Adaptive Image Research Articles

ZnO Nanowire Cold Cathode Hemispherical X‐Ray Sources

AbstractCurved or spherical X‐ray sources are significant for use in intraoperative radiotherapy, adaptive static medical imaging, and high‐throughput industrial inspection, but they are hard to achieve using traditional thermionic cathode point electron sources. In this study, copper (Cu)‐doped zinc oxide (ZnO) nanowires grown on a brass substrate with a designed shape are proposed to achieve cold cathode hemispherical X‐ray sources. The strain‐driven solid–liquid growth model of Cu‐doped ZnO nanowires is proposed, and the oxidation temperature‐dependent and time‐dependent growth characteristics are investigated to optimize the morphologies of ZnO nanowire cold cathodes with a typical turn‐on field of 7.36 MV m−1, a maximum current of 12.54 mA (4.93 mA cm−2) and a uniform field emission image with an area of 2.54 cm2. Hemispherical X‐ray sources formed by Cu‐doped ZnO nanowire field emitters grown on spherical brass alloy and an Al thin film transmission anode target deposited on a hemispherical quartz glass are successfully fabricated, achieving an operating voltage of 39 kV, a dose rate of 240 µGyair s−1 and a projection X‐ray imaging resolution of 2.8 lp mm−1, demonstrating their promising use in a variety of applications.

Adaptive Wireless Image Transmission Transformer Architecture for Image Transmission and Reconstruction

The advancement of 6G (6th Generation Mobile Networks) communication technology has posed challenges for traditional communication network architectures in meeting the demands for communication efficiency and quality. Semantic communication technology, characterized by its “understand before transmit” approach, has emerged as a pivotal technology driving the progress of 6G due to its ability to enhance communication efficiency and quality. The Wireless Image Transmission Transformer (WITT) model, which operates as a semantic communication system leveraging vision transformer technology for the transmission of semantic images, has shown efficacy in transmitting input images through processes of feature extraction and channel adaptation. This study introduces an advanced channel adaptive module that is informed by deep learning methodologies and the adaptive modulation principles of the Variational Information Bottleneck (VIB). This innovation enhances the original WITT model, resulting in the development of the Adaptive Wireless Image Transmission Transformer (ADWITT) architecture. Comprehensive experimental results have unequivocally shown that the transmission performance of the ADWITT architecture substantially surpasses that of the conventional WITT (Wavelet Image Transmission Technique) model, particularly in scenarios characterized by harsh and detrimental channel conditions. These findings underscore the robustness and adaptability of the ADWITT approach, which is poised to improve the field of image transmission by offering superior performance and resilience in environments where traditional methods falter.

Domain adaptive multi-frequency underwater image enhancement network

Domain adaptive multi-frequency underwater image enhancement network

The possibilities of using adaptive optics in modern ophthalmology

Until recently, the assessment of individual retinal cells was possible only with the help of histological examination, since such retinal imaging methods as scanning laser ophthalmoscopy and optical coherence tomography had low resolution to obtain images of structures at the cellular level, which was mainly due to aberrations caused by the optics of the eye. Adaptive optics technology has improved the performance of optical systems by correcting optical wavefront aberrations. Adaptive optics allows noninvasively visualizing the retina at the microscopic level in vivo, providing the opportunity to analyze individual structures such as photoreceptors, blood vessels, nerve fibers, ganglion cells and a lattice plate. Adaptive optics imaging in patients with diabetic retinopathy makes it possible to accurately determine the spatial distribution of cones, a decrease in which is associated with the presence of diabetic retinopathy and an increase in the severity of the disease. The detection of differences in cone distribution density between the control group and patients with diabetes mellitus without clinical signs of diabetic retinopathy may contribute to its early diagnosis, as well as a deeper understanding of the consequences of changes in the photoreceptor apparatus. Adaptive optics imaging methods are able to identify disorders of photoreceptor cells and assess the degree of progression of age-related macular degeneration, which definitely expands diagnostic capabilities at the early stages of its detection. Assessment of the condition of nerve fiber bundles through the use of Adaptive optics helps to identify changes associated with glaucoma, and also provides the ability to visualize details that cannot be evaluated using optical coherence tomography. Adaptive optics imaging allows you to directly measure the wall of retinal vessels and the diameter of their lumen. The ratio of wall thickness to vessel lumen and the cross-sectional area of the vessel wall directly reflect the remodeling process and can be used for the purpose of early diagnosis and monitoring of hypertension.

