Journal articles on the topic 'Super-resolved image reconstruction'
To see the other types of publications on this topic, follow the link: Super-resolved image reconstruction.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 43 journal articles for your research on the topic 'Super-resolved image reconstruction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sahithi, V. S., and S. Agrawal. "Sub pixel location identification using super resolved multilooking CHRIS data." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-8 (November 28, 2014): 463–68. http://dx.doi.org/10.5194/isprsarchives-xl-8-463-2014.
Full textAbstract:
CHRIS /Proba is a multiviewing hyperspectral sensor that monitors the earth in five different zenith angles +55°, +36°, nadir, −36° and −55° with a spatial resolution of 17 m and within a spectral range of 400–1050 nm in mode 3. These multiviewing images are suitable for constructing a super resolved high resolution image that can reveal the mixed pixel of the hyperspectral image. In the present work, an attempt is made to find the location of various features constituted within the 17m mixed pixel of the CHRIS image using various super resolution reconstruction techniques. Four different super resolution reconstruction techniques namely interpolation, iterative back projection, projection on to convex sets (POCS) and robust super resolution were tried on the −36, nadir and +36 images to construct a super resolved high resolution 5.6 m image. The results of super resolution reconstruction were compared with the scaled nadir image and bicubic convoluted image for comparision of the spatial and spectral property preservance. A support vector machine classification of the best super resolved high resolution image was performed to analyse the location of the sub pixel features. Validation of the obtained results was performed using the spectral unmixing fraction images and the 5.6 m classified LISS IV image.
2
Pashaei, Mohammad, Michael J. Starek, Hamid Kamangir, and Jacob Berryhill. "Deep Learning-Based Single Image Super-Resolution: An Investigation for Dense Scene Reconstruction with UAS Photogrammetry." Remote Sensing 12, no. 11 (May 29, 2020): 1757. http://dx.doi.org/10.3390/rs12111757.
Full textAbstract:
The deep convolutional neural network (DCNN) has recently been applied to the highly challenging and ill-posed problem of single image super-resolution (SISR), which aims to predict high-resolution (HR) images from their corresponding low-resolution (LR) images. In many remote sensing (RS) applications, spatial resolution of the aerial or satellite imagery has a great impact on the accuracy and reliability of information extracted from the images. In this study, the potential of a DCNN-based SISR model, called enhanced super-resolution generative adversarial network (ESRGAN), to predict the spatial information degraded or lost in a hyper-spatial resolution unmanned aircraft system (UAS) RGB image set is investigated. ESRGAN model is trained over a limited number of original HR (50 out of 450 total images) and virtually-generated LR UAS images by downsampling the original HR images using a bicubic kernel with a factor × 4 . Quantitative and qualitative assessments of super-resolved images using standard image quality measures (IQMs) confirm that the DCNN-based SISR approach can be successfully applied on LR UAS imagery for spatial resolution enhancement. The performance of DCNN-based SISR approach for the UAS image set closely approximates performances reported on standard SISR image sets with mean peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index values of around 28 dB and 0.85 dB, respectively. Furthermore, by exploiting the rigorous Structure-from-Motion (SfM) photogrammetry procedure, an accurate task-based IQM for evaluating the quality of the super-resolved images is carried out. Results verify that the interior and exterior imaging geometry, which are extremely important for extracting highly accurate spatial information from UAS imagery in photogrammetric applications, can be accurately retrieved from a super-resolved image set. The number of corresponding keypoints and dense points generated from the SfM photogrammetry process are about 6 and 17 times more than those extracted from the corresponding LR image set, respectively.
3
Xiang, Peng-Cheng, Cong-Bo Cai, Jie-Chao Wang, Shu-Hui Cai, and Zhong Chen. "Super-resolved reconstruction method for spatiotemporally encoded magnetic resonance imaging based on deep neural network." Acta Physica Sinica 71, no. 5 (2022): 058702. http://dx.doi.org/10.7498/aps.71.20211754.
Full textAbstract:
Single-shot spatiotemporally-encoded magnetic resonance imaging (SPEN MRI) is a novel ultrafast MRI technology. The SPEN MRI possesses great resistance to inhomogeneous <i>B</i><sub>0</sub> magnetic field and chemical shift effect. However, it has inherently low spatial resolution, and the super-resolved reconstruction is required to improve the spatial resolution of SPEN MRI image without additional signal acquisition. Several super-resolved reconstruction methods have been proposed, but they all suffer the problems of long iterative solution time and/or aliasing artifacts residue in the reconstructed results. In this paper, a super-resolved reconstruction method is proposed for single-shot SPEN MRI based on deep neural network. In this method the simulation samples are used to train the deep neural network, and then the trained network model is adopted to reconstruct the real sampled signals. Experimental results of numerical simulation, water phantom and in vivo rat brain show that this method can quickly reconstruct a super-resolved SPEN image with no residual aliasing artifacts, and clear texture information. An appropriate number of training samples and an appropriate random noise level for training samples contribute to improving the reconstruction results.
4
Wang, Bowen. "Infrared fiber bundle image super-resolved based on computational imaging." Journal of Physics: Conference Series 2478, no. 6 (June 1, 2023): 062009. http://dx.doi.org/10.1088/1742-6596/2478/6/062009.
Full textAbstract:
Abstract As the representative of flexibility in optical imaging media, in recent years, fiber bundles have emerged as a promising architecture in the development of compact visual systems. Dedicated to tackling the problems of universal honeycomb artifacts and low signal-to-noise ratio (SNR) imaging in fiber bundles, the iterative super-resolution reconstruction network based on a physical model is proposed. Under the constraint of solving the two subproblems of data fidelity and prior regular term alternately, the network can efficiently “regenerate” the lost spatial resolution with deep learning. By building and calibrating a dual-path imaging system, the real-world dataset where paired low resolution (LR) - high resolution (HR) images on the same scene can be obtained simultaneously. Numerical results on both USAF target and complex target objects demonstrate that the algorithm can restore high contrast images without pixilated noise. On the basis of super-resolution reconstruction, compound eye image composition based on fiber bundle is also realized in this paper for the actual imaging requirements. The proposed work is the first to apply a physical model-based network structure to fiber bundle imaging in the long-wave infrared band, effectively promoting the engineering application of thermal radiation detection.
5
Čapek, Martin, Michaela Blažíková, Ivan Novotný, Helena Chmelová, David Svoboda, Barbora Radochová, Jiří Janáček, and Ondrej Horváth. "The Wavelet-Based Denoising Of Images in Fiji, With Example Applications in Structured Illumination Microscopy." Image Analysis & Stereology 40, no. 1 (April 9, 2021): 3–16. http://dx.doi.org/10.5566/ias.2432.
Full textAbstract:
Filtration of super-resolved microscopic images brings often troubles with removing undesired image parts like, e.g., noise, inhomogenous background and reconstruction artifacts. Standard filtration techniques, e.g., convolution- or Fourier transform-based methods are not always appropriate, since they may lower image resolution that was acquired by hi-tech and expensive microscopy systems. Thus, in this article it is proposed to filter such images using discrete wavelet transform (DWT). Newly developed Wavelet_Denoise plugin for free available Fiji software package demonstrates important possibilities of applying DWT to images: Decomposition of a filtered picture using various wavelet filters and levels of details with showing decomposed images and visualization of effects of back transformation of the picture with chosen level of suppression or denoising of wavelet coefficients. The Fiji framework allows, for example, using a plethora of various microscopic image formats for data opening, users can easily install the plugin through a menu command and the plugin supports processing 3D images in Z-stacks. The application of the plugin for removal of reconstruction artifacts and undesirable background in images acquired by super-resolved structured illumination microscopy is demonstrated as well.
