检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Abdelhalim, Ibrahim Elsharkawy, Mohamed Nadmid, Namuunaa Ghazal, Mohammed Mahmoud, Ali El-Baz, Ayman Department of Bioengineering University of Louisville LouisvilleKY United States Electrical and Computer Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031781032

The early diagnosis and effective treatment of age-related macular degeneration (AMD), a leading cause of vision impairment, is contingent upon accurate grading. This paper introduces a novel framework, named Mask-UnMask Regions (MUMR), designed to distinguish between normal retina, intermediate AMD, geographic atrophy (GA), and wet AMD using retinal fundus images, with the input resolution standardized to 1024×1024 pixels. The framework begins by downscaling images to a quarter of their size using a Preserving High-Frequency Information (PHFI) module, which maintains critical details essential for furthure analysis. Furthermore, we developed a simple, lightweight, yet effective ResNet-like network for efficient feature extraction and introduced a Region Interaction (RI) module, which consists of Adaptive Mask and UnMask Sub-Modules. This module identifies significant regions while reconstructing the insignificant ones using a direction-constrained self-attention mechanism to ensure the learning of global structural cues of AMD grades. The proposed method was evaluated on a dataset of 864 retinal fundus images. Our model consistently achieves superior results compared to other state-of-the-art models, with mean accuracy, mean F1-score, and mean Cohen’s Kappa of 92.55%, 92.59%, and 89.97%, respectively. Additionally, we demonstrate that these results are statistically significant compared to other models based on F1-score, indicating that our proposed framework achieves robust and improved AMD grading performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Universal linear intensity transformations using spatially incoherent diffractive processors

引用

Light(Science & Applications) 2023年第9期12卷 1830-1856页

作者： Md Sadman Sakib Rahman Xilin Yang Jingxi Li Bijie Bai Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCA 90095USA Bioengineering Department University of CaliforniaLos AngelesCA 90095USA California NanoSystems Institute(CNSI) University of CaliforniaLos AngelesCA 90095USA

Under spatially coherent light,a diffractive optical network composed of structured surfaces can be designed to perform any arbitrary complex-valued linear transformation between its input and output fields-of-view(FOVs)if the total number(N)of optimizable phase-only diffractive features is≥~2N_(i)N_(o),where Ni and No refer to the number of useful pixels at the input and the output FOVs,*** we report the design of a spatially incoherent diffractive optical processor that can approximate any arbitrary linear transformation in time-averaged intensity between its input and output *** spatially incoherent monochromatic light,the spatially varying intensity point spread function(H)of a diffractive network,corresponding to a given,arbitrarily-selected linear intensity transformation,can be written as H(m,n;m′,n′)=|h(m,n;m′,n′)|^(2),where h is the spatially coherent point spread function of the same diffractive network,and(m,n)and(m′,n′)define the coordinates of the output and input FOVs,*** numerical simulations and deep learning,supervised through examples of input-output profiles,we demonstrate that a spatially incoherent diffractive network can be trained to all-optically perform any arbitrary linear intensity transformation between its input and output if N≥~2N_(i)N_(o).We also report the design of spatially incoherent diffractive networks for linear processing of intensity information at multiple illumination wavelengths,operating ***,we numerically demonstrate a diffractive network design that performs all-optical classification of handwritten digits under spatially incoherent illumination,achieving a test accuracy of>95%.Spatially incoherent diffractive networks will be broadly useful for designing all-optical visual processors that can work under natural light.

关键词： spatially intensity arbitrary

来源：评论

学校读者我要写书评

暂无评论

Neural network-based processing and reconstruction of compromised biophotonic image data

引用

Light(Science & Applications) 2024年第10期13卷 2101-2113页

作者： Michael John Fanous Paloma Casteleiro Costa Gagatay lsi Luzhe Huang Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCAUSA Bioengineering Department University of CaliforniaLos AngelesCAUSA California NanoSystems Institute(CNSi) University of CaliforniaLos AngelesCAUSA Department of Surgery David Geffen School of MedicineUniversity of CaliforniaLos AngelesCAUSA