Underwater image restoration via spatially adaptive polarization imaging and color correction

Polarization imaging is extensively employed in underwater image restoration owing to its effectiveness in eliminating backscattered light. However, the existing polarization-based imaging methods rely on the strong assumption that the degrees of polarization (DoPs) of the target and backscattered light remain constant. Additionally, these methods ignore wavelength-specific absorption phenomena. To address these challenges, we propose an underwater image restoration method via spatially adaptive polarization imaging and color correction. First, based on optimal polarization difference images, we propose a method for calculating the spatial DoP of the target. In this method, the polarization characteristics of the target and background are fully exploited, and a scoring function is designed to achieve an optimal differential image. Second, we propose an adaptive local optimization method to estimate the spatial DoP of backscattering, which involves dividing the image into multiple local regions, and then employing improved particle swarm optimization (IPSO) algorithms to obtain the optimal value of DoP for each region. Finally, we introduce an adaptive compensation method based on the channel with minimal color absorption to correct color shifts during underwater polarization imaging. Extensive experiments demonstrate that our method exhibits superior generalization capability and outstanding restoration performance compared to existing methods.

Adaptive prototype few-shot image classification method based on feature pyramid

Few-shot learning aims to enable machines to recognize unseen novel classes using limited samples akin to human capabilities. Metric learning is a crucial approach to addressing this challenge, with its performance primarily dependent on the effectiveness of feature extraction and prototype computation. This article introduces an Adaptive Prototype few-shot image classification method based on Feature Pyramid (APFP). APFP employs a novel feature extraction method called FResNet, which builds upon the ResNet architecture and leverages a feature pyramid structure to retain finer details. In the 5-shot scenario, traditional methods for computing average prototypes exhibit limitations due to the typically diverse and uneven distribution of samples, where simple means may inadequately reflect such diversity. To address this issue, APFP proposes an Adaptive Prototype method (AP) that dynamically computes class prototypes of the support set based on the similarity between support set samples and query samples. Experimental results demonstrate that APFP achieves 67.98% and 85.32% accuracy in the 5-way 1-shot and 5-way 5-shot scenarios on the MiniImageNet dataset, respectively, and 84.02% and 94.44% accuracy on the CUB dataset. These results indicate that the proposed APFP method addresses the few-shot learning problem.

Deep Joint Source-Channel Coding for Adaptive Image Transmission Over MIMO Channels

Deep Joint Source-Channel Coding for Adaptive Image Transmission Over MIMO Channels

Wireless Adaptive Image Transmission Over OFDM Channels Based on Entropy Model

Wireless Adaptive Image Transmission Over OFDM Channels Based on Entropy Model

Application of high-density 2D receiver coil arrays for improved SNR in prostate MRI.

To study if adaptive image receive (AIR) receiver coil elements can be configured into a 2D array with high (>45% by diameter) element-to-element overlap, allowing improved SNR at depth (0.7-1.5× element diameter) versus conventional (20%) overlap. An anterior array composed of twenty 10-cm diameter elements with 45% overlap arranged into a 4 × 5 grid and a similar 3 × 7 twenty-one-element posterior array were constructed. SNR and g-factor were measured in a pelvic phantom using the new high-density (HD) arrays (41 total elements) and compared to vendor AIR-based arrays (30 total elements) with conventional overlap. T2-weighted fast-spin-echo (T2SE) images acquired using both arrays were compared in 20 subjects. SNR was estimated in vivo. Results were compared blindly by three uroradiologists using a five-point scale. Images using the HD arrays were also compared to a set of images acquired over a range of acceleration factors (R = 2.0, 2.5, 3.0) with the conventional arrays. SNR within the phantom was on average 15% higher for R = 1.0, 1.5, and 2.0 using the HD arrays. Across the 20 subjects SNR within the prostate was 11% higher and assessed radiologically as significantly higher (p < 0.001) for the HD versus conventional arrays. At all acceleration factors the new HD arrays outperformed the conventional arrays (p ≤ 0.01), allowing increased R for similar SNR. AIR elements can be configured into 2D arrays with high (45%) element-to-element overlap, consistently providing increased SNR at depth versus arrays with conventional (20%) overlap. The SNR improvement allows increased acceleration in T2SE prostate MRI.