6
Ahn, Il Jun, Ji Hye Kim, YongJin Chang, Kye Young Jeong, and Jong Beom Ra. "LOR-Based Reconstruction for Super-Resolved 3D PET Image on GPU." IEEE Transactions on Nuclear Science 62, no. 3 (June 2015): 859–68. http://dx.doi.org/10.1109/tns.2015.2421908.
Full text
7
Yang, Xue, Feng Li, Lei Xin, Xiaotian Lu, Ming Lu, and Nan Zhang. "An Improved Mapping with Super-Resolved Multispectral Images for Geostationary Satellites." Remote Sensing 12, no. 3 (February 2, 2020): 466. http://dx.doi.org/10.3390/rs12030466.
Full textAbstract:
Super-resolution (SR) technology has shown great potential for improving the performance of the mapping and classification of multispectral satellite images. However, it is very challenging to solve ill-conditioned problems such as mapping for remote sensing images due to the presence of complicated ground features. In this paper, we address this problem by proposing a super-resolution reconstruction (SRR) mapping method called the mixed sparse representation non-convex high-order total variation (MSR-NCHOTV) method in order to accurately classify multispectral images and refine object classes. Firstly, MSR-NCHOTV is employed to reconstruct high-resolution images from low-resolution time-series images obtained from the Gaofen-4 (GF-4) geostationary orbit satellite. Secondly, a support vector machine (SVM) method was used to classify the results of SRR using the GF-4 geostationary orbit satellite images. Two sets of GF-4 satellite image data were used for experiments, and the MSR-NCHOTV SRR result obtained using these data was compared with the SRR results obtained using the bilinear interpolation (BI), projection onto convex sets (POCS), and iterative back projection (IBP) methods. The sharpness of the SRR results was evaluated using the gray-level variation between adjacent pixels, and the signal-to-noise ratio (SNR) of the SRR results was evaluated by using the measurement of high spatial resolution remote sensing images. For example, compared with the values obtained using the BI method, the average sharpness and SNR of the five bands obtained using the MSR-NCHOTV method were higher by 39.54% and 51.52%, respectively, and the overall accuracy (OA) and Kappa coefficient of the classification results obtained using the MSR-NCHOTV method were higher by 32.20% and 46.14%, respectively. These results showed that the MSR-NCHOTV method can effectively improve image clarity, enrich image texture details, enhance image quality, and improve image classification accuracy. Thus, the effectiveness and feasibility of using the proposed SRR method to improve the classification accuracy of remote sensing images was verified.
8
Han, Sujy, Tae Bok Lee, and Yong Seok Heo. "Deep Image Prior for Super Resolution of Noisy Image." Electronics 10, no. 16 (August 20, 2021): 2014. http://dx.doi.org/10.3390/electronics10162014.
Full textAbstract:
Single image super-resolution task aims to reconstruct a high-resolution image from a low-resolution image. Recently, it has been shown that by using deep image prior (DIP), a single neural network is sufficient to capture low-level image statistics using only a single image without data-driven training such that it can be used for various image restoration problems. However, super-resolution tasks are difficult to perform with DIP when the target image is noisy. The super-resolved image becomes noisy because the reconstruction loss of DIP does not consider the noise in the target image. Furthermore, when the target image contains noise, the optimization process of DIP becomes unstable and sensitive to noise. In this paper, we propose a noise-robust and stable framework based on DIP. To this end, we propose a noise-estimation method using the generative adversarial network (GAN) and self-supervision loss (SSL). We show that a generator of DIP can learn the distribution of noise in the target image with the proposed framework. Moreover, we argue that the optimization process of DIP is stabilized when the proposed self-supervision loss is incorporated. The experiments show that the proposed method quantitatively and qualitatively outperforms existing single image super-resolution methods for noisy images.
9
Eadie, Matthew, Jinpeng Liao, Wael Ageeli, Ghulam Nabi, and Nikola Krstajić. "Fiber Bundle Image Reconstruction Using Convolutional Neural Networks and Bundle Rotation in Endomicroscopy." Sensors 23, no. 5 (February 23, 2023): 2469. http://dx.doi.org/10.3390/s23052469.
Full textAbstract:
Fiber-bundle endomicroscopy has several recognized drawbacks, the most prominent being the honeycomb effect. We developed a multi-frame super-resolution algorithm exploiting bundle rotation to extract features and reconstruct underlying tissue. Simulated data was used with rotated fiber-bundle masks to create multi-frame stacks to train the model. Super-resolved images are numerically analyzed, which demonstrates that the algorithm can restore images with high quality. The mean structural similarity index measurement (SSIM) improved by a factor of 1.97 compared with linear interpolation. The model was trained using images taken from a single prostate slide, 1343 images were used for training, 336 for validation, and 420 for testing. The model had no prior information about the test images, adding to the robustness of the system. Image reconstruction was completed in 0.03 s for 256 × 256 images indicating future real-time performance is within reach. The combination of fiber bundle rotation and multi-frame image enhancement through machine learning has not been utilized before in an experimental setting nut could provide a much-needed improvement to image resolution in practice.
10
Liu, Shanshan, Qingbin Huang, and Minghui Wang. "Multi-Frame Blind Super-Resolution Based on Joint Motion Estimation and Blur Kernel Estimation." Applied Sciences 12, no. 20 (October 20, 2022): 10606. http://dx.doi.org/10.3390/app122010606.
Full textAbstract:
Multi-frame super-resolution makes up for the deficiency of sensor hardware and significantly improves image resolution by using the information of inter-frame and intra-frame images. Inaccurate blur kernel estimation will enlarge the distortion of the estimated high-resolution image. Therefore, multi-frame blind super resolution with unknown blur kernel is more challenging. For the purpose of reducing the impact of inaccurate motion estimation and blur kernel estimation on the super-resolved image, we propose a novel method combining motion estimation, blur kernel estimation and super resolution. The confidence weight of low-resolution images and the parameter value of the motion model obtained in image reconstruction are added to the modified motion estimation and blur kernel estimation. At the same time, Jacobian matrix, which can better describe the motion change, is introduced to further correct the error of motion estimation. Based on the results acquired from the experiments on synthetic data and real data, the superiority of the proposed method over others is obvious. The reconstructed high-resolution image retains the details of the image effectively, and the artifacts are greatly reduced.
11
Irfan, Muhammad, Sahib Khan, Arslan Arif, Khalil Khan, Aleem Khaliq, Zain Memon, and Muhammad Ismail. "Single Image Super Resolution Technique: An Extension to True Color Images." Symmetry 11, no. 4 (April 2, 2019): 464. http://dx.doi.org/10.3390/sym11040464.
Full textAbstract:
The super-resolution (SR) technique reconstructs a high-resolution image from single or multiple low-resolution images. SR has gained much attention over the past decade, as it has significant applications in our daily life. This paper provides a new technique of a single image super-resolution on true colored images. The key idea is to obtain the super-resolved image from observed low-resolution images. A proposed technique is based on both the wavelet and spatial domain-based algorithms by exploiting the advantages of both of the algorithms. A back projection with an iterative method is implemented to minimize the reconstruction error and for noise removal wavelet-based de-noising method is used. Previously, this technique has been followed for the grayscale images. In this proposed algorithm, the colored images are taken into account for super-resolution. The results of the proposed method have been examined both subjectively by observation of the results visually and objectively by considering the peak signal-to-noise ratio (PSNR) and mean squared error (MSE), which gives significant results and visually better in quality from the bi-cubic interpolation technique.
