检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chen, Hanlong Huang, Luzhe Liu, Tairan 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 David Geffen School of Medicine University of California Los AngelesCA90095 United States

Deep learning-based image reconstruction methods have achieved remarkable success in phase recovery and holographic imaging. However, the generalization of their image reconstruction performance to new types of samples never seen by the network remains a challenge. Here we introduce a deep learning framework, termed Fourier Imager Network (FIN), that can perform end-to-end phase recovery and image reconstruction from raw holograms of new types of samples, exhibiting unprecedented success in external generalization. FIN architecture is based on spatial Fourier transform modules that process the spatial frequencies of its inputs using learnable filters and a global receptive field. Compared with existing convolutional deep neural networks used for hologram reconstruction, FIN exhibits superior generalization to new types of samples, while also being much faster in its image inference speed, completing the hologram reconstruction task in ~0.04 s per 1 mm2 of the sample area. We experimentally validated the performance of FIN by training it using human lung tissue samples and blindly testing it on human prostate, salivary gland tissue and Pap smear samples, proving its superior external generalization and image reconstruction speed. Beyond holographic microscopy and quantitative phase imaging, FIN and the underlying neural network architecture might open up various new opportunities to design broadly generalizable deep learning models in computational imaging and machine vision fields. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Plasmon-enhanced chiral absorption through electric dipole-electric quadrupole interaction

arXiv

引用

arXiv 2024年

作者： Wang, Hanwei Zhao, Yang Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Nick Holonyak Micro and Nanotechnology Laboratory University of Illinois Urbana-Champaign UrbanaIL61801 United States Beckman Institute University of Illinois Urbana-Champaign UrbanaIL61801 United States Department of Bioengineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Carl R. Woese Institute of Genomic Biology University of Illinois Urbana-Champaign UrbanaIL61801 United States

Enantioselective interactions of chiral molecules include distinct absorptions to opposite-handed circularly polarized light, known as chiral absorption. Traditionally, chiral absorption has been primarily attributed to electric dipole and magnetic dipole interaction with molecular chirality. However, this approach falls short for large molecules that support high-order multipolar components, such as electric quadrupole moment. Here, we introduce a theoretical model to study the chiral absorption of large molecules in the presence of plasmonic nanostructures. This model considers both electric dipole-magnetic dipole interaction and electric dipole-electric quadrupole interaction enhanced by a resonant structure. We numerically study such interactions of the chiral molecular solution in the vicinity of an achiral plasmonic nano-resonator. Our results show the distinct spectral information of the chiral medium on- and off-resonance of the resonator. © 2024, CC BY.

关键词： Chirality

来源：评论

学校读者我要写书评

暂无评论

Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network

arXiv

引用

arXiv 2022年

作者： Huang, Luzhe Yang, Xilin Liu, Tairan 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 David Geffen School of Medicine University of California Los AngelesCA90095 United States

Deep learning-based methods in computational microscopy have been shown to be powerful but in general face some challenges due to limited generalization to new types of samples and requirements for large and diverse training data. Here, we demonstrate a few-shot transfer learning method that helps a holographic image reconstruction deep neural network rapidly generalize to new types of samples using small datasets. We pre-trained a convolutional recurrent neural network on a large dataset with diverse types of samples, which serves as the backbone model. By fixing the recurrent blocks and transferring the rest of the convolutional blocks of the pre-trained model, we reduced the number of trainable parameters by ~90% compared with standard transfer learning, while achieving equivalent generalization. We validated the effectiveness of this approach by successfully generalizing to new types of samples using small holographic datasets for training, and achieved (i) ~2.5-fold convergence speed acceleration, (ii) ~20% computation time reduction per epoch, and (iii) improved reconstruction performance over baseline network models trained from scratch. This few-shot transfer learning approach can potentially be applied in other microscopic imaging methods, helping to generalize to new types of samples without the need for extensive training time and data. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Video-rate multimodal multiphoton imaging and three-dimensional characterization of cellular dynamics in wounded skin

引用

Journal of Innovative Optical Health Sciences 2020年第2期13卷 70-80页

作者： Joanne Li Madison N.Wilson Andrew J.Bower Marina Marjanovic Eric J.Chaney Ronit Barkalifa Stephen A.Boppart Department of Bioengineering University of Illinois at Urbana-Champaign Urbana ILU.S.A Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana ILU.S.A Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign Urbana ILU.S.A Carle Illinois College of Medicine University of Illinois at Urbana-Champaign Urbana ILU.S.A

