检索结果-内蒙古大学图书馆

Temporal feature fusion with sampling pattern optimization for multi-echo gradient echo acquisition and image reconstruction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Jinwei Zhang, Hang Li, Chao Spincemaille, Pascal Sabuncu, Mert Nguyen, Thanh D. Wang, Yi Department of Biomedical Engineering Cornell University IthacaNY United States Department of Electrical and Computer Engineering Cornell University IthacaNY United States Department of Radiology Weill Medical College of Cornell University New YorkNY United States Department of Applied Physics Cornell University IthacaNY United States

Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging. In this work, we focus on optimizing the acquisition and reconstruction process of multi-echo gradient echo pulse sequence for quantitative susceptibility mapping as one important quantitative imaging method in MRI. A multi-echo sampling pattern optimization block extended from LOUPE-ST is proposed to optimize the k-space sampling patterns along echoes. Besides, a recurrent temporal feature fusion block is proposed and inserted into a backbone deep ADMM network to capture the signal evolution along echo time during reconstruction. Experiments show that both blocks help improve multi-echo image reconstruction performance. © 2021, CC BY.

关键词： Image reconstruction

Brain tumor classification using deep learning technique - A comparison between cropped, uncropped, and segmented lesion images with different sizes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Alqudah, Ali Mohammad Alquraan, Hiam Qasmieh, Isam Abu Alqudah, Amin Al-Sharu, Wafaa Department of Biomedical Systems and Informatics Engineering Yarmouk University Irbid Jordan Department of Computer Engineering Yarmouk University Irbid Jordan Department of Electrical Engineering Hashemite University Zarqa Jordan

Deep Learning is the newest and the current trend of the machine learning field that paid a lot of the researchers' attention in the recent few years. As a proven powerful machine learning tool, deep learning was widely used in several applications for solving various complex problems that require extremely high accuracy and sensitivity, particularly in the medical field. In general, the brain tumor is one of the most common and aggressive malignant tumor diseases which is leading to a very short expected life if it is diagnosed at a higher grade. Based on that, brain tumor grading is a very critical step after detecting the tumor in order to achieve an effective treating plan. In this paper, we used Convolutional Neural Network (CNN) which is one of the most widely used deep learning architectures for classifying a dataset of 3064 T1 weighted contrast-enhanced brain MR images for grading (classifying) the brain tumors into three classes (Glioma, Meningioma, and Pituitary Tumor). The proposed CNN classifier is a powerful tool and its overall performance with an accuracy of 98.93% and sensitivity of 98.18% for the cropped lesions, while the results for the uncropped lesions are 99% accuracy and 98.52% sensitivity and the results for segmented lesion images are 97.62% for accuracy and 97.40% sensitivity.68Txx (Primary), 30F20 (Secondary) Copyright © 2020, The Authors. All rights reserved.

关键词： Brain

MedNet: Pre-trained convolutional neural network model for the medical imaging tasks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Alzubaidi, Laith Santamaría, J. Manoufali, Mohamed Mohammed, Beadaa Fadhel, Mohammed A. Zhang, Jinglan Al-Timemy, Ali H. Al-Shamma, Omran Duan, Ye School of Computer Science Queensland University of Technology BrisbaneQLD4000 Australia Department of Computer Science University of Jaén Jaén23071 Spain School of Information Technology and Electrical Engineering The University of Queensland Brisbane4072 Australia College of Computer Science and Information Technology University of Sumer Thi Qar64005 Iraq Biomedical Engineering Department Al-Khwarizmi College of Engineering University of Baghdad Baghdad10066 Iraq The University of Information Technology & Communications Baghdad10001 Iraq Faculty of Electrical Engineering & Computer Science University of Missouri ColumbiaMO65211 United States