12
Huang, Jianpan, Lin Chen, Kannie W. Y. Chan, Congbo Cai, Shuhui Cai, and Zhong Chen. "Super-resolved water/fat image reconstruction based on single-shot spatiotemporally encoded MRI." Journal of Magnetic Resonance 314 (May 2020): 106736. http://dx.doi.org/10.1016/j.jmr.2020.106736.
Full text
13
Gong, Hai, Wenjun Guo, and Mark A. A. Neil. "GPU-accelerated real-time reconstruction in Python of three-dimensional datasets from structured illumination microscopy with hexagonal patterns." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 379, no. 2199 (April 26, 2021): 20200162. http://dx.doi.org/10.1098/rsta.2020.0162.
Full textAbstract:
We present a structured illumination microscopy system that projects a hexagonal pattern by the interference among three coherent beams, suitable for implementation in a light-sheet geometry. Seven images acquired as the illumination pattern is shifted laterally can be processed to produce a super-resolved image that surpasses the diffraction-limited resolution by a factor of over 2 in an exemplar light-sheet arrangement. Three methods of processing data are discussed depending on whether the raw images are available in groups of seven, individually in a stream or as a larger batch representing a three-dimensional stack. We show that imaging axially moving samples can introduce artefacts, visible as fine structures in the processed images. However, these artefacts are easily removed by a filtering operation carried out as part of the batch processing algorithm for three-dimensional stacks. The reconstruction algorithms implemented in Python include specific optimizations for calculation on a graphics processing unit and we demonstrate its operation on experimental data of static objects and on simulated data of moving objects. We show that the software can process over 239 input raw frames per second at 512 × 512 pixels, generating over 34 super-resolved frames per second at 1024 × 1024 pixels. This article is part of the Theo Murphy meeting issue ‘Super-resolution structured illumination microscopy (part 1)’.
14
Wazawa, Tetsuichi, Yoshiyuki Arai, Yoshinobu Kawahara, Hiroki Takauchi, Takashi Washio, and Takeharu Nagai. "Highly biocompatible super-resolution fluorescence imaging using the fast photoswitching fluorescent protein Kohinoor and SPoD-ExPAN with L p-regularized image reconstruction." Microscopy 67, no. 2 (February 2, 2018): 89–98. http://dx.doi.org/10.1093/jmicro/dfy004.
Full textAbstract:
Abstract Far-field super-resolution fluorescence microscopy has enabled us to visualize live cells in great detail and with an unprecedented resolution. However, the techniques developed thus far have required high-power illumination (102–106 W/cm2), which leads to considerable phototoxicity to live cells and hampers time-lapse observation of the cells. In this study we show a highly biocompatible super-resolution microscopy technique that requires a very low-power illumination. The present technique combines a fast photoswitchable fluorescent protein, Kohinoor, with SPoD-ExPAN (super-resolution by polarization demodulation/excitation polarization angle narrowing). With this technique, we successfully observed Kohinoor-fusion proteins involving vimentin, paxillin, histone and clathrin expressed in HeLa cells at a spatial resolution of 70–80 nm with illumination power densities as low as ~1 W/cm2 for both excitation and photoswitching. Furthermore, although the previous SPoD-ExPAN technique used L1-regularized maximum-likelihood calculations to reconstruct super-resolved images, we devised an extension to the Lp-regularization to obtain super-resolved images that more accurately describe objects at the specimen plane. Thus, the present technique would significantly extend the applicability of super-resolution fluorescence microscopy for live-cell imaging.
15
Wang, Bowen, Yan Zou, Linfei Zhang, Yan Hu, Hao Yan, Chao Zuo, and Qian Chen. "Low-Light-Level Image Super-Resolution Reconstruction Based on a Multi-Scale Features Extraction Network." Photonics 8, no. 8 (August 10, 2021): 321. http://dx.doi.org/10.3390/photonics8080321.
Full textAbstract:
Wide field-of-view (FOV) and high-resolution (HR) imaging are essential to many applications where high-content image acquisition is necessary. However, due to the insufficient spatial sampling of the image detector and the trade-off between pixel size and photosensitivity, the ability of current imaging sensors to obtain high spatial resolution is limited, especially under low-light-level (LLL) imaging conditions. To solve these problems, we propose a multi-scale feature extraction (MSFE) network to realize pixel-super-resolved LLL imaging. In order to perform data fusion and information extraction for low resolution (LR) images, the network extracts high-frequency detail information from different dimensions by combining the channel attention mechanism module and skip connection module. In this way, the calculation of the high-frequency components can receive greater attention. Compared with other networks, the peak signal-to-noise ratio of the reconstructed image was increased by 1.67 dB. Extensions of the MSFE network are investigated for scene-based color mapping of the gray image. Most of the color information could be recovered, and the similarity with the real image reached 0.728. The qualitative and quantitative experimental results show that the proposed method achieved superior performance in image fidelity and detail enhancement over the state-of-the-art.
16
Pilger, Christian, Jakub Pospíšil, Marcel Müller, Martin Ruoff, Martin Schütte, Heinrich Spiecker, and Thomas Huser. "Super-resolution fluorescence microscopy by line-scanning with an unmodified two-photon microscope." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 379, no. 2199 (April 26, 2021): 20200300. http://dx.doi.org/10.1098/rsta.2020.0300.
Full textAbstract:
Fluorescence-based microscopy as one of the standard tools in biomedical research benefits more and more from super-resolution methods, which offer enhanced spatial resolution allowing insights into new biological processes. A typical drawback of using these methods is the need for new, complex optical set-ups. This becomes even more significant when using two-photon fluorescence excitation, which offers deep tissue imaging and excellent z-sectioning. We show that the generation of striped-illumination patterns in two-photon laser scanning microscopy can readily be exploited for achieving optical super-resolution and contrast enhancement using open-source image reconstruction software. The special appeal of this approach is that even in the case of a commercial two-photon laser scanning microscope no optomechanical modifications are required to achieve this modality. Modifying the scanning software with a custom-written macro to address the scanning mirrors in combination with rapid intensity switching by an electro-optic modulator is sufficient to accomplish the acquisition of two-photon striped-illumination patterns on an sCMOS camera. We demonstrate and analyse the resulting resolution improvement by applying different recently published image resolution evaluation procedures to the reconstructed filtered widefield and super-resolved images. This article is part of the Theo Murphy meeting issue ‘Super-resolution structured illumination microscopy (part 1)'.
17
Feng, Liang, Xiaolei Wang, Xinlei Sun, Sende Wang, Lie Lin, Olga Kosareva, and Weiwei Liu. "Efficient Multifocal Structured Illumination Microscopy Utilizing a Spatial Light Modulator." Applied Sciences 10, no. 12 (June 26, 2020): 4396. http://dx.doi.org/10.3390/app10124396.
