Imaging Algorithm Research Articles

Online evolution of a phased array for ultrasonic imaging by a novel adaptive data acquisition method

Ultrasonic imaging, using ultrasonic phased arrays, has an enormous impact in science, medicine and society and is a widely used modality in many application fields. The maximum amount of information which can be captured by an array is provided by the data acquisition method capturing the complete data set of signals from all possible combinations of ultrasonic generation and detection elements of a dense array. However, capturing this complete data set requires long data acquisition time, large number of array elements and transmit channels and produces a large volume of data. All these reasons make such data acquisition unfeasible due to the existing phased array technology or non-applicable to cases requiring fast measurement time. This paper introduces the concept of an adaptive data acquisition process, the Selective Matrix Capture (SMC), which can adapt, dynamically, to specific imaging requirements for efficient ultrasonic imaging. SMC is realised experimentally using Laser Induced Phased Arrays (LIPAs), that use lasers to generate and detect ultrasound. The flexibility and reconfigurability of LIPAs enable the evolution of the array configuration, on-the-fly. The SMC methodology consists of two stages: a stage for detecting and localising regions of interest, by means of iteratively synthesising a sparse array, and a second stage for array optimisation to the region of interest. The delay-and-sum is used as the imaging algorithm and the experimental results are compared to images produced using the complete generation-detection data set. It is shown that SMC, without a priori knowledge of the test sample, is able to achieve comparable results, while preforming ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document}10 times faster data acquisition and achieving ∼\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sim$$\\end{document} 10 times reduction in data size.

Model-driven CT reconstruction algorithm for nano-resolution x-ray phase contrast imaging

Abstract The low-density imaging performance of a zone plate-based nano-resolution hard x-ray computed tomography (CT) system can be significantly improved by incorporating a grating-based Lau interferometer. Due to the diffraction, however, the acquired nano-resolution phase signal may suffer splitting problem, which impedes the direct reconstruction of phase contrast CT (nPCT) images. To overcome, a new model-driven nPCT image reconstruction algorithm is developed in this study. In it, the diffraction procedure is mathematically modeled into a matrix B , from which the projections without signal splitting can be generated invertedly. Furthermore, a penalized weighted least-square model with total variation (PWLS-TV) is employed to denoise these projections, from which nPCT images with high accuracy are directly reconstructed. Numerical experiments demonstrate that this new algorithm is able to work with phase projections having any splitting distances. Moreover, results also reveal that nPCT images of higher signal-to-noise-ratio (SNR) could be reconstructed from projections having larger splitting distances. In summary, a novel model-driven nPCT image reconstruction algorithm with high accuracy and robustness is verified for the Lau interferometer-based hard x-ray nano-resolution phase contrast imaging.

A Survey on Reversible Data Hiding for Uncompressed Images

Reversible data hiding (RDH) has developed various theories and algorithms since the early 1990s. The existing works involve a large amount of specialized knowledge, making it difficult for researchers, especially primary learners, to have a good grounding in the basic ideas. In this survey, we will review the mainstream RDH algorithms in uncompressed images and analyze their unique features to provide readers with an introduction to basic topics in RDH. We analyze the most effective RDH frameworks and their common extensions. The classic techniques, including lossless compression-based RDH, difference expansion, integer transform, histogram shifting, prediction-error expansion (PEE), and their extensions, will be reviewed first. Then, three currently popular investigated schemes, i.e., multiple histograms modification, pairwise PEE, and pixel-value-ordering, are presented in detail. Four aspects of these mainstream techniques are reviewed and analyzed, including the evolution of embedding frameworks, detailed technological features, extensions, and the current state of the art. Furthermore, we look forward the possible future research based on early-age motivations.

Crustal structure beneath Central Kamchatka inferred from ambient noise tomography

