检索结果-内蒙古大学图书馆

Improving the Neural Segmentation of Blurry Serial SEM Images by Blind Deblurring

Computational intelligence and neuroscience 2023年第1期2023卷 8936903页

作者： Ao Cheng Kai Kang Zhanpeng Zhu Ruobing Zhang Lirong Wang School of Electronic and Information Engineering Soochow University Suzhou 215009 China. Jiangsu Key Laboratory of Medical Optics Suzhou Institute of Biomedical Engineering and Technology Chinese Academy of Sciences Suzhou 215163 China. Etiometry Inc 280 Summer St Fl 4 Boston MA 02210 USA. Department of Neurosurgery The First Hospital of Jilin University Changchun Jilin 130021 China. Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei 230088 China.

Serial scanning electron microscopy (sSEM) has recently been developed to reconstruct complex largescale neural connectomes, through learning-based instance segmentation. However, blurry images are inevitable amid prolonged automated data acquisition due to imprecision in autofocusing and autostigmation, which impose a great challenge to accurate segmentation of the massive sSEM image data. Recently, learning-based methods, such as adversarial learning and supervised learning, have been proven to be effective for blind EM image deblurring. However, in practice, these methods suffer from the limited training dataset and the underrepresentation of high-resolution decoded features. Here, we propose a semisupervised learning guided progressive decoding network (SGPN) to exploit unlabeled blurry images for training and progressively enrich high-resolution feature representation. The proposed method outperforms the latest deblurring models on real SEM images with much less ground truth input. The improvement of the PSNR and SSIM is 1.04 dB and 0.086, respectively. We then trained segmentation models with deblurred datasets and demonstrated significant improvement in segmentation accuracy. The A-rand (Bogovic et al. 2013) decreased by 0.119 and 0.026, respectively, for 2D and 3D segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting out-of-distribution samples via variational auto-encoder with reliable uncertainty estimation

arXiv

引用

arXiv 2020年

作者： Ran, Xuming Xu, Mingkun Mei, Lingrui Xu, Qi Liu, Quanying Shenzhen Key Laboratory of Smart Healthcare Engineering Department of Biomedical Engineering Southern University of Science and Technology Shenzhen518055 China Center for Brain Inspired Computing Research Department of Precision Instrument Tsinghua University Beijing100084 China China Automotive Engineering Research Institute Chongqing401122 China School of Artifical Intelligence Electronic and Electrical Engineering School of Artifical Intelligence Dalian University of Technology Dalian116024 China College of Mathematics and Statistics Chongqing Jiaotong University Chongqing400074 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China

Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distribution (OOD) inputs than in-distribution (ID) inputs. To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs. In this study, we propose an improved noise contrastive prior (INCP) to be able to integrate into the encoder of VAEs, called INCPVAE. INCP is scalable, trainable and compatible with VAEs, and it also adopts the merits from the INCP for uncertainty estimation. Experiments on various datasets demonstrate that compared to the standard VAEs, our model is superior in uncertainty estimation for the OOD data and is robust in anomaly detection tasks. The INCPVAE model obtains reliable uncertainty estimation for OOD inputs and solves the OOD problem in VAE models. © 2020, CC BY.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Artificial neural network-based fungal chitin production for submicron-chitosan synthesis: effects on bioremediation for heavy metal pollution

引用

International Journal of Biological Macromolecules 2025年 314卷 144271页

作者： El-Feki, Khaled M.A. El-Metwally, Mohammad M. Taha, Tark H. Mohammed, Youssef M.M. Al-Otibi, Fatimah O. Fakhouri, Abdulaziz S. Menaa, Farid Saber, WesamEldin I.A. Bacteriological laboratory Beheira Water and Drainage Company Damanhour Egypt Botany and Microbiology Department Faculty of Science Damanhour University Damanhour22511 Egypt Department of Environmental Biotechnology Genetic Engineering and Biotechnology Research Institute City of Scientific Research and Technological Applications Alexandria Borg El-Arab21934 Egypt Botany and Microbiology Department Faculty of Science King Saud University Riyadh11451 Saudi Arabia Center of Excellence in Biotechnology Research King Saud University Riyadh11451 Saudi Arabia Department of Biomedical Technology College of Applied Medical Sciences King Saud University Riyadh12372 Saudi Arabia San DiegoCA92037 United States Giza12619 Egypt