Full textAbstract:
We demonstrated an efficient system for multifocal structured illumination microscopy (MSIM) utilizing a spatial light modulator (SLM). Nine phase profiles of chessboard phase plates loaded on the SLM in sequence are used to generate nine multifocal arrays on the focal plane. Subsequently, nine raw multifocal images are acquired. Finally, by extracting the parameters of the illumination patterns from the raw images precisely, a final super-resolved image is reconstructed by performing the standard reconstruction procedure of structured illumination microscopy (SIM). Our MSIM system realized nearly a 1.5-fold enhancement in spatial resolution compared with wide-field (WF) microscopy. The feasibility of the present system is validated on experiments and the results show its great performances along with good compatibility.
18
HEINZ, K., and H. WEDLER. "HOLOGRAPHIC INVERSION OF DIFFUSE ELECTRON DIFFRACTION INTENSITIES FOR THE Ni(001)/K STRUCTURE." Surface Review and Letters 01, no. 02n03 (August 1994): 319–34. http://dx.doi.org/10.1142/s0218625x94000321.
Full textAbstract:
At low temperatures many adsorbates arrange in lattice gas disorder on crystalline substrates. In a low energy electron diffraction (LEED) experiment this leads to diffuse intensities super-imposed on the sharp spots caused by the substrate. For the disordered adsorption system Ni(001)/K, we present two-dimensional intensity distributions as function of the electron energy and angle of incidence. They can be measured very fast (20 s per frame) and reliably using an automatic video based data acquisition technique. We show that diffuse intensity spectra DI(E) taken as function of energy for fixed surface parallel electron momentum transfer carry the information about the local adsorption structure. This is equivalent to conventional I(E) spectra taken for sharp spots. In the light of recent proposals it is shown that the diffuse single energy intensity pattern is not a hologram of the local structure because e.g. the reference wave is ill defined. However, the diffraction processes disturbing the pure reference wave cancel when the intensities of different energies are suitably averaged. It is demonstrated that the holographic reconstruction of real space information from such scanned energy data leads to reliable and well resolved atomic images. Full widths at half-maximum of such atomic images are not greater than 1 Å. Substrate atoms behind the reference atom in direction of the incident beam are imaged best. So, image reconstructions for different beam directions produce a full and high quality three-dimensional image of the local adsorption structure.
19
Nie, Xingyu, Kirk Huang, Joseph Deasy, Andreas Rimner, and Guang Li. "Enhanced super‐resolution reconstruction of T1w time‐resolved 4DMRI in low‐contrast tissue using 2‐step hybrid deformable image registration." Journal of Applied Clinical Medical Physics 21, no. 10 (September 22, 2020): 25–39. http://dx.doi.org/10.1002/acm2.12988.
Full text
20
Buongiorno Nardelli, Bruno, Davide Cavaliere, Elodie Charles, and Daniele Ciani. "Super-Resolving Ocean Dynamics from Space with Computer Vision Algorithms." Remote Sensing 14, no. 5 (February 26, 2022): 1159. http://dx.doi.org/10.3390/rs14051159.
Full textAbstract:
Surface ocean dynamics play a key role in the Earth system, contributing to regulate its climate and affecting the marine ecosystem functioning. Dynamical processes occur and interact in the upper ocean at multiple scales, down to, or even less than, few kilometres. These scales are not adequately resolved by present observing systems, and, in the last decades, global monitoring of surface currents has been based on the application of geostrophic balance to absolute dynamic topography maps obtained through the statistical interpolation of along-track satellite altimeter data. Due to the cross-track distance and repetitiveness of satellite acquisitions, the effective resolution of interpolated data is limited to several tens of kilometres. At the kilometre scale, sea surface temperature pattern evolution is dominated by advection, providing indirect information on upper ocean currents. Computer vision techniques are perfect candidates to infer this dynamical information from the combination of altimeter data, surface temperature images and observing-system geometry. Here, we exploit one class of image processing techniques, super-resolution, to develop an original neural-network architecture specifically designed to improve absolute dynamic topography reconstruction. Our model is first trained on synthetic observations built from a numerical general-circulation model and then tested on real satellite products. Provided concurrent clear-sky thermal observations are available, it proves able to compensate for altimeter sampling/interpolation limitations by learning from primitive equation data. The algorithm can be adapted to learn directly from future surface topography, and eventual surface currents, high-resolution satellite observations.
21
Velumani, Ramesh, Hariharasitaraman Sudalaimuthu, Gaurav Choudhary, Srinivasan Bama, Maranthiran Victor Jose, and Nicola Dragoni. "Secured Secret Sharing of QR Codes Based on Nonnegative Matrix Factorization and Regularized Super Resolution Convolutional Neural Network." Sensors 22, no. 8 (April 12, 2022): 2959. http://dx.doi.org/10.3390/s22082959.
Full textAbstract:
Advances in information technology have harnessed the application of Quick Response (QR) codes in day-to-day activities, simplifying information exchange. QR codes are witnessed almost everywhere, on consumables, newspapers, information bulletins, etc. The simplicity of QR code creation and ease of scanning with free software have tremendously influenced their wide usage, and since QR codes place information on an object they are a tool for the IoT. Many healthcare IoT applications are deployed with QR codes for data-labeling and quick transfer of clinical data for rapid diagnosis. However, these codes can be duplicated and tampered with easily, attributed to open- source QR code generators and scanners. This paper presents a novel (n,n) secret-sharing scheme based on Nonnegative Matrix Factorization (NMF) for secured transfer of QR codes as multiple shares and their reconstruction with a regularized Super Resolution Convolutional Neural Network (SRCNN). This scheme is an alternative to the existing polynomial and visual cryptography-based schemes, exploiting NMF in part-based data representation and structural regularized SRCNN to capture the structural elements of the QR code in the super-resolved image. The experimental results and theoretical analyses show that the proposed method is a potential solution for secured exchange of QR codes with different error correction levels. The security of the proposed approach is evaluated with the difficulty in launching security attacks to recover and decode the secret QR code. The experimental results show that an adversary must try 258 additional combinations of shares and perform 3 × 288 additional computations, compared to a representative approach, to compromise the proposed system.
22
Pratim Mondal, Partha. "Probabilistic Optically-Selective Single-molecule Imaging Based Localization Encoded (POSSIBLE) microscopy for ultra-superresolution imaging." PLOS ONE 15, no. 11 (November 16, 2020): e0242452. http://dx.doi.org/10.1371/journal.pone.0242452.
Full textAbstract:
To be able to resolve molecular-clusters it is crucial to access vital information (such as, molecule density, cluster-size, and others) that are key in understanding disease progression and the underlying mechanism. Traditional single-molecule localization microscopy (SMLM) techniques use molecules of variable sizes (as determined by its localization precision (LP)) to reconstruct a super-resolution map. This results in an image with overlapping and superimposing PSFs (due to a wide size-spectrum of single-molecules) that undermine image resolution. Ideally, it should be possible to identify the brightest molecules (also termed as the fortunate molecules) to reconstruct ultra-superresolution map, provided sufficient statistics is available from the recorded data. Probabilistic Optically-Selective Single-molecule Imaging Based Localization Encoded (POSSIBLE) microscopy explores this possibility by introducing a narrow probability size-distribution of single-molecules (narrow size-spectrum about a predefined mean-size). The reconstruction begins by presetting the mean and variance of the narrow distribution function (Gaussian function). Subsequently, the dataset is processed and single-molecules are filtered by the Gaussian function to remove unfortunate molecules. The fortunate molecules thus retained are then mapped to reconstruct an ultra-superresolution map. In-principle, the POSSIBLE microscopy technique is capable of infinite resolution (resolution of the order of actual single-molecule size) provided enough fortunate molecules are experimentally detected. In short, bright molecules (with large emissivity) holds the key. Here, we demonstrate the POSSIBLE microscopy technique and reconstruct single-molecule images with an average PSF sizes of σ ± Δσ = 15 ± 10 nm, 30 ± 2 nm & 50 ± 2 nm. Results show better-resolved Dendra2-HA clusters with large cluster-density in transfected NIH3T3 fibroblast cells as compared to the traditional SMLM techniques. Cluster analysis indicates densely-packed HA molecules, HA-HA interaction, and a surge in the number of HA molecules per cluster post 24 Hrs of transfection. The study using POSSIBLE microscopy introduces new insights in influenza biology. We anticipate exciting applications in the multidisciplinary field of disease biology, oncology, and biomedical imaging.
