检索结果-内蒙古大学图书馆

ADVANCED INTELLIGENT SYSTEMS 2025年

作者： Ding, Di Yao, Tianliang Feng, Genyi Gao, Xueqing Sun, Xusen Luo, Rong Fudan Univ Qingpu Branch Dept Cardiol Zhongshan Hosp Shanghai 201700 Peoples R China Tongji Univ Coll Elect & Informat Engn Dept Control Sci & Engn Shanghai 200092 Peoples R China Chinese Univ Hong Kong Dept Elect Engn Fac Engn Hong Kong 999077 Peoples R China Tongji Univ Sch Med Shanghai 200092 Peoples R China Tongji Univ Sch Phys Sci & Engn Dept Optoelect Informat Engn Shanghai 200092 Peoples R China

The integration of foundation models in artificial intelligence (AI) is transforming computational microscopy, driving significant advancements in biomedical research. Trained on extensive and diverse datasets, these models overcome critical limitations of traditional microscopy, such as low resolution, slow processing speeds, and difficulties in analyzing complex, high-dimensional biological data. Foundation models enable enhanced image resolution, accelerated data processing, and real-time analysis of dynamic biological processes. Despite these advancements, challenges persist, including concerns related to data quality, model generalizability across varied biological contexts, and the interpretability of AI-generated insights. This review explores the application of foundation models in computational microscopy, emphasizing their theoretical foundations and practical implications across biomedical disciplines. Key obstacles are identified, such as the requirement for large-scale, high-quality annotated datasets and the need for model adaptation to specific clinical and preclinical settings. The review highlights the transformative potential of foundation models in advancing precision medicine, improving disease diagnostics, and enabling innovative therapeutic strategies, ultimately reshaping the landscape of biomedical research.

关键词： biomedical image analysis computational microscopy foundation models intelligent imaging systems

来源：评论

学校读者我要写书评

暂无评论

High-Throughput, Label-Free and Slide-Free Histological Imaging by computational microscopy and Unsupervised Learning

引用

ADVANCED SCIENCE 2022年第2期9卷 e2102358页

作者： Zhang, Yan Kang, Lei Wong, Ivy H. M. Dai, Weixing Li, Xiufeng Chan, Ronald C. K. Hsin, Michael K. Y. Wong, Terence T. W. Hong Kong Univ Sci & Technol Dept Chem & Biol Engn Translat & Adv Bioimaging Lab Kowloon Hong Kong Peoples R China Chinese Univ Hong Kong Dept Anat & Cellular Pathol Shatin Hong Kong Peoples R China Queen Mary Hosp Dept Cardiothorac Surg Kowloon Hong Kong Peoples R China

Rapid and high-resolution histological imaging with minimal tissue preparation has long been a challenging and yet captivating medical pursuit. Here, the authors propose a promising and transformative histological imaging method, termed computational high-throughput autofluorescence microscopy by pattern illumination (CHAMP). With the assistance of computational microscopy, CHAMP enables high-throughput and label-free imaging of thick and unprocessed tissues with large surface irregularity at an acquisition speed of 10 mm(2)/10 s with 1.1-mu m lateral resolution. Moreover, the CHAMP image can be transformed into a virtually stained histological image (Deep-CHAMP) through unsupervised learning within 15 s, where significant cellular features are quantitatively extracted with high accuracy. The versatility of CHAMP is experimentally demonstrated using mouse brain/kidney and human lung tissues prepared with various clinical protocols, which enables a rapid and accurate intraoperative/postoperative pathological examination without tissue processing or staining, demonstrating its great potential as an assistive imaging platform for surgeons and pathologists to provide optimal adjuvant treatment.

关键词： computational microscopy histology label-free imaging unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

computational microscopy of PEDOT:PSS/Cellulose Composite Paper

引用

ACS APPLIED ENERGY MATERIALS 2019年第5期2卷 3568-3577页

作者： Mehandzhiyski, Aleksandar Y. Zozoulenko, Igor Linkoping Univ ITN Lab Organ Elect S-60174 Norrkoping Sweden

Organic composite cellulose/conducting polymer materials have recently demonstrated their potential for energy storage applications. Here, we report a computational morphological study of CNF-PEDOT paper, which is composed of cellulose nanofibers (CNFs), and conducting polymer poly(3,4-ethylenedioxythiophene) blended with poly(styrenesulfonate) (PEDOT:PSS). With use of coarse-grained MARTINI molecular dynamics simulations, we study the aggregation of PEDOT:PSS on the cellulose surface, exploring different initial conditions for the self-assembly. The orientation of PEDOT chains with respect to the cellulose surface was studied, and the diffraction patterns were simulated. Finally, available experimental data were discussed and compared with calculated morphological models.