This study focused on optimizing fungal chitin (CT) production from a newly identified Fusarium incarnatum (GenBank: OL314753) for subsequent synthesis of submicron chitosan (sm-CS) tailored for enhanced heavy metal removal. Initial attempts to optimize CT yield using mixed nitrogen sources (potassium nitrate, peptone, yeast extract) via Box-Behnken Design (BBD) were insufficient for predicting optimal conditions. Consequently, Artificial Neural Networks (ANN) successfully modeled the BBD experimental data, the optimal nitrogen concentrations to 4.89, 5.70, and 4.25 g/L, respectively, achieving an experimental CT yield of 3.998 g/L. The fungal CT was deacetylated to chitosan (CS), subsequently processed into sm-CS using ionotropic gelation. Characterization (FTIR, Raman, SEM, HR-TEM, EDX) confirmed the successful formation of sm-CS, demonstrating reduced particle size and increased surface area. Batch adsorption experiments revealed the superior heavy metal sequestration capacity of sm-CS, removing 80–90 % of Fe2+, Mn2+, Cu2+, and Zn2+, which outperformed CS (20–60 % removal). CS preferentially adsorbed Mn2+, whereas sm-CS showed affinity for Cu2+. sm-CS demonstrated excellent reusability, maintaining >85 % efficiency through five adsorption-desorption cycles, markedly surpassing CS regeneration. This integration of specific fungal strain, ANN optimization, and sm-CS, offers an efficient material for addressing complex multi-metal contamination, potentially mitigating nanotoxicity risks associated with some nanocomposite adsorbents. © 2025 Elsevier B.V.

关键词： Bioremediation

来源：评论

学校读者我要写书评

暂无评论

Causal inference of brain connectivity from fMRI with ψ-Learning Incorporated Linear non-Gaussian Acyclic Model (ψ-LiNGAM)

arXiv

引用

arXiv 2020年

作者： Wang, Yu-Ping Wilson, Tony W. Xiao, Li Calhoun, Vince D. Hu, Wenxing Cai, Biao Zhang, Gemeng Stephen, Julia M. Zhang, Aiying Department of Biomedical Engineering Tulane University New OrleansLA70118 United States Department of Neurological Sciences University of Nebraska Medical Center OmahaNE68198 United States Mind Research Network AlbuquerqueNM87106 United States Georgia State University Georgia Institute of Technology Emory University AtlantaGA30303 United States

Functional connectivity (FC) has become a primary means of understanding brain functions by identifying brain network interactions and, ultimately, how those interactions produce cognitions. A popular definition of FC is by statistical associations between measured brain regions. However, this could be problematic since the associations can only provide spatial connections but not causal interactions among regions of interests. Hence, it is necessary to study their causal relationship. Directed acyclic graph (DAG) models have been applied in recent FC studies but often encountered problems such as limited sample sizes and large number of variables (namely high-dimensional problems), which lead to both computational difficulty and convergence issues. As a result, the use of DAG models is problematic, where the identification of DAG models in general is nondeterministic polynomial time hard (NP-hard). To this end, we propose a ψ-learning incorporated linear non-Gaussian acyclic model (ψ-LiNGAM). We use the association model (ψ-learning) to facilitate causal inferences and the model works well especially for high-dimensional cases. Our simulation results demonstrate that the proposed method is more robust and accurate than several existing ones in detecting graph structure and direction. We then applied it to the resting state fMRI (rsfMRI) data obtained from the publicly available Philadelphia Neurodevelopmental Cohort (PNC) to study the cognitive variance, which includes 855 individuals aged 822 years. Therein, we have identified three types of hub structure: the in-hub, out-hub and sum-hub, which correspond to the centers of receiving, sending and relaying information, respectively. We also detected 16 most important pairs of causal flows. Several of the results have been verified to be biologically significant. To facilitate reproducible research, we make the code to be publicly available at https://***/Aiying0512/psi-LiNGAM. Copyright © 2020, The Authors. A

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Correction to: A Standards Organization for Open and FAIR Neuroscience: the International Neuroinformatics Coordinating Facility

