Multichannel Image Research Articles

Machine Learning Application of Two-Dimensional Fracture Properties Estimation

Fractures are substantial contributors to solute transport sedimentary systems that form pathways. The pathway formed in a fracture has two physical parameters, there are mean aperture and surface roughness. Mean aperture is the thickness of the pathway that the fluid will pass through, and surface roughness is the roughness of the fracture pathway. The two physical parameters of the fracture are important to determine since they affect the permeability value in petroleum reservoir analysis. We developed a machine learning algorithm based on the Convolutional Neural Network (CNN) to predict those two parameters. Furthermore, image processing analysis is performed to generate the datasets. The results show that the CNN algorithm shows good agreement with the reference results. In addition, the algorithms showed efficient performance in terms of computational time. CNN is a type of deep neural designed to perform analysis on multi-channel images that can classify fracture geometry. The best model was determined using a benchmark dataset with a CNN model provided by Keras. The results of experiments conducted on fracture geometry images show that the machine learning model created is able to predict the mean aperture and surface roughness values.

Machine learning prediction of tortuosity in digital rock

Physical rock property measurement is an important stage in energy exploration, both for hydrocarbons and geothermal sources. The value of physical rock properties can provide information about reservoir quality, and one of these properties is tortuosity. Tortuosity is an intrinsic property of porous materials that describes the level of complexity of the porous arrangement when a fluid passes through it. Conventionally, tortuosity values are measured through laboratory analysis and numerical simulation, but these measurements can take a long time. An alternative method for measuring tortuosity is using machine learning with a convolutional neural network (CNN). A CNN is a type of deep neural network designed to analyze multi-channel images and has been applied successfully to classification and non-linear regression problems. By training a CNN on a dataset of digital rock samples that have been simulated using numerical computation to obtain their tortuosity values, it is possible to demonstrate that CNNs can accurately predict the tortuosity of digital rock. The result is that the CNN model can predict tortuosity values with the Xception model being the most accurate with the lowest RMSE value of 0.90962.

Single-cell multimodal imaging uncovers energy conversion pathways in biohybrids.

Microbe-semiconductor biohybrids, which integrate microbial enzymatic synthesis with the light-harvesting capabilities of inorganic semiconductors, have emerged as promising solar-to-chemical conversion systems. Improving the electron transport at the nano-bio interface and inside cells is important for boosting conversion efficiencies, yet the underlying mechanism is challenging to study by bulk measurements owing to the heterogeneities of both constituents. Here we develop a generalizable, quantitative multimodal microscopy platform that combines multi-channel optical imaging and photocurrent mapping to probe such biohybrids down to single- to sub-cell/particle levels. We uncover and differentiate the critical roles of different hydrogenases in the lithoautotrophic bacterium Ralstonia eutropha for bioplastic formation, discover this bacterium's surprisingly large nanoampere-level electron-uptake capability, and dissect the cross-membrane electron-transport pathways. This imaging platform, and the associated analytical framework, can uncover electron-transport mechanisms in various types of biohybrid, and potentially offers a means to use and engineer R. eutropha for efficient chemical production coupled with photocatalytic materials.

Broadband plasmonic metasurface for spin-selective hologram in near-infrared band

Metasurface holography is a significant technology for the development of ultrathin optical devices. Multichannel holography has received close attention due to its applications in increasing information capacity and optical secret sharing. However, existing design methods for multichannel holography mainly focus on interleaved metasurface imaging in the vertical direction, which will inevitably suffer from the unexpected crosstalk affecting imaging quality. This work presents noninterleaved spin-selective metasurfaces by combining the geometric phase and the propagating phase. It can achieve independent phase control on two orthogonal circular polarizations and image at the desired angle. As a proof-of-concept, two broadband plasmonic metasurfaces are designed for multichannel holographic imaging in the near-infrared band (800–1200 nm). When two orthogonal circularly polarized waves are normally incident, the first plasmonic metasurface displays two different holograms in the vertical direction, thus achieving dual-channel imaging, and the second plasmonic metasurface can make two holograms deflected to the desired angle. It means that these two holograms can be displayed without overlapping for a linearly polarized wave, and the orientable three-channel holographic imaging is realized. Our work provides a general and compact scheme for multichannel orientable holographic imaging.