关键词： cellulose PEDOT self-assembly computational microscopy coarse-grained nanocomposites

来源：评论

学校读者我要写书评

暂无评论

Plant Sterol Clustering Correlates with Membrane Microdomains as Revealed by Optical and computational microscopy

引用

MEMBRANES 2021年第10期11卷 747-747页

作者： Tang, Ling Li, Yang Zhong, Cheng Deng, Xin Wang, Xiaohua Chinese Acad Sci Inst Bot Key Lab Plant Resources Beijing 100093 Peoples R China Univ Chinese Acad Sci Coll Life Sci Beijing 100049 Peoples R China Wuhan Univ Dept Chem Hubei Key Lab Organ & Polymer Optoelect Mat Wuhan 430072 Peoples R China

Local inhomogeneities in lipid composition play a crucial role in the regulation of signal transduction and membrane traffic. This is particularly the case for plant plasma membrane, which is enriched in specific lipids, such as free and conjugated forms of phytosterols and typical phytosphingolipids. Nevertheless, most evidence for microdomains in cells remains indirect, and the nature of membrane inhomogeneities has been difficult to characterize. We used a new push-pull pyrene probe and fluorescence lifetime imaging microscopy (FLIM) combined with all-atom multiscale molecular dynamics simulations to provide a detailed view on the interaction between phospholipids and phytosterol and the effect of modulating cellular phytosterols on membrane-associated microdomains and phase separation formation. Our understanding of the organization principles of biomembranes is limited mainly by the challenge to measure distributions and interactions of lipids and proteins within the complex environment of living cells. Comparing phospholipids/phytosterol compositions typical of liquid-disordered (Ld) and liquid-ordered (Lo) domains, we furthermore show that phytosterols play crucial roles in membrane homeostasis. The simulation work highlights how state-of-the-art modeling alleviates some of the prior concerns and how unrefuted discoveries can be made through a computational microscope. Altogether, our results support the role of phytosterols in the lateral structuring of the PM of plant cells and suggest that they are key compounds for the formation of plant PM microdomains and the lipid-ordered phase.

关键词： FLIM computational microscopy phase separation microdomain phytosterol

来源：评论

学校读者我要写书评

暂无评论

A Multispectral Bayesian-based computational microscopy Method for Enhancing Image Quality 17

A Multispectral Bayesian-based Computational Microscopy Meth...

引用

Conference on Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XVII

作者： Deglint, Jason L. Jin, Chao Wong, Alexander Univ Waterloo Dept Syst Design Engn VIP Lab Waterloo ON Canada Waterloo Artificial Intelligence Inst Waterloo ON Canada Sun Yat Sen Univ Sch Environm Sci & Engn Guangzhou 510275 Guangdong Peoples R China

ISBN: (数字)9781510624054

ISBN: (纸本)9781510624054

Brightfield microscopy is a standard method for the identification and enumeration of different micro-organisms, specifically for analyzing different types of algae and planktonic organisms in water samples. Typically, bright-field microscopy is performed in a broadband visible spectrum configuration;however, important distinguishing features in various micro-organisms are much better captured using a narrow-band multispectral configuration. One challenge with leveraging multispectral microscopy, particularly in low-cost field-portable instrument setups, is the presence of significant chromatic aberrations. Therefore, we introduce a multispectral Bayesian-based computational microscopy method for enhancing image quality by jointly correcting for chromatic aberrations, illumination inhomogeneities and noise across multiple spectral wavelengths within a probabilistic framework. To test the efficacy of this method, calibration parameters associated with a field-portable multi-spectral microscopy instrument are measured by characterizing the point spread functions at different spectral wavelengths ranging from 465 nm - 655 nm with a pinhole target. We demonstrate the effective optical resolution improvements of the microscopy instrument augmented with the proposed method using the 1951 USAF resolution test chart. Finally, we evaluate the qualitative performance of this instrument by imaging Anabaena ftos-aqua, a toxin-producing cyanobacteria, as well as Ankistrodesmus falcatus, a type of green algae. The efficacy of this proposed framework shows the potential of having an in-situ instrument to observe biological organisms at multiple narrow-band wavelengths, providing both additional spectral information and the ability for continuous detection and monitoring of micro-organisms.

