检索结果-内蒙古大学图书馆

Parallel deep neural networks for endoscopic OCT image segmentation

BIOMEDICAL OPTICS EXPRESS 2019年第3期10卷 1126-1135页

作者： Li, Dawei Wu, Jimin He, Yufan Yao, Xinwen Yuan, Wu Chen, Defu Park, Hyeon-Cheol Yu, Shaoyong Prince, Jerry L. Li, Xingde Johns Hopkins Univ Dept Biomed Engn Baltimore MD 21205 USA Johns Hopkins Univ Dept Elect & Comp Engn Baltimore MD 21218 USA Johns Hopkins Univ Sch Med Dept Med Baltimore MD 21205 USA

We report parallel-trained deep neural networks for automated endoscopic OCT image segmentation feasible even with a limited training data set. These U-Net-based deep neural networks were trained using a modified dice loss function and manual segmentations of ultrahigh-resolution cross-sectional images collected by an 800 nm OCT endoscopic system. The method was tested on in vivo guinea pig esophagus images. Results showed its robust layer segmentation capability with a boundary error of 1.4 mu m insensitive to lay topology disorders. To further illustrate its clinical potential, the method was applied to differentiating in vivo OCT esophagus images from an eosinophilic esophagitis (EOE) model and its control group, and the results clearly demonstrated quantitative changes in the top esophageal layers' thickness in the EOE model. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： image processing image processing algorithms Medical image processing Neural networks Optical imaging Speckle noise

来源：评论

学校读者我要写书评

暂无评论

image registration method for mobile-device-based multispectral optical diagnostics for buildings

引用

APPLIED OPTICS 2019年第26期58卷 7165-7173页

作者： Sahin, Cem Dogan Menguc, M. Pinar Ozyegin Univ CEEE ECEM TR-34394 Istanbul Turkey Ozyegin Univ Mech Engn TR-34394 Istanbul Turkey

The recent advances in mobile device hardware and software introduced new opportunities to perform more advanced computation and measurements for buildings. Multispectral optical imaging is a widely recognized technique for building diagnostics, as it is non-destructive, quick, and provides rich spatial-spectral information about the different surfaces for decisions related to building energy performance. However, such implementations require an accurate image fission. The purpose of this study is to introduce a practical and robust image registration method for mobile-device-based multispectral imaging analysis for building diagnostics. Considering the complicated building geometries including walls, floors, ceilings, roofs, windows, and doors, a new approach based on planar homography is chosen for determining the feature points that are required to perform image fusion between different images. The results obtained are compared against the other available methods, which show that the current method provides multispectral images enhanced with accurate qualitative information, as long as the constraints are satisfied. The results are compared with the state-of-the-art methods. The possible impact of the multispectral imaging to the future of building diagnostics is also discussed. (C) 2019 Optical Society of America

关键词： image enhancement image fusion image processing image processing algorithms Multispectral imaging Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Divide and conquer: real-time maximum likelihood fitting of multiple emitters for super-resolution localization microscopy

引用

OPTICS EXPRESS 2019年第15期27卷 21029-21049页

作者： Li, Luchang Xin, Bo Kuang, Weibing Zhou, Zhiwei Huang, Zhen-Li Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Britton Chance Ctr Biomed Photon Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Engn Sci Collaborat Innovat Ctr Biomed Engn MoE Key Lab Biomed Photon Wuhan 430074 Hubei Peoples R China

Multi-emitter localization has great potential for maximizing the imaging speed of super-resolution localization microscopy. However, the slow image analysis speed of reported multi-emitter localization algorithms limits their usage in mostly off-line image processing with small image size. Here we adopt the well-known divide and conquer strategy in computer science and present a fitting-based method called QC-STORM for fast multi-emitter localization. Using simulated and experimental data, we verify that QC-STORM is capable of providing real-time full image processing on raw images with 100 mu m x 100 mu m field of view and 10 ms exposure time, with comparable spatial resolution as the popular fitting-based ThunderSTORM and the up-to-date non-iterative WindSTORM. This study pushes the development and practical use of super-resolution localization microscopy in high-throughput or high-content imaging of cell-to-cell differences or discovering rare events in a large cell population. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： image analysis image processing image processing algorithms image reconstruction Three dimensional image processing Three dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning

引用

BIOMEDICAL OPTICS EXPRESS 2019年第2期10卷 892-913页

作者： Gomez-Valverde, Juan J. Anton, Alfonso Fatti, Gianluca Liefers, Bart Herranz, Alejandra Santos, Andres Sanchez, Clara, I Ledesma-Carbay, Maria J. Univ Politecn Madrid Biomed Image Technol Lab BIT ETSI Telecomunicac E-28040 Madrid Spain Biomed Res Ctr Bioengn Biomat & Nanomed CIBER BBN Madrid Spain Parc Salut Mar Barcelona Spain Univ Int Catalunya Barcelona Spain Inst Catala Retina Barcelona Spain Radboud Univ Nijmegen Dept Radiol & Nucl Med Diagnost Image Anal Grp Med Ctr Nijmegen Netherlands

Glaucoma detection in color fundus images is a challenging task that requires expertise and years of practice. In this study we exploited the application of different Convolutional Neural Networks (CNN) schemes to show the influence in the performance of relevant factors like the data set size, the architecture and the use of transfer learning vs newly defined architectures. We also compared the performance of the CNN based system with respect to human evaluators and explored the influence of the integration of images and data collected from the clinical history of the patients. We accomplished the best performance using a transfer learning scheme with VGG19 achieving an AUC of 0.94 with sensitivity and specificity ratios similar to the expert evaluators of the study. The experimental results using three different data sets with 2313 images indicate that this solution can be a valuable option for the design of a computer aid system for the detection of glaucoma in large-scale screening programs. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： image processing algorithms image quality assessment Medical image processing Medical imaging Retinal ganglion cells Retinal nerve fiber layer

来源：评论

学校读者我要写书评

暂无评论

High-speed collagen fiber modeling and orientation quantification for optical coherence tomography imaging

引用

OPTICS EXPRESS 2019年第10期27卷 14457-14471页

作者： McLean, James P. Gan, Yu Lye, Theresa H. Qu, Dovina Lu, Helen H. Hendon, Christine P. Columbia Univ Fu Fdn Sch Engn & Appl Sci Elect Engn 1300 West 120th St New York NY 10025 USA Columbia Univ Fu Fdn Sch Engn & Appl Sci Biomed Engn 1300 West 120th St New York NY 10025 USA

Quantifying collagen fiber architecture has clinical and scientific relevance across a variety of tissue types and adds functionality to otherwise largely qualitative imaging modalities. Optical coherence tomography (OCT) is uniquely suited for this task due to its ability to capture the collagen microstructure over larger fields of view than traditional microscopy. Existing image processing techniques for quantifying fiber architecture, while accurate and effective, are very slow for processing large datasets and tend to lack structural specificity. We describe here a computationally efficient method for quantifying and visualizing collagen fiber organization. The algorithm is demonstrated on swine atria, bovine anterior cruciate ligament, and human cervical tissue samples. Additionally, we show an improved performance for images with crimped fiber textures and low signal to noise when compared to similar methods. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： image processing image processing algorithms In vivo imaging Magnetic resonance imaging Nonlinear spatial filtering Speckle noise

来源：评论

学校读者我要写书评

暂无评论

Inclusion extraction from diamond clarity images based on the analysis of diamond optical properties

引用

OPTICS EXPRESS 2019年第19期27卷 27242-27255页

作者： Wang, Wenjing Cai, Lilong Hong Kong Univ Sci & Technol Dept Mech Engn Kowloon Clear Water Bay Hong Kong Peoples R China

Diamond clarity refers to the absence of tiny, natural inclusions (imperfections) inside a diamond or on its surface. Almost all diamonds contain their own unique inclusions due to their natural formation process. In this paper, a new inclusion extraction approach is developed to accurately separate the regions of interest in a diamond clarity image and then identify the image features of each region. The inclusion regions can be successfully distinguished from other types of signals. The findings of the theoretical optical analysis facilitate the image processing development and also reduce its complexity and operation time. The experimental results verify the effectiveness and robustness of the proposed inclusion extraction approach. The diamond inclusions can be accurately extracted from the captured diamond clarity image. The extracted inclusions can also be converted to their actual size as seen by the naked human eye. The proposed approach is verified to be significantly less sensitive to noise than existing approaches and unaffected by the fluctuations in illumination. (C) 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

关键词： CCD cameras Edge detection Fresnel reflection image processing image processing algorithms image quality

来源：评论

学校读者我要写书评

暂无评论

Broadband field-of-view expansion using a pair of digital micromirror devices

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS image SCIENCE AND VISION 2019年第10期36卷 1631-1641页

