Article
Biology
Guy M. Hagen, Justin Bendesky, Rosa Machado, Tram-Anh Nguyen, Tanmay Kumar, Jonathan Ventura
Summary: Fluorescence microscopy is important in biological research, but photobleaching and phototoxicity are limiting factors. Machine learning methods can improve signal-to-noise ratio and reduce phototoxicity. High-quality data is essential for training deep learning methods.
Article
Engineering, Electrical & Electronic
Alireza Esmaeilzehi, M. Omair Ahmad, M. N. S. Swamy
Summary: This paper proposes a new multi-domain residual block for image super resolution that combines spatial and spectral features to enhance the performance of light-weight super resolution networks.
IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
(2021)
Article
Optics
S. Crombez, P. Leclerc, C. Ray, N. Ducros
Summary: We present a computational light-sheet microscope that enables hyperspectral acquisition at high spectral resolution. By focusing the emitted fluorescence light onto the entrance slit of an imaging spectrometer using a cylindrical lens, and illuminating the specimen with a sequence of structured light patterns to capture the spatial dimension orthogonal to the slit, we demonstrate the feasibility of this method and report the initial results in vivo using hydra specimens labeled with two fluorophores.
Article
Nanoscience & Nanotechnology
Yuan Luo, Ming Lun Tseng, Sunil Vyas, Ting-Yu Hsieh, Jui-Ching Wu, Shang-Yang Chen, Hsiao-Fang Peng, Vin-Cent Su, Tzu-Ting Huang, Hsin Yu Kuo, Cheng Hung Chu, Mu Ku Chen, Jia-Wern Chen, Yu-Chun Chen, Kuang-Yuh Huang, Chieh-Hsiung Kuan, Xu Shi, Hiroaki Misawa, Din Ping Tsai
Summary: Light-sheet fluorescent microscopy (LSFM) is the leading technique for in vivo imaging in the fields of disease, medicine, and cell biology research. This study demonstrates the successful integration of a nanophotonic meta-lens as the illumination component for LSFM, addressing the challenges of high image resolution and optical sectioning. With the meta-lens, the LSFM system complexity is significantly reduced, enabling multicolor fluorescent imaging of live biological specimens with cellular resolution.
Article
Optics
N. R. Subedi, S. Yaraghi, P. S. Jung, G. Kukal, A. G. McDonald, D. N. Christodoulides, A. E. Vasdekis
Summary: Research shows that digitally scanned Airy beams can improve the throughput rates in Raman imaging by an order of magnitude compared to traditional diffraction-limited beams, achieving high contrast and 1 micron axial resolution for three-dimensional imaging of microparticles. This method also achieves orders of magnitude lower irradiation density than coherent Raman imaging schemes, with faster speed and lower phototoxicity.
Article
Optics
Anne Stockhausen, Juan Eduardo Rodriguez-Gatica, Jens Schweihoff, Martin Karl Schwarz, Ulrich Kubitscheck
Summary: Common light sheet microscopy has limitations in balancing light sheet width and usable field of view, which can be overcome by using low-diverging Airy beams. However, Airy beams have side lobes that degrade image contrast. In this study, we constructed an Airy beam light sheet microscope and developed a deep learning image deconvolution method to remove side lobe effects. The combination of Airy beam light sheet microscopy and deep learning deconvolution allows for rapid and high-quality imaging of large volumes.
Article
Telecommunications
Fang Jiang, Da-Wei Chang, Song Ma, Yan-Jun Hu, Yao-Hua Xu
Summary: Sparse code multiple access (SCMA) is a technology proposed for large-scale intelligent terminal devices with high spectrum utilization. In this study, we design a new end-to-end autoencoder combining convolutional neural networks (CNNs) and residual networks to improve the accuracy and computational complexity of SCMA for the internet of things (IoT) scenario. Our scheme, with a residual network utilizing multitask learning and CNN units for SCMA codeword mapping, outperforms existing autoencoder schemes in terms of bit error rate (BER) and computational complexity according to simulations.
IEEE COMMUNICATIONS LETTERS
(2023)
Article
Computer Science, Information Systems
Lucas D. Lo Vercio, Rebecca M. Green, Samuel Robertson, Sienna Guo, Andreas Dauter, Marta Marchini, Marta Vidal-Garcia, Xiang Zhao, Anandita Mahika, Ralph S. Marcucio, Benedikt Hallgrimsson, Nils D. Forkert
Summary: Various genetic mutations affecting cell proliferation during organism development have been found to cause structural birth defects. This study developed and evaluated automatic methods based on convolutional neural networks (CNNs) for accurate segmentation of tissue and cells in mouse embryos using Light-Sheet Microscopy (LSM) imaging. The proposed methods achieved high accuracy and consistency compared to manual segmentations, providing a useful tool for LSM image analysis.