To date,numerous studies have been performed to elucidate the complex cellular dynamics in skin diseases,but few have attempted to characterize these cellular events under conditions similar to the native *** address this challenge,a three-dimensional(3D)multimodal analysis platform was developed for characterizing in vivo cellular dynamics in skin,which was then utilized to process in vivo wound healing data to demonstrate its *** attention is focused on in vivo biological parameters that are difficult to study with ex vivo analysis,including 3D cell tracking and techniques to connect biological information obtained from different imaging *** results here open new possibilities for evaluating 3D cellular dynamics in vivo,and can potentially provide new tools for characterizing the skin microenvironment and pathologies in the future.

关键词： Cellular dynamics multimodal imaging multiphoton microscopy

来源：评论

学校读者我要写书评

暂无评论

Beta-Band Cortico-Muscular Phase Coherence in Hemiparetic Stroke

SSRN

引用

SSRN 2024年

作者： Parmar, Nishaal Sirpal, Parikshat Sikora, William A. Dewald, Julius P.A. Refai, Hazem H. Yang, Yuan University of Oklahoma School of Electrical and Computer Engineering Gallogly College of Engineering NormanOK United States University of Oklahoma Stephenson School of Biomedical Engineering NormanOK United States Northwestern University Departments of Physical Therapy and Human Movement Sciences ChicagoIL United States Northwestern University Departments of Biomedical Engineering EvanstonIL United States University of Illinois Urbana-Champaign Department of Bioengineering Grainger College of Engineering UrbanaIL United States Carle Foundation Hospital Stephenson Family Clinical Research Institute Clinical Imaging Research Center UrbanaIL United States University of Illinois Urbana-Champaign Beckman Institute for Advanced Science and Technology UrbanaIL United States

During post-stroke recovery, the brain undergoes reorganization, compensating for loss of ipsilesional corticospinal and corticobulbar pathways, resulting in increased contralesional cortical activity during paretic arm movement tasks. Better understanding underlying mechanisms may improve post-stroke motor rehabilitation, with the study objective being to provide insight into poststroke contralesional cortical adaptation. This proof-of-concept study involves eight healthy controls and ten post-stroke participants. Electroencephalographic (EEG) and deltoid electromyographic (EMG) data were collected during an upper-limb exertion task. Phase coupling between beta-band motor cortex EEG and deltoid EMG was assessed using the Multi-Phase Locking Value (M-PLV) method. The nerve conduction delay from the contralateral motor cortex to the deltoid muscle of the paretic arm was estimated from EEG/EMG phase coherence. Our results show the ipsilateral (contralesional) motor cortex beta-band phase coherence behavior is altered in stroke participants. These show a significant difference in ipsilateral EEG-EMG coherence values, ipsilateral time course percentage above the significance threshold, and ipsilateral time course area above the significance threshold, in comparison to controls. M-PLV phase coherence analysis provides evidence for poststroke contralesional motor adaptation, highlighting its increased role in the paretic shoulder abduction task. Nerve conduction delay between the motor cortexes and deltoid muscle is significantly higher in stroke participants. Beta-band M-PLV phase coherence analysis shows greater phase-coherence distribution convergence between the ipsilateral and contralateral motor cortices in stroke participants, which we conclude may be interpreted as evidence of maladaptive neural adaptation resulting from a greater reliance on the contralesional motor cortex. © 2024, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Label-free evaluation of lung and heart transplant biopsies using virtual staining

arXiv

引用

arXiv 2024年

作者： Li, Yuzhu Pillar, Nir Liu, Tairan Ma, Guangdong Qi, Yuxuan de Haan, Kevin Zhang, Yijie Yang, Xilin Correa, Adrian J. Xiao, Guangqian Jen, Kuang-Yu Iczkowski, Kenneth A. Wu, Yulun Wallace, William Dean 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 School of Physics Xi’an Jiaotong University Shaanxi Xi’an710049 China Department of Computer Science University of California Los Angeles90095 United States Department of Pathology Keck School of Medicine University of Southern California Los AngelesCA90033 United States Department of Pathology and Laboratory Medicine School of Medicine University of California Davis SacramentoCA95817 United States Department of Mathematics University of California Los AngelesCA90095 United States Department of Surgery University of California Los AngelesCA90095 United States