In this study, we investigated the crustal structure beneath the area of Central Kamchatka (Kamchatka Peninsula, Russian Far East) limited by latitudes 52.8 and 54.1 degrees. This area comprises parts of the active Eastern Volcanic Front and two mountain ridges Sredinny and Ganalsky, as well as several backarc volcanoes. We used the continuous data from the permanent stations and the temporary network installed in 2019–2020 to perform ambient noise tomography. We implemented a two-step tomographic inversion algorithm that initially generated the two-dimensional maps of group velocities for periods ranging from 1 s to 30 s, then found the optimal 1D model of shear wave velocities and derived the three-dimensional S-wave velocity distribution. In the resulting model, we observe a prominent low-velocity anomaly below the active volcanoes of Avacha and Koryaksky, which is traced to depths of ∼40 km and may be associated with a zone of heated rocks suitable for petrothermal energy extraction. We propose that this anomaly represents a common magma pathway through the crust feeding both volcanoes. Beneath another active Zhupanovsky volcano, we observe three low-velocity layers at depths of 2 km, 8 km and 20 km indicative of a multilevel magma feeding system. We believe our findings will further the understanding of the complex processes occurring within these active volcanoes, which pose a tangible hazard to the relatively populated Petropavlovsk-Kamchatsky urban district. Beneath the Sredinny Ridge we reveal a high-velocity pattern at shallow depths, likely associated with consolidated magmatic structures. The low-velocity in the lower crust is interpreted as a high-temperature zone conserved here since the time when this area hosted an active volcanic arc. Upon further exploration, this high-temperature zone could prove to be a prospective source of geothermal energy. Below the Ganalsky Ridge, a prominent high-velocity anomaly extending to a depth of ∼15 km can be attributed to the Precambrian to Carboniferous metamorphic rocks of predominantly mafic composition.

Multi-exposure high dynamic range imaging based on LSGAN

Deep learning-based multi-exposure HDR imaging methods achieve better performance than traditional methods in recovering image information and removing ghosting artifacts, but still produce images with severe ghosting artifacts when dealing with poorly exposed dynamic scenes. In this paper, we proposed a least square generative adversarial network (LSGAN) based HDR imaging algorithm for dynamic scenes. In the generator, we presented a global dilated residual dense block (GDRDB) as the basic component for feature fusion. The GDRDB is able to acquire both local and global information of the images, so that the network can both preserve image details and remove ghosting artifacts effectively. We use two stages to train the model. The first phase pre-trains the generator network by content loss, and the second phase adversarially trains the generators and discriminators by LSGAN loss. Extensive experiments on three benchmark datasets show that our approach outperforms most of state-of-the-art methods qualitatively and quantitatively.

Design of three-dimensional encryption algorithm for image based on improved 6th-order cellular neural network

The chaotic trajectory of the traditional natural chaotic system and the single chaotic system is relatively simple, and the keyspace is small, resulting in low security, low complexity, and poor resistance to attacks based on traditional chaotic design encryption algorithms. This article first constructed a 6th-order cellular neural network hyperchaotic system based on the theory of a 6th-order cellular neural network. Then the Chaotic Sequence Enhancer (CSE) is constructed by using infinite folding mapping. We use CSE to improve our cellular neural network. Compared with the old system, the new system has a larger Lyapunov exponent, higher PE complexity values, and 0–1 test results. Then based on the new chaotic system, a three-dimensional encryption algorithm was designed. The algorithm rearranges the pixels of the image into cubes and performs scrambling and diffusion operations based on the cubes. While making the encryption effect better, the information entropy of the ciphertext image is also above 7.99, and the correlation between adjacent pixels is less than 0.1. At the same time, the encryption algorithm can better resist various corrosion attacks, and the original image can still be better decrypted even when the ciphertext image has received a 25% loss. The result of the NPCR and UACI test is close to the expected values of 99.61% and 33.46%. The ciphertext image produced by the algorithm can pass the NIST SP800-22 statistical tests. The results of various tests and experiments show that our proposed encryption algorithm has high initial value sensitivity, resistance to differential attacks, and resistance to cropping attacks, and has good application prospects in the field of image security.

Iterative and mixed-spaces image gradient inversion attack in federated learning

As a distributed learning paradigm, federated learning is supposed to protect data privacy without exchanging users’ local data. Even so, the gradient inversion attack, in which the adversary can reconstruct the original data from shared training gradients, has been widely deemed as a severe threat. Nevertheless, most existing researches are confined to impractical assumptions and narrow range of applications. To mitigate these shortcomings, we propose a comprehensive framework for gradient inversion attack, with well-designed algorithms for image and label reconstruction. For image reconstruction, we fully utilize the generative image prior, which derives from wide-used generative models, to improve the reconstructed results, by additional means of iterative optimization on mixed spaces and gradient-free optimizer. For label reconstruction, we design an adaptive recovery algorithm regarding real data distribution, which can adjust previous attacks to more complex scenarios. Moreover, we incorporate a gradient approximation method to efficiently fit our attack for FedAvg scenario. We empirically verify our attack framework using benchmark datasets and ablation studies, considering loose assumptions and complicated circumstances. We hope this work can greatly reveal the necessity of privacy protection in federated learning, while urge more effective and robust defense mechanisms.

