Search

Your search keyword '"Lei, Wenbin"' showing total 216 results
Start Over Author "Lei, Wenbin"
216 results on '"Lei, Wenbin"'

1. 3D-LSPTM: An Automatic Framework with 3D-Large-Scale Pretrained Model for Laryngeal Cancer Detection Using Laryngoscopic Videos

Author

Qiu, Meiyu, Li, Yun, Huang, Wenjun, Zhang, Haoyun, Zheng, Weiping, Lei, Wenbin, and Fan, Xiaomao

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Laryngeal cancer is a malignant disease with a high morality rate in otorhinolaryngology, posing an significant threat to human health. Traditionally larygologists manually visual-inspect laryngeal cancer in laryngoscopic videos, which is quite time-consuming and subjective. In this study, we propose a novel automatic framework via 3D-large-scale pretrained models termed 3D-LSPTM for laryngeal cancer detection. Firstly, we collect 1,109 laryngoscopic videos from the First Affiliated Hospital Sun Yat-sen University with the approval of the Ethics Committee. Then we utilize the 3D-large-scale pretrained models of C3D, TimeSformer, and Video-Swin-Transformer, with the merit of advanced featuring videos, for laryngeal cancer detection with fine-tuning techniques. Extensive experiments show that our proposed 3D-LSPTM can achieve promising performance on the task of laryngeal cancer detection. Particularly, 3D-LSPTM with the backbone of Video-Swin-Transformer can achieve 92.4% accuracy, 95.6% sensitivity, 94.1% precision, and 94.8% F_1.

Published
2024

2. SAM-FNet: SAM-Guided Fusion Network for Laryngo-Pharyngeal Tumor Detection

Author

Wei, Jia, Li, Yun, Qiu, Meiyu, Chen, Hongyu, Fan, Xiaomao, and Lei, Wenbin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Laryngo-pharyngeal cancer (LPC) is a highly fatal malignant disease affecting the head and neck region. Previous studies on endoscopic tumor detection, particularly those leveraging dual-branch network architectures, have shown significant advancements in tumor detection. These studies highlight the potential of dual-branch networks in improving diagnostic accuracy by effectively integrating global and local (lesion) feature extraction. However, they are still limited in their capabilities to accurately locate the lesion region and capture the discriminative feature information between the global and local branches. To address these issues, we propose a novel SAM-guided fusion network (SAM-FNet), a dual-branch network for laryngo-pharyngeal tumor detection. By leveraging the powerful object segmentation capabilities of the Segment Anything Model (SAM), we introduce the SAM into the SAM-FNet to accurately segment the lesion region. Furthermore, we propose a GAN-like feature optimization (GFO) module to capture the discriminative features between the global and local branches, enhancing the fusion feature complementarity. Additionally, we collect two LPC datasets from the First Affiliated Hospital (FAHSYSU) and the Sixth Affiliated Hospital (SAHSYSU) of Sun Yat-sen University. The FAHSYSU dataset is used as the internal dataset for training the model, while the SAHSYSU dataset is used as the external dataset for evaluating the model's performance. Extensive experiments on both datasets of FAHSYSU and SAHSYSU demonstrate that the SAM-FNet can achieve competitive results, outperforming the state-of-the-art counterparts. The source code of SAM-FNet is available at the URL of https://github.com/VVJia/SAM-FNet.

Published
2024

3. Rethinking Radiology Report Generation via Causal Inspired Counterfactual Augmentation

Author

Song, Xiao, Liu, Jiafan, Li, Yun, Liu, Yan, Lei, Wenbin, and Wang, Ruxin

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Computation and Language, Computer Science - Multimedia
Abstract