Article
Computer Science, Information Systems
Yukti Aparna, Yukti Bhatia, Rachna Rai, Varun Gupta, Naveen Aggarwal, Aparna Akula
Summary: Potholes on roads are a major cause of accidents and vehicle wear and tear. Current pothole detection techniques have drawbacks, so this study aims to analyze the feasibility and accuracy of thermal imaging for pothole detection. Deep learning using convolutional neural networks approach is adopted, and a comparison between self-built and pre-trained models is conducted. The results show that thermal imaging achieved a highest accuracy of 97.08% with one of the pre-trained models. This study is important for guiding future research in the field of pothole detection.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Biochemical Research Methods
Kevin M. Dean, Tonmoy Chakraborty, Stephan Daetwyler, Jinlong Lin, Gerard Garrelts, Ons M'Saad, Hannahmariam T. Mekbib, Fabian F. Voigt, Martina Schaettin, Esther T. Stoeckli, Fritjof Helmchen, Joerg Bewersdorf, Reto Fiolka
Summary: The protocol provides detailed instructions for assembling and operating a versatile variant of light-sheet fluorescence microscopy called axially swept light-sheet microscopy (ASLM), which offers an unparalleled combination of field of view, optical resolution, and optical sectioning. It includes information on the working principle, applications, practical tips, part lists, schematics, and software for instrument control of ASLM.
Article
Computer Science, Artificial Intelligence
Abduljalil Radman, Amer Sallam, Shahrel Azmin Suandi
Summary: This paper proposes a unified face sketch synthesis model considering ethnicity issues and photo variations. A new DResNet model is designed using deep learning and deep residual blocks to learn a regression model for face sketch synthesis. Through training on a heterogeneous database, the proposed method shows superior performance and can be generalized to real-world applications.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Biochemical Research Methods
Petra Paie, Gianmaria Calisesi, Alessia Candeo, Andrea Comi, Federico Sala, Francesco Ceccarelli, Ada De Luigi, Pietro Veglianese, Korbinian Muhlberger, Michael Fokine, Gianluca Valentini, Roberto Osellame, Mark Neil, Andrea Bassi, Francesca Bragheri
Summary: Heterogeneity investigation at the single-cell level is crucial in clinical research. The combination of light sheet fluorescence microscopy and structured illumination microscopy in an optofluidic platform enables high throughput super-resolution imaging, allowing comprehensive evaluation of cellular heterogeneity at high resolution.
Article
Chemistry, Analytical
Changjie Cai, Tomoki Nishimura, Jooyeon Hwang, Xiao-Ming Hu, Akio Kuroda
Summary: This study aimed to accurately detect asbestos using the YOLOv4 model, achieving exceptional performance with a mean average precision of 96.1% +/- 0.4%. Compared to previous software, YOLOv4 demonstrated higher accuracy, precision, recall, and F-1 score, particularly excelling in detecting low fiber concentration samples.
Article
Optics
Yanhong Gan, Zitong Ye, Yubing Han, Ye Ma, Chuankang Li, Qiulan Liu, Wenjie Liu, Cuifang Kuang, Xu Liu
Summary: Light sheet fluorescence microscopy (LSFM) is a promising tool for biological research due to its ability to observe living cells dynamically. However, obtaining optimal image quality in LSFM requires precise alignment between the light sheet and detection focal plane. In this study, we propose a fast and accurate autofocusing method based on deep learning to overcome the challenge of unstable focusing in LSFM with a single shot. Our method is compatible with any light sheet imaging setup using a spatial light modulator. It achieves a predicted root-mean-square error of 0.0942 μm within a range of ± 0.7 μm in a light sheet microscope with a 1.1 numerical aperture detection objective. The neural network architecture we propose has the advantages of small memory size, few training data requirements, and good generalization to untrained sample types.
OPTICS AND LASERS IN ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Darren Wei Wen Low, Akshay Chaudhari, Dharmesh Kumar, A. Senthil Kumar
Summary: This paper presents the use of Convolutional Neural Networks-Forming Prediction (CNN-FP) in predicting geometric errors in die-less single point incremental forming (SPIF). The CNN-FP model was trained to quantify local geometries and achieved good performance in most validation tests. However, limitations in the training samples resulted in degraded performance in some instances.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Optics
Runze Li, Tong Peng, Meiling Zhou, Xianghua Yu, Junwei Min, Yanlong Yang, Baoli Yao
Article
Physics, Applied
Dan Dan, Peng Gao, Tianyu Zhao, Shipei Dang, Jia Qian, Ming Lei, Junwei Min, Xianghua Yu, Baoli Yao
Summary: The study developed an integrated SIM with both super-resolution (SR) and optical sectioning (OS) capabilities, utilizing a new image reconstruction algorithm to combine the advantages of SR and OS. The validity of the integrated SIM was confirmed through experimental and simulation methods, with the potential to assist biologists in obtaining clearer SR images of thick specimens.