Sparse SAR Imaging Algorithm in Marine Environments Based on Memory-Augmented Deep Unfolding Network

Oceanic targets, including ripples, islands, vessels, and coastlines, display distinct sparse characteristics, rendering the ocean a significant arena for sparse Synthetic Aperture Radar (SAR) imaging rooted in sparse signal processing. Deep neural networks (DNNs), a current research emphasis, have, when integrated with sparse SAR, attracted notable attention for their exceptional imaging capabilities and high computational efficiency. Yet, the efficiency of traditional unfolding techniques is impeded by their architecturally inefficient design, which curtails their information transmission capacity and consequently detracts from the quality of reconstruction. This paper unveils a novel Memory-Augmented Deep Unfolding Network (MADUN) for SAR imaging in marine environments. Our methodology harnesses the synergies between deep learning and algorithmic unfolding, enhanced with a memory component, to elevate SAR imaging’s computational precision. At the heart of our investigation is the incorporation of High-Throughput Short-Term Memory (HSM) and Cross-Stage Long-Term Memory (CLM) within the MADUN framework, ensuring robust information flow across unfolding stages and solidifying the foundation for deep, long-term informational correlations. Our experimental results demonstrate that our strategy significantly surpasses existing methods in enhancing the reconstruction of sparse marine scenes.

A Comprehensive Analysis of Exploring the Efficacy of Machine Learning Algorithms in Text, Image, and Speech Analysis

Our study demonstrates a comprehensive investigation of multiple machine learning models based on text, image, and speech analysis. More specifically, concerning text analysis, we studied the application of such models as Recurrent Neural Networks, Gated Recurrent Units, and Bidirectional Encoder Representations from Transformers in classifying documents into pre-defined categories. The outcomes revealed that RNNs observed the highest precision, recall, F1 score, as well as the highest accuracy. Importantly, the models are well-suited to detect sequential dependencies and create semantic representations on the basis of textual data. With regard to image analysis, we found out that Convolutional Neural Networks were the best model. At the same time, VGG16 and GANs also demonstrated rather promising results suggesting that deep learning is paramount to extract significant data features. As far as speech analysis is concerned, we found out that CNNs are exceptional in terms of accuracy to recognize speech patterns in comparison with the other models. Simultaneously, LSTM also observed a high level of accuracy allowing to capture temporal dependencies in audio signals. In conclusion, the findings of our study suggest that it is exigent to identify an appropriate machine learning model depending on the task and the selected dataset. It is also crucial to understand the nature of each of the studied models to assess their applicability for a specific task. Moreover, our study might be valuable for other researchers given that it contributes to the development of the field of deep learning and, thus, promotes the emergence of new applications in different domains.

Classification of Mango Leaf Disease using Machine Learning to Enhance Yield Productivity

Fruits provide critical nourishment to the human body. Proper Care and upkeep are essential for the fruit to be healthy. Lack of maintenance, infections, spot, fungus all cause significant production and profit losses. Mango is a seasonal and famous fruit which is consumed all over the world. It is a delicate fruit that is susceptible to disease that reduce the quality as well as quantity. Manual illness or infection inspection is a time-consuming and labour-intensive technique that necessitates a large amount of resources and therefore it is inefficient. On the other hand, automatic inspection provides various advantages such as less time consuming, less labour and also the number of resources required are less. Image classification techniques and algorithms can be used to distinguish between infected and healthy mangoes, decreasing losses.

An airborne radar forward-looking imaging algorithm based on multi-scale U-shaped networks

ABSTRACT Radar forward-looking imaging has gained increasingly significance in diverse applications, including battlefield reconnaissance, target surveillance, and precision guidance. While Synthetic Aperture Radar techniques are widely employed to achieve high azimuth resolution, the domain of forward-looking imaging has its challenges. These challenges arise due to the minimal Doppler frequency changes in forward-looking areas and the symmetrical Doppler history about flight path. These constraints negatively impact the radar’s ability to accurately detect and image targets in forward-looking areas. Consequently, there has been a growing interest in the development of novel approaches to these problems. Due to the application of deep learning, image super-resolution methods based on convolutional neural networks (CNNs) have received extensive attention and demonstrated good performance. This avenue of research provides fresh insights into improving the azimuth resolution of radar imaging. In this letter, we propose a novel convolutional neural network, called MSUS-Net (Multi-scale U-shaped Network), for radar forward-looking imaging. It combines asymmetric feature fusion with a unique connection structure to replace traditional layers. Moreover, different from conventional image restoration networks that use content loss, we use the L1 distance in the frequency domain, restoring missing high-frequency details. Simulated and real radar data validate that this approach offers robust recovery and better imaging performance.