23
Lu, Xiaochen, Dezheng Yang, Junping Zhang, and Fengde Jia. "Hyperspectral Image Super-Resolution Based on Spatial Correlation-Regularized Unmixing Convolutional Neural Network." Remote Sensing 13, no. 20 (October 12, 2021): 4074. http://dx.doi.org/10.3390/rs13204074.
Full textAbstract:
Super-resolution (SR) technology has emerged as an effective tool for image analysis and interpretation. However, single hyperspectral (HS) image SR remains challenging, due to the high spectral dimensionality and lack of available high-resolution information of auxiliary sources. To fully exploit the spectral and spatial characteristics, in this paper, a novel single HS image SR approach is proposed based on a spatial correlation-regularized unmixing convolutional neural network (CNN). The proposed approach takes advantage of a CNN to explore the collaborative spatial and spectral information of an HS image and infer the high-resolution abundance maps, thereby reconstructing the anticipated high-resolution HS image via the linear spectral mixture model. Moreover, a dual-branch architecture network and spatial spread transform function are employed to characterize the spatial correlation between the high- and low-resolution HS images, aiming at promoting the fidelity of the super-resolved image. Experiments on three public remote sensing HS images demonstrate the feasibility and superiority in terms of spectral fidelity, compared with some state-of-the-art HS image super-resolution methods.
24
Hu, Jing, Minghua Zhao, and Yunsong Li. "Hyperspectral Image Super-Resolution by Deep Spatial-Spectral Exploitation." Remote Sensing 11, no. 10 (May 23, 2019): 1229. http://dx.doi.org/10.3390/rs11101229.
Full textAbstract:
Limited by the existing imagery sensors, hyperspectral images are characterized by high spectral resolution but low spatial resolution. The super-resolution (SR) technique aiming at enhancing the spatial resolution of the input image is a hot topic in computer vision. In this paper, we present a hyperspectral image (HSI) SR method based on a deep information distillation network (IDN) and an intra-fusion operation. Specifically, bands are firstly selected by a certain distance and super-resolved by an IDN. The IDN employs distillation blocks to gradually extract abundant and efficient features for reconstructing the selected bands. Second, the unselected bands are obtained via spectral correlation, yielding a coarse high-resolution (HR) HSI. Finally, the spectral-interpolated coarse HR HSI is intra-fused with the input HSI to achieve a finer HR HSI, making further use of the spatial-spectral information these unselected bands convey. Different from most existing fusion-based HSI SR methods, the proposed intra-fusion operation does not require any auxiliary co-registered image as the input, which makes this method more practical. Moreover, contrary to most single-based HSI SR methods whose performance decreases significantly as the image quality gets worse, the proposal deeply utilizes the spatial-spectral information and the mapping knowledge provided by the IDN, which achieves more robust performance. Experimental data and comparative analysis have demonstrated the effectiveness of this method.
25
Fukami, Kai, Koji Fukagata, and Kunihiko Taira. "Super-resolution reconstruction of turbulent flows with machine learning." Journal of Fluid Mechanics 870 (May 7, 2019): 106–20. http://dx.doi.org/10.1017/jfm.2019.238.
Full textAbstract:
We use machine learning to perform super-resolution analysis of grossly under-resolved turbulent flow field data to reconstruct the high-resolution flow field. Two machine learning models are developed, namely, the convolutional neural network (CNN) and the hybrid downsampled skip-connection/multi-scale (DSC/MS) models. These machine learning models are applied to a two-dimensional cylinder wake as a preliminary test and show remarkable ability to reconstruct laminar flow from low-resolution flow field data. We further assess the performance of these models for two-dimensional homogeneous turbulence. The CNN and DSC/MS models are found to reconstruct turbulent flows from extremely coarse flow field images with remarkable accuracy. For the turbulent flow problem, the machine-leaning-based super-resolution analysis can greatly enhance the spatial resolution with as little as 50 training snapshot data, holding great potential to reveal subgrid-scale physics of complex turbulent flows. With the growing availability of flow field data from high-fidelity simulations and experiments, the present approach motivates the development of effective super-resolution models for a variety of fluid flows.
26
Wang, Zhibo, Xiangru Li, Luhan Liu, Xuecheng Wu, Pengfei Hao, Xiwen Zhang, and Feng He. "Deep-learning-based super-resolution reconstruction of high-speed imaging in fluids." Physics of Fluids 34, no. 3 (March 2022): 037107. http://dx.doi.org/10.1063/5.0078644.
Full textAbstract:
In many fluid experiments, we can only obtain low-spatial high-temporal resolution flow images and high-spatial low-temporal resolution flow images due to the limitation of high-speed imaging systems. To solve this problem, we proposed a degradation and super-resolution attention model (D-SRA) using unsupervised machine learning to super-resolution reconstruct high resolution (HR) time-resolved fluid images from coarse data. Unlike the prior research to increase the resolution of coarse data artificially generated by simple bilinear down-sampling, our model that consists of a degradation neural network and a super-resolution neural network aims to learn the mappings between experimental low-resolution data and corresponding HR data. What is more, channel and spatial attention modules are also adopted in D-SRA to facilitate the restoration of abundant and critical details of flow fields. The proposed model is validated by two high-speed schlieren experiments of under-expanded impinging supersonic jets. The comprehensive capability of D-SRA is statistically analyzed based on the synthetic unpaired schlieren images. The spatial-resolution of coarse images can be successfully augmented by [Formula: see text] times and [Formula: see text] times with most physical details recovered perfectly, which outperforms the existing method. The D-SRA also exhibits considerable generalization and robustness against unknown-degenerated schlieren images. Moreover, the practicability of the proposed method is also further explored on real unpaired jets schlieren images. It is convincingly demonstrated that the present study successfully surpasses the performance limitations of high-speed cameras and has significant applications in various fluid experiments to obtain flow images with high spatial and temporal resolution.
27
Boroomand, Ameneh, Alexander Wong, Edward Li, Daniel S. Cho, Betty Ni, and Kostandinka Bizheva. "Multi-penalty conditional random field approach to super-resolved reconstruction of optical coherence tomography images." Biomedical Optics Express 4, no. 10 (September 6, 2013): 2032. http://dx.doi.org/10.1364/boe.4.002032.
Full text
28
Lüke, J. P., F. Pérez Nava, J. G. Marichal-Hernández, J. M. Rodríguez-Ramos, and F. Rosa. "Near Real-Time Estimation of Super-Resolved Depth and All-In-Focus Images from a Plenoptic Camera Using Graphics Processing Units." International Journal of Digital Multimedia Broadcasting 2010 (2010): 1–12. http://dx.doi.org/10.1155/2010/942037.
