检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pinkard, Henry Liu, Cherry Nyatigo, Fanice Fletcher, Daniel A. Waller, Laura Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Berkeley Institute for Data Science United States University of California San Francisco Bakar Computational Health Sciences Institute United States Department of Bioengineering University of California Berkeley United States

Computational microscopy, in which hardware and algorithms of an imaging system are jointly designed, shows promise for making imaging systems that cost less, perform more robustly, and collect new types of information. Often, the performance of computational imaging systems, especially those that incorporate machine learning, is sample-dependent. Thus, standardized datasets are an essential tool for comparing the performance of different approaches. Here, we introduce the Berkeley Single Cell Computational Microscopy (BSCCM) dataset, which contains over 12,000,000 images of 400,000 of individual white blood cells. The dataset contains images captured with multiple illumination patterns on an LED array microscope and fluorescent measurements of the abundance of surface proteins that mark different cell types. We hope this dataset will provide a valuable resource for the development and testing of new algorithms in computational microscopy and computer vision with practical biomedical applications. © 2024, CC BY.

关键词： Imaging systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning-enabled multiplexed point-of-care sensor using a paper-based fluorescence vertical flow assay

arXiv

引用

arXiv 2023年

作者： Goncharov, Artem Joung, Hyou-Arm Ghosh, Rajesh Han, Gyeo-Re Ballard, Zachary S. Maloney, Quinn Bell, Alexandra Aung, Chew Tin Zar Garner, Omai B. Di Carlo, Dino Ozcan, Aydogan Electrical & Computer Engineering Department United States Bioengineering Department United States Microbiology Immunology & Molecular Genetics United States United States Department of Pathology and Laboratory Medicine University of California Los AngelesCA90095 United States

We demonstrate multiplexed computational sensing with a point-of-care serodiagnosis assay to simultaneously quantify three biomarkers of acute cardiac injury. This point-of-care sensor includes a paper-based fluorescence vertical flow assay (fxVFA) processed by a low-cost mobile reader, which quantifies the target biomarkers through trained neural networks, all within 0.9 linearity and Copyright © 2023, The Authors. All rights reserved.

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Virtual Staining-Based Diagnosis of Organ Transplant Rejection

Virtual Staining-Based Diagnosis of Organ Transplant Rejecti...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Yuzhu Li Nir Pillar Tairan Liu Guangdong Ma Kevin de Haan Yijie Zhang Adrian J. Correa Yulun Wu Bijie Bai Xilin Yang Yuxuan Qi William Dean Wallace Aydogan Ozcan Electrical and Computer Engineering Department Bioengineering Department California NanoSystems Institute (CNSI) University of California Los Angeles CA USA School of Physics Xi'an Jiaotong University Xi'an Shaanxi China Department of Pathology Keck School of Medicine University of Southern California Los Angeles CA USA Department of Mathematics Computer Science Department Department of Surgery University of California Los Angeles CA USA

We present deep learning-based virtual staining of unlabeled lung and heart tissue sections to diagnose organ transplant rejection, achieving comparable diagnostic accuracy to histochemical staining methods, while sig... 详细信息

ISBN: (纸本)9798350369311

关键词： Heart Costs Accuracy Lung Lasers and electrooptics Organ transplantation Electro-optical waveguides

来源：评论

学校读者我要写书评

暂无评论

Switching Multiplicative Watermark Design Against Covert Attacks

arXiv

引用

arXiv 2025年

作者： Gallo, Alexander J. Anand, Sribalaji C. Teixeira, Andre M.H. Ferrari, Riccardo M.G. Department of Electronics Information and Bioengineering Politecnico di Milano Milano Italy School of Electrical Engineering and Computer Science and Digital Futures KTH Royal Institute of Technology Sweden Department of Information Technology Uppsala University PO Box 337 UppsalaSE-75105 Sweden Delft Center for Systems and Control Mechanical Engineering TU Delft Delft Netherlands

Active techniques have been introduced to give better detectability performance for cyber-attack diagnosis in cyber-physical systems (CPS). In this paper, switching multiplicative watermarking is considered, whereby we propose an optimal design strategy to define switching filter parameters. Optimality is evaluated exploiting the so-called output-to-output gain of the closed loop system, including some supposed attack dynamics. A worst-case scenario of a matched covert attack is assumed, presuming that an attacker with full knowledge of the closed-loop system injects a stealthy attack of bounded energy. Our algorithm, given watermark filter parameters at some time instant, provides optimal next-step parameters. Analysis of the algorithm is given, demonstrating its features, and demonstrating that through initialization of certain parameters outside of the algorithm, the parameters of the multiplicative watermarking can be randomized. Simulation shows how, by adopting our method for parameter design, the attacker’s impact on performance diminishes. © 2025, CC BY-NC-ND.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