关键词： multispectral imaging optical microscopy computational microscopy point spread function water conservation

来源：评论

学校读者我要写书评

暂无评论

computational microscopy: ILLUMINATION CODING AND NONLINEAR OPTIMIZATION ENABLES GIGAPIXEL 3D PHASE IMAGING

COMPUTATIONAL MICROSCOPY: ILLUMINATION CODING AND NONLINEAR ...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tian, Lei Yeh, Li-hao Eckert, Regina Waller, Laura Boston Univ Elect & Comp Engn 8 St Marys St Boston MA 02215 USA Univ Calif Berkeley Elect Engn & Comp Sci Cory Hall Berkeley CA 94720 USA

ISBN: (纸本)9781509041176

Microscope lenses can have either large field of view (FOV) or high resolution, not both. computational microscopy based on illumination coding circumvents this limit by fusing images from different illumination angles using nonlinear optimization algorithms. The result is a Gigapixel-scale image having both wide FOV and high resolution. We demonstrate an experimentally robust reconstruction algorithm based on a 2nd order quasi-Newton's method, combined with a novel phase initialization scheme. To further extend the Gigapixel imaging capability to 3D, we develop a reconstruction method to process the 4D light field measurements from sequential illumination scanning. The algorithm is based on a 'multislice' forward model that incorporates both 3D phase and diffraction effects, as well as multiple forward scatterings. To solve the inverse problem, an iterative update procedure that combines both phase retrieval and 'error back-propagation' is developed. To avoid local minimum solutions, we further develop a novel physical model-based initialization technique that accounts for both the geometric-optic and 1st order phase effects. The result is robust reconstructions of Gigapixel 3D phase images having both wide FOV and super resolution in all three dimensions. Experimental results from an LED array microscope were demonstrated.

关键词： computational microscopy coded illumination phase retrieval Fourier ptychography light field

来源：评论

学校读者我要写书评

暂无评论

computational microscopy: Illumination coding and nonlinear optimization enables Gigapixel 3D phase imaging

Computational microscopy: Illumination coding and nonlinear ...

引用

Conference on Three-Dimensional Imaging, Visualization, and Display

作者： Tian, Lei Waller, Laura Boston Univ Dept Elect & Comp Engn Boston MA 02215 USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94709 USA

ISBN: (纸本)9781510609396;9781510609402

Microscope lenses can have either large field of view (FOV) or high resolution, not both. computational microscopy based on illumination coding circumvents this limit by fusing images from different illumination angles using nonlinear optimization algorithms. The result is a Gigapixel-scale image having both wide FOV and high resolution. We demonstrate an experimentally robust reconstruction algorithm based on a 2nd order quasi Newton's method, combined with a novel phase initialization scheme. To further extend the Gigapixel imaging capability to 3D, we develop a reconstruction method to process the 4D light field measurements from sequential illumination scanning. The algorithm is based on a `multislice' forward model that incorporates both 3D phase and diffraction effects, as well as multiple forward scatterings. To solve the inverse problem, an iterative update procedure that combines both phase retrieval and 'error back-propagation' is developed. To avoid local minimum solutions, we further develop a novel physical model-based initialization technique that accounts for both the geometric-optic and 1st order phase effects. The result is robust reconstructions of Gigapixel 3D phase images having both wide FOV and super resolution in all three dimensions. Experimental results from an LED array microscope were demonstrated.

关键词： computational microscopy computational illumination coded illumination phase retrieval Fourier ptychography light field

来源：评论

学校读者我要写书评

暂无评论

High-Throughput Quantification of Nanoparticle Degradation Using computational microscopy and Its Application to Drug Delivery Nanocapsules

引用

ACS PHOTONICS 2017年第5期4卷 1216-1224页

作者： Ray, Aniruddha Li, Shuoran Segura, Tatiana Ozcan, Aydogan Univ Calif Los Angeles David Geffen Sch Med Elect Engn Dept Los Angeles CA 90095 USA Univ Calif Los Angeles David Geffen Sch Med Bioengn Dept Los Angeles CA 90095 USA Univ Calif Los Angeles David Geffen Sch Med Dept Chem & Biomol Engn Los Angeles CA 90095 USA Univ Calif Los Angeles David Geffen Sch Med Dept Med Dermatol Los Angeles CA 90095 USA Univ Calif Los Angeles David Geffen Sch Med Dept Surg Los Angeles CA 90095 USA Univ Calif Los Angeles CNSI Los Angeles CA 90095 USA

Design and synthesis of degradable nanoparticles are very important in drug delivery and biosensing fields. Although accurate assessment of nanoparticle degradation rate would improve the characterization and optimization of drug delivery vehicles, current methods rely on estimating the size of the particles at discrete points over time using, for example, electron microscopy or dynamic light scattering (DLS), among other techniques, all of which have drawbacks and practical limitations. There is a significant need for a high-throughput and cost-effective technology to accurately monitor nanoparticle degradation as a function of time and using small amounts of sample. To address this need, here we present two different computational imaging-based methods for monitoring and quantification of nanoparticle degradation. The first method is suitable for discrete testing, where a computational holographic microscope is designed to track the size changes of protease-sensitive protein-core nanoparticles following degradation, by periodically sampling a subset of particles mixed with proteases. In the second method, a sandwich structure was utilized to observe, in real-time, the change in the properties of liquid nanolenses that were self-assembled around degrading nanoparticles, permitting continuous monitoring and quantification of the degradation process. These cost-effective holographic imaging based techniques enable high-throughput monitoring of the degradation of any type of nanoparticle, using an extremely small amount of sample volume that is at least 3 orders of magnitude smaller than what is required by, for example, DLS-based techniques.