Radiology Report Generation (RRG) draws attention as a vision-and-language interaction of biomedical fields. Previous works inherited the ideology of traditional language generation tasks, aiming to generate paragraphs with high readability as reports. Despite significant progress, the independence between diseases-a specific property of RRG-was neglected, yielding the models being confused by the co-occurrence of diseases brought on by the biased data distribution, thus generating inaccurate reports. In this paper, to rethink this issue, we first model the causal effects between the variables from a causal perspective, through which we prove that the co-occurrence relationships between diseases on the biased distribution function as confounders, confusing the accuracy through two backdoor paths, i.e. the Joint Vision Coupling and the Conditional Sequential Coupling. Then, we proposed a novel model-agnostic counterfactual augmentation method that contains two strategies, i.e. the Prototype-based Counterfactual Sample Synthesis (P-CSS) and the Magic-Cube-like Counterfactual Report Reconstruction (Cube), to intervene the backdoor paths, thus enhancing the accuracy and generalization of RRG models. Experimental results on the widely used MIMIC-CXR dataset demonstrate the effectiveness of our proposed method. Additionally, a generalization performance is evaluated on IU X-Ray dataset, which verifies our work can effectively reduce the impact of co-occurrences caused by different distributions on the results., Comment: 10 pages,5 figures

Published
2023

16. Exosomal circPVT1 promotes angiogenesis in laryngeal cancer by activating the Rap1b–VEGFR2 signaling pathway.

Author

Lyu, Kexing, Tang, Bingjie, Huang, Bixue, Xu, Zhenglin, Liu, Tesi, Fang, Ruihua, Li, Yun, Chen, Yi, Chen, Lin, Zhang, Minjuan, Chen, Lifan, and Lei, Wenbin

Subjects
VASCULAR endothelial growth factor receptors, VASCULAR endothelial growth factors, LINCRNA, PHOSPHATIDYLINOSITOL 3-kinases, CIRCULAR RNA
Abstract

Laryngeal cancer (LC) is the second most common head and neck cancer and has a decreasing 5-year survival rate worldwide. Circular RNAs (circRNAs) regulate cancer development in diverse ways based on their distinct biogenesis mechanisms and expansive regulatory roles. However, currently, there is little research on how exosomal circRNAs are involved in the development of LC. Here, we demonstrated that circPVT1, a circRNA derived from the well-studied long noncoding RNA PVT1, is correlated with disease progression in LC and promotes angiogenesis both in vivo and in vitro. Mechanistically, circPVT1 is loaded into LC cell-secreted exosomes and taken up by vascular epithelium cells. By sponging miR-30c-5p, exosomal circPVT1 promotes Rap1b expression, which dramatically enhances vascular endothelial growth factor receptor 2 and the phosphatidylinositol 3-kinase (PI3K)/AKT pathway activation, ultimately resulting in the induction of angiogenesis. Furthermore, our xenograft models demonstrated that the combination of short hairpin RNA-circPVT1 and cetuximab showed high efficacy in inhibiting tumor growth and angiogenesis. Collectively, these findings uncover a novel mechanism of exosomal circRNA-mediated angiogenesis modulation and provide a preclinical rationale for testing this analogous combination in patients with LC. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

19. Mr-ResNeXt: A Multi-resolution Network Architecture for Detection of Obstructive Sleep Apnea

Author

Chen, Qiren, Yue, Huijun, Pang, Xiongwen, Lei, Wenbin, Zhao, Gansen, Liao, Enhong, Wang, Yongquan, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Kotenko, Igor, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Zhang, Haijun, editor, Zhang, Zhao, editor, Wu, Zhou, editor, and Hao, Tianyong, editor

Published
2020
Full Text
View/download PDF

26. Rethinking Radiology Report Generation via Causal Reasoning and Counterfactual Augmentation

Author

Song, Xiao, Liu, Jiafan, Li, Yun, Lei, Wenbin, Wang, Ruxin, Song, Xiao, Liu, Jiafan, Li, Yun, Lei, Wenbin, and Wang, Ruxin

Abstract

Radiology Report Generation (RRG) draws attention as an interaction between vision and language fields. Previous works inherited the ideology of vision-to-language generation tasks,aiming to generate paragraphs with high consistency as reports. However, one unique characteristic of RRG, the independence between diseases, was neglected, leading to the injection of disease co-occurrence as a confounder that effects the results through backdoor path. Unfortunately, this confounder confuses the process of report generation worse because of the biased RRG data distribution. In this paper, to rethink this issue thoroughly, we reason about its causes and effects from a novel perspective of statistics and causality, where the Joint Vision Coupling and the Conditional Sentence Coherence Coupling are two aspects prone to implicitly decrease the accuracy of reports. Then, a counterfactual augmentation strategy that contains the Counterfactual Sample Synthesis and the Counterfactual Report Reconstruction sub-methods is proposed to break these two aspects of spurious effects. Experimental results and further analyses on two widely used datasets justify our reasoning and proposed methods., Comment: 10 pages,5 figures

Published
2023

28. Transnasal negative pressure therapy for accelerating healing and improving the prognosis of pharyngocutaneous fistula.

