检索结果-内蒙古大学图书馆

arXiv 2022年

作者： ValizadehAslani, Taha Shi, Yiwen Wang, Jing Ren, Ping Zhang, Yi Hu, Meng Zhao, Liang Liang, Hualou Department of Electrical and Computer Engineering College of Engineering Drexel University PhiladelphiaPA United States College of Computing and Informatics Drexel University PhiladelphiaPA United States Office of Research and Standards Office of Generic Drugs Center for Drug Evaluation and Research United States Food and Drug Administration Silver SpringMD United States School of Biomedical Engineering Science and Health Systems Drexel University PhiladelphiaPA United States

Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and hence poor performance on tail classes with only a few samples. Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task. In this work, we present a simple modification of standard fine-tuning to cope with these challenges. Specifically, we propose a two-stage fine-tuning: we first fine-tune the final layer of the pretrained model with class-balanced reweighting loss, and then we perform the standard fine-tuning. Our modification has several benefits: (1) it leverages pretrained representations by only fine-tuning a small portion of the model parameters while keeping the rest untouched;(2) it allows the model to learn an initial representation of the specific task;and importantly (3) it protects the learning of tail classes from being at a disadvantage during the model updating. We conduct extensive experiments on synthetic datasets of both two-class and multi-class tasks of text classification as well as a real-world application to ADME (i.e., absorption, distribution, metabolism, and excretion) semantic labeling. The experimental results show that the proposed two-stage fine-tuning outperforms both fine-tuning with conventional loss and fine-tuning with a reweighting loss on the above datasets. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Ultraefficient thermoacoustic conversion through a split ring resonator

引用

Advanced Photonics 2020年第3期2卷 69-77页

作者： Lu Lan Yueming Li Tiffany Yang-Tran Ying Jiang Yingchun Cao Ji-Xin Cheng Boston University Department of Biomedical EngineeringBostonMassachusettsUnited States Boston University Department of Mechanical EngineeringBostonMassachusettsUnited States Boston University Department of Electrical and Computer EngineeringBostonMassachusettsUnited States Boston University Photonics Center BostonMassachusettsUnited States

Microwaves,which have a∼10-cm wavelength,can penetrate deeper into tissue than photons,heralding exciting deep tissue applications such as modulation or imaging via the thermoacoustic *** conversion efficiency is however very low,even with an exogenous contrast *** break this low-conversion limit,using a split ring resonator to effectively collect and confine the microwaves into a submillimeter hot spot for ultrasound emission and achieve a conversion efficiency over 2000 times higher than other reported thermoacoustic contrast ***,the frequency of emitted ultrasound can be precisely tuned and multiplexed by modulation of the microwave *** performance is inaccessible by a piezoelectric-based transducer or a photoacoustic emitter and,therefore,split ring resonators open up new opportunities to study the frequency response of cells in ultrasonic *** applications in deep tissue localization,a split ring resonator can be used as a wireless,battery-free ultrasound beacon placed under a breast phantom.

关键词： thermoacoustic effect metamaterial photoacoustic effect split ring resonator ultrasound

来源：评论

学校读者我要写书评

暂无评论

Cell Spatial Analysis in Crohn's Disease: Unveiling Local Cell Arrangement Pattern with Graph-based Signatures

arXiv

引用

arXiv 2023年

作者： Bao, Shunxing Zhu, Sichen Kolachala, Vasantha L. Remedios, Lucas W. Hwang, Yeonjoo Sun, Yutong Deng, Ruining Cui, Can Li, Yike Li, Jia Roland, Joseph T. Liu, Qi Lau, Ken S. Kugathasan, Subra Qiu, Peng Wilson, Keith T. Coburn, Lori A. Landman, Bennett A. Huo, Yuankai Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Department of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States Division of Pediatric Gastroenterology Department of Pediatrics Pediatric Research Institute Children's Healthcare of Atlanta Emory University School of Medicine AtlantaGA United States Department of Computer Science Vanderbilt University NashvilleTN United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Department of Biostatistics Vanderbilt University Medical Center NashvilleTN United States Department of Surgery Vanderbilt University Medical Center NashvilleTN United States Department of Cell and Developmental Biology Vanderbilt University School of Medicine NashvilleTN United States Division of Gastroenterology Hepatology and Nutrition Department of Medicine Vanderbilt University Medical Center NashvilleTN United States Veterans Affairs Tennessee Valley Healthcare System NashvilleTN United States Department of Otolaryngology-Head and Neck Surgery Vanderbilt University Medical Center NashvilleTN United States