关键词： holographic microscopy nanoparticle degradation protease-mediated degradation drug delivery on-chip imaging lensless imaging computational microscopy

来源：评论

学校读者我要写书评

暂无评论

computational microscopy: illumination coding and nonlinear optimization enables Gigapixel 3D phase imaging

Computational microscopy: illumination coding and nonlinear ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Lei Tian Li-hao Yeh Regina Eckert Laura Waller Electrical & Computer Engineering Boston University 8 St. Mary's St. MA 02215 USA Electrical Engineering & Computer Science University of California Berkeley Cory Hall 94720 USA

ISBN: (纸本)9781509041183

Microscope lenses can have either large field of view (FOV) or high resolution, not both. computational microscopy based on illumination coding circumvents this limit by fusing images from different illumination angles using nonlinear optimization algorithms. The result is a Gigapixel-scale image having both wide FOV and high resolution. We demonstrate an experimentally robust reconstruction algorithm based on a 2nd order quasi-Newton's method, combined with a novel phase initialization scheme. To further extend the Gigapixel imaging capability to 3D, we develop a reconstruction method to process the 4D light field measurements from sequential illumination scanning. The algorithm is based on a `multi-slice' forward model that incorporates both 3D phase and diffraction effects, as well as multiple forward scatterings. To solve the inverse problem, an iterative update procedure that combines both phase retrieval and `error back-propagation' is developed. To avoid local minimum solutions, we further develop a novel physical model-based initialization technique that accounts for both the geometric-optic and 1st order phase effects. The result is robust reconstructions of Gigapixel 3D phase images having both wide FOV and super resolution in all three dimensions. Experimental results from an LED array microscope were demonstrated.

关键词： computational microscopy coded illumination phase retrieval Fourier ptychography light field Light fields Reconstruction algorithm Lighting illumination Phase super-resolution Three Dimensions High definition Optimization algorithms microscopy

来源：评论

学校读者我要写书评

暂无评论

Spatial mapping and analysis of aerosols during a forest fire using computational mobile microscopy 4

Spatial mapping and analysis of aerosols during a forest fir...

引用

Conference on Optics and Biophotonics in Low-Resource Settings IV

作者： Wu, Yichen Shiledar, Ashutosh Luo, Yi Wong, Jeffrey Chen, Cheng Bai, Bijie Zhang, Yibo Tamamitsu, Miu Ozcan, Aydogan Univ Calif Los Angeles Dept Elect Engn Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Bioengn Los Angeles CA 90095 USA Univ Calif Los Angeles CNSI Los Angeles CA 90095 USA Univ Calif Los Angeles Dept Comp Sci Los Angeles CA 90095 USA Univ Calif Los Angeles David Geffen Sch Med Los Angeles CA 90095 USA

ISBN: (数字)9781510614567

ISBN: (纸本)9781510614567

Forest fires are a major source of particulate matter (PM) air pollution on a global scale. The composition and impact of PM are typically studied using only laboratory instruments and extrapolated to real fire events owing to a lack of analytical techniques suitable for field-settings. To address this and similar field test challenges, we developed a mobilemicroscopy- and machine-learning-based air quality monitoring platform called c-Air, which can perform air sampling and microscopic analysis of aerosols in an integrated portable device. We tested its performance for PM sizing and morphological analysis during a recent forest fire event in La Tuna Canyon Park by spatially mapping the PM. The result shows that with decreasing distance to the fire site, the PM concentration increases dramatically, especially for particles smaller than 2 mu m. Image analysis from the c-Air portable device also shows that the increased PM is comparatively strongly absorbing and asymmetric, with an aspect ratio of 0.5-0.7. These PM features indicate that a major portion of the PM may be open-flame-combustion-generated element carbon soot-type particles. This initial small-scale experiment shows that c-Air has some potential for forest fire monitoring.

关键词： computational microscopy c-Air digital holography lensless microscope environmental sensing air pollution monitoring particulate matter forest fire black carbon

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：