Author

Hu, Zhangwei, Guo, Xueqin, Chen, Lin, and Lei, Wenbin

Subjects
LARYNGECTOMY, NEGATIVE-pressure wound therapy, HEALING, WOUND healing, FISTULA, LOG-rank test, PROGNOSIS
Abstract

Background: Pharyngocutaneous fistula (PCF) is one of the most common complications of total laryngectomy. This study is to investigate the efficacy of a novel platform called transnasal negative pressure therapy (TNPT) in the management of PCF. Methods: We retrospectively reviewed 47 patients who underwent total laryngectomy between April 2015 and February 2021 and developed PCF in our hospital. We focused on the healing rate, dressing change frequency, and healing time between the TNPT and non‐TNPT groups. The 2 years overall survival (OS) was compared through the log‐rank test. Results: There were 18 patients in the TNPT group and 29 in the non‐TNPT group. There was no significant between‐group difference in the healing rate (chi‐square test). However, the frequency of dressing changes was significantly lower (p < 0.001) and the healing time was significantly shorter (p = 0.0194) in the TNPT group than in the non‐TNPT group. The 2‐year OS rate was significantly higher in the TNPT group (p = 0.0473, log‐rank test). Conclusion: TNPT promoted wound healing after surgery for PCF and improved the 2‐year OS rate. This tool is worthy of clinical application and promotion. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

33. ELISA based assays to measure adenosine deaminases concentration in serum and saliva for the diagnosis of ADA2 deficiency and cancer

Author

Luo, Wenwen, Dong, Liang, Chen, Fenghong, Lei, Wenbin, He, Liya, Zhou, Qing, Lamy, Thierry, and Zavialov, Andrey V.

Subjects
Adenosine, Adenosine Deaminase, Agammaglobulinemia, Neoplasms, Immunology, Humans, Intercellular Signaling Peptides and Proteins, Immunology and Allergy, Enzyme-Linked Immunosorbent Assay, Severe Combined Immunodeficiency, Saliva, Polyarteritis Nodosa
Abstract

Adenosine deaminases (ADAs) are enzymes of purine metabolism converting adenosine to inosine. There are two types of ADAs in humans ADA1 and ADA2. While both ADA1 and ADA2 share the same substrate, they differ in expression, cellular localization, and catalytic properties. The genetic deficiency of ADA1 results in severe combined immunodeficiency (SCID), while lack in ADA2 (DADA2) results in multiple phenotypes ranging from systemic inflammation to vascular pathology. Clinical studies have shown that the levels of ADAs in biological fluids are altered in pathophysiological conditions, suggesting that ADA activity could be a convenient marker for the diagnosis of immune diseases and cancer. Here, we describe sensitive and straightforward ELISA assays to measure ADA1 and ADA2 concentrations in biological fluids. Analysis of the serum and saliva samples from the healthy controls and DADA2 patients revealed that ADA2 enzyme concentration is significantly lower in patients than in healthy controls. In contrast, the concentration of ADA2 increases in the serum of patients with large granular leukocyte leukemia (LGLL) and patients’ saliva with head and neck cancer. Thus, this simple, non-invasive method allows for distinguishing healthy controls from the affected patient. It can be implemented in screening and diagnosis of DADA2 and follow up the treatment of LGLL and several types of head and neck cancer.

Published
2022

34. Type 2 and Type 17 Invariant Natural Killer T Cells Contribute to Local Eosinophilic and Neutrophilic Inflammation and Their Function Is Regulated by Mucosal Microenvironment in Nasal Polyps

Author

Ye, Xiaoyan, primary, Bao, Qing, additional, Chen, Hexin, additional, Meng, Qingxiang, additional, Li, Qianying, additional, Sun, Lin, additional, Li, Jian, additional, Lei, Wenbin, additional, Wen, Weiping, additional, He, Wenjing, additional, Jiao, Linyi, additional, Fang, Bixing, additional, Gao, Yifang, additional, and Li, Chunwei, additional