In the last few years, deep learning (DL) methods have dramatically improved the state-of-the-art in visual object recognition, speech recognition, and object detection, among many other applications. Specifically, DL requires a large amount of training data to provide quality outcomes. However, the field of medical imaging suffers from the lack of sufficient data for properly training DL models because medical images require manual labelling carried out by clinical experts thus the process is time-consuming, expensive, and error prone. Recently, transfer learning (TL) was introduced to reduce the need for the annotation procedure by means of transferring the knowledge performed by a previous task and then fine-tuning the result using a relatively small dataset. Nowadays, multiple classification methods from medical imaging make use of TL from general-purpose pre-trained models, e.g., ImageNet, which has been proven to be ineffective due to the mismatch between the features learned from natural images (ImageNet) and those more specific from medical images especially medical gray images such as X-rays. ImageNet does not have grayscale images such as MRI, CT, and X-ray. In this paper, we propose a novel DL model to be used for addressing classification tasks of medical imaging, called MedNet. To do so, we aim to issue two versions of MedNet. The first one is Gray-MedNet which will be trained on 3M publicly available gray-scale medical images including MRI, CT, X-ray, ultrasound, and PET. The second version is Color-MedNet which will be trained on 3M publicly available color medical images including histopathology, taken images, and many other. To validate the effectiveness MedNet, both versions will be fine-tuned to train on the target tasks of a more reduced set of medical images. MedNet performs as the pre-trained model to tackle any real-world application from medical imaging and achieve the level of generalization needed for dealing with medical imaging tasks, e.g

关键词： Magnetic resonance imaging

Development of a Selective Wet-Chemical Etchant for 3D Structuring of Silicon via Nonlinear Laser Lithography

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Borra, Mona Zolfaghari Radfar, Behrad Nasser, Hisham Çolakoğlu, Tahir Tokel, Onur Turnalı, Ahmet Demirtaş, Merve Ustunel, Hande Toffoli, Daniele Ömer İlday, F. Turan, Raşit Pavlov, Ihor Bek, Alpan ODTÜ-GÜNAM Middle East Technical University Ankara06800 Turkey Ankara06800 Turkey Department of Electronics and Nanoengineering Aalto University Tietotie 3 EspooFI-02150 Finland Department of Physics Engineering Ankara University Ankara06100 Turkey Department of Physics Bilkent University Ankara06800 Turkey UNAM National Nanotechnology Research Center Institute of Materials Science and Nanotechnology Bilkent University Ankara06800 Turkey Department of Electrical and Electronics Engineering Bilkent University Ankara06800 Turkey Department of Electrical and Computer Engineering Boston University 8 Saint Mary’s Street BostonMA02215 United States Ankara06800 Turkey Network Technologies Department TUBITAK ULAKBIM Ankara06800 Turkey Department of Chemical and Pharmaceutical Sciences Trieste University Trieste Italy IOM-CNR Istituto Officina dei Materiali Trieste34149 Italy Micro and Nanotechnology Graduate Program of Natural and Applied Sciences Middle East Technical Turkey

Recently-demonstrated high-quality three-dimensional (3D) subsurface laser processing inside crystalline silicon (c-Si) wafers opens a door to a wide range of novel applications in multidisciplinary research areas. Using this technique, a novel maskless micro-pillars with precise control on the surface reflection and coverage are successfully fabricated by etching the laser processed region of c-Si wafer. To achieve this, a particular selective wet chemical etching is developed to follow subsurface laser processing of c-Si to reveal the desired 3D structures with smooth surfaces. Here, we report the development of a novel chromium-free chemical etching recipe based on copper nitrate, which yields substantially smooth surfaces at high etch rate and selectivity on the both laser-processed Si surface and subsurface, i.e., without significant etching of the unmodified Si. Our results show that the etch rate and surface morphology are interrelated and strongly influenced by the composition of the adopted etching solution. After an extensive compositional study performed at room temperature, we identify an etchant with a selectivity of over 1600 times for laser-modified Si with respect to unmodified Si. We also support our findings using density functional theory calculations of HF and Cu adsorption energies, indicating significant diversity on the c-Si and laser-modified surfaces. Copyright © 2023, The Authors. All rights reserved.

关键词： Morphology

A New Stator Winding Inter-Turn Short Circuit Fault Detection Method For Brushless Doubly Fed Induction Machine

学校读者我要写书评

暂无评论

A New Stator Winding Inter-Turn Short Circuit Fault Detectio...