引用

Neuroinformatics 2022年第1期20卷 37-38页

作者： Mathew Birdsall Abrams Jan G Bjaalie Samir Das Gary F Egan Satrajit S Ghosh Wojtek J Goscinski Jeffrey S Grethe Jeanette Hellgren Kotaleski Eric Tatt Wei Ho David N Kennedy Linda J Lanyon Trygve B Leergaard Helen S Mayberg Luciano Milanesi Roman Mouček J B Poline Prasun K Roy Stephen C Strother Tong Boon Tang Paul Tiesinga Thomas Wachtler Daniel K Wójcik Maryann E Martone INCF Secretariat Karolinska Institutet Stockholm Sweden. mathew@***. Institute of Basic Medical Sciences University of Oslo Oslo Norway. McGill Centre for Integrative Neuroscience McGill University Montreal QC Canada. Monash Biomedical Imaging Monash University Clayton VIC Australia. McGovern Institute for Brain Research Massachusetts Institute of Technology Cambridge MA USA. Department of Otolaryngology - Head and Neck Surgery Harvard Medical School Boston Boston MA USA. Monash eResearch Centre Monash University Melbourne VIC Australia. Department of Neuroscience School of Medicine University of California San Diego La Jolla CA USA. KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden. Centre for Intelligent Signal and Imaging Research Institute of Health and Analytics Universiti Teknologi PETRONAS Perak Malaysia. Department of Psychiatry University of Massachusetts Medical School Worcester MA USA. Serendipitea.World Hasselby Sweden. Nash Family Center for Advanced Circuit Therapeutics Icahn School of Medicine New York NY USA. Institute of Biomedical Technologies National Research Council (CNR) Milan Italy. Department of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic. Montreal Neurological Institute Faculty of Medicine and Health Sciences McGill University Montreal Canada. Computational Neuroscience & Neuroimaging Laboratory School of Bio-Medical Engineering Indian Institute of Technology (BHU) Varanasi UP India. Rotman Research Institute Baycrest Centre Department of Medical Biophysics University of Toronto Toronto ON Canada. Centre for Intelligent Signal and Imaging Research Institute of Health and Analytics Universiti Teknologi PETRONAS Bandar Seri Iskandar Malaysia. Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Nijmegen Netherlands. Department of Biology II Ludwig-Maximilians-Univers

A Correction to this paper has been published: https://***/10.1007/s12021-021-09522-x

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine reading and recovery of colors for hemoglobin-related bioassays and bioimaging

引用

Science Advances 2025年第23期11卷

作者： Sang Mok Park Semin Kwon Yuhyun Ji Haripriya Sakthivel Jung Woo Leem Yunsang Kwak Jonathan Huang George T.-C. Chiu Andrew R. O’Brien Raymond L. Konger Ying Wang Young L. Kim Weldon School of Biomedical Engineering Purdue University West Lafayette IN 47907 USA. Department of Mechanical System Engineering Kumoh National Institute of Technology 61 Daehak-ro Gumi-si Gyeongsangbuk-do 39177 Republic of Korea. Department of Medicine Indiana University School of Medicine Indianapolis IN 46202 USA. School of Mechanical Engineering Purdue University West Lafayette IN 47907 USA. Indiana University Simon Cancer Center Indianapolis IN 46202 USA. Department of Pathology and Laboratory Medicine Indiana University School of Medicine Indianapolis IN 46202 USA. Department of Dermatology Indiana University School of Medicine Indianapolis IN 46202 USA. Richard L. Roudebush Veterans’ Administration Medical Center Indianapolis IN 46202 USA. Department of Anesthesia Stark Neurosciences Research Institute Indiana University School of Medicine Indianapolis IN 46202 USA. Purdue Institute for Cancer Research West Lafayette IN 47907 USA. Purdue Quantum Science and Engineering Institute West Lafayette IN 47907 USA.