Published
2022
Full Text
View/download PDF

42. Risk factors and survival outcomes of laryngeal squamous cell carcinoma patients with lung metastasis: A population-based study

Author

Yang, Weiqiang, primary, Mei, Xueshuang, additional, Zhou, Yaqi, additional, Su, Rongfei, additional, Lei, Wenbin, additional, Zheng, Shixin, additional, Zhu, Rufei, additional, Guo, Lianrong, additional, Tao, Yuan, additional, Su, Yongjin, additional, Li, Jianyu, additional, Ding, Chuchu, additional, Zou, Songfeng, additional, Li, Xiaoling, additional, and Hu, Hongyi, additional

Published
2021
Full Text
View/download PDF

43. Long Noncoding RNA GAS5 Acts As A Tumor Suppressor In Laryngeal Squamous Cell Carcinoma Via miR-21

Author

Lyu,Kexing, Xu,Yang, Yue,Huijun, Li,Yun, Zhao,Jing, Chen,Lin, Wu,Jianhui, Zhu,Xiaolin, Chai,Liping, Li,Chunwei, Wen,Weiping, and Lei,Wenbin

Subjects
Cancer Management and Research, LSCC, proliferation, GAS5, apoptosis, long noncoding RNA, miR-21, Original Research
Abstract

Kexing Lyu,1,* Yang Xu,1,* Huijun Yue,1 Yun Li,1 Jing Zhao,2 Lin Chen,1 Jianhui Wu,3 Xiaolin Zhu,1 Liping Chai,1 Chunwei Li,1 Weiping Wen,1 Wenbin Lei1 1Department of Otolaryngology, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, People’s Republic of China; 2Department of Otolaryngology, The Third Hospital of Heibei Medical University, Shijiazhuang, People’s Republic of China; 3Department of Otolaryngology, Meizhou People’s Hospital, Meizhou, People’s Republic of China*These authors contributed equally to this workCorrespondence: Weiping Wen; Wenbin LeiDepartment of Otolaryngology, The First Affiliated Hospital of Sun Yet-Sen University, Yuexiu, Guangzhou, Guangdong, People’s Republic of ChinaTel +86 20 8733 3733Fax +86 20 8733 3108Email wenwp@mail.sysu.edu.cn; leiwb@mail.sysu.edu.cnPurpose: Long noncoding RNAs (lncRNAs) have been identified as an important class of noncoding RNAs that are deeply involved in multiple biological processes in tumorigenesis. This study is to investigate the critical roles and biological function of lncRNA growth arrest-specific 5 (GAS5) in tumorigenesis of laryngeal squamous cell carcinoma (LSCC).Patients and methods: A total of 59 samples of LSCC and paired adjacent tissue, as well as corresponding clinicopathological information were collected. GAS5 expression in both LSCC tissues and human SUN1076 and SNU899 cell lines were analyzed by Real-time quantitative RT-PCR method. Ectopic expression of GAS5 by vector transfection in LSCC cell lines and followed by in vitro experiments was to investigate the critical roles and function of GAS5 in LSCC. Cell Counting Kit 8 (CCK8) assay and PE/7AAD Annexin V Apoptosis analysis was to evaluate cell proliferation ability and cell apoptosis. Co-transfection of GAS5 and miR-21 was to explore the interaction between GAS5 and miR-21 in LSCC. BAX and CDK6 protein level were analyzed by western blot method.Results: This study demonstrated that GAS5 was significantly downregulated in LSCC tissue and human LSCC cell lines. GAS5 levels were correlated with the clinicopathological features of LSCC patients. In addition, the ectopic expression of GAS5 significantly inhibited cell proliferation and promoted apoptosis. Co-expression analyses indicated that GAS5 is negatively correlated with miR-21 in LSCC tissues. Overexpression of miR-21 eliminated GAS5-mediated cell apoptosis and proliferation suppression. Furthermore, GAS5, which upregulated BAX mRNA expression and downregulated CDK6 mRNA expression, was reversed by ectopic expression of miR-21.Conclusion: GAS5 suppresses LSCC progression through the negative regulation of miR-21 and its targets involved in cell proliferation and apoptosis, indicating that GAS5 may serve as a biomarker and potential target for LSCC therapy.Keywords: long noncoding RNA, GAS5, LSCC, miR-21, proliferation, apoptosisCorrigendumfor this paper has been published