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Mojtaba Afshar Salman Abdi Abolfazl Mortazavizadeh Poria Fajri Mohammad Ebrahimi Department of Electrical and Biomedical Engineering University of Nevada Reno Reno NV USA School of Engineering University of East Anglia Norwich UK Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran

ISBN: (数字)9781728156354

ISBN: (纸本)9781728156361

The brushless Doubly Fed Induction Machine (BDFIM) with high reliability and robust structure demonstrates technical and commercial advantages both as a generator and motor for variable speed drive applications. As a generator it is particularly attractive to be used in offshore wind turbines where reliability improvement and maintenance cost reduction are the key factors in wind power market growth. As a motor it can be utilized in application requiring adjustable speed operation. Inter-turn short circuit fault is one of the most frequent electrical faults in electric machines, which can also be the cause of other stator winding faults in the machine, hence its early detection can significantly reduce the maintenance cost and improve reliability. In this paper a novel fault detection method for inter-turn short circuit fault is proposed for the BDFIM based on the discrete wavelet transform of the stator winding currents. The analytical winding function method as well as the finite element analysis of an experimental D180 BDFIM is used in order to verify the proposed fault detection method.

关键词： Stator windings Circuit faults Rotors Windings Transforms Fault detection

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Feng Sedler, Andrew R. Grier, Harrison A. Ahad, Nauman Davenport, Mark A. Kaufman, Matthew T. Giovannucci, Andrea Pandarinath, Chethan Neuroscience Graduate Program Emory University Center for Machine Learning Georgia Tech Computational Neuroscience Graduate Program The University of Chicago School of Electrical and Computer Engineering Georgia Tech Dept. of Organismal Biology and Anatomy The University of Chicago Neuroscience Institute The University of Chicago Joint Dept. of Biomedical Engineering UNC Chapel Hill NC State University UNC Chapel Hill Neuroscience Center Coulter Dept. of Biomedical Engineering Emory University Georgia Tech Dept. of Neurosurgery Emory University

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data. © 2021, CC BY-NC-SA.

关键词： Neurons

DCFormer: Efficient 3D Vision-Language Modeling with Decomposed Convolutions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ates, Gorkem Can Xin, Yu Gong, Kuang Shao, Wei Department of Medicine University of Florida GainesvilleFL32611 United States Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Department of Biomedical Engineering University of Florida GainesvilleFL32611 United States Intelligent Clinical Care Center University of Florida GainesvilleFL32611 United States

Vision-language models (VLMs) have been widely applied to 2D medical image analysis due to their ability to align visual and textual representations. However, extending VLMs to 3D imaging remains computationally challenging. Existing 3D VLMs often rely on Vision Transformers (ViTs), which are computationally expensive due to the quadratic complexity of self-attention, or on 3D convolutions, which require large numbers of parameters and FLOPs as kernel size increases. We introduce DCFormer, an efficient 3D image encoder that factorizes 3D convolutions into three parallel 1D convolutions along the depth, height, and width dimensions. This design preserves spatial information while significantly reducing computational cost. Integrated into a CLIP-based vision-language framework, DCFormer is trained and evaluated on CT-RATE, a dataset of 50,188 paired 3D chest CT volumes and radiology reports. In zero-shot and fine-tuned detection of 18 pathologies, as well as in image–text retrieval tasks, DCFormer consistently outperforms state-of-the-art 3D vision encoders, including CT-ViT, ViT, ConvNeXt, PoolFormer, and TransUNet. These results highlight DCFormer’s potential for scalable, clinically deployable 3D medical VLMs. Our code is available at: https://***/mirthAI/DCFormer. © 2025, CC BY-NC-SA.

