检索结果-内蒙古大学图书馆

Association of structural MRI with Braak staging using neural network-based risk scoring

Alzheimer's & Dementia 2023年第S3期19卷

作者： Matthew I. Miller Shangran Qiu Prajakta S. Joshi Joyce Lee Rhoda Au Vijaya B. Kolachalama Boston University School of Medicine Boston MA USA College of Arts & Sciences Boston University Boston MA USA Framingham Heart Study Boston University Chobanian & Avedisian School of Medicine Boston MA USA Boston University Alzheimer’s Disease Center Boston University Boston MA USA Boston University School of Public Health Boston MA USA Department of Anatomy and Neurobiology Boston University Chobanian & Avedisian School of Medicine Boston MA USA Hariri Institute for Computing and Computational Science & Engineering Boston University Boston MA USA Faculty of Computing & Data Sciences Boston University Boston MA USA Boston University Alzheimer’s Disease Center Boston University Chobanian & Avedisian School of Medicine Boston MA USA Whitaker Cardiovascular Institute Boston University Chobanian & Avedisian School of Medicine Boston MA USA

Background The gold standard of Alzheimer’s disease (AD) diagnosis remains histopathologic examination of neuropathologic changes. However, the dependence on post-mortem microscopic analysis limits the role of pathology in clinical care. Magnetic resonance imaging (MRI) is routinely used to diagnose suspected dementia (DE) due to AD, but correlating neuroimaging to underlying pathologic changes remains challenging. Herein, we report the development of two risk scores derived from convolutional neural network (CNN) processing of MRI scans, which we then validate against Braak staging of neurofibrillary tangles from autopsy reports. Method Using T1-weighted MRIs from the National Alzheimer’s Coordinating Center (NACC), we trained two CNNs (Figure 1) to predict continuous scores for overall cognitive status (“COG” score) and AD probability (“ALZ” score). The COG score, ranging from 0-2, graded a subject’s cognitive status on a spectrum from normal cognition (NC, 0), to mild cognitive impairment (MCI, 1), and DE due to any cause (2). The ALZ score then graded each DE individual’s probability of AD from 0 to 1. These CNNs were then applied to a subset of participants with autopsy reports available within 6 months of MRI. CNN performance was evaluated by area under receiver operating characteristic curve (AUC). Differences in risk scores were assessed by Kruskal-Wallis H testing with post hoc Dunn testing. Result The CNN models for COG and ALZ score estimation were trained on 4,822 NACC participants. Thresholding of COG scores distinguished individuals with DE from those with NC and MCI (AUC = 0.87). ALZ scores distinguished individuals with AD from those with non-AD causes of DE (AUC = 0.77). Among 74 persons with available neuropathology data, COG scores differed significantly among Braak staging groups (p<0.001), increasing from a mean of 0.99±0.36 in Stage 1 to 1.47±0.41 in Stage 6 (p = 0.010). Significant differences in ALZ scores were also observed (p = 0.039) betwe

关键词：

来源：评论

学校读者我要写书评

暂无评论

End-to-end prediction of multimaterial stress fields and fracture patterns using cycle-consistent adversarial and transformer neural networks

引用

Biomedical engineering Advances 2022年 4卷

作者： Eric L. Buehler Markus J. Buehler Masconomet Regional School District Boxford MA 01921 United States Laboratory for Atomistic and Molecular Mechanics (LAMM) Massachusetts Institute of Technology 77 Massachusetts Ave. Cambridge MA 02139 United States Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology 77 Massachusetts Ave. Cambridge MA 02139 United States