Published
2019

44. Deep Learning for Diagnosis and Classification of Obstructive Sleep Apnea: A Nasal Airflow-Based Multi-Resolution Residual Network

Author

Yue,Huijun, Lin,Yu, Wu,Yitao, Wang,Yongquan, Li,Yun, Guo,Xueqin, Huang,Ying, Wen,Weiping, Zhao,Gansen, Pang,Xiongwen, Lei,Wenbin, Yue,Huijun, Lin,Yu, Wu,Yitao, Wang,Yongquan, Li,Yun, Guo,Xueqin, Huang,Ying, Wen,Weiping, Zhao,Gansen, Pang,Xiongwen, and Lei,Wenbin

Abstract

Huijun Yue,1,* Yu Lin,1,* Yitao Wu,2,* Yongquan Wang,1 Yun Li,1 Xueqin Guo,1 Ying Huang,3 Weiping Wen,1 Gansen Zhao,2 Xiongwen Pang,2 Wenbin Lei1 1Otorhinolaryngology Hospital, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, 510080, People’s Republic of China; 2School of Computer Science, South China Normal University, Guangzhou, 510631, People’s Republic of China; 3Guangdong Province Traditional Chinese Medical Hospital, Guangzhou, 510000, People’s Republic of China*These authors contributed equally to this workCorrespondence: Wenbin LeiOtorhinolaryngology Hospital, The First Affiliated Hospital, Sun Yat-sen University, 58 Zhongshan Road II, Guangzhou, Guangdong, 510080, People’s Republic of ChinaTel +86-13922113299Email leiwb@mail.sysu.edu.cnXiongwen PangSchool of Computer Science, South China Normal University, 55 West Zhongshan Avenue, Guangzhou, Guangdong, 510631, People’s Republic of ChinaTel +86-18620638848Email augepang@scnu.edu.cnPurpose: This study evaluated a novel approach for diagnosis and classification of obstructive sleep apnea (OSA), called Obstructive Sleep Apnea Smart System (OSASS), using residual networks and single-channel nasal pressure airflow signals.Methods: Data were collected from the sleep center of the First Affiliated Hospital, Sun Yat-sen University, and the Integrative Department of Guangdong Province Traditional Chinese Medical Hospital. We developed a new model called the multi-resolution residual network (Mr-ResNet) based on a residual network to detect nasal pressure airflow signals recorded by polysomnography (PSG) automatically. The performance of the model was assessed by its sensitivity, specificity, accuracy, and F1-score. We built OSASS based on Mr-ResNet to estimate the apnea‒hypopnea index (AHI) and to classify the severity of OSA, and compared the agreement between OSASS output and the registered polysomnographic technologist (RPSGT) score, assessed by

Published
2021

45. Improving Survival of T3cN0M0 Glottic Squamous Cell Cancer With Elective Neck Dissection.

Author

Cai, Zhimou, Chen, Lin, Zhang, Jingwei, Wen, Yihui, and Lei, Wenbin

Abstract

Objectives/hypothesis: This study aimed to elucidate the role of elective neck dissection (END) in improving the outcome of T3cN0M0 glottic squamous cell cancer (GSCC).Study Design: Retrospective population-based database analysis.Methods: Patients with T3cN0M0 GSCC in the Surveillance, Epidemiology, and End Results database (SEER) were extracted and stratified into END and non-END cohorts. Propensity score matching (PSM) was used to eliminate the baseline variations. The Kaplan-Meier method was performed to access the association between END and survival.Results: We retrospectively analyzed 1,589 T3cN0M0 GSCC patients in the SEER database from 2004 to 2015, and found that only 22% to 58% T3cN0M0 GSCC were performed with END. After PSM, END cohort had better overall survival (OS) (median survival time: 93 vs. 55 months, respectively; P = .0047) and cancer-specific survival (CSS) (hazard ratio [HR] 0.48, 95% confidence interval [CI] 0.29-0.77, P = .003) than non-END cohort. In addition, Subgroup analysis also indicated END cohort had better OS or CSS than non-END cohort.Conclusion: This study demonstrated that in patients with T3cN0M0 GSCC, END significantly associated with better survival outcomes compared with non-END.Level Of Evidence: 3 Laryngoscope, 132:1807-1816, 2022. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results