关键词： Three dimensional computer graphics

Quantum simulation of an extended Dicke model with a magnetic solid

学校读者我要写书评

暂无评论

Communications Materials

Communications Materials 2024年第1期5卷 42页

作者： Marquez Peraca, Nicolas Li, Xinwei Moya, Jaime M. Hayashida, Kenji Kim, Dasom Ma, Xiaoxuan Neubauer, Kelly J. Fallas Padilla, Diego Huang, Chien-Lung Dai, Pengcheng Nevidomskyy, Andriy H. Pu, Han Morosan, Emilia Cao, Shixun Bamba, Motoaki Kono, Junichiro Department of Physics and Astronomy Rice University HoustonTX United States Department of Physics California Institute of Technology PasadenaCA United States Applied Physics Graduate Program Smalley–Curl Institute Rice University HoustonTX United States Division of Applied Physics Graduate School of Engineering Hokkaido University Hokkaido Japan Department of Electrical and Computer Engineering Rice University HoustonTX United States Department of Physics International Center of Quantum and Molecular Structures and Materials Genome Institute Shanghai University Shanghai China Department of Physics and Center for Quantum Frontiers of Research and Technology National Cheng Kung University Tainan Taiwan Department of Chemistry Rice University HoustonTX United States Department of Physics I Kyoto University Kyoto Japan The Hakubi Center for Advanced Research Kyoto University Kyoto Japan PRESTO Japan Science and Technology Agency Saitama Japan Department of Physics Yokohama National University Yokohama Japan Department of Materials Science and NanoEngineering Rice University HoustonTX United States

The Dicke model describes the cooperative interaction of an ensemble of two-level atoms with a single-mode photonic field and exhibits a quantum phase transition as a function of light–matter coupling strength. Extending this model by incorporating short-range atom–atom interactions makes the problem intractable but is expected to produce new physical phenomena and phases. Here, we simulate such an extended Dicke model using a crystal of ErFeO3, where the role of atoms (photons) is played by Er3+ spins (Fe3+ magnons). Through terahertz spectroscopy and magnetocaloric effect measurements as a function of temperature and magnetic field, we demonstrated the existence of a novel atomically ordered phase in addition to the superradiant and normal phases that are expected from the standard Dicke model. Further, we elucidated the nature of the phase boundaries in the temperature–magnetic-field phase diagram, identifying both first-order and second-order phase transitions. These results lay the foundation for studying multiatomic quantum optics models using well-characterized many-body solid-state systems. © The Author(s) 2024.

关键词： Atoms

A review of fluid-structure interaction: blood flow in arteries

学校读者我要写书评

暂无评论

biomedical engineering Advances 2025年 9卷

作者： Zubeir Allum Saib Farid Abed Mergen H. Ghayesh Marco Amabili Biomedical Engineering Graduate Program American University of Sharjah Sharjah United Arab Emirates Department of Bioengineering New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Civil Engineering American University of Sharjah Sharjah United Arab Emirates School of Electrical and Mechanical Engineering University of Adelaide South Australia Australia School of Engineering Westlake University Hangzhou Zhejiang province China

Over the past decade, Fluid-Structure Interaction studies related to blood vessels have been an active area of research, as they adequately capture the multiphysics of blood flow within the circulatory system. Despite the growing interest, only few state-of-the-art reviews have been published in the literature, each focusing individually on the coronary artery, carotid artery, aorta, heart valves and peripheral arteries. This systematic review assesses the current research and implications of Fluid-Structure Interaction implementation strategies in relation to human arteries. It is meant to comprehensively amalgamate research studies on an array of arteries coupled with cardiovascular complications such as atherosclerosis, plaque calcification, aneurysms, aortic dissections and valve dysfunction. It additionally covers computational finite element and finite volume solver demands, coupling schemes, inlet and outlet boundary conditions specifications, Newtonian and non-Newtonian blood rheological properties, laminar and turbulent flow types, as well as the modelling of the vessel wall’s hyperelastic and viscoelastic mechanical behavior. The research information is retrieved from the last ten years and summarized in a tabulated format, to help researchers in easily extracting useful information for future investigations and reviews.

关键词： Fluid-structure interaction Computational fluid dynamics Finite element analysis Blood flow Hemodynamics Biomechanics Atherosclerosis Aneurysm Calcification Artery Plaque Valve