Despite advances in machine learning and computer vision for biomedical imaging, machine reading and learning of colors remain underexplored. Color consistency in computer vision, color constancy in human perception, and color accuracy in biomedical imaging are intertwined, complicating digital color–based diagnostics. Existing color reference charts and correction algorithms are inadequate for mobile health (mHealth) and telemedicine in digital health applications where detecting subtle color changes is critical. We present a machine reading and learning platform for color recognition and quantification to extract diagnostic information from colors. A unique combination of spectroscopic gamut determination, reference color optimization, nonsubjective quantification metrics, and neural network–based color recovery retrieves absolute colors of biological tissue. Studies on inflammation bioimaging of photocarcinogenesis and mHealth blood hemoglobin assessment demonstrate accuracy and precision in color recovery across diverse acquisition scenarios. The reported framework overcomes limitations of conventional colorimetric detection, enabling machine-compatible color-based bioassays and bioimaging, advancing digital diagnostics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selective CO2Reduction to Ethylene Mediated by Adaptive Small-molecule engineering of Copper-based Electrocatalysts

引用

Angewandte Chemie 2023年第50期135卷

作者： Dr. Shenghua Chen Dr. Chengliang Ye Dr. Ziwei Wang Dr. Peng Li Dr. Wenjun Jiang Dr. Zechao Zhuang Dr. Jiexin Zhu Dr. Xiaobo Zheng Dr. Shahid Zaman Dr. Honghui Ou Lei Lv Dr. Lin Tan Dr. Yaqiong Su Dr. Jiang Ouyang Prof. Dingsheng Wang National Innovation Platform (Center) for Industry-Education Integration of Energy Storage Technology School of Chemical Engineering and Technology Xi'an Jiaotong University Xi'an 710049 P. R. China Engineering Research Center of Advanced Rare Earth Materials Department of Chemistry Tsinghua University Beijing 100084 P. R. China School of Chemistry Xi'an Key Laboratory of Sustainable Energy Materials Chemistry State Key Laboratory of Electrical Insulation and Power Equipment Engineering Research Center of Energy Storage Materials and Devices Ministry of Education Xi'an Jiaotong University Xi'an 710049 P. R. China Qian Xuesen Laboratory of Space Technology China Academy of Space Technology Beijing 100094 P. R. China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing International School of Materials Science and Engineering Wuhan University of Technology Wuhan 430070 P. R China Key Laboratory of Energy Conversion and Storage Technologies Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen 518055 P. R. China School of Biomedical Engineering Guangzhou Medical University Guangzhou 511436 P. R. China

Electrochemical CO 2 reduction reaction (CO 2 RR) over Cu catalysts exhibits enormous potential for efficiently converting CO 2 to ethylene (C 2 H 4 ). However, achieving high C 2 H 4 selectivity remains a considerable challenge due to the propensity of Cu catalysts to undergo structural reconstruction during CO 2 RR. Herein, we report an in situ molecule modification strategy that involves tannic acid (TA) molecules adaptive regulating the reconstruction of a Cu-based material to a pathway that facilitates CO 2 reduction to C 2 H 4 products. An excellent Faraday efficiency (FE) of 63.6 % on C 2 H 4 with a current density of 497.2 mA cm −2 in flow cell was achieved, about 6.5 times higher than the pristine Cu catalyst which mainly produce CH 4 . The in situ X-ray absorption spectroscopy and Raman studies reveal that the hydroxyl group in TA stabilizes Cu δ+ during the CO 2 RR. Furthermore, theoretical calculations demonstrate that the Cu δ+ /Cu 0 interfaces lower the activation energy barrier for *CO dimerization, and hydroxyl species stabilize the *COH intermediate via hydrogen bonding, thereby promoting C 2 H 4 production. Such molecule engineering modulated electronic structure provides a promising strategy to achieve highly selective CO 2 reduction to value-added chemicals.

关键词： C2H4 CO2RR Cuδ+/Cu0 Hydrogen Bonding TA Molecule

来源：评论

学校读者我要写书评

暂无评论

Mental Arousal Level Recognition Competition on the Shared Database

Mental Arousal Level Recognition Competition on the Shared D...

引用

Iranian Conference on Electrical engineering

作者： Maryam Saidi Razieh Kaveh Amin Mohammadian Sajedeh Rezania Vahid Abootalebi Mohsen Mozafari Ensieh Khazaei Sara Bagheri Navid Hasanzadeh Behrad TaghiBeyglou Morteza Homayounfar Hossein Dini Seyedeh Sogand Hashemi Mohammadreza Asadi Hamideh Mirjani Sarvi Department of Signal Processing Research Center for Development of Advanced Technologies Tehran Iran Department of Electrical Engineering Sharif University of Technology Tehran Iran Department of Electrical Engineering Yazd University Yazd Iran Department of Biomedical Engineering Amirkabir University of Technology Tehran Iran

This paper presents the results of the shared task with the aim of arousal level recognition for the competition held in conjunction with the 27th Iranian Conference on Electrical engineering (ICEE 2019). A database annotated with arousal level labels released by Research center for Development of Advanced Technologies. The contest was held on arousal database according to a defined protocol. Three teams were able to enter into the final stage of the competition according to compare their performance measure with the baseline method. The baseline method is proposed by the data owner. The aim of this paper is outlining the database, protocol design, and providing an overview of top-ranked algorithms proposed for the shared task.