Shot noise reduction in radiographic and tomographic multi-channel imaging with self-supervised deep learning.

Shot noise is a critical issue in radiographic and tomographic imaging, especially when additional constraints lead to a significant reduction of the signal-to-noise ratio. This paper presents a method for improving the quality of noisy multi-channel imaging datasets, such as data from time or energy-resolved imaging, by exploiting structural similarities between channels. To achieve that, we broaden the application domain of the Noise2Noise self-supervised denoising approach. The method draws pairs of samples from a data distribution with identical signals but uncorrelated noise. It is applicable to multi-channel datasets if adjacent channels provide images with similar enough information but independent noise. We demonstrate the applicability and performance of the method via three case studies, namely spectroscopic X-ray tomography, energy-dispersive neutron tomography, and in vivo X-ray cine-radiography.

A Super-Resolution Algorithm Based on Hybrid Network for Multi-Channel Remote Sensing Images

In recent years, the development of super-resolution (SR) algorithms based on convolutional neural networks has become an important topic in enhancing the resolution of multi-channel remote sensing images. However, most of the existing SR models suffer from the insufficient utilization of spectral information, limiting their SR performance. Here, we derive a novel hybrid SR network (HSRN) which facilitates the acquisition of joint spatial–spectral information to enhance the spatial resolution of multi-channel remote sensing images. The main contributions of this paper are three-fold: (1) in order to sufficiently extract the spatial–spectral information of multi-channel remote sensing images, we designed a hybrid three-dimensional (3D) and two-dimensional (2D) convolution module which can distill the nonlinear spectral and spatial information simultaneously; (2) to enhance the discriminative learning ability, we designed the attention structure, including channel attention, before the upsampling block and spatial attention after the upsampling block, to weigh and rescale the spectral and spatial features; and (3) to acquire fine quality and clear texture for reconstructed SR images, we introduced a multi-scale structural similarity index into our loss function to constrain the HSRN model. The qualitative and quantitative comparisons were carried out in comparison with other SR methods on public remote sensing datasets. It is demonstrated that our HSRN outperforms state-of-the-art methods on multi-channel remote sensing images.

ЕФЕКТИВНІ МЕТОДИ ІНТЕЛЕКТУАЛЬНОЇ ОБРОБКИ ЗОБРАЖЕНЬ ТА ВІДЕО НА ОСНОВІ МЕТРИК ВІЗУАЛЬНОЇ ЯКОСТІ ДЛЯ ПЕРСПЕКТИВНИХ ЗАСТОСУВАНЬ

This chapter contains the results obtained during execution of Ukrainian-Polish Project in 2021 intended on design of methods and means for processing grayscale and multichannel images and video using visual quality metrics. The combined metrics have been

Homomorphic filtering in digital multichannel image processing

Purpose. The purpose of this article is to develop a preprocessing method for digital multispectral remote sensing images obtained through optical and infrared means in the electromagnetic spectrum. The method aims to ensure invariance with respect to positional formation conditions that determine spatial and radiometric resolution. By implementing homomorphic filtering in this method, we can significantly increase the informative value of processed imagery. Methodology. The problem solving, including the development of the spatial and radiometric resolution increase ways for multispectral geospatial data are based on the methods of brightness spatial distribution fusion, methods of data dimension reduction, de-correlation techniques and geometric correction of image spatial distributions. Findings. The method of preprocessing digital remote sensing data has been developed, which is a component of the methodology for identifying geometric shapes (GS) of objects in multi-channel aerospace images, allowing for a significant improvement in their recognition efficiency when noise is present. Originality. The method of preprocessing photogrammetric scenes using homomorphic filtering to enhance their informational significance is proposed. The method ensures invariance to positional conditions of fixation, improves the accuracy of further recognition, eliminates the drawbacks of known methods associated with the existence of parametric uncertainty dependence, the features of fixation of species information, low values of information indices of synthesized images, and computational process peculiarities. Practical value. Practical value is consists in improving of identification accuracy of objects GS in digital geospatial data, in significant increasing of raster multispectral images information value and in rising of automated image processing efficiency. The use of the method can greatly enhance the value and usefulness of multispectral photogrammetric images in a wide range of applications, from environmental monitoring to urban planning.

