and Sb50 refer to the tissue signal when b is 0 or 50 s/mm2. Due to the complexity of pre-eclampsia (PE), even a combination of risk factors and available tests cannot accurately diagnose or predict PE. This study applies DDVD to assess the perfusion of placenta, and study placenta perfusion disturbance in PE patients. Methods: Diffusion-weighted images with b-values of 0, 50 s/mm2 were acquired in 44 normal pregnancies and 25 patients with PE with a 3.0-T magnet. Diffusion-derived vessel density ratio (DDVDr) was calculated according to: DDVD of placenta/DDVD of fetal brain. Results: The DDVD values of the control placentas [n=44, median: 67.53, 95% confidence interval (CI): 52.84–79.46] were significantly higher than those of the PE patients (n=25, median: 23.66, 95% CI: 17.22–45.57, PConclusions: DDVDr may play an important role in patient PE prediction and follow-up.
- 1 January 2025
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 15 (1) , 1-14
Open AccessHigh performance of the diffusion magnetic resonance imaging biomarker diffusion-derived ‘vessel density’ (DDVD) for separating placentas associated with pre-eclampsia from placentas in normal pregnancy
Background: Diffusion-derived ‘vessel density’ (DDVD) is a surrogate of the area of micro-vessels per unit tissue. DDVD is calculated according to: DDVD (b0b50) = Sb0/ROIarea0 − Sb50/ROIarea50, where Sb0 and Sb50 refer to the tissue signal when b is 0 or 50 s/mm2. Due to the complexity of pre-eclampsia (PE), even a combination of risk factors and available tests cannot accurately diagnose or predict PE. This study applies DDVD to assess the perfusion of placenta, and study placenta perfusion disturbance in PE patients. Methods: Diffusion-weighted images with b-values of 0, 50 s/mm2 were acquired in 44 normal pregnancies and 25 patients with PE with a 3.0-T magnet. Diffusion-derived vessel density ratio (DDVDr) was calculated according to: DDVD of placenta/DDVD of fetal brain. Results: The DDVD values of the control placentas [n=44, median: 67.53, 95% confidence interval (CI): 52.84–79.46] were significantly higher than those of the PE patients (n=25, median: 23.66, 95% CI: 17.22–45.57, PConclusions: DDVDr may play an important role in patient PE prediction and follow-up.
- Open Access
- 1 December 2024
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 14 (12) , 9246-9257
Relationship between glymphatic system dysfunction and cognitive impairment in patients with mild-to-moderate chronic traumatic brain injury: an analysis of the analysis along the perivascular space (ALPS) index
Cognitive impairment associated with mild-to-moderate chronic traumatic brain injury (TBI) presents substantial challenges for which the functionality of the brain glymphatic system is a key area of interest. This study aimed to explore the functionality of the brain glymphatic system in patients with chronic cognitive impairment following mild-to-moderate TBI using diffusion tensor image analysis along the perivascular space (DTI-ALPS). This was a prospective cross-sectional study. A total of 56 patients with mild-to-moderate chronic TBI at the Radiology Outpatient Clinic of the First Affiliated Hospital of Hainan Medical University were enrolled in the study between January 2021 and July 2022. Additionally, 20 healthy control (HC) subjects were recruited from the Health Screening Center during the same period as the HC group. Relevant clinical data for all the participants were collected, and cognitive assessments were conducted using cognitive scales. The TBI patients were categorized into the traumatic brain injury cognitive impairment (TBI-CI) and traumatic brain injury cognitively normal (TBI-CN) groups based on their of the Chinese Version of the Montreal Cognitive Assessment-Basic (MoCA-BC) scores. Each group comprised 20 subjects. All three groups of participants underwent diffusion tensor imaging (DTI). The DTI data were processed and analyzed using the MRIcron and FMRIB Software Library (FSL) toolboxes, and the analysis along the perivascular space (ALPS) index was calculated. Differences in the ALPS index among the three groups were examined by an analysis of covariance, adjusted for age and gender. A corrected receiver operating characteristic (ROC) curve analysis was employed to evaluate the diagnostic performance of the ALPS index in identifying patients with traumatic chronic cognitive impairment. Compared with the HC group, both the mild-to-moderate TBI patients with and without cognitive impairment had a decreased ALPS index (HC vs. TBI-CI: 1.629 vs. 1.302, P<0.001; HC vs. TBI-CN: 1.629 vs. 1.523, P=0.003). Moreover, the decrease in the ALPS index was more significant in the mild-to-moderate TBI patients with cognitive impairment (TBI-CN vs. TBI-CI: 1.523 vs. 1.302, P<0.001). The adjusted ROC curve analysis revealed that the area under the curve (AUC) of the ALPS index for diagnosing traumatic chronic cognitive impairment was 0.983 [95% confidence interval (CI): 0.953–1, P<0.001], with a sensitivity of 90% and specificity of 95%. Cognitive impairment in patients with mild-to-moderate chronic TBI may be associated with impairment of the glymphatic system. Additionally, the ALPS index may serve as a potential predictor of the disease. Our findings provide some novel insights into the pathophysiological mechanisms underlying cognitive impairment in mild-to-moderate chronic TBI.