The prediction of stress, strain fields or fracture patterns, along with other physical quantities as a function of boundary conditions and material microstructure, is an important objective of various physics-based simulation methods like finite element models or molecular dynamics modeling. However, such simulations may be expensive and can be costly in their execution, limiting their application to solve inverse design problems, or in the discovery of novel materials that feature a desirable performance. In other fields of studies, such as in mechanobiology, field data can often not be calculated due to a lack of models to begin with; where experimental observations may be the only source of insight. Here we introduce a data-driven method to relate input microstructures and field data using an alternative approach, enabled by deep learning, to predict complex mechanical fields directly based on input microstructure data. We report two approaches to solve said problem, first using cycle-consistent adversarial neural networks trained on unpaired images of microstructures and physical fields, and second, using a Perceiver neural networks based on an attention mechanism based on paired images, implemented in a transformer neural network. Due to the cycle consistent nature of the GAN model we can immediately make forward (from microstructure to stress field) and backward (from stress field to microstructure) predictions, offering an avenue for inverse material design. The Perceiver model, implementing an efficient transformer model that can be scaled to very large input and output data, shows strong generalizability and can be successfully applied to scenarios distinct from those in the training set. We demonstrate the model in several sample microstructures including a set of small cracks (voids) to predict both stress fields and fracture patterns, as well as in a composite microstructure of a soft matrix and rigid inclusions, and in a series of solutions to the inve

关键词： Molecular modeling Cracks Fracture Deep learning transformer Perceiver Adversarial neural nets AI Attention model

来源：评论

学校读者我要写书评

暂无评论

SHREC’20 benchmark: Classification in cryo-electron tomograms

引用

Computers and Graphics (Pergamon) 2020年 91卷 279-289页

作者： Gubins, Ilja Chaillet, Marten L. van der Schot, Gijs Veltkamp, Remco C. Förster, Friedrich Hao, Yu Wan, Xiaohua Cui, Xuefeng Zhang, Fa Moebel, Emmanuel Wang, Xiao Kihara, Daisuke Zeng, Xiangrui Xu, Min Nguyen, Nguyen P. White, Tommi Bunyak, Filiz Department of Information and Computing Sciences Utrecht University Netherlands Department of Chemistry Utrecht University Netherlands Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology Shandong University China Inria Rennes Bretagne Atlantique France Department of Computer Science Purdue University United States Department of Biological Sciences Purdue University United States Computational Biology Department Carnegie Mellon University United States Department of Electrical Engineering and Computer Science University of Missouri United States Department of Biochemistry University of Missouri United States

Cryo-electron tomography (cryo-ET) is an imaging technique that allows us to three-dimensionally visualize both the structural details of macro-molecular assemblies under near-native conditions and its cellular context. Electrons strongly interact with biological samples, limiting electron dose. The latter limits the signal-to-noise ratio and hence resolution of an individual tomogram to about 50 (5 nm). Biological molecules can be obtained by averaging volumes, each depicting copies of the molecule, allowing for resolutions beyond 4 (0.4 nm). To this end, the ability to localize and classify components is crucial, but challenging due to the low signal-to-noise ratio. computational innovation is key to mine biological information from cryo-electron tomography. To promote such innovation, we provide a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in cryo-electron tomograms. Our publicly available dataset contains ten tomographic reconstructions of simulated cell-like volumes. Each volume contains twelve different types of complexes, varying in size, function and structure. In this paper, we have evaluated seven different methods of finding and classifying proteins. Six research groups present results obtained with learning-based methods and trained on the simulated dataset, as well as a baseline template matching, a traditional method widely used in cryo-ET research. We find that method performance correlates with particle size, especially noticeable for template matching which performance degrades rapidly as the size decreases. We learn that neural networks can achieve significantly better localization and classification performance, in particular convolutional networks with focus on high-resolution details such as those based on U-Net architecture. © 2020 Elsevier Ltd

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Optimal solution predictions for mixed integer programs

arXiv

引用

arXiv 2019年

作者： Ding, Jian-Ya Shen, Lei Wang, Bing Zhang, Chao Li, Shengyin Xu, Yinghui Song, Le Artificial Intelligence Department Zhejiang Cainiao Supply Chain Management Co. Ltd Computational Science and Engineering College of Computing Georgia Institute of Technology