A secure controlled quantum image steganography scheme based on the multi-channel effective quantum image representation model

A secure controlled quantum image steganography scheme based on the multi-channel effective quantum image representation model

An iterative reconstruction algorithm based on total nuclear variation for multi-channel EPRI

Oxygen concentration in tumor is a key information for effective radiation therapy. Electron paramagnetic resonance imaging (EPRI) is an advanced oxygen imaging technique. However, in the case of multi-channel EPRI， traditional imaging methods including filtered back-projection (FBP) and optimization algorithm related to total variation (TV) only consider the features of individual channel images and ignore the similarities among images of each channel. Total nuclear variation encourages shared edge positions and consistent gradient directions across multi-channel images. In this study, we propose a data divergence constrained, total nuclear variation minimization model and its Chambolle-Pock solving algorithm. We validate the accuracy of the algorithm and analyze its convergence through simulation studies using mathematical phantoms that simulate T1-weighted EPRI. Furthermore, we investigate the influence of algorithm parameters on convergence rate and evaluate the algorithm’s capability for sparse reconstruction and noise suppression. The experimental results show that the total nuclear variation minimization algorithm promotes edge structure information and gradient direction within individual channels of images. As a result, this algorithm successfully preserves essential image features while achieving accurate image reconstruction.

Liquid cloud optical property retrieval and associated uncertainties using multi-angular and bispectral measurements of the airborne radiometer OSIRIS

Abstract. In remote sensing applications, clouds are generally characterized by two properties: cloud optical thickness (COT) and effective radius of water–ice particles (Reff), as well as additionally by geometric properties when specific information is available. Most of the current operational passive remote sensing algorithms use a mono-angular bispectral method to retrieve COT and Reff. They are based on pre-computed lookup tables while assuming a homogeneous plane-parallel cloud layer. In this work, we use the formalism of the optimal estimation method, applied to airborne near-infrared high-resolution multi-angular measurements, to retrieve COT and Reff as well as the corresponding uncertainties related to the measurement errors, the non-retrieved parameters, and the cloud model assumptions. The measurements used were acquired by the airborne radiometer OSIRIS (Observing System Including PolaRization in the Solar Infrared Spectrum), developed by the Laboratoire d'Optique Atmosphérique. It provides multi-angular measurements at a resolution of tens of meters, which is very suitable for refining our knowledge of cloud properties and their high spatial variability. OSIRIS is based on the POLDER (POlarization and Directionality of the Earth's Reflectances) concept as a prototype of the future 3MI (Multi-viewing Multi-channel Multi-polarization Imager) planned to be launched on the EUMETSAT-ESA MetOp-SG platform in 2024. The approach used allows the exploitation of all the angular information available for each pixel to overcome the radiance angular effects. More consistent cloud properties with lower uncertainty compared to operational mono-directional retrieval methods (traditional bispectral method) are then obtained. The framework of the optimal estimation method also provides the possibility to estimate uncertainties of different sources. Three types of errors were evaluated: (1) errors related to measurement uncertainties, which reach 6 % and 12 % for COT and Reff, respectively, (2) errors related to an incorrect estimation of the ancillary data that remain below 0.5 %, and (3) errors related to the simplified cloud physical model assuming independent pixel approximation. We show that not considering the in-cloud heterogeneous vertical profiles and the 3D radiative transfer effects leads to an average uncertainty of 5 % and 4 % for COT and 13 % and 9 % for Reff.

Optimizing the Cell Painting assay for image-based profiling.