PRE-TRAINING GRAPH CONTRASTIVE MASKED AU-TOENCODERS ARE STRONG DISTILLERS FOR EEG

arXiv

引用

arXiv 2024年

作者： Wei, Xinxu Zhao, Kanhao Jiao, Yong Carlisle, Nancy B. Xie, Hua Zhang, Yu Department of Electrical and Computer Engineering Lehigh University BethlehemPA United States Department of Bioengineering Lehigh University BethlehemPA United States Department of Psychology Lehigh University BethlehemPA United States Center for Neuroscience Research Children’s National Hospital WashingtonDC United States

Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this by framing it as a graph transfer learning and knowledge distillation problem. We propose a Unified Pre-trained Graph Contrastive Masked Autoencoder Distiller, named EEG-DisGCMAE, to bridge the gap between unlabeled/labeled and high/low-density EEG data. To fully leverage the abundant unlabeled EEG data, we introduce a novel unified graph self-supervised pre-training paradigm, which seamlessly integrates Graph Contrastive Pre-training and Graph Masked Autoencoder Pre-training. This approach synergistically combines contrastive and generative pre-training techniques by reconstructing contrastive samples and contrasting the reconstructions. For knowledge distillation from high-density to low-density EEG data, we propose a Graph Topology Distillation loss function, allowing a lightweight student model trained on low-density data to learn from a teacher model trained on high-density data, effectively handling missing electrodes through contrastive distillation. To integrate transfer learning and distillation, we jointly pre-train the teacher and student models by contrasting their queries and keys during pre-training, enabling robust distillers for downstream tasks. We demonstrate the effectiveness of our method on four classification tasks across two clinical EEG datasets with abundant unlabeled data and limited labeled data. The experimental results show that our approach significantly outperforms contemporary methods in both efficiency and accuracy. © 2024, CC BY-NC-SA.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Morphological imaging of 3D cultured kidney mesangial cells using gradient light interference microscopy

Morphological imaging of 3D cultured kidney mesangial cells ...

引用

Digital Holography and Three-Dimensional Imaging, DH 2024

作者： Butola, Ankit Ghosh, Biswajoy Park, Jaena Kwon, Minsung De la Cadena, Alejandro Mukherjee, Sudipta Bhargava, Rohit Boppart, Stephen A. Agarwal, Krishna Department of Physics and Technology UiT The Arctic University of Norway Tromsø9037 Norway 405 N. Mathews Ave. UrbanaIL61801 United States Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign 405 N Mathews Avenue UrbanaIL61801 United States Department of Bioengineering University of Illinois at Urbana-Champaign 1406 W Green Street UrbanaIL61801 United States Department of Chemical and Biomolecular Engineering University of Illinois Urbana-Champaign UrbanaIL United States Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL United States Cancer Center at Illinois University of Illinois Urbana-Champaign UrbanaIL United States Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign 306 N Wright Street UrbanaIL61801 United States Carle Illinois College of Medicine University of Illinois at Urbana-Champaign 506 S Mathews Avenue UrbanaIL61801 United States

We present a gradient light interference microscopy system to visualize 3D quantitative imaging of kidney mesangial cells. We used the system to obtain the morphology of 3D cultured kidney cells of thickness 200 µ... 详细信息

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

Sample Preconcentration Through Airjet-Induced Liquid Phase Enrichment

SSRN

引用

SSRN 2023年

作者： Wang, Edward Laurent, Louise C. Hall, Drew A. Lo, Yu-Hwa Department of Aerospace and Mechanical Engineering Materials Science and Engineering Program University of California La Jolla San DiegoCA United States Sanford Consortium of Regenerative Medicine United States Department of Electrical and Computer Engineering University of California La Jolla San DiegoCA United States Department of Bioengineering

Sample preparation is essential for nucleic acid assays, affecting their sensitivity and reliability. However, this process often results in a significant loss or dilution of the analyte, which becomes a bottleneck that limits downstream assay performance, particularly for assays that accept a limited input sample volume. To overcome this challenge, we present an evaporative-based sample enrichment method that uses an airjet to concentrate analytes within a small, defined volume by reversing the coffee-ring effect. A small, concentrated sample can then be collected for analysis to increase the initial sample load. The effectiveness of the reported airjet enrichment was quantified using qPCR of λ-DNA, HeLa-S3 RNA, and heat-inactivated SARS-CoV-2 samples. Comparisons between airjet enrichment and conventional evaporative concentration methods demonstrated significant advantages of airjet enrichment, including the ability to concentrate a high percentage of analyte within a 1 µL volume. The enrichment method was then integrated and adapted for various fluid volumes commonly found in nucleic acid sample preparation procedures. Here, airjet enrichment reduced the overall [[EQUATION]] by an average of 9.27 cycles for each analyte, resulting in a 600-fold enrichment from the initial concentration. In addition, to perform selective enrichment and prevent salt-based interference in downstream analysis, PEG was added to reduce the co-enrichment of salt. These studies show how airjet enrichment technology can be easily integrated into existing laboratory protocols with minimal modification and significantly improve the performance of nucleic acid amplification assays. © 2023, The Authors. All rights reserved.