Mixed Integer Programming (MIP) is one of the most widely used modeling techniques to deal with combinatorial optimization problems. In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients. This offers the opportunity for machine learning method to explore the correlations between model structures and the resulting solution values. To address this issue, we propose to represent an MIP instance using a tripartite graph, based on which a Graph Convolutional Network (GCN) is constructed to predict solution values for binary variables. The predicted solutions are used to generate a local branching cut to the model which accelerate the solution process for MIP. computational evaluations on 8 distinct types of MIP problems show that the proposed framework improves the performance of a state-of-the-art open source MIP solver significantly in terms of running time and solution quality. Copyright © 2019, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

On energy stable, maximum-principle preserving, second order BDF scheme with variable steps for the Allen-Cahn equation

arXiv

引用

arXiv 2020年

作者： Liao, Hong-Lin Tang, Tao Zhou, Tao Department of Mathematics Nanjing University of Aeronautics and Astronautics Nanjing211106 China SUSTech International Center for Mathematics Shenzhen China Division of Science and Technology BNU-HKBU United International College ZhuhaiGuangdong Province China NCMIS LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

In this work, we investigate the two-step backward differentiation formula (BDF2) with nonuniform grids for the Allen-Cahn equation. We show that the nonuniform BDF2 scheme is energy stable under the time-step ratio r... 详细信息

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

Large language models for disease diagnosis: a scoping review

npj Artificial Intelligence

引用

npj Artificial Intelligence 2025年第1期1卷 1-17页

作者： Shuang Zhou Jeremy Yeung Mingquan Lin Rui Zhang Zidu Xu Mian Zhang Chunpu Xu Jiashuo Wang Kaishuai Xu Yawen Guo Zaifu Zhan Yi Fang Sirui Ding Liqiao Xia Daochen Zha Dongming Cai Genevieve B. Melton Division of Computational Health Sciences Department of Surgery University of Minnesota Minneapolis MN USA School of Nursing Columbia University New York New York USA Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas Richardson TX USA Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong SAR Department of Informatics University of California Irvine Irvine CA USA Department of Electrical and Computer Engineering University of Minnesota Minneapolis MN USA Department of Computer Science New York University (Shanghai) Shanghai China Bakar Computational Health Sciences Institute University of California San Francisco San Francisco CA USA Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong Hong Kong SAR Independent Researcher San Francisco CA USA Department of Neurology University of Minnesota Minneapolis MN USA Institute for Health Informatics and Division of Colon and Rectal Surgery Department of Surgery University of Minnesota Minneapolis MN USA

Automatic disease diagnosis has become increasingly valuable in clinical practice. The advent of large language models (LLMs) has catalyzed a paradigm shift in artificial intelligence, with growing evidence supporting the efficacy of LLMs in diagnostic tasks. Despite the increasing attention in this field, a holistic view is still lacking. Many critical aspects remain unclear, such as the diseases and clinical data to which LLMs have been applied, the LLM techniques employed, and the evaluation methods used. In this article, we perform a comprehensive review of LLM-based methods for disease diagnosis. Our review examines the existing literature across various dimensions, including disease types and associated clinical specialties, clinical data, LLM techniques, and evaluation methods. Additionally, we offer recommendations for applying and evaluating LLMs for diagnostic tasks. Furthermore, we assess the limitations of current research and discuss future directions. To our knowledge, this is the first comprehensive review for LLM-based disease diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ParaDiag: Parallel-in-time algorithms based on the diagonalization technique

arXiv

引用

arXiv 2020年

作者： Gander, Martin J. Liu, Jun Wu, Shu-Lin Yue, Xiaoqiang Zhou, Tao Section of Mathematics University of Geneva GenevaCH-1211 Switzerland Department of Mathematics and Statistics Southern Illinois University Edwardsville EdwardsvilleIL62026 United States School of Mathematics and Statistics Northeast Normal University Changchun130024 China School of Mathematics and Computational Science Xiangtan University Xiangtan411105 China Institute of Computational Mathematics and Scientific/Engineering Computing AMSS Chinese Academy of Sciences Beijing China