In image-based profiling, software extracts thousands of morphological features of cells from multi-channel fluorescence microscopy images, yielding single-cell profiles that can be used for basic research and drug discovery. Powerful applications have been proven, including clustering chemical and genetic perturbations on the basis of their similar morphological impact, identifying disease phenotypes by observing differences in profiles between healthy and diseased cells and predicting assay outcomes by using machine learning, among many others. Here, we provide an updated protocol for the most popular assay for image-based profiling, Cell Painting. Introduced in 2013, it uses six stains imaged in five channels and labels eight diverse components of the cell: DNA, cytoplasmic RNA, nucleoli, actin, Golgi apparatus, plasma membrane, endoplasmic reticulum and mitochondria. The original protocol was updated in 2016 on the basis of several years' experience running it at two sites, after optimizing it by visual stain quality. Here, we describe the work of the Joint Undertaking for Morphological Profiling Cell Painting Consortium, to improve upon the assay via quantitative optimization by measuring the assay's ability to detect morphological phenotypes and group similar perturbations together. The assay gives very robust outputs despite various changes to the protocol, and two vendors' dyes work equivalently well. We present Cell Painting version 3, in which some steps are simplified and several stain concentrations can be reduced, saving costs. Cell culture and image acquisition take 1-2 weeks for typically sized batches of ≤20 plates; feature extraction and data analysis take an additional 1-2 weeks.This protocol is an update to Nat. Protoc. 11, 1757-1774 (2016): https://doi.org/10.1038/nprot.2016.105.

A novel whole-head RF coil design tailored for concurrent multichannel brain stimulation and imaging at 3T

PurposeMultichannel Transcranial Magnetic Stimulation (mTMS) [1] is a novel non-invasive brain stimulation technique allowing multiple sites to be stimulated simultaneously or sequentially under electronic control without movement of the coils. To enable simultaneous mTMS and MR imaging, we have designed and constructed a whole-head 28-channel receive-only RF coil at 3T. MethodsA helmet-shaped structure was designed considering a specific layout for a mTMS system with holes for positioning the TMS units next to the scalp. Diameter of the TMS units defined the diameter of RF loops. The placement of the preamplifiers was designed to minimize possible interactions and to allow straightforward positioning of the mTMS units around the RF coil. Interactions between TMS-MRI were analyzed for the whole-head system extending the results presented in previous publications [2]. Both SNR- and g-factors maps were obtained to compare the imaging performance of the coil with commercial head coils. ResultsSensitivity losses for the RF elements containing TMS units show a well-defined spatial pattern. Simulations indicate that the losses are predominantly caused by eddy currents on the coil wire windings. The average SNR performance of the TMSMR 28-channel coil is about 66% and 86% of the SNR of the 32/20-channel head coil respectively. The g-factor values of the TMSMR 28-channel coil are similar to the 32-channel coil and significantly better than the 20-channel coil. ConclusionWe present the TMSMR 28-channel coil, a head RF coil array to be integrated with a multichannel 3-axisTMS coil system, a novel tool that will enable causal mapping of human brain function.

MCR toolkit: A GPU-based toolkit for multi-channel reconstruction of preclinical and clinical x-ray CT data.