In recent years,the integration of deep learning techniques with biophotonic setups has opened new horizons in bioimaging.A compelling trend in this feld involves deliberately compromising certain measurement metrics to engineer better bioimaging tools in terms of e.g,cost,speed,and form-factor,followed by compensating for the resulting defects through the utilization of deep learning models trained on a large amount of ideal,superior or alternative *** strategic approach has found increasing popularity due to its potential to enhance various aspects of biophotonic *** of the primary motivations for employing this strategy is the pursuit of higher temporal resolution or increased imaging speed,critical for capturing fine dynamic biological ***,this approach offers the prospect of simplifying hardware requirements and complexities,thereby making advanced imaging standards more accessible in terms of cost and/or *** article provides an in-depth review of the diverse measurement aspects that researchers intentionally impair in their biophotonic setups,including the point spread function(PSF),signal-to-noise ratio(SNR),sampling density,and pixel *** deliberately compromising these metrics,researchers aim to not only recuperate them through the application of deep learning networks,but also bolster in return other crucial parameters,such as the field of view(FOV),depth of field(DOF),and space-bandwidth product(SBP).Throughout this article,we discuss various biophotonic methods that have successfully employed this strategic *** techniques span a wide range of applications and showcase the versatility and effectiveness of deep learning in the context of compromised biophotonic ***,by offering our perspectives on the exciting future possibilities of this rapidly evolving concept,we hope to motivate our readers from various disciplines to explore novel ways of balancing hardware compromises with compensatio

关键词： offering hardware return

来源：评论

学校读者我要写书评

暂无评论

Remarks on the Gradient Training of Linear Neural Network Based Feedback for the LQR Problem 63

Remarks on the Gradient Training of Linear Neural Network Ba...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： De Oliveira, Arthur Castello B. Siami, Milad Sontag, Eduardo D. Northeastern University Department of Electrical & Computer Engineering BostonMA02115 United States Northeastern University Department of Bioengineering BostonMA02115 United States

ISBN: (纸本)9798350316339

Motivated by the growing use of Artificial intelligence (AI) tools in control design, this paper takes steps toward bridging results from Direct Gradient methods for the Linear Quadratic Regulator (LQR), and neural networks. More specifically, it looks into the case where one wants to find a Linear Feed-Forward Neural Network (LFFNN) feedback that minimizes the LQR cost. This work develops gradient formulas that can be used to implement the training of such networks and derives an important conservation law of the system. This conservation law is then leveraged to prove the global convergence of solutions and invariance of the set of stabilizing networks under the training dynamics. These theoretical results are followed by an extensive analysis of the simplest version of the problem (the 'scalar case') and by numerical evidence of faster convergence of the training of general LFFNNs when compared to traditional direct gradient methods. © 2024 IEEE.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

All-optical image classification through unknown random diffusers using a single-pixel diffractive network

引用

Light(Science & Applications) 2023年第4期12卷 570-584页

作者： Bijie Bai Yuhang Li Yi Luo Xurong Li Ege Cetintas Mona Jarrrahi Aydogan Ozcan Electrical and Computer Engineering Department University of CaliforniaLos AngelesCalifornia 90095USA Bioengineering Department University of CaliforniaLos AngelesCalifornia 90095USA California Nano Systems Institute(CNSI) University of CaliforniaLos AngelesCalifornia 90095USA

Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision *** deep learning-based approaches demonstrated the classification of objects using diffuser-distorted patterns collected by an image *** methods demand relatively large-scale computing using deep neural networks running on digital ***,we present an all-optical processor to directly classify unknown objects through unknown,random phase diffusers using broadband illumination detected with a single pixel.A set of transmissive diffractive layers,optimized using deep learning,forms a physical network that all-optically maps the spatial information of an input object behind a random diffuser into the power spectrum of the output light detected through a single pixel at the output plane of the diffractive *** numerically demonstrated the accuracy of this framework using broadband radiation to classify unknown handwritten digits through random new diffusers,never used during the training phase,and achieved a blind testing accuracy of 87.74±1.12%.We also experimentally validated our single-pixel broadband diffractive network by classifying handwritten digits"0"and"1"through a random diffuser using terahertz waves and a 3D-printed diffractive *** single-pixel all-optical object classification system through random diffusers is based on passive diffractive layers that process broadband input light and can operate at any part of the electromagnetic spectrum by simply scaling the diffractive features proportional to the wavelength range of *** results have various potential applications in,e.g.,biomedical imaging,security,robotics,and autonomous driving.