Crohn's disease (CD) is a chronic and relapsing inflammatory condition that affects segments of the gastrointestinal tract. CD activity is determined by histological findings, particularly the density of neutrophils observed on Hematoxylin and Eosin stains (H&E) imaging. However, understanding the broader morphometry and local cell arrangement beyond cell counting and tissue morphology remains challenging. To address this, we characterize six distinct cell types from H&E images and develop a novel approach for the local spatial signature of each cell. Specifically, we create a 10-cell neighborhood matrix, representing neighboring cell arrangements for each individual cell. Utilizing t-SNE for non-linear spatial projection in scatter-plot and Kernel Density Estimation contour-plot formats, our study examines patterns of differences in the cellular environment associated with the odds ratio of spatial patterns between active CD and control groups. This analysis is based on data collected at the two research institutes. The findings reveal heterogeneous nearest-neighbor patterns, signifying distinct tendencies of cell clustering, with a particular focus on the rectum region. These variations underscore the impact of data heterogeneity on cell spatial arrangements in CD patients. Moreover, the spatial distribution disparities between the two research sites highlight the significance of collaborative efforts among healthcare organizations. All research analysis pipeline tools are available at https://***/MASILab/cellNN. © 2023, CC BY.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment

arXiv

引用

arXiv 2022年

作者： Shi, Yiwen Wang, Jing Ren, Ping ValizadehAslani, Taha Zhang, Yi Hu, Meng Liang, Hualou College of Computing and Informatics Drexel University PhiladelphiaPA United States Office of Research and Standards Office of Generic Drugs Center for Drug Evaluation and Research United States Food and Drug Administration Silver Spring MD United States Department of Electrical and Computer Engineering College of Engineering Drexel University PhiladelphiaPA United States School of Biomedical Engineering Science and Health Systems Drexel University PhiladelphiaPA United States

Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development. To assess a PSG, the FDA assessor needs to take extensive time and effort to manually retrieve supportive drug information of absorption, distribution, metabolism, and excretion (ADME) from the reference listed drug labeling. In this work, we leveraged the state-of-the-art pre-trained language models to automatically label the ADME paragraphs in the pharmacokinetics section from the FDA-approved drug labeling to facilitate PSG assessment. We applied a transfer learning approach by fine-tuning the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to develop a novel application of ADME semantic labeling, which can automatically retrieve ADME paragraphs from drug labeling instead of manual work. We demonstrated that fine-tuning the pre-trained BERT model can outperform the conventional machine learning techniques, achieving up to 11.6% absolute F1 improvement. To our knowledge, we were the first to successfully apply BERT to solve the ADME semantic labeling task. We further assessed the relative contribution of pre-training and fine-tuning to the overall performance of the BERT model in the ADME semantic labeling task using a series of analysis methods such as attention similarity and layer-based ablations. Our analysis revealed that the information learned via fine-tuning is focused on task-specific knowledge in the top layers of the BERT, whereas the benefit from the pre-trained BERT model is from the bottom layers. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

High resolution, deep imaging using confocal time-of-flight diffuse optical tomography

arXiv

引用

arXiv 2021年

作者： Zhao, Yongyi Raghuram, Ankit Kim, Hyun K. Hielscher, Andreas H. Robinson, Jacob T. Veeraraghavan, Ashok Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Department of Radiology Columbia University New YorkNY United States Department of Biomedical Engineering New York University New York CityNY11201 United States

Light scattering by tissue severely limits how deep beneath the surface one can image, and the spatial resolution one can obtain from these images. Diffuse optical tomography (DOT) is one of the most powerful techniques for imaging deep within tissue – well beyond the conventional ∼10-15 mean scattering lengths tolerated by ballistic imaging techniques such as confocal and two-photon microscopy. Unfortunately, existing DOT systems are limited, achieving only centimeter-scale resolution. Furthermore, they suffer from slow acquisition times and slow reconstruction speeds making real-time imaging infeasible. We show that time-of-flight diffuse optical tomography (ToF-DOT) and its confocal variant (CToF-DOT), by exploiting the photon travel time information, allow us to achieve millimeter spatial resolution in the highly scattered diffusion regime (> 50 mean free paths). In addition, we demonstrate two additional innovations: focusing on confocal measurements, and multiplexing the illumination sources allow us to significantly reduce the measurement acquisition time. Finally, we rely on a novel convolutional approximation that allows us to develop a fast reconstruction algorithm, achieving a 100× speedup in reconstruction time compared to traditional DOT reconstruction techniques. Together, we believe that these technical advances serve as the first step towards real-time, millimeter resolution, deep tissue imaging using DOT. Copyright © 2021, The Authors. All rights reserved.