The advancement of x-ray CT into the domains of photon counting spectral imaging and dynamic cardiac and perfusion imaging has created many new challenges and opportunities for clinicians and researchers. To address challenges such as dose constraints and scanning times while capitalizing on opportunities such as multi-contrast imaging and low-dose coronary angiography, these multi-channel imaging applications require a new generation of CT reconstruction tools. These new tools should exploit the relationships between imaging channels during reconstruction to set new image quality standards while serving as a platform for direct translation between the preclinical and clinical domains. We outline and demonstrate a new Multi-Channel Reconstruction (MCR) Toolkit for GPU-based analytical and iterative reconstruction of preclinical and clinical multi-energy and dynamic x-ray CT data. To promote open science, open-source distribution of the Toolkit will coincide with the release of this publication (GPL v3; gitlab.oit.duke.edu/dpc18/mcr-toolkit-public). The MCR Toolkit source code is implemented in C/C++ and NVIDIA's CUDA GPU programming interface, with scripting support from MATLAB and Python. The Toolkit implements matched, separable footprint CT reconstruction operators for projection and backprojection in two geometries: planar, cone-beam CT (CBCT) and 3rd generation, cylindrical multi-detector row CT (MDCT). Analytical reconstruction is performed using filtered backprojection (FBP) for circular CBCT, weighted FBP (WFBP) for helical CBCT, and cone-parallel projection rebinning followed by WFBP for MDCT. Arbitrary combinations of energy and temporal channels are iteratively reconstructed under a generalized multi-channel signal model for joint reconstruction. We solve this generalized model algebraically using the split Bregman optimization method and the BiCGSTAB(l) linear solver interchangeably for both CBCT and MDCT data. Rank-sparse kernel regression (RSKR) and patch-based singular value thresholding (pSVT) are used to regularize the energy and time dimensions, respectively. Under a Gaussian noise model, regularization parameters are estimated automatically from the input data, dramatically reducing algorithm complexity for end users. Multi-GPU parallelization of the reconstruction operators is supported to manage reconstruction times. Denoising with RSKR and pSVT and post-reconstruction material decomposition are illustrated with preclinical and clinical cardiac photon-counting (PC)CT data. A digital MOBY mouse phantom with cardiac motion is used to illustrate single energy (SE), multi-energy (ME), time resolved (TR), and combined multi-energy and time-resolved (METR) helical, CBCT reconstruction. A fixed set of projection data is used across all reconstruction cases to demonstrate the Toolkit's robustness to increasing data dimensionality. Identical reconstruction code is applied to in vivo cardiac PCCT data acquired in a mouse model of atherosclerosis (METR). Clinical cardiac CT reconstruction is illustrated using the XCAT phantom and the DukeSim CT simulator, while dual-source, dual-energy CT reconstruction is illustrated for data acquired with a Siemens Flash scanner. Benchmarking results with NVIDIA RTX 8000 GPU hardware demonstrate 61%-99% efficiency in scaling computation from one to four GPUs for these reconstruction problems. The MCR Toolkit provides a robust solution for temporal and spectral x-ray CT reconstruction problems and was built from the ground up to facilitate translation of CT research and development between preclinical and clinical applications.

Color Printing and Encryption with Polarization-Switchable Structural Colors on All-Dielectric Metasurfaces.

Metasurface-based structural color with high resolution is promising for color printing and encryption. However, achieving tunable structural colors in practical applications is challenging owing to the immutability after the fabrication of metasurfaces. Herein, we proposed the polarization-switchable dielectric metasurfaces with full colors. The colorful images can be switched on/off by controlling the polarization of incident light. For the nanorods metasurfaces, all colors turned to black in the "off" mode because of the near-zero reflection, and the uniform black was advantageous for designing encryption applications. For the nanocrosses metasurfaces, colors reversed in two different "on" modes and images hidden in the "off" mode. With the polarization-sensitive metasurfaces, a fish-bird image, an overlapped dual-channel image, and a green-red heart image were obtained, respectively. The demonstrations can be applied to dynamic displays, optical cryptography, multichannel imaging, and optical data storage.

Multichannel cross-fusional convolutional neural networks

As one of the main methods of information fusion, artificial intelligence class fusion algorithm not only inherits the powerful skills of artificial intelligence, but also inherits many advantages of information fusion. Similarly, as an important sub-field of artificial intelligence class fusion algorithm, deep learning class fusion algorithm also inherits advantages of deep learning and information fusion. Hence, deep learning fusion algorithm has become one of the research hotspots of many scholars. To solve the problem that the existing neural networks are input into multiple channels as a whole and cannot fully learn information of multichannel images, Shan et al. proposed multichannel concat-fusional convolutional neural networks. To mine more multichannel images’ information and further explore the performance of different fusion types, the paper proposes new fusional neural networks called multichannel cross-fusion convolutional neural networks (McCfCNNs) with fusion types of “R+G+B/R+G+B/R+G+B” and “R+G/G+B/B+R” based on the tremendous strengths of information fusion. Experiments show that McCfCNNs obtain 0.07-6.09% relative performance improvement in comparison with their corresponding non-fusion convolutional neural networks (CNNs) on diverse datasets (such as CIFAR100, SVHN, CALTECH256, and IMAGENET) under a certain computational complexity. Hence, McCfCNNs with fusion types of “R+G+B/R+G+B/R+G+B” and “R+G/G+B/B+R” can learn more fully multichannel images’ information, which provide a method and idea for processing multichannel information fusion, for example, remote sensing satellite images.