JOURNAL OF PHYSICS D-APPLIED PHYSICS
(2021)
Article
Optics
Chao Liu, Chen Bai, Xianghua Yu, Shaohui Yan, Yuan Zhou, Xing Li, Junwei Min, Yanlong Yang, Dan Dan, Baoli Yao
Summary: The study proposes a method to generate a large field of view light-sheet by scanning multiple focus-shifted Gaussian beam arrays while maintaining high axial resolution. The complementary beam subtraction method is adopted to further improve axial resolution. Numerical simulations and experiments verify the effectiveness of the method.
Article
Engineering, Electrical & Electronic
Dan Dan, Zhaojun Wang, Xing Zhou, Ming Lei, Tianyu Zhao, Jia Qian, Xianghua Yu, Shaohui Yan, Junwei Min, Piero Bianco, Baoli Yao
Summary: The new method SDR for SIM image reconstruction is faster than the traditional FDR, making it suitable for real-time and dynamic imaging applications, enhancing SIM as the desired method for live-cell, instant super-resolution imaging.
IEEE PHOTONICS JOURNAL
(2021)
Article
Optics
Chao Liu, Xianghua Yu, Chen Bai, Xing Li, Yuan Zhou, Shaohui Yan, Junwei Min, Dan Dan, Runze Li, Shuangyu Gu, Baoli Yao
Summary: Airy beam light-sheet illumination can extend the field of view of light-sheet fluorescence microscopy, but may lead to poor axial resolution and low image contrast due to undesirable out-of-focus background. The Airy complementary beam subtraction method improves axial resolution by scanning an optimized designed complementary beam while maintaining the extended field of view, resulting in better imaging quality.
Article
Engineering, Electrical & Electronic
Tong Peng, Runze Li, Junwei Min, Dan Dan, Meiling Zhou, Xianghua Yu, Chunmin Zhang, Chen Bai, Baoli Yao
Summary: This article investigates a compressive sensing (CS) method for identifying the transmission matrix (TM) of a scatter in an imaging system. By calibrating the TM, the phase information of the object can be quantitatively obtained. This method, featuring noninterference measurements of the TM and exploiting a large field of view, can be used in phase imaging applications.
IEEE PHOTONICS JOURNAL
(2022)
Article
Optics
Chen Bai, Tong Peng, Junwei Min, Runze Li, Yuan Zhou, Baoli Yao
Summary: Dual-wavelength in-line digital holography (DIDH) is a popular method for high-accuracy phase imaging of objects, facing challenges in suppressing amplified noise and twin-image. A new DIDH network (DIDH-Net) is proposed in this paper to effectively address these challenges.
PHOTONICS RESEARCH
(2021)
Article
Engineering, Electrical & Electronic
Meiling Zhou, Chen Bai, Yang Zhang, Runze Li, Tong Peng, Jia Qian, Dan Dan, Junwei Min, Yuan Zhou, Baoli Yao
Summary: In this study, a deep-learning method based on the improved optical scheme is proposed to accelerate the data acquisition and image reconstruction speed of the shower-curtain effect and ptychography (PSE) for large field-of-view object reconstruction behind scattering media. By replacing the mechanical translation stage with a digital micromirror device (DMD), a large amount of training data can be collected, and single-shot pattern and sub-second reconstruction can be achieved. Qualitative and quantitative analysis on binary resolution target and 2D biological slide specimens demonstrate the effectiveness and feasibility of the proposed method, showing promising applications in tissue imaging.
IEEE PHOTONICS TECHNOLOGY LETTERS
(2022)
Article
Optics
Jinwei Song, Junwei Min, Xun Yuan, Yuge Xue, Chen Bai, Baoli Yao
Summary: A method for quantitatively measuring the refractive index and topography of transparent samples is proposed. The method utilizes quadriwave lateral shearing interferometry to obtain quantitative phase images at different wavelengths, and uses Cauchy's dispersion formula to independently calculate the refractive indexes and physical thickness distribution of the sample. No highly dispersive medium or manual operation is required. The measured refractive indexes can identify the composition of the sample in addition to its topography. Simulation and experimental results have confirmed the effectiveness and feasibility of the proposed method.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Optics
Zhou Yuan, Li Runze, Yu Xianghua, Yan Shaohui, Li Xing, Gao Wenyu, Liu Chao, Peng Tong, Yang Yanlong, Min Junwei, Wang Ping, Qu Jun, Yao Boli
Summary: The paper introduces the operating principles of liquid crystal spatial light modulators in spatial optical field modulation technology, discusses some applications and development prospects, and provides references for researchers in this field.
ACTA PHOTONICA SINICA
(2021)
Article
Optics
Zhang Meiling, Gao Peng, Wen Kai, Zhuo Kequn, Wang Yang, Liu Lixin, Min Junwei, Yao Baoli
Summary: Phase-shifting Digital Holography (PSDH) combines phase-shifting technology with digital holography to provide a fast and high-precision approach for imaging the three-dimensional morphology or refractive index distribution of microscopic objects. Parallel phase-shifting technique enhances imaging speed by simultaneously obtaining multiple phase-shifting holograms.
ACTA PHOTONICA SINICA
(2021)