关键词： network processor random

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Classification of Breast Ultrasound with Parametric Quantitative Images and RF Beamsum Data

Deep Learning-based Classification of Breast Ultrasound with...

引用

Medical Imaging 2025: Ultrasonic Imaging and Tomography

作者： Hasnat, Rehnuma Wiacek, Alycen Department of Electrical and Computer Engineering Oakland University RochesterMI United States Department of Bioengineering Oakland University RochesterMI United States

ISBN: (纸本)9781510686021

Due to its high false positive rate, ultrasound is often used as a supplement to mammography to diagnose breast cancer. Recently, the use of computer aided diagnosis (CAD) systems have enabled the automatic analysis of ultrasound images using deep learning, reducing false positives. However, the majority of these CAD systems analyze grayscale images, resulting in a significant loss of acoustic information available in the raw data. Therefore, the objective of this study is to investigate the novel fusion of seven distinct features engineered from raw ultrasound data to classify breast ultrasound images using deep learning. A publicly available dataset, OASBUD, including raw radiofrequency (RF) data from 100 breast masses, was processed to extract seven types of parametric, domain-specific features: raw RF, grayscale, parametric spectral features (i.e., spectral slope, 0-MHz intercept, and midband fit), and envelope statistics (i.e., Nakagami scale and shape parameters). A custom U-Net was trained to classify benign and malignant breast masses using combinations of these features. In addition, rectangular convolutional kernels were investigated as a result of the rectangular character of raw ultrasound data. The optimal network, including all 7 features and a 7x3 rectangular kernel, resulted in 78.12% accuracy, a 15.62% improvement over grayscale features alone. These results demonstrate that the proposed inclusion of domain-specific, parametric quantitative ultrasound images as features for deep learning is promising to improve CAD systems for classification of breast ultrasound images and improve the diagnosis of breast cancer. © 2025 SPIE.

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

Estimating and Analyzing Neural Information flow using Signal Processing on Graphs 48

Estimating and Analyzing Neural Information flow using Signa...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Schwock, Felix Bloch, Julien Atlas, Les Abadi, Shima Yazdan-Shahmorad, Azadeh University of Washington Department of Electrical and Computer Engineering Seattle United States University of Washington Department of Bioengineering Seattle United States

ISBN: (纸本)9781728163277

Correlating neural communication in brain networks with behavior and cognition can provide fundamental insights into the functionality of both healthy and diseased brains. We demonstrate how communication in the brain can be estimated from recorded neural activity using concepts from graph signal processing. The communication is modeled as a flow signals on the edges of a graph and naturally arises from a graph diffusion process. We apply the diffusion model to micro-electrocorticography (ECoG) recordings from sensorimo-tor cortex of two non-human primates to estimate the neural communication flow during excitatory optogenetics. Comparisons with a baseline model demonstrate that adding the neural flow can improve ECoG predictions. Finally, we demonstrate how the neural flow can be decomposed into a gradient and rotational component and show that the gradient component depends on the location of stimulation. This technique, for the first time, offers the opportunity to study neural communication on an unprecedented spatiotemporal scale. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Imaging Snapshot Spectrometers enabled with 2-Photon Polymerization based Additive Manufacturing

Imaging Snapshot Spectrometers enabled with 2-Photon Polymer...