Organ transplantation serves as the primary therapeutic strategy for end-stage organ failures. However, allograft rejection is a common complication of organ transplantation, which can lead to life-threatening outcomes if not promptly managed. Histological assessment is essential for the timely detection and diagnosis of transplant rejection and remains the gold standard. Nevertheless, the traditional histochemical staining process is time-consuming, costly, and labor-intensive. These challenges are particularly pronounced for transplant biopsy evaluations, which necessitate multiple stains. Moreover, once these tissue slides are stained, they cannot be reused for other ancillary tests. More importantly, suboptimal handling of very small tissue fragments from transplant biopsies may impede their effective histochemical staining, and color variations across different laboratories or batches can hinder efficient histological analysis by pathologists. To mitigate these challenges, here we present a panel of virtual staining neural networks for lung and heart transplant biopsies, which digitally convert autofluorescence microscopic images of label-free tissue sections into their brightfield histologically stained counterparts – bypassing the traditional histochemical staining process. Specifically, we virtually generated Hematoxylin and Eosin (H&E), Masson’s Trichrome (MT), and Elastic Verhoeff-Van Gieson (EVG) stains for label-free transplant lung tissue, along with H&E and MT stains for label-free transplant heart tissue. Subsequent blind evaluations conducted by three board-certified pathologists have confirmed that the virtual staining networks consistently produce high-quality histology images with high color uniformity, closely resembling their well-stained histochemical counterparts across various tissue features. The use of virtually stained images for the evaluation of transplant biopsies achieved comparable diagnostic outcomes to those obtained via traditional

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

Electrochemical measurement of serotonin by Au-CNT electrodes fabricated on microporous cell culture membranes

引用

Microsystems & Nanoengineering 2020年第1期6卷 494-506页

作者： Ashley A.Chapin Pradeep R.Rajasekaran David N.Quan Liangbing Hu Jens Herberholz William E.Bentley Reza Ghodssi Fischell Department of Bioengineering College ParkMD 20742USA Institute for Systems Research College ParkMD 20740USA Department of Materials Science and Engineering College ParkMD 20740USA Department of Psychology and Neuroscience and Cognitive Science Program College ParkMD 20740USA Institute for Bioscience and Biotechnology Research RockvilleMD 20850USA Robert E.Fischell Institute for Biomedical Devices RockvilleMD 20850USA Department of Electrical and Computer Engineering College ParkMD 20742USA

Gut–brain axis(GBA)communication relies on serotonin(5-HT)signaling between the gut epithelium and the peripheral nervous system,where 5-HT release patterns from the basolateral(i.e.,bottom)side of the epithelium activate nerve *** have been few quantitative studies of this gut-neuron signaling due to a lack of real-time measurement tools that can access the basolateral gut *** vitro platforms allow quantitative studies of cultured gut tissue,but they mainly employ offline and endpoint assays that cannot resolve dynamic molecular-release ***,we present the modification of a microporous cell culture membrane with carbon nanotube-coated gold(Au-CNT)electrodes capable of continuous,label-free,and direct detection of 5-HT at physiological *** characterization of single-walled carbon nanotube(SWCNT)-coated Au electrodes shows increased electroactive surface area,5-HT specificity,sensitivity,and saturation time,which are correlated with the CNT film drop-cast *** microliters of CNT films,with a 10-min saturation time,0.6μA/μM 5-HT sensitivity,and reliable detection within a linear range of 500 nM–10μM 5-HT,can be targeted for high-concentration,high-time-resolution 5-HT *** films(12.5μL)with a 2-h saturation time,4.5μA/μM 5-HT sensitivity,and quantitative detection in the linear range of 100 nM–1μM can target low concentrations with low time *** electrodes achieved continuous detection of dynamic diffusion across the porous membrane,mimicking basolateral 5-HT release from cells,and detection of cell-released 5-HT from separately cultured RIN14B cell ***-integrated cell culture systems such as this can improve in vitro molecular detection mechanisms and aid in quantitative GBA signaling studies.