In 2008, Maday and Rønquist introduced an interesting new approach for the direct parallel-in-time (PinT) solution of time-dependent PDEs. The idea is to diagonalize the time stepping matrix, keeping the matrices for the space discretization unchanged, and then to solve all time steps in parallel. Since then, several variants appeared, and we call these closely related algorithms ParaDiag algorithms. ParaDiag algorithms in the literature can be classified into two groups: We will explain the basic features of each group in this note. To have concrete examples, we will introduce ParaDiag-I and ParaDiag-II for the advection-diffusion equation. We will also introduce ParaDiag-II for the wave equation and an optimal control problem for the wave equation. We could have used the advection-diffusion equation as well to illustrate ParaDiag-II, but wave equations are known to cause problems for certain PinT algorithms and thus constitute an especially interesting example for which ParaDiag algorithms were tested. We show the main known theoretical results in each case, and also provide Matlab codes for testing. The goal of the Matlab codes is to help the interested reader understand the key features of the ParaDiag algorithms, without intention to be highly tuned for efficiency and/or low memory use. We also provide speedup measurements of ParaDiag algorithms for a 2D linear advection-diffusion equation. These results are obtained on the Tianhe-1 supercomputer in China and the SIUE Campus Cluster in the US, which is a multi-array, configurable and cooperative parallel system, and we compare these results to the performance of parareal and MGRiT, two widely used PinT algorithms. In a forthcoming update of this note, we will provide more material on ParaDiag algorithms, in particular further Matlab codes and parallel computing results, also for more realistic applications. Copyright © 2020, The Authors. All rights reserved.

关键词： Advection

来源：评论

学校读者我要写书评

暂无评论

Searching for axion dark matter with the MeerKAT radio telescope

引用

Physical Review D 2022年第8期106卷 083006-083006页

作者： Yun-Fan Zhou Nick Houston Gyula I. G. Józsa Hao Chen Yin-Zhe Ma Qiang Yuan Tao An Yogesh Chandola Ran Ding Fujun Du Shao-Guang Guo Xiaoyuan Huang Mengtian Li Chandreyee Sengupta Key Laboratory of Radio Astronomy Purple Mountain Observatory Chinese Academy of Sciences Nanjing 210023 China School of Astronomy and Space Science University of Science and Technology of China Hefei Anhui 230026 China Institute of Theoretical Physics Faculty of Science Beijing University of Technology Beijing 100124 China Max-Planck-Institut für Radioastronomie Auf dem Hügel 69 53121 Bonn Germany Department of Physics and Electronics Rhodes University PO Box 94 Makhanda 6140 South Africa South African Radio Astronomy Observatory Black River Park 2 Fir Street Observatory Cape Town 7925 South Africa Department of Astronomy University of Cape Town Private Bag X3 7701 Rondebosch South Africa Research Center for Intelligent Computing Platforms Zhejiang Laboratory Hangzhou 311100 China School of Chemistry and Physics University of KwaZulu-Natal Westville Campus Durban 4000 South Africa NAOC-UKZN Computational Astrophysics Centre (NUCAC) University of KwaZulu-Natal Durban 4000 South Africa National Institute for Theoretical and Computational Sciences (NITheCS) Durbun 3630 South Africa Key Laboratory of Dark Matter and Space Astronomy Purple Mountain Observatory Chinese Academy of Sciences Nanjing 210023 China Shanghai Astronomical Observatory Chinese Academy of Sciences Nandan Road 80 Shanghai 200030 China School of Physics and Optoelectronics Engineering Anhui University Hefei 230601 China

Axions provide a natural and well-motivated dark matter candidate, with the capability to convert directly to photons in the presence of an electromagnetic field. A particularly compelling observational target is the conversion of dark matter axions into photons in the magnetospheres of highly magnetised neutron stars, which is expected to produce a narrow spectral peak centerd at the frequency of the axion mass. We point the MeerKAT radio telescope towards the isolated neutron star J0806.4−4123 for 10-hours of observation and obtain the radio spectra in the frequency range 769–1051 MHz. By modeling the conversion process of infalling axion dark matter (DM), we then compare these spectra to theoretical expectations for a given choice of axion parameters. Whilest finding no signal above 5σ in the data, we provide a unique constraint on the Primakoff coupling of axion DM, gaγγ≲9.3×10−12 GeV−1 at the 95% confidence level, in the mass range 3.18–4.35 μeV. This result serves the strongest constraint in the axion mass range 4.20–4.35 μeV.

