Wenhui Lei
YOU?
Author Swipe
View article: A co-evolving agentic AI system for medical imaging analysis
A co-evolving agentic AI system for medical imaging analysis Open
Agentic AI is rapidly advancing in healthcare and biomedical research. However, in medical image analysis, their performance and adoption remain limited due to the lack of a robust ecosystem, insufficient toolsets, and the absence of real-…
View article: Gut microbiota-driven neuroinflammation in Alzheimer’s disease: from mechanisms to therapeutic opportunities
Gut microbiota-driven neuroinflammation in Alzheimer’s disease: from mechanisms to therapeutic opportunities Open
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder characterized by amyloid-beta (Aβ) plaques, tau hyperphosphorylation, and chronic neuroinflammation. While neuroinflammation—mediated by microglial and astrocyte activati…
View article: Combining PIM‐2 and PARP1 Inhibitors Induces MICA Expression on Multiple Myeloma Cells to Activate NK Cells through NKG2D Binding
Combining PIM‐2 and PARP1 Inhibitors Induces MICA Expression on Multiple Myeloma Cells to Activate NK Cells through NKG2D Binding Open
While immunogenic death in tumor cells activates specific anti‐tumor T cells, the activation of non‐specific natural killer (NK) cells through tumor interactions remains underexplored. This study investigates how inducing DNA damage in mul…
View article: Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling
Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling Open
Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explici…
View article: TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation
TK-Mamba: Marrying KAN With Mamba for Text-Driven 3D Medical Image Segmentation Open
3D medical image segmentation is important for clinical diagnosis and treatment but faces challenges from high-dimensional data and complex spatial dependencies. Traditional single-modality networks, such as CNNs and Transformers, are ofte…
View article: Harnessing the human gut microbiota: an emerging frontier in combatting multidrug-resistant bacteria
Harnessing the human gut microbiota: an emerging frontier in combatting multidrug-resistant bacteria Open
Antimicrobial resistance (AMR) has become a major and escalating global health threat, undermining the effectiveness of current antibiotic and antimicrobial therapies. The rise of multidrug-resistant bacteria has led to increasingly diffic…
View article: Interactive Segmentation and Report Generation for CT Images
Interactive Segmentation and Report Generation for CT Images Open
Automated CT report generation plays a crucial role in improving diagnostic accuracy and clinical workflow efficiency. However, existing methods lack interpretability and impede patient-clinician understanding, while their static nature re…
View article: LesionDiffusion: Towards Text-controlled General Lesion Synthesis
LesionDiffusion: Towards Text-controlled General Lesion Synthesis Open
Fully-supervised lesion recognition methods in medical imaging face challenges due to the reliance on large annotated datasets, which are expensive and difficult to collect. To address this, synthetic lesion generation has become a promisi…
View article: Unifying Multiple Foundation Models for Advanced Computational Pathology
Unifying Multiple Foundation Models for Advanced Computational Pathology Open
Foundation models have advanced computational pathology by learning transferable visual representations from large histological datasets, yet recent evaluations reveal substantial variability in their performance across tasks. This inconsi…
View article: Oral fungal dysbiosis and systemic immune dysfunction in Chinese patients with schizophrenia
Oral fungal dysbiosis and systemic immune dysfunction in Chinese patients with schizophrenia Open
Oral microbial dysbiosis contributes to the development of schizophrenia (SZ). While numerous studies have investigated alterations in the oral bacterial microbiota among SZ patients, investigations into the fungal microbiota, another inte…
View article: Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment
Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment Open
Recent advancements in medical vision-language pre-training models have driven significant progress in zero-shot disease recognition. However, transferring image-level knowledge to pixel-level tasks, such as lesion segmentation in 3D CT sc…
View article: Altered gut microbiota and systemic immunity in Chinese patients with schizophrenia comorbid with metabolic syndrome
Altered gut microbiota and systemic immunity in Chinese patients with schizophrenia comorbid with metabolic syndrome Open
These findings suggested that gut microbiota dysbiosis and immune dysfunction play a vital role in SZ-MetS development, highlighting potential therapeutic approaches targeting the gut microbiota. While these therapies show promise, further…
View article: CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation
CT Synthesis with Conditional Diffusion Models for Abdominal Lymph Node Segmentation Open
Despite the significant success achieved by deep learning methods in medical image segmentation, researchers still struggle in the computer-aided diagnosis of abdominal lymph nodes due to the complex abdominal environment, small and indist…