关键词： release saturation dynamic

来源：评论

学校读者我要写书评

暂无评论

Single-Pixel Machine Vision Using Spectral Encoding Through Diffractive Optical Networks

Single-Pixel Machine Vision Using Spectral Encoding Through ...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Jingxi Li Deniz Mengu Nezih T. Yardimci Yi Luo Xurong Li Muhammed Veli Yair Rivenson Mona Jarrahi Aydogan Ozcan Electrical and Computer Engineering Department University of California Los Angeles CA USA Bioengineering Department University of California Los Angeles CA USA California NanoSystems Institute (CNSI) University of California Los Angeles CA USA

We present and experimentally demonstrate a deep learning-driven machine-vision framework that trains diffractive surfaces to encode the spatial information objects into the output power spectrum for all-optical image... 详细信息

ISBN: (纸本)9781943580910

关键词： Machine vision Neural networks Optical coherence tomography Optical components Optical networks Optical systems

来源：评论

学校读者我要写书评

暂无评论

MicroSegNet: A Deep Learning Approach for Prostate Segmentation on Micro-Ultrasound Images

arXiv

引用

arXiv 2023年

作者： Jiang, Hongxu Imran, Muhammad Muralidharan, Preethika Patel, Anjali Pensa, Jake Liang, Muxuan Benidir, Tarik Grajo, Joseph R. Joseph, Jason P. Terry, Russell DiBianco, John Michael Su, Li-Ming Zhou, Yuyin Brisbane, Wayne G. Shao, Wei Department of Electrical and Computer Engineering University of Florida GainesvilleFL32608 United States Department of Medicine University of Florida GainesvilleFL32608 United States Department of Health Outcomes and Biomedical Informatics University of Florida GainesvilleFL32608 United States College of Medicine University of Florida GainesvilleFL32608 United States Department of Bioengineering University of California Los AngelesCA90095 United States Department of Biostatistics University of Florida GainesvilleFL32608 United States Department of Urology University of Florida GainesvilleFL32608 United States Department of Radiology University of Florida GainesvilleFL32608 United States Department of Computer Science and Engineering University of California Santa CruzCA95064 United States Department of Urology University of California Los AngelesCA90095 United States

Micro-ultrasound (micro-US) is a novel 29-MHz ultrasound technique that provides 3-4 times higher resolution than traditional ultrasound, potentially enabling low-cost, accurate diagnosis of prostate cancer. Accurate prostate segmentation is crucial for prostate volume measurement, cancer diagnosis, prostate biopsy, and treatment planning. However, prostate segmentation on micro-US is challenging due to artifacts and indistinct borders between the prostate, bladder, and urethra in the midline. This paper presents MicroSegNet, a multi-scale annotation-guided transformer UNet model designed specifically to tackle these challenges. During the training process, MicroSegNet focuses more on regions that are hard to segment (hard regions), characterized by discrepancies between expert and non-expert annotations. We achieve this by proposing an annotation-guided binary cross entropy (AG-BCE) loss that assigns a larger weight to prediction errors in hard regions and a lower weight to prediction errors in easy regions. The AG-BCE loss was seamlessly integrated into the training process through the utilization of multi-scale deep supervision, enabling MicroSegNet to capture global contextual dependencies and local information at various scales. We trained our model using micro-US images from 55 patients, followed by evaluation on 20 patients. Our MicroSegNet model achieved a Dice coefficient of 0.939 and a Hausdorff distance of 2.02 mm, outperforming several state-of-the-art segmentation methods, as well as three human annotators with different experience levels. Our code is publicly available at https://***/mirthAI/MicroSegNet and our dataset is publicly available at https://***/records/10475293. © 2023, CC BY-NC-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

3D Dynamic Lensing via Enhanced Light-Sound Interactions

3D Dynamic Lensing via Enhanced Light-Sound Interactions

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Hamid Reza Chabok Thompson Lu Mohammad Reza Mostaan Babak Bahari Pawel S. Jung Demetrios N. Christodoulides Mercedeh Khajavikhan Department of Physics and Astronomy University of Southern California Los Angeles California USA Department of Bioengineering University of California Riverside California USA Department of Physics Simon Fraser University Burnaby B.C. Canada Department of Electrical and Computer Engineering University of Southern California Los Angeles California USA CREOL The College of Optics and Photonics University of Central Florida Orlando Florida USA

Most acousto-optic lenses produce energy dissipating annular fringes. Here, we report a 3D dynamic focusing with fully-localized focus and 477-fold beam confinement with an extended depth of field (DoF) of more than 2... 详细信息

ISBN: (数字)9781957171050

ISBN: (纸本)9781665466660

关键词： Three-dimensional displays Focusing Lasers and electrooptics Laser beams Electrooptical waveguides Lenses

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：