Full textAbstract:
Depth range cameras are a promising solution for the 3DTV production chain. The generation of color images with their accompanying depth value simplifies the transmission bandwidth problem in 3DTV and yields a direct input for autostereoscopic displays. Recent developments in plenoptic video-cameras make it possible to introduce 3D cameras that operate similarly to traditional cameras. The use of plenoptic cameras for 3DTV has some benefits with respect to 3D capture systems based on dual stereo cameras since there is no need for geometric and color calibration or frame synchronization. This paper presents a method for simultaneously recovering depth and all-in-focus images from a plenoptic camera in near real time using graphics processing units (GPUs). Previous methods for 3D reconstruction using plenoptic images suffered from the drawback of low spatial resolution. A method that overcomes this deficiency is developed on parallel hardware to obtain near real-time 3D reconstruction with a final spatial resolution of800×600pixels. This resolution is suitable as an input to some autostereoscopic displays currently on the market and shows that real-time 3DTV based on plenoptic video-cameras is technologically feasible.
29
Roesler, Alexander Scott, Pietro Miozzo, Billur Akkaya, Margery Smelkinson, Joseph Brzostowski, Juraj Kabat, Javier Traba, David W. Dorward, Susan K. Pierce, and Munir Akkaya. "Application of super-resolution microscopy to the study of B and T lymphocyte mitochondria morphology and metabolism." Journal of Immunology 198, no. 1_Supplement (May 1, 2017): 81.2. http://dx.doi.org/10.4049/jimmunol.198.supp.81.2.
Full textAbstract:
Abstract High-resolution microscopy techniques have advanced our understanding of lymphocyte biology. An emerging focus in the field of immunometabolism on activation-induced metabolic reprogramming and its effects on immune cell function will require in-depth analyses of mitochondria. However, even with newer imaging technologies, obtaining super-resolution images of lymphocyte mitochondria remains challenging due to their small cytoplasmic sizes. Here, we compared standard confocal laser microscopy with three commonly used super-resolution methods to analyze activation-induced mitochondrial changes in B and T cells. Naïve B cells were stimulated in vitro via Toll-like receptor 9 and/or the B cell receptor, and naïve T cells were differentiated in vitro into activated or T regulatory phenotypes. The cells were imaged using standard laser confocal microscopy, AiryScan, stimulated emission depletion (STED) microscopy, and computerized tomography electron microscopy (TEM). Mitochondrial morphology was best resolved by staining both the mitochondrial membrane and matrix simultaneously. In preliminary analyses, we observed activation-induced changes in the distribution of lymphocyte mitochondria. Of the imaging methods used, only TEM allowed for 3D reconstructions of the mitochondria’s internal structure, which revealed swelling of the inner matrix and significant loss of cristae in B cells, but not in T cells. In conclusion, the super-resolution light microscopy techniques we developed appear to be powerful tools for immunometabolism studies of lymphocyte mitochondria, having demonstrated clear visualization even at the molecular level, while TEM answered key questions about intra-mitochondrial morphology.
30
Barth, R., K. Bystricky, and H. A. Shaban. "Coupling chromatin structure and dynamics by live super-resolution imaging." Science Advances 6, no. 27 (July 2020): eaaz2196. http://dx.doi.org/10.1126/sciadv.aaz2196.
Full textAbstract:
Chromatin conformation regulates gene expression and thus, constant remodeling of chromatin structure is essential to guarantee proper cell function. To gain insight into the spatiotemporal organization of the genome, we use high-density photoactivated localization microscopy and deep learning to obtain temporally resolved super-resolution images of chromatin in living cells. In combination with high-resolution dense motion reconstruction, we find elongated ~45- to 90-nm-wide chromatin “blobs.” A computational chromatin model suggests that these blobs are dynamically associating chromatin fragments in close physical and genomic proximity and adopt topologically associated domain–like interactions in the time-average limit. Experimentally, we found that chromatin exhibits a spatiotemporal correlation over ~4 μm in space and tens of seconds in time, while chromatin dynamics are correlated over ~6 μm and last 40 s. Notably, chromatin structure and dynamics are closely related, which may constitute a mechanism to grant access to regions with high local chromatin concentration.
31
Luo, Hui, Zhenhong Li, Zhen Dong, Anxi Yu, Yongsheng Zhang, and Xiaoxiang Zhu. "Super-Resolved Multiple Scatterers Detection in SAR Tomography Based on Compressive Sensing Generalized Likelihood Ratio Test (CS-GLRT)." Remote Sensing 11, no. 16 (August 17, 2019): 1930. http://dx.doi.org/10.3390/rs11161930.
Full textAbstract:
The application of SAR tomography (TomoSAR) on the urban infrastructure and other man-made buildings has gained increasing popularity with the development of modern high-resolution spaceborne satellites. Urban tomography focuses on the separation of the overlaid targets within one azimuth-range resolution cell, and on the reconstruction of their reflectivity profiles. In this work, we build on the existing methods of compressive sensing (CS) and generalized likelihood ratio test (GLRT), and develop a multiple scatterers detection method named CS-GLRT to automatically recognize the number of scatterers superimposed within a single pixel as well as to reconstruct the backscattered reflectivity profiles of the detected scatterers. The proposed CS-GLRT adopts a two-step strategy. In the first step, an L1-norm minimization is carried out to give a robust estimation of the candidate positions pixel by pixel with super-resolution. In the second step, a multiple hypothesis test is implemented in the GLRT to achieve model order selection, where the mapping matrix is constrained within the afore-selected columns, namely, within the candidate positions, and the parameters are estimated by least square (LS) method. Numerical experiments on simulated data were carried out, and the presented results show its capability of separating the closely located scatterers with a quasi-constant false alarm rate (QCFAR), as well as of obtaining an estimation accuracy approaching the Cramer–Rao Low Bound (CRLB). Experiments on real data of Spotlight TerraSAR-X show that CS-GLRT allows detecting single scatterers with high density, distinguishing a considerable number of double scatterers, and even detecting triple scatterers. The estimated results agree well with the ground truth and help interpret the true structure of the complex or buildings studied in the SAR images. It should be noted that this method is especially suitable for urban areas with very dense infrastructure and man-made buildings, and for datasets with tightly-controlled baseline distribution.
32
Moodley, Chané, and Andrew Forbes. "Super-resolved quantum ghost imaging." Scientific Reports 12, no. 1 (June 20, 2022). http://dx.doi.org/10.1038/s41598-022-14648-2.
Full textAbstract:
AbstractQuantum ghost imaging offers many advantages over classical imaging, including low photon fluxes and non-degenerate object and image wavelengths for imaging light sensitive structures, but suffers from slow image reconstruction speeds. Image reconstruction times depend on the resolution of the required image which scale quadratically with the image resolution. Here, we propose a super-resolved imaging approach based on neural networks where we reconstruct a low resolution image, which we denoise and super-resolve to a high resolution image. To test the approach, we implemented both a generative adversarial network as well as a super-resolving autoencoder in conjunction with an experimental quantum ghost imaging setup, demonstrating its efficacy across a range of object and imaging projective mask types. We achieved super-resolving enhancement of $$4\times$$ 4 × the measured resolution with a fidelity close to 90$$\%$$ % at an acquisition time of N$$^2$$ 2 measurements, required for a complete N $$\times$$ × N pixel image solution. This significant resolution enhancement is a step closer to a common ghost imaging goal, to reconstruct images with the highest resolution and the shortest possible acquisition time.