The radius distribution of M dwarf-hosted planets and its evolution

Abstract M dwarf stars are the most promising hosts for detection and characterization of small and potentially habitable planets, and provide leverage relative to solar-type stars to test models of planet formation and evolution. Using Gaia astrometry, adaptive optics imaging, and calibrated gyrochronologic relations to estimate stellar properties and filter binaries we refined the radii of 117 Kepler Objects of Interest (confirmed or candidate planets) transiting 74 single late K- and early M-type stars, and assigned stellar rotation-based ages to 113 of these. We constructed the radius distribution of 115 small (&amp;lt;4R⊕) planets and assessed its evolution. As for solar-type stars, the inferred distribution contains distinct populations of ‘super-Earths’ (at ∼1.3R⊕) and ‘sub-Neptunes’ (at ∼2.2 R⊕) separated by a gap or ‘valley’ at ≈1.7R⊕that has a period dependence that is significantly weaker (power law index of -0.03$^{+0.01}_{-0.03}$) than for solar-type stars. Sub-Neptunes are largely absent at short periods (&amp;lt;2 days) and high irradiance, a feature analogous to the ‘Neptune desert’ observed around solar-type stars. The relative number of sub-Neptunes to super-Earths declines between the younger and older halves of the sample (median age 3.86 Gyr), although the formal significance is low (p = 0.08) because of the small sample size. The decline in sub-Neptunes appears to be more pronounced on wider orbits and low stellar irradiance. This is not due to detection bias and suggests a role for H2O as steam in inflating the radii of sub-Neptunes and/or regulating the escape of H/He from them.

Achieving the Best Symmetry by Finding the Optimal Clustering Filters for Specific Lighting Conditions

This article explores the efficiency of various clustering methods for image segmentation under different luminosity conditions. Image segmentation plays a crucial role in computer vision applications, and clustering algorithms are commonly used for this purpose. The search for an adaptive clustering mechanism aims to ensure the maximum symmetry of real objects with objects/segments in their digital representations. However, clustering method performances can fluctuate with varying lighting conditions during image capture. Therefore, we assess the performance of several clustering algorithms—including K-Means, K-Medoids, Fuzzy C-Means, Possibilistic C-Means, Gustafson–Kessel, Entropy-based Fuzzy, Ridler–Calvard, Kohonen Self-Organizing Maps and MeanShift—across images captured under different illumination conditions. Additionally, we develop an adaptive image segmentation system utilizing empirical data. Conducted experiments highlight varied performances among clustering methods under different luminosity conditions. This research enhances a better understanding of luminosity’s impact on image segmentation and aids the method selection for diverse lighting scenarios.

Towards adaptable synchrotron image restoration pipeline

Towards adaptable synchrotron image restoration pipeline

A Pilot Study from A Course-Based Undergraduate Research Experience for Online Degree-Seeking Astronomy Students

Research-based active learning approaches are critical for the teaching and learning of undergraduate STEM majors. Course-based undergraduate research experiences (CUREs) are becoming more commonplace in traditional, in-person academic environments, but have only just started to be utilized in online education. Online education has been shown to create accessible pathways to knowledge for individuals from nontraditional student backgrounds, and increasing the diversity of STEM fields has been identified as a priority for future generations of scientists and engineers. We developed and instructed a rigorous, six-week curriculum on the topic of observational astronomy, dedicated to educating second year online astronomy students in practices and techniques for astronomical research. Throughout the course, the students learned about telescopes