关键词： Arousal detection Physiological signals Multi-level arousal

来源：评论

学校读者我要写书评

暂无评论

Integrated wireless theranostic contact lens for in situ electrical sensing and regulation of glaucoma

Research Square

引用

Research Square 2021年

作者： Yang, Cheng Wu, Qianni Liu, Junqing Mo, Jingshan Li, Xiangling Yang, Chengduan Liu, Ziqi Yang, Jingbo Jiang, Lelun Chen, Weirong Chen, Hui-Jiuan Wang, Ji Xie, Xi State Key Laboratory of Optoelectronic Materials and Technologies Guangdong Province Key Laboratory of Display Material and Technology School of Electronics and Information Technology Sun Yat-Sen University Guangzhou510006 China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-Sen University Guangzhou510006 China The First Affiliated Hospital of Sun Yat-Sen University Sun Yat-Sen University Guangzhou510006 China Department of Cardiology The First Affiliated Hospital of Jinan University Guangzhou510630 China School of Biomedical Engineering Sun Yat-Sen University Guangzhou510006 China

Engineered closed-loop devices that can wirelessly track intraocular pressure (IOP) and offer feedback-medicine administrations are highly desirable for glaucoma treatments, yet remain difficult to develop. Integrated theranostic systems based on contact lens still confront several challenges, including size limits, requirements of wireless operations, and cross-coupling between multiple functional modulus. Here, for the first time to our knowledge, an integrated wireless theranostic contact lens (WTCL) for in situ electrical sensing and on-demand drug delivery of glaucoma was developed. The WTCL utilized a highly compact circuitry and structural design, which enabled high-degreed integration of IOP sensing and electrically controlled delivery modulus on the curved and limited surface of contact lens. The wireless IOP sensing modulus could ultra-sensitively detect IOP fluctuations, due to the unique cantilever configuration design of LCR circuit with ultra-soft air dielectric film sandwiched between each capacitive sensing plate. The drug delivery modulus employed a highly efficient wireless power transfer circuit, to trigger delivery of anti-glaucoma drug into aqueous chamber via iontophoresis to enhance drug permeation across cornea. The specialized design of frequency separation enabled individual operations of different modules without cross-coupling. The noninvasive, smart, wireless and closed-loop theranostic features endowed the WTCL as a highly promising system for glaucoma treatments. © 2021, CC BY.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

BAF45D cooperates with SMAD signaling and promotes early neural differentiation in P19 and H9 cells

引用

解剖学杂志 2021年第S1期44卷 220-220页

作者： Hu Xiujuan Jiang Jing Chen Xueying Liu Chang Liu Lihua Fang Shengyun Shen Yuxian Liu Chao Department of Histology and Embryology Institute of Stem Cell and Tissue EngineeringSchool of Basic Medical Sciences Institute of Clinical Phar macology Anhui Medical UniversityHefei 230032 Center for Biomedical Engineering and Technology University of MarylandBaltimoreMD 21201USA

BAF45Dis a member of BAF complex,which may play a crucial role in neural ***6 determines neuroectoderm formation,which is highly level ***45D is required for retinoic acid(RA)induced PAX6 ***6 expression is also regulated by TGF-beta/SMAD ***,mechanism of such regulation remains *** therefore sought to explore whether BAF45D regulates PAX6 expression through cooperating with TGF-beta/SMAD *** we identified BAF45D is required for expression of phosphorylated SMAD3 and PAX6 induced by ***-wide analysis revealed that during RA-induced early neural differentiation,BAF 45D knockdown failed to activate TGF-beta/SMAD signaling and induce expression of STAT3 and SMAD7,two negative regulators of TGF-beta/SMAD ***,in RA treated P19 and H9 cells,BAF45D interacts with BRG1 and phosphorylated SMAD3.

关键词： SMAD expression. PAX6

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：