Wavelength sequential selection technique for high-throughput multi-channel phase interrogation surface plasmon resonance imaging sensing.

Phase interrogation surface plasmon resonance (P-SPR) biosensors have the highest sensitivity among different types of surface plasmon resonance (SPR) biosensors. However, P-SPR sensors have small dynamic detection range and complex device configuration. To solve these two problems, we designed a multi-channel P-SPR imaging (mcP-SPRi) sensing platform based on a common-path ellipsometry scheme. A wavelength sequential selection (WSS) technique for P-SPRi sensing is developed to select the optimal sensing wavelengths according to different refractive indexes (RIs) of the samples, so the inconsistency of SPR signal response for different biomolecule types caused by the small dynamic detection range is eliminated. And a dynamic detection range of 3.7×10-3 RIU is achieved, which is the largest among the current mcP-SPRi biosensors. Remarkably, the individual SPR phase image acquisition time has been greatly reduced to 1s by using WSS method instead of whole spectrum scanning, which enables the high-throughput mcP-SPRi sensing.

Interferometric ISAR Imaging of Space Targets Using Pulse-Level Image Registration Method

Interferometric inverse synthetic aperture radar (InISAR) imaging is capable of retrieving three-dimensional target information from multi-channel inverse synthetic aperture radar (ISAR) images obtained by adjacent radars or antennas. The InISAR imaging of space targets is more difficult, compared with that observes short range targets with small radar systems. Considering the practical constraints when observing space targets with multiple large radars, this paper establishes a flexible InISAR imaging system which allows for non-perpendicular baselines and observation of targets under squint mode. Based on this, the generalized formulas for calculating scatterers' coordinates from measured interferometric phases are derived. Moreover, a pulse-level image registration method based on joint translational motion compensation is proposed to recover the coherence between multi-channel ISAR images, under condition of inconsistent pulse delays at different radar channels. With the proposed method, promising InISAR imaging results are obtained via two simulation experiments. The first experiment assumes ideal point scattering of the target, which verifies the high accuracy and computational efficiency of the proposed ISAR image registration method; the second experiment considers more practical target scattering using facet target model and physical optics algorithm, which demonstrates the possible deviation in InISAR imaging result caused by scatterer's anisotropic scattering and residual error of translational motion compensation. We believe that the derivation and simulation results in this paper would be helpful reference for practical InISAR imaging experiments.

МЕТОДИ ІНТЕЛЕКТУАЛЬНОЇ ОБРОБКИ ЗОБРАЖЕНЬ ТА ВІДЕО НА ОСНОВІ МЕТРИК ВІЗУАЛЬНОЇ ЯКОСТІ ДЛЯ ПЕРСПЕКТИВНИХ ЗАСТОСУВАНЬ

This chapter contains the results obtained during execution of Ukrainian-Polish Project in 2020 intended on design of methods and means for processing grayscale and multichannel images and video using visual quality metrics. The combined metrics have been

Joint deconvolution and blind source separation with non-coplanar interferometric data

With the fastly increasing development of multichannel imagers, blind source separation (BSS) algorithms are ubiquitous in astrophysics to unmix multispectral images. In this context, analyzing data from the forthcoming very large, continental-size, radio interferometers using BSS algorithms raises two challenges. Firstly, the data are incomplete and deteriorated by instrumental effects, which requires incorporating a deconvolution step to retrieve exploitable images. Secondly, the data are affected by non-coplanar effects that notably arise from the very large antenna baselines and which must be accounted for in the separation scheme. For this purpose, we introduce a joint non-coplanar deconvolution and BSS algorithm, called wGMCA. The algorithm is tested and characterized in many challenging configurations, showing remarkable robustness to initialization and inversion. It is compared to classical methods that process the deconvolution and separation separately; these tests demonstrate the advantage of performing the deconvolution and separation in a single pass.