Identifying synergies between VLBI and STIX imaging

Context. Reconstructing an image from noisy, sparsely sampled Fourier data is an ill-posed inverse problem that occurs in a variety of subjects within science, including data analysis for Very Long Baseline Interferometry (VLBI) and the Spectrometer/Telescope for Imaging X-rays (STIX) with respect to solar observations. The need for high-resolution, high-fidelity imaging fosters the active development of a range of novel imaging algorithms in a variety of different algorithmic settings. However, despite these ongoing, parallel developments, such synergies remain unexplored. Aims. We study, for the first time, the synergies between the data analysis for the STIX instrument and VLBI. In particular, we compare the methodologies that have been developed in both fields and evaluate their potential. In this way, we identify key trends in the performance of several algorithmic ideas and draw recommendations for the future spending of resources in the study and implementation of novel imaging algorithms. Methods. To this end, we organized a semi-blind imaging challenge with data sets and source structures that are typical for sparse VLBI, specifically in the context of the Event Horizon Telescope (EHT) as well as STIX observations. We used 17 different algorithms from both communities, from six different imaging frameworks, in the challenge, making this work the largest scale code comparison for STIX and VLBI to date. Results. We identified strong synergies between the two communities, as proven by the success of the imaging methods proposed for STIX in imaging VLBI data sets and vice versa. Novel imaging methods outperform the standard CLEAN algorithm significantly in every test case. Improvements over the performance of CLEAN offer deeper updates to the inverse modeling pipeline necessary or, consequently, the possibility to replace inverse modeling with forward modeling. Entropy-based methods and Bayesian methods perform best on STIX data. The more complex imaging algorithms utilizing multiple regularization terms (recently proposed for VLBI) add little to no additional improvements for STIX. However, they do outperform the other methods on EHT data, which correspond to a larger number of angular scales. Conclusions. This work demonstrates the great synergy between the STIX and VLBI imaging efforts and the great potential for common developments. The comparison identifies key trends on the efficacy of specific algorithmic ideas for the VLBI and the STIX setting that may evolve into a roadmap for future developments.

A Decision-Making Algorithm for Robotic Breast Ultrasound High-Quality Imaging via Broad Reinforcement Learning From Demonstration

A Decision-Making Algorithm for Robotic Breast Ultrasound High-Quality Imaging via Broad Reinforcement Learning From Demonstration

A decomposition algorithm for streak camera data

We describe a novel reconstruction algorithm for time-resolved images obtained using a streak camera. This algorithm operates by decomposing a recorded image into a set of individual photoelectron-induced signals, thereby providing a powerful method for streak camera image reconstruction. This deconstruction allows for a standard statistical analysis of the resulting image. We demonstrate the effectiveness of this technique by analyzing the temporal spacing between the emitted fs-long laser pulse and its succeeding first, second, and third reflections within a thick glass captured by a streak image.

Synchrotron-source micro-x-ray computed tomography for examining butterfly eyes.

Comparative anatomy is an important tool for investigating evolutionary relationships among species, but the lack of scalable imaging tools and stains for rapidly mapping the microscale anatomies of related species poses a major impediment to using comparative anatomy approaches for identifying evolutionary adaptations. We describe a method using synchrotron source micro-x-ray computed tomography (syn-μXCT) combined with machine learning algorithms for high-throughput imaging of Lepidoptera (i.e., butterfly and moth) eyes. Our pipeline allows for imaging at rates of ~15 min/mm3 at 600 nm3 resolution. Image contrast is generated using standard electron microscopy labeling approaches (e.g., osmium tetroxide) that unbiasedly labels all cellular membranes in a species-independent manner thus removing any barrier to imaging any species of interest. To demonstrate the power of the method, we analyzed the 3D morphologies of butterfly crystalline cones, a part of the visual system associated with acuity and sensitivity and found significant variation within six butterfly individuals. Despite this variation, a classic measure of optimization, the ratio of interommatidial angle to resolving power of ommatidia, largely agrees with early work on eye geometry across species. We show that this method can successfully be used to determine compound eye organization and crystalline cone morphology. Our novel pipeline provides for fast, scalable visualization and analysis of eye anatomies that can be applied to any arthropod species, enabling new questions about evolutionary adaptations of compound eyes and beyond.