关键词： Biomolecules

来源：评论

学校读者我要写书评

暂无评论

Neural network-based image reconstruction in swept-source optical coherence tomography using undersampled spectral data

引用

Light(Science & Applications) 2021年第9期10卷 1658-1671页

作者： Yijie Zhang Tairan Liu Manmohan Singh EgeÇetintaş Yilin Luo Yair Rivenson Kirill V.Larin Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA90095USA Department of Bioengineering University of CaliforniaLos AngelesCA90095USA California NanoSystems Institute University of CaliforniaLos AngelesCA90095USA Department of Biomedical Engineering University of HoustonHoustonTX77204USA Department of Molecular Physiology and Biophysics Baylor College of MedicineUniversity of HoustonHoustonTX77204USA Department of Surgery David Geffen School of MedicineUniversity of CaliforniaLos AngelesCA90095USA

Optical coherence tomography(OCT)is a widely used non-invasive biomedical imaging modality that can rapidly provide volumetric images of ***,we present a deep learning-based image reconstruction framework that can generate swept-source OCT(SS-OCT)images using undersampled spectral data,without any spatial aliasing *** neural network-based image reconstruction does not require any hardware changes to the optical setup and can be easily integrated with existing swept-source or spectral-domain OCT systems to reduce the amount of raw spectral data to be *** show the efficacy of this framework,we trained and blindly tested a deep neural network using mouse embryo samples imaged by an SS-OCT *** 2-fold undersampled spectral data(i.e.,640 spectral points per A-line),the trained neural network can blindly reconstruct 512 A-lines in 0.59 ms using multiple graphics-processing units(GPUs),removing spatial aliasing artifacts due to spectral undersampling,also presenting a very good match to the images of the same samples,reconstructed using the full spectral OCT data(i.e.,1280 spectral points per A-line).We also successfully demonstrate that this framework can be further extended to process 3×undersampled spectral data per A-line,with some performance degradation in the reconstructed image quality compared to 2×spectral ***,an A-line-optimized undersampling method is presented by jointly optimizing the spectral sampling locations and the corresponding image reconstruction network,which improved the overall imaging performance using less spectral data points per A-line compared to 2×or 3×spectral undersampling *** deep learning-enabled image reconstruction approach can be broadly used in various forms of spectral-domain OCT systems,helping to increase their imaging speed without sacrificing image resolution and signal-to-noise ratio.

关键词： graphics hardware image

来源：评论

学校读者我要写书评

暂无评论

Leakage Current Measurements of Amorphous Silicon Carbide Encapsulation for Implantable Microelectrode Arrays

Leakage Current Measurements of Amorphous Silicon Carbide En...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Christopher K. Nguyen Alexandra Joshi-Imre Sandeep Negi Stuart F. Cogan Department of Bioengineering University of Texas at Dallas Richardson TX USA Office of Research and Innovation University of Texas at Dallas Richardson TX USA Blackrock Neurotech Salt Lake City UT USA Department of Electrical and Computer Engineering University of Utah Salt Lake City UT USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Advancements in implantable microelectrode arrays (MEAs) for neural applications are hindered by challenges in maintaining long-term stability within the body. Amorphous silicon carbide (a-SiC), recognized for its chemical inertness and biocompatibility, emerges as a promising material to address these challenges. Our findings demonstrate that IDEs with a-SiC exhibit high electrical insulation on the order of TΩ emphasizing its potential for enhancing encapsulation reliability. The primary objective of this research is to develop a methodology for evaluating the encapsulation effectiveness of a-SiC under electrical stress. Utilizing interdigitated electrodes (IDEs), the research applies a non-thermal, voltage-driven approach to assess a-SiC's encapsulation. The resistance of a-SiC encapsulated IDEs, crucial for implantable device functionality, is analyzed through this process. This approach not only reinforces the understanding of a-SiC as a viable material for MEAs and identifies an electrical methodology particularly suitable for evaluating implantable *** Relevance—This study developed a methodology for measuring leakage current in a-SiC encapsulation, which can be implemented for voltage-driven accelerated testing of implantable microelectrode arrays

关键词： Encapsulation Microelectrodes Insulation Electric potential Voltage measurement Current measurement electrical resistance measurement Reliability Leakage currents Immune system

来源：评论

学校读者我要写书评

暂无评论

Neural network-based multiplexed and micro-structured virtual staining of unlabeled tissue

Neural network-based multiplexed and micro-structured virtua...

引用

CLEO: Applications and Technology, A and T 2022

作者： Zhang, Yijie de Haan, Kevin Li, Jingxi Rivenson, Yair Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States Department of Surgery David Geffen School of Medicine University of California Los AngelesCA90095 United States

ISBN: (纸本)9781957171050

We present a method to generate multiple virtual stains on an image of label-free tissue using a single deep neural network, which is fed with the autofluorescence images of the unlabeled tissue alongside a user-defined digital-staining matrix. Users can indicate which stain to apply on each pixel by editing the digital-staining matrix and blend multiple virtual stains, creating entirely new stain combinations. © Optica Publishing Group 2022, © 2022 The Author(s)

关键词： Tissue

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：