关键词： Fluorescence imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Noise Calculation in Deep Learning-based MRI Reconstructions

arXiv

引用

arXiv 2025年

作者： Dalmaz, Onat Desai, Arjun D. Heckel, Reinhard Çukur, Tolga Chaudhari, Akshay S. Hargreaves, Brian A. Department of Electrical Engineering Stanford University StanfordCA United States Department of Radiology Stanford University StanfordCA United States Department of Computer Engineering Technical University of Munich Munich Germany Department of Electrical and Electronics Engineering Bilkent University Ankara Turkey Department of Biomedical Data Science Stanford University StanfordCA United States Department of Bioengineering Stanford University StanfordCA United States

Accelerated MRI reconstruction involves solving an ill-posed inverse problem where noise in acquired data propagates to the reconstructed images. Noise analyses are central to MRI reconstruction for providing an explicit measure of solution fidelity and for guiding the design and deployment of novel reconstruction methods. However, deep learning (DL)-based reconstruction methods have often overlooked noise propagation due to inherent analytical and computational challenges, despite its critical importance. This work proposes a theoretically grounded, memory-efficient technique to calculate voxel-wise variance for quantifying uncertainty due to acquisition noise in accelerated MRI reconstructions. Our approach approximates noise covariance using the DL network’s Jacobian, which is intractable to calculate. To circumvent this, we derive an unbiased estimator for the diagonal of this covariance matrix—voxel-wise variance—, and introduce a Jacobian sketching technique to efficiently implement it. We evaluate our method on knee and brain MRI datasets for both data- and physics-driven networks trained in supervised and unsupervised manners. Compared to empirical references obtained via Monte-Carlo simulations, our technique achieves near-equivalent performance while reducing computational and memory demands by an order of magnitude or more. Furthermore, our method is robust across varying input noise levels, acceleration factors, and diverse undersampling schemes, highlighting its broad applicability. Our work reintroduces accurate and efficient noise analysis as a central tenet of reconstruction algorithms, holding promise to reshape how we evaluate and deploy DL-based MRI. Our code will be made publicly available upon *** Codes 65C60, 94A08, 68T07 © 2025, CC BY-NC-ND.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Data-driven Nucleus Subclassification on Colon H&E using Style-transferred Digital Pathology

arXiv

引用

arXiv 2024年

作者： Remedios, Lucas W. Bao, Shunxing Remedios, Samuel W. Lee, Ho Hin Cai, Leon Y. Li, Thomas Deng, Ruining Newlin, Nancy R. Saunders, Adam M. Cui, Can Li, Jia Liu, Qi Lau, Ken S. Roland, Joseph T. Washington, Mary K. Coburn, Lori A. Wilson, Keith T. Huo, Yuankai Landman, Bennett A. Vanderbilt University Department of Computer Science Nashville United States Vanderbilt University Department of Electrical and Computer Engineering Nashville United States Johns Hopkins University Department of Computer Science Baltimore United States National Institutes of Health Department of Radiology and Imaging Sciences Bethesda United States Vanderbilt University Department of Biomedical Engineering Nashville United States Vanderbilt University Medical Center Department of Biostatistics Nashville United States Vanderbilt University Medical Center Center for Quantitative Sciences Nashville United States Vanderbilt University Medical Center Epithelial Biology Center Nashville United States Vanderbilt University School of Medicine Department of Cell and Developmental Biology Nashville United States Vanderbilt University Medical Center Division of Gastroenterology Hepatology and Nutrition Department of Medicine Nashville United States Vanderbilt University Medical Center Vanderbilt Center for Mucosal Inflammation and Cancer Nashville United States Vanderbilt University School of Medicine Program in Cancer Biology Nashville United States Veterans Affairs Tennessee Valley Healthcare System NashvilleTN United States Vanderbilt University Medical Center Department of Pathology Microbiology and Immunology NashvilleTN United States

Purpose: Cells are building blocks for human physiology;consequently, understanding the way cells communicate, co-locate, and interrelate is essential to furthering our understanding of how the body functions in both health and disease. Hematoxylin and eosin (H&E) is the standard stain used in histological analysis of tissues. Microscope slides of H&E-stained tissues are widely available in both clinical and research settings. While H&E is ubiquitous and reveals tissue microanatomy, the classification and tracking of cell subtypes often requires expert knowledge and the use of specialized stains, such as immunofluorescence staining. To reduce both the manual annotation burden and reliance on specialized staining technologies, artificial intelligence has been proposed for the automatic classification of cell types on H&E slides. For example, the recent Colon Nucleus Identification and Classification (CoNIC) Challenge focused on labeling 6 cell types on imaging of H&E stains from the human colon. However, this is a very small fraction of the number of potential cell subtypes within the intestines. Specifically, the CoNIC Challenge was unable to classify epithelial subtypes (progenitor, enteroendocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), and connective subtypes (fibroblasts). To approach this problem, we propose to use inter-modality learning to label previously un-labelable cell types on H&E. Approach: We take advantage of the cell classification information inherent in whole slide images (WSIs) of multiplexed immunofluorescence (MxIF) histology to create cell level annotations for 14 subclasses. We performed style transfer on the same MxIF tissues to synthesize realistic virtual H&E which we paired with the MxIF-derived cell subclassification labels. We evaluated the efficacy of using a supervised learning scheme where the input was realistic-quality virtual H&E and the labels were MxIF-derived cell subclasses. We assessed our model on a testing

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation

arXiv

引用

arXiv 2022年

作者： Heidari, Moein Kazerouni, Amirhossein Soltany, Milad Azad, Reza Aghdam, Ehsan Khodapanah Cohen-Adad, Julien Merhof, Dorit School of Electrical Engineering Iran University of Science and Technology Tehran Iran Institute of Imaging and Computer Vision RWTH Aachen University Aachen Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran Functional Neuroimaging Unit CRIUGM University of Montreal Canada NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal Canada MILA Quebec AI Institute Montreal Canada Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution operation. Although transformers were first developed to address this issue, they fail to capture low-level features. In contrast, it is demonstrated that both local and global features are crucial for dense prediction, such as segmenting in challenging contexts. In this paper, we propose HiFormer, a novel method that efficiently bridges a CNN and a transformer for medical image segmentation. Specifically, we design two multi-scale feature representations using the seminal Swin Transformer module and a CNN-based encoder. To secure a fine fusion of global and local features obtained from the two aforementioned representations, we propose a Double-Level Fusion (DLF) module in the skip connection of the encoder-decoder structure. Extensive experiments on various medical image segmentation datasets demonstrate the effectiveness of HiFormer over other CNN-based, transformer-based, and hybrid methods in terms of computational complexity, quantitative and qualitative results. Our code is publicly available at GitHub. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Relaxation Based Modeling of GMD Induced Cascading Failures in ***

Relaxation Based Modeling of GMD Induced Cascading Failures ...

引用

2021 North American Power Symposium, NAPS 2021

作者： Mate, Adam Barnes, Arthur K. Morley, Steven K. Friz-Trillo, Jacob A. Cotilla-Sanchez, Eduardo Blake, Sean P. Los Alamos National Laboratory Advanced Network Science Initiative Los AlamosNM87545 United States Los Alamos National Laboratory Space Science and Applications Group Los AlamosNM87545 United States Department of Electrical and Biomedical Engineering University of Vermont BurlingtonVT05405 United States Oregon State University School of Electrical Engineering and Computer Science CorvallisOR97331 United States NASA Goddard Space Flight Center Heliophysics Science Division GreenbeltMD20771 United States

ISBN: (纸本)9781665420815

A major risk of geomagnetic disturbances (GMDs) is cascading failure of electrical grids. The modeling of GMD events and cascading outages in power systems is difficult, both independently and jointly, because of the many different mechanisms and physics involved. This paper introduces a relaxation based modeling of GMD-induced cascading failures: the dc approximation-based DCSIMSEP solver was adapted to simulate cascading as a result of GMDs, the full set of ac power flow equations were relaxed to guarantee optimality, and the reactive power losses were modeled while keeping the problem convex. The developed algorithm was implemented in *** - an open-source software specifically designed to model and analyze geomagnetic hazards - and demonstrated to work on the RTS-GMLC-GIC-EAST synthetic test network. © 2021 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Modeling and Passivity Properties of Multi-Producer District Heating Systems

arXiv

引用

arXiv 2020年

作者： Martinez, Juan Eduardo Machado Cucuzzella, Michele Scherpen, Jacquelien M.A. Faculty of Science and Engineering University of Groningen Netherlands Department of Electrical Computer and Biomedical Engineering University of Pavia Italy

We propose a comprehensive nonlinear ODE-based thermo-hydraulic model of a district heating system featuring several heat producers, consumers and storage devices which are interconnected through a distribution network of meshed topology whose temperature dynamics are explicitly considered. Moreover, we analyze the conditions under which the hydraulic and thermal subsystems of the model exhibit shifted passivity properties. For the hydraulic subsystem, our claims on passivity draw on the monotonicity of the vector field associated to the district heating system’s flow dynamics, which mainly codifies viscous friction effects on the system’s pressures. For the temperature dynamics, we propose a storage function based on the ectropy function of a thermodynamic system, recently used in the passivity analysis of heat exchanger networks. Copyright © 2020, The Authors. All rights reserved.

关键词： District heating

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：