Optimized raw data selection for artifact reduction of breathing controlled four-dimensional sequence scanning

Background and purposeEven with most breathing-controlled four-dimensional computed tomography (4DCT) algorithms image artifacts caused by single significant longer breathing still occur, resulting in negative consequences for radiotherapy. Our study presents first phantom examinations of a new optimized raw data selection and binning algorithm, aiming to improve image quality and geometric accuracy without additional dose exposure. Materials and methodsTo validate the new approach, phantom measurements were performed to assess geometric accuracy (volume fidelity, root mean square error, Dice coefficient of volume overlap) for one- and three-dimensional tumor motion trajectories with and without considering motion hysteresis effects. Scans without significantly longer breathing cycles served as references. ResultsMedian volume deviations between optimized approach and reference of at maximum 1% were obtained considering all movements. In comparison, standard reconstruction yielded median deviations of 9%, 21% and 12% for one-dimensional, three-dimensional, and hysteresis motion, respectively. Measurements in one- and three-dimensional directions reached a median Dice coefficient of 0.970 ± 0.013 and 0.975 ± 0.012, respectively, but only 0.918 ± 0.075 for hysteresis motions averaged over all measurements for the optimized selection. However, for the standard reconstruction median Dice coefficients were 0.845 ± 0.200, 0.868 ± 0.205 and 0.915 ± 0.075 for one- and three-dimensional as well as hysteresis motions, respectively. Median root mean square errors for the optimized algorithm were 30 ± 16HU2 and 120 ± 90HU2 for three-dimensional and hysteresis motions, compared to 212 ± 145HU2 and 130 ± 131HU2 for the standard reconstruction. ConclusionsThe algorithm was proven to reduce 4DCT-related artifacts due to missing projection data without further dose exposure. An improvement in radiotherapy treatment planning due to better image quality can be expected.

Split Bregman quantum noise removal algorithm for 3D reconstruction of neutron computed tomography image

The low intensity of the neutron source for neutron computed tomography (CT) results in a long acquisition time for a single projection, which causes the neutron projection data to contain a large amount of quantum noise. Quantum noise will degrade the quality of neutron CT reconstruction images. Therefore, an efficient quantum noise removal algorithm must be used in CT reconstruction. In this paper, an efficient quantum noise removal algorithm for neutron CT 3D image reconstruction is proposed by analysing classical image processing algorithms and quantum image processing algorithms, which employs the maximum likelihood expectation maximization to reconstruct the image and split Bregman algorithm to solve for the total variation (MLEM-SBTV). Experimental results show that MLEM-SBTV performs well in removing quantum noise and reconstructing the detailed structure of images.

IMJENSE: Scan-Specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI.

Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.

Automated ultrasonic testing for near-surface flaws in CFRP

ABSTRACT In ultrasonic testing of Carbon Fiber Reinforced Polymers (CFRP), signals of near-surface flaws are often submerged in interface signals, resulting in blind spots for defect detection. To address this issue, this paper presents an autocorrelation imaging algorithm that combines Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA) with l 0 -norm sparse representation. Firstly, the ultrasonic signal can be modelled as a convolution process. By using MOMEDA, the sequence of reflected pulses in the ultrasonic signal is obtained. Then, the l 0 -norm sparse representation is utilised to enhance the temporal resolution of the sequence, successfully separating near-surface defect signals from interface signals. Finally, the processed data is input into the autocorrelation algorithm, achieving automated imaging of near-surface flaws. Simulation results demonstrate the efficacy of the algorithm in separating overlapping signals. Finally, experimental validation was conducted on flaws at three different depths. The algorithm presented in this paper is capable of identifying all near-surface flaws, with a defect size error rate consistently below 5%.

Distribution and Storage Characteristics of Soil Organic Carbon in Tidal Wetland of Dandou Sea, Guangxi

In order to study the distribution characteristics of soil organic carbon (SOC) and soil organic carbon storage (SOCS) among different wetland types in Dandou Sea tidal wetland in Guangxi, firstly, based on Sentinel–2 imaging and random forest algorithm, combined with the existing tidal wetland data, a 10 m resolution tidal wetland dataset in Guangxi from 2019 to 2023 was generated, covering mangroves, salt marshes and tidal flats. The results show that the overall accuracy of the recognition results is higher than 96%, and the Kappa coefficient is higher than 0.95, which indicates high accuracy. Subsequently, the distribution characteristics and influencing factors of SOC and SOCS in different habitats were analyzed. The results showed that the SOC content of mangroves and salt marshes was higher than that of tidal flats. The SOC content of mangrove, salt marshes and tidal flats in 0–60 cm soil layer was 5.30–10.42 g/kg, 7.60–9.84 g/kg, and 1.29–2.25 g/kg, respectively. The changes of SOCS were 12.41–26.48 t/ha, 19.58–24.15 t/ha, and 3.61–6.86 t/ha, respectively. With the increase of soil depth, the SOC and SOCS of mangroves decreased gradually, and the SOC and SOCS of salt marshes increased gradually, and SOC and SOCS were mainly affected by soil bulk density (BD), soil moisture content (MC) and pH.