33
Xiao, Guangyi, and Long Zhang. "Super-resolved synthetic aperture radar image reconstruction based on multiresolution fusion discrimination." Journal of Electronic Imaging 31, no. 04 (August 10, 2022). http://dx.doi.org/10.1117/1.jei.31.4.043036.
Full text
34
Markwirth, Andreas, Mario Lachetta, Viola Mönkemöller, Rainer Heintzmann, Wolfgang Hübner, Thomas Huser, and Marcel Müller. "Video-rate multi-color structured illumination microscopy with simultaneous real-time reconstruction." Nature Communications 10, no. 1 (September 20, 2019). http://dx.doi.org/10.1038/s41467-019-12165-x.
Full textAbstract:
Abstract Super-resolved structured illumination microscopy (SR-SIM) is among the fastest fluorescence microscopy techniques capable of surpassing the optical diffraction limit. Current custom-build instruments are able to deliver two-fold resolution enhancement with high acquisition speed. SR-SIM is usually a two-step process, with raw-data acquisition and subsequent, time-consuming post-processing for image reconstruction. In contrast, wide-field and (multi-spot) confocal techniques produce high-resolution images instantly. Such immediacy is also possible with SR-SIM, by tight integration of a video-rate capable SIM with fast reconstruction software. Here we present instant SR-SIM by VIGOR (Video-rate Immediate GPU-accelerated Open-Source Reconstruction). We demonstrate multi-color SR-SIM at video frame-rates, with less than 250 ms delay between measurement and reconstructed image display. This is achieved by modifying and extending high-speed SR-SIM image acquisition with a new, GPU-enhanced, network-enabled image-reconstruction software. We demonstrate high-speed surveying of biological samples in multiple colors and live imaging of moving mitochondria as an example of intracellular dynamics.
35
Yebouet, Marie-Florence, Ambroise Diby, Kenneth Kaduki, and Jérémie Zoueu. "Unstained blood smear contrast enhancement using spectral time multiplexing super resolution." Journal of Spectral Imaging, January 1, 2020. http://dx.doi.org/10.1255/jsi.2020.a1.
Full textAbstract:
We report the use of Time Multiplexing Super Resolution (TMSR) to reduce significantly speckle noise in spectral imaging microscopy of unstained thin blood smear samples of malaria-infected blood. The method is based on combining speckle illumination with a moving array serving as an encoding mask. We propose the use of a new encoding mask to improve the performance of the conventional TMSR method. The new mask is a two-dimensional generalisation of the one- dimensional Ipatov code. The mask is projected on the object and 13 low-resolution images captured and subsequently decoded properly using the same array. The low contrast images are added and extracted from the resulting reconstruction, giving a super-resolved, high-contrast image. The Ipatov filter used in this work performs better than the Barker filter.
36
Wu, Yumin, Linpeng Lu, Jialin Zhang, Zhuoshi Li, and Chao Zuo. "Autofocusing Algorithm for Pixel-Super-Resolved Lensfree On-Chip Microscopy." Frontiers in Physics 9 (March 29, 2021). http://dx.doi.org/10.3389/fphy.2021.651316.
Full textAbstract:
In recent years, lensfree on-chip microscopy has developed into a promising and powerful computational optical microscopy technique that allows for wide-field, high-throughput microscopic imaging without using any lenses. However, due to the limited pixel size of the state-of-the-art image sensors, lens-free on-chip microscopy generally suffers from low imaging resolution, which is far from enough to meet the current demand for high-resolution microscopy. Many pixel super-resolution techniques have been developed to solve or at least partially solve this problem by acquiring a series of low-resolution holograms with multiple lateral sub-pixel shifting or axial distances. However, the prerequisite of these pixel super-resolution techniques is that the propagation distance of each low-resolution hologram can be obtained precisely, which faces two major challenges. On the one hand, the captured hologram is inherent pixelated and of low resolution, making it difficult to determine the focal plane by evaluating the image sharpness accurately. On the other hand, the twin-image is superimposed on the backpropagated raw hologram, further exacerbating the difficulties in accurate focal plane determination. In this study, we proposed a high-precision autofocusing algorithm for multi-height pixel-super-resolved lensfree on-chip microscopy. Our approach consists of two major steps: individual preliminary estimation and global precise estimation. First, an improved critical function that combines differential critical function and frequency domain critical function is proposed to obtain the preliminary focus distances of different holograms. Then, the precise focus distances can be determined by further evaluating the global offset of the averaged, low-noise reconstruction from all backpropagated holograms with preliminary focus distances. Simulations and experimental results verified the validity and effectiveness of the proposed algorithm.
37
Berberich, Andreas, Andreas Kurz, Sebastian Reinhard, Torsten Johann Paul, Paul Ray Burd, Markus Sauer, and Philip Kollmannsberger. "Fourier Ring Correlation and Anisotropic Kernel Density Estimation Improve Deep Learning Based SMLM Reconstruction of Microtubules." Frontiers in Bioinformatics 1 (October 15, 2021). http://dx.doi.org/10.3389/fbinf.2021.752788.
Full textAbstract:
Single-molecule super-resolution microscopy (SMLM) techniques like dSTORM can reveal biological structures down to the nanometer scale. The achievable resolution is not only defined by the localization precision of individual fluorescent molecules, but also by their density, which becomes a limiting factor e.g., in expansion microscopy. Artificial deep neural networks can learn to reconstruct dense super-resolved structures such as microtubules from a sparse, noisy set of data points. This approach requires a robust method to assess the quality of a predicted density image and to quantitatively compare it to a ground truth image. Such a quality measure needs to be differentiable to be applied as loss function in deep learning. We developed a new trainable quality measure based on Fourier Ring Correlation (FRC) and used it to train deep neural networks to map a small number of sampling points to an underlying density. Smooth ground truth images of microtubules were generated from localization coordinates using an anisotropic Gaussian kernel density estimator. We show that the FRC criterion ideally complements the existing state-of-the-art multiscale structural similarity index, since both are interpretable and there is no trade-off between them during optimization. The TensorFlow implementation of our FRC metric can easily be integrated into existing deep learning workflows.
38
Avagyan, Shushik, Vladimir Katkovnik, and Karen Egiazarian. "Modified SSR-NET: A Shallow Convolutional Neural Network for Efficient Hyperspectral Image Super-Resolution." Frontiers in Remote Sensing 3 (July 7, 2022). http://dx.doi.org/10.3389/frsen.2022.889915.
Full textAbstract:
A fast and shallow convolutional neural network is proposed for hyperspectral image super-resolution inspired by Spatial-Spectral Reconstruction Network (SSR-NET). The feature extraction ability is improved compared to SSR-NET and other state-of-the-art methods, while the proposed network is also shallow. Numerical experiments show both the visual and quantitative superiority of our method. Specifically, for the fusion setup with two inputs, obtained by 32× spatial downsampling for the low-resolution hyperspectral (LR HSI) input and 25× spectral downsampling for high-resolution multispectral (HR MSI) input, a significant improvement of the quality of super-resolved HR HSI over 4 dB is demonstrated as compared with SSR-NET. It is also shown that, in some cases, our method with a single input, HR MSI, can provide a comparable result with that achieved with two inputs, HR MSI and LR HSI.
39
Hajhosseiny, Reza, Camila Munoz, Gastao Cruz, Ramzi Khamis, Won Yong Kim, Claudia Prieto, and René M. Botnar. "Coronary Magnetic Resonance Angiography in Chronic Coronary Syndromes." Frontiers in Cardiovascular Medicine 8 (August 17, 2021). http://dx.doi.org/10.3389/fcvm.2021.682924.