作者： Dahan, Daniel Yaacobi, Ami Aharonovich, Gil Pinsky, Ephraim Zalevsky, Zeev Bar Ilan Univ Fac Engn IL-5290002 Ramat Gan Israel RAFAEL Electro Opt Dept POB 225039 IL-3102102 Haifa Israel

Broadband field-of-view expansion using computational optics methods is presented. A pair of chirp gratings, implemented by digital micromirror devices, is placed on the optical entrance pupil plane of an optical system. The gratings perform achromatic translations of the image across the camera, and a wide image is reconstructed by a post-processing procedure. Optical design for such a system is proposed, and physical analysis shows the considerations of using these optical elements. All methods are established by simulations and experiments. (C) 2019 Optical Society of America

关键词： Diffraction gratings Digital micromirror devices image processing algorithms Optical design Optical elements Optical systems

来源：评论

学校读者我要写书评

暂无评论

Improved autofocus method for human red blood cell images

引用

APPLIED OPTICS 2019年第29期58卷 8031-8038页

作者： Zhong, Bowen Zhang, Yuxuan Hu, Junjie Jin, Ziqi Wang, Zhenhua Sun, Lining Soochow Univ Coll Mech & Elect Engn Suzhou 215000 Peoples R China

This paper presents an improved autofocus method for human red blood cell images in a microscope. The products of the sum modulus difference and the real-valued fast Fourier transform function are multiplied to obtain an improved sharpness evaluation using the properties of a Gaussian function. It is superior to traditional evaluations in terms of unimodality, steepness, and sensitivity. A new quantitative criterion is proposed to represent the ability of sharpness evaluation against noise. An adaptive focus window with great robustness is proposed that can reduce the computation cost and adverse effects of the background. The better performances of the proposed algorithms are all proved by experiment results, and they can help to find the quasi-focus position more quickly and accurately. (C) 2019 Optical Society of America

关键词： Bandpass filters CMOS cameras Fast Fourier transforms image metrics image processing algorithms Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Depth imaging denoising of photon-counting lidar

引用

APPLIED OPTICS 2019年第16期58卷 4390-4394页

作者： Huang, Pengwei He, Weiji Gu, Guohua Chen, Qian Nanjing Univ Sci & Technol Nanjing 210094 Jiangsu Peoples R China

Photon-counting lidar systems have difficulty reconstructing target depth images due to ambient noise. In this paper, we propose a novel way of using correlative photons and spatial correlations to reduce the false alarm probability. Experimental results show that the root mean square error of the depth image reconstructed by the proposed algorithm can be 1.68 times and 1.11 times better than that of the fast depth imaging denoising algorithm and log-matched filter estimation. The experimental results show that the proposed algorithm can effectively improve the reconstructed image of photon-counting lidar. (c) 2019 Optical Society of America

关键词： Avalanche photodiodes Geiger modes image processing algorithms image reconstruction Photon correlations Photon counting

来源：评论

学校读者我要写书评

暂无评论

Combined multiphoton fluorescence microscopy and photoacoustic imaging for stratigraphic analysis of paintings

引用

OPTICS LETTERS 2019年第5期44卷 1154-1157页

作者： Tserevelakis, George J. Tsafas, Vassilis Melessanaki, Kristalia Zacharakis, Giannis Filippidis, George Fdn Res & Technol Hellas Inst Elect Struct & Laser N Plastira 100 Iraklion Crete Greece Univ Crete Dept Phys Iraklion Crete Greece

We demonstrate the effective combination of multiphoton and photoacoustic (PA) imaging for the high-resolution stratigraphic analysis of multilayered art objects with emphasis on paintings. A novel convolution-based algorithm is additionally applied for the precise discrimination of nonlinear signals, providing valuable information in regard to the thickness and composition of successive varnish and paint layers in the mock-up samples. On the other hand, PA contrast complements the extracted data by revealing well-hidden graphite underdrawings below the paint at high sensitivity levels. The final composite images are directly compared with cross-sectional brightfield observations, validating the capabilities of the bimodal diagnosis in terms of measurement accuracy and contrast specificity. The presented hybrid diagnostic approach has the potential to optimize delicate interventions in works of art such as the selective removal of aged materials, thus promoting a significantly improved restoration outcome. (c) 2019 Optical Society of America

关键词： Absorption coefficient Attenuation coefficient image processing algorithms Imaging techniques Medical imaging Optical coherence tomography

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：