引用

2024 Imaging Systems and Applications, ISA 2024 - Part of Optica Imaging Congress

作者： Tkaczyk, Tomasz S. Lu, Jiawei Cao, Haimu Department of Bioengineering Rice University HoustonTX77005 United States Electrical and Computer Engineering Rice University HoustonTX77005 United States

The work presents examples of two imaging spectrometers enabled with 2-Photon Polymerization 3D printing. The presented spectrometers are field integral devices and image reorganization is achieved with high density waveguide array (waveguide spectrometer) or multifaceted, multi-angle mirror array respectively (Image Mapping Spectrometer - IMS). Fabricated components allow void spaces between image points dedicated for spectral information. High precision and repeatability of the fabricated components simplifies system calibration, improved image quality allows and more compact systems implementations. © 2024 The Author(s).

关键词： Spectrometers

来源：评论

学校读者我要写书评

暂无评论

Experimental measurement and numerical modeling of deformation behavior of breast cancer cells passing through constricted microfluidic channels

引用

Microsystems & Nanoengineering 2024年第1期10卷 129-147页

作者： Pouyan Keshavarz Motamed Hesam Abouali Mahla Poudineh Nima Maftoon Department of Systems Design Engineering University of WaterlooWaterlooON N2L 3G1Canada Center for Bioengineering and Biotechnology University of WaterlooWaterlooON N2L 3G1Canada Department of Electrical and Computer Engineering University of WaterlooWaterlooON N2L 3G1Canada

During the multistep process of metastasis,cancer cells encounter various mechanical forces which make them deform *** accurate in-silico models,capable of simulating the interactions between the mechanical forces and highly deformable cancer cells,can pave the way for the development of novel diagnostic and predictive methods for metastatic ***-network models of cancer cell,empowered by our recently proposed identification approach,promises a versatile numerical tool for developing experimentally validated models that can simulate complex interactions at cellular *** this numerical tool,we presented spring-network models of breast cancer cells that can accurately replicate the experimental data of deformation behavior of the cells flowing in a fluidic domain and passing narrow constrictions comparable to ***,using high-speed imaging,we experimentally studied the deformability of breast cancer cell lines with varying metastatic potential(MCF-7(less invasive),SKBR-3(medium-high invasive),and MDA-MB-231(highly invasive)in terms of their entry time to a constricted microfluidic *** observed that MDA-MB-231,that has the highest metastatic potential,is the most deformable cell among the ***,by focusing on this cell line,experimental measurements were expanded to two more constricted microchannel *** experimental deformability data in three constricted microchannel sizes for various cell sizes,enabled accurate identification of the unknown parameters of the spring-network model of the breast cancer cell line(MDA-MB-231).Our results show that the identifed parameters depend on the cell size,suggesting the need for a systematic procedure for identifying the size-dependent parameters of spring-network models of *** the numerical results show,the presented cell models can simulate the entry process of the cell into constricted channels with very good agreements with the measured experimen

关键词： strict passing numerical

来源：评论

学校读者我要写书评

暂无评论

UMAP for Dimensionality Reduction in Sleep Stage Classification Using EEG Data 46

UMAP for Dimensionality Reduction in Sleep Stage Classificat...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Deng, Yangfan Albidah, Hamad Cheng, Haoliang Dallal, Ahmed Yin, Jijun Mao, Zhi-Hong University of Pittsburgh Department of Computer Science PittsburghPA United States University of Pittsburgh Department of Electrical and Computer Engineering PittsburghPA United States University of Pittsburgh Department of Bioengineering PittsburghPA United States

ISBN: (纸本)9798350371499

Sleep is vital for wellness, and electroencephalography (EEG) serves as an instrumental tool in the study of sleep. Sleep is classified into four stages: stages N1-N3, and rapid eye movement (REM). To acquire effective and robust EEG features for sleep detection and analysis, we explore the dimensionality reduction effects of Uniform Manifold Approximation and Projection (UMAP) on various features of the EEG signals. Compared with traditional band power analysis, UMAP demonstrated higher accuracy for sleep stage classification and better reliability. Using UMAP, we observed an average of 11% increase in accuracy and an average of 20% increase in Macro-F1 Score on the same dataset. Particularly, in the wakefulness stage, Macro-F1 Score increased by 23%. Moreover, the 2D visual analysis revealed the outstanding ability of UMAP to cluster EEG signals after significant dimensionality reduction of the data. © 2024 IEEE.

关键词： Dimensionality reduction

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：