Full textAbstract:
Cardiovascular disease is the leading cause of mortality worldwide, with atherosclerotic coronary artery disease (CAD) accounting for the majority of cases. X-ray coronary angiography and computed tomography coronary angiography (CCTA) are the imaging modalities of choice for the assessment of CAD. However, the use of ionising radiation and iodinated contrast agents remain drawbacks. There is therefore a clinical need for an alternative modality for the early identification and longitudinal monitoring of CAD without these associated drawbacks. Coronary magnetic resonance angiography (CMRA) could be a potential alternative for the detection and monitoring of coronary arterial stenosis, without exposing patients to ionising radiation or iodinated contrast agents. Further advantages include its versatility, excellent soft tissue characterisation and suitability for repeat imaging. Despite the early promise of CMRA, widespread clinical utilisation remains limited due to long and unpredictable scan times, onerous scan planning, lower spatial resolution, as well as motion related image quality degradation. The past decade has brought about a resurgence in CMRA technology, with significant leaps in image acceleration, respiratory and cardiac motion estimation and advanced motion corrected or motion-resolved image reconstruction. With the advent of artificial intelligence, great advances are also seen in deep learning-based motion estimation, undersampled and super-resolution reconstruction promising further improvements of CMRA. This has enabled high spatial resolution (1 mm isotropic), 3D whole heart CMRA in a clinically feasible and reliable acquisition time of under 10 min. Furthermore, latest super-resolution image reconstruction approaches which are currently under evaluation promise acquisitions as short as 1 min. In this review, we will explore the recent technological advances that are designed to bring CMRA closer to clinical reality.
40
Mamyrbayev, T., K. Ikematsu, P. Meyer, A. Ershov, A. Momose, and J. Mohr. "Super-Resolution Scanning Transmission X-Ray Imaging Using Single Biconcave Parabolic Refractive Lens Array." Scientific Reports 9, no. 1 (October 7, 2019). http://dx.doi.org/10.1038/s41598-019-50869-8.
Full textAbstract:
Abstract A new super resolution imaging technique which potentially enables sub-µm spatial resolution, using a detector of pixels much larger than the spatial resolution, is proposed. The method utilizes sample scanning through a large number of identical X-ray microprobes periodically spaced (the period corresponds to a multiple of the pixel size), which reduces drastically the scanning time. The information about the sample illuminated by the microprobes is stored by large detector pixels. Using these data and sample position information, a super-resolution image reconstruction is performed. With a one-dimensional (1D) high aspect ratio nickel single lens array designed for theoretically expected sub-µm microprobes at 17 keV and fabricated by deep X-ray lithography and electroforming technique, 2 µm X-ray microprobes with a period of 10 µm were achieved. We performed a first experiment at KARA synchrotron facility, and it was demonstrated that the smallest structure of a test pattern with a size of 1.5 µm could be easily resolved by using images generated from a detector having a pixel size of 10.4 µm. This new approach has a great potential for providing a new microscopic imaging modality with a large field of view and short scan time.
41
Zunino, Alessandro, Marco Castello, and Giuseppe Vicidomini. "Reconstructing the image scanning microscopy dataset: an inverse problem." Inverse Problems, April 18, 2023. http://dx.doi.org/10.1088/1361-6420/accdc5.
Full textAbstract:
Abstract Confocal laser-scanning microscopy (CLSM) is one of the most popular optical architectures for fluorescence imaging. In CLSM, a focused laser beam excites the fluorescence emission from a specific specimen position. Some actuators scan the probed region across the sample and a photodetector collects a single intensity value for each scan point, building a two-dimensional image pixel-by-pixel.
Recently, new fast single-photon array detectors have allowed the recording of a full bi-dimensional image of the probed region for each scan point, transforming CLSM into image scanning microscopy (ISM). This latter offers significant improvements over traditional imaging but requires an optimal processing tool to extract a super-resolved image from the four-dimensional dataset.
Here we describe the image formation process in ISM from a statistical point of view, and we use the Bayesian framework to formulate a multi-image deconvolution problem. Notably, the single-photon detector suffers exclusively from the photon shot noise, enabling the development of an effective likelihood model. We derive an iterative likelihood maximization algorithm and test it on experimental and simulated data.
Furthermore, we demonstrate that the ISM dataset is redundant, enabling the possibility of obtaining reconstruction sampled at twice the scanning step. Our results prove that in ISM, under appropriate conditions, the Nyquist-Shannon sampling criterium is effectively relaxed. This finding can be exploited to speed up the acquisition process by a factor of four, further improving the versatility of ISM systems.
42
Ward, Edward N., Lisa Hecker, Charles N. Christensen, Jacob R. Lamb, Meng Lu, Luca Mascheroni, Chyi Wei Chung, et al. "Machine learning assisted interferometric structured illumination microscopy for dynamic biological imaging." Nature Communications 13, no. 1 (December 21, 2022). http://dx.doi.org/10.1038/s41467-022-35307-0.
Full textAbstract:
AbstractStructured Illumination Microscopy, SIM, is one of the most powerful optical imaging methods available to visualize biological environments at subcellular resolution. Its limitations stem from a difficulty of imaging in multiple color channels at once, which reduces imaging speed. Furthermore, there is substantial experimental complexity in setting up SIM systems, preventing a widespread adoption. Here, we present Machine-learning Assisted, Interferometric Structured Illumination Microscopy, MAI-SIM, as an easy-to-implement method for live cell super-resolution imaging at high speed and in multiple colors. The instrument is based on an interferometer design in which illumination patterns are generated, rotated, and stepped in phase through movement of a single galvanometric mirror element. The design is robust, flexible, and works for all wavelengths. We complement the unique properties of the microscope with an open source machine-learning toolbox that permits real-time reconstructions to be performed, providing instant visualization of super-resolved images from live biological samples.
43
Jeong, Dokyung, Min Jeong Kim, Yejin Park, Jinkyoung Chung, Hee-Seok Kweon, Nae-Gyu Kang, Seung Jin Hwang, Sung Hun Youn, Bo Kyoung Hwang, and Doory Kim. "Visualizing extracellular vesicle biogenesis in gram-positive bacteria using super-resolution microscopy." BMC Biology 20, no. 1 (December 5, 2022). http://dx.doi.org/10.1186/s12915-022-01472-3.
Full textAbstract:
Abstract Background Recently, bacterial extracellular vesicles (EVs) have been considered to play crucial roles in various biological processes and have great potential for developing cancer therapeutics and biomedicine. However, studies on bacterial EVs have mainly focused on outer membrane vesicles released from gram-negative bacteria since the outermost peptidoglycan layer in gram-positive bacteria is thought to preclude the release of EVs as a physical barrier. Results Here, we examined the ultrastructural organization of the EV produced by gram-positive bacteria using super-resolution stochastic optical reconstruction microscopy (STORM) at the nanoscale, which has not been resolved using conventional microscopy. Based on the super-resolution images of EVs, we propose three major mechanisms of EV biogenesis, i.e., membrane blebbing (mechanisms 1 and 2) or explosive cell lysis (mechanism 3), which are different from the mechanisms in gram-negative bacteria, despite some similarities. Conclusions These findings highlight the significant role of cell wall degradation in regulating various mechanisms of EV biogenesis and call for a reassessment of previously unresolved EV biogenesis in gram-positive bacteria.