View article: Challenges and strategies associated with CAR-T cell therapy in blood malignancies
Challenges and strategies associated with CAR-T cell therapy in blood malignancies Open
Cellular immunotherapy, particularly CAR-T cells, has shown potential in the improvement of outcomes in patients with refractory and recurrent malignancies of the blood. However, achieving sustainable long-term complete remission for blood…
View article: Exploring the gut mycobiome: differential composition and clinical associations in hypertension, chronic kidney disease, and their comorbidity
Exploring the gut mycobiome: differential composition and clinical associations in hypertension, chronic kidney disease, and their comorbidity Open
Background Hypertension (HTN) and chronic kidney disease (CKD) pose significant global health challenges and often coexist, amplifying cardiovascular risks. Recent attention has turned to the gut mycobiome as a potential factor in their pa…
View article: Prosthetic brachial artery-external jugular vein arteriovenous grafts as a novel option for hemodialysis access: A case report
Prosthetic brachial artery-external jugular vein arteriovenous grafts as a novel option for hemodialysis access: A case report Open
Following the exhaustion of all conventional hemodialysis access options in the upper extremities, a prosthetic arteriovenous loop was performed between the brachial artery (BA) and the external jugular vein (EJV) as a novel access option …
View article: Akkermansia muciniphila in neuropsychiatric disorders: friend or foe?
Akkermansia muciniphila in neuropsychiatric disorders: friend or foe? Open
An accumulating body of evidence suggests that the bacterium Akkermansia muciniphila exhibits positive systemic effects on host health, mainly by improving immunological and metabolic functions, and it is therefore regarded as a promising …
View article: Efficient Subclass Segmentation in Medical Images
Efficient Subclass Segmentation in Medical Images Open
As research interests in medical image analysis become increasingly fine-grained, the cost for extensive annotation also rises. One feasible way to reduce the cost is to annotate with coarse-grained superclass labels while using limited fi…
View article: MedLSAM: Localize and Segment Anything Model for 3D CT Images
MedLSAM: Localize and Segment Anything Model for 3D CT Images Open
Recent advancements in foundation models have shown significant potential in medical image analysis. However, there is still a gap in models specifically designed for medical image localization. To address this, we introduce MedLAM, a 3D m…
View article: Probiotics for the treatment of depression and its comorbidities: A systemic review
Probiotics for the treatment of depression and its comorbidities: A systemic review Open
Depression is one of the most common psychiatric conditions, characterized by significant and persistent depressed mood and diminished interest, and often coexists with various comorbidities. The underlying mechanism of depression remain e…
View article: Alterations of the fecal and vaginal microbiomes in patients with systemic lupus erythematosus and their associations with immunological profiles
Alterations of the fecal and vaginal microbiomes in patients with systemic lupus erythematosus and their associations with immunological profiles Open
Background Exploring the human microbiome in multiple body niches is beneficial for clinicians to determine which microbial dysbiosis should be targeted first. We aimed to study whether both the fecal and vaginal microbiomes are disrupted …
View article: CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation Open
Generalization to previously unseen images with potential domain shifts and different styles is essential for clinically applicable medical image segmentation, and the ability to disentangle domain-specific and domain-invariant features is…
View article: Elevated Levels of Serum Alkaline Phosphatase are Associated with Increased Risk of Cardiovascular Disease: A Prospective Cohort Study
Elevated Levels of Serum Alkaline Phosphatase are Associated with Increased Risk of Cardiovascular Disease: A Prospective Cohort Study Open
Higher ALP levels, even within the normal range, were significantly associated with increased risks of CVD, in a dose-dependent manner. These findings suggested that regular monitoring of ALP levels may help in improving the early identifi…
View article: Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures
Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures Open
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for medical image segmentation, yet need plenty of manual annotations for training. Semi-Supervised Learning (SSL) methods are promising to reduce the requirem…
View article: HMRNet: High and Multi-Resolution Network with Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy
HMRNet: High and Multi-Resolution Network with Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy Open
Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy. Despite that variants of U-Net are state-of-the-a…