- 1 December 2024
- Published by AME Publishing Company in Quantitative Imaging in Medicine and Surgery
- Vol. 14 (12) , 9246-9257
Open AccessRelationship between glymphatic system dysfunction and cognitive impairment in patients with mild-to-moderate chronic traumatic brain injury: an analysis of the analysis along the perivascular space (ALPS) index
Cognitive impairment associated with mild-to-moderate chronic traumatic brain injury (TBI) presents substantial challenges for which the functionality of the brain glymphatic system is a key area of interest. This study aimed to explore the functionality of the brain glymphatic system in patients with chronic cognitive impairment following mild-to-moderate TBI using diffusion tensor image analysis along the perivascular space (DTI-ALPS). This was a prospective cross-sectional study. A total of 56 patients with mild-to-moderate chronic TBI at the Radiology Outpatient Clinic of the First Affiliated Hospital of Hainan Medical University were enrolled in the study between January 2021 and July 2022. Additionally, 20 healthy control (HC) subjects were recruited from the Health Screening Center during the same period as the HC group. Relevant clinical data for all the participants were collected, and cognitive assessments were conducted using cognitive scales. The TBI patients were categorized into the traumatic brain injury cognitive impairment (TBI-CI) and traumatic brain injury cognitively normal (TBI-CN) groups based on their of the Chinese Version of the Montreal Cognitive Assessment-Basic (MoCA-BC) scores. Each group comprised 20 subjects. All three groups of participants underwent diffusion tensor imaging (DTI). The DTI data were processed and analyzed using the MRIcron and FMRIB Software Library (FSL) toolboxes, and the analysis along the perivascular space (ALPS) index was calculated. Differences in the ALPS index among the three groups were examined by an analysis of covariance, adjusted for age and gender. A corrected receiver operating characteristic (ROC) curve analysis was employed to evaluate the diagnostic performance of the ALPS index in identifying patients with traumatic chronic cognitive impairment. Compared with the HC group, both the mild-to-moderate TBI patients with and without cognitive impairment had a decreased ALPS index (HC vs. TBI-CI: 1.629 vs. 1.302, P<0.001; HC vs. TBI-CN: 1.629 vs. 1.523, P=0.003). Moreover, the decrease in the ALPS index was more significant in the mild-to-moderate TBI patients with cognitive impairment (TBI-CN vs. TBI-CI: 1.523 vs. 1.302, P<0.001). The adjusted ROC curve analysis revealed that the area under the curve (AUC) of the ALPS index for diagnosing traumatic chronic cognitive impairment was 0.983 [95% confidence interval (CI): 0.953–1, P<0.001], with a sensitivity of 90% and specificity of 95%. Cognitive impairment in patients with mild-to-moderate chronic TBI may be associated with impairment of the glymphatic system. Additionally, the ALPS index may serve as a potential predictor of the disease. Our findings provide some novel insights into the pathophysiological mechanisms underlying cognitive impairment in mild-to-moderate chronic TBI.