关键词： Axions Particle dark matter

来源：评论

学校读者我要写书评

暂无评论

Benchmarking adaptive variational quantum eigensolvers

arXiv

引用

arXiv 2020年

作者： Claudino, Daniel Wright, Jerimiah McCaskey, Alexander J. Humble, Travis S. Quantum Computing Institute Oak Ridge National Laboratory Oak RidgeTN37831 United States Computer Science and Mathematics Oak Ridge National Laboratory Oak RidgeTN37831 United States Computational Sciences and Engineering Oak Ridge National Laboratory Oak RidgeTN37831 United States

By design, the variational quantum eigensolver (VQE) strives to recover the lowest-energy eigenvalue of a given Hamiltonian by preparing quantum states guided by the variational principle. In practice, the prepared quantum state is indirectly assessed by the value of the associated energy. Novel adaptive derivative-assembled pseudo-trotter (ADAPT) ansatz approaches and recent formal advances now establish a clear connection between the theory of quantum chemistry and the quantum state ansatz used to solve the electronic structure problem. Here we benchmark the accuracy of VQE and ADAPT-VQE to calculate the electronic ground states and potential energy curves for a few selected diatomic molecules, namely H2, NaH, and KH. Using numerical simulation, we find both methods provide good estimates of the energy and ground state, but only ADAPT-VQE proves to be robust to particularities in optimization methods. Another relevant finding is that gradient-based optimization is overall more economical and delivers superior performance than analogous simulations carried out with gradient-free optimizers. The results also identify small errors in the prepared state fidelity which show an increasing trend with molecular size. Copyright © 2020, The Authors. All rights reserved.

关键词： Electronic structure

来源：评论

学校读者我要写书评

暂无评论

Modality completion via gaussian process prior variational autoencoders for multi-modal glioma segmentation

arXiv

引用

arXiv 2021年

作者： Hamghalam, Mohammad Frangi, Alejandro F. Lei, Baiying Simpson, Amber L. School of Computing Queen's University KingstonON Canada Department of Electrical Biomedical and Mechatronics Engineering Qazvin Branch Azad University Qazvin34116846-13114 Iran Department of Biomedical and Molecular Sciences Queen's University KingstonON Canada CISTIB Centre for Computational Imaging & Simulation Technologies in Biomedicine School of Computing University of Leeds LeedsLS2 9LU United Kingdom LICAMM Leeds Institute of Cardiovascular and Metabolic Medicine School of Medicine LeedsLS2 9LU United Kingdom University Hospital Gasthuisberg KU Leuven Herestraat 49 Leuven3000 Belgium National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China

In large studies involving multi protocol Magnetic Resonance Imaging (MRI), it can occur to miss one or more sub-modalities for a given patient owing to poor quality (e.g. imaging artifacts), failed acquisitions, or hallway interrupted imaging examinations. In some cases, certain protocols are unavailable due to limited scan time or to retrospectively harmonise the imaging protocols of two independent studies. Missing image modalities pose a challenge to segmentation frameworks as complementary information contributed by the missing scans is then lost. In this paper, we propose a novel model, Multi-modal Gaussian Process Prior Variational Autoencoder (MGP-VAE), to impute one or more missing sub-modalities for a patient scan. MGP-VAE can leverage the Gaussian Process (GP) prior on the Variational Autoencoder (VAE) to utilize the subjects/patients and sub-modalities correlations. Instead of designing one network for each possible subset of present sub-modalities or using frameworks to mix feature maps, missing data can be generated from a single model based on all the available samples. We show the applicability of MGP-VAE on brain tumor segmentation where either, two, or three of four sub-modalities may be missing. Our experiments against competitive segmentation baselines with missing sub-modality on BraTS'19 dataset indicate the effectiveness of the MGP-VAE model for segmentation tasks. © 2021, CC BY.

关键词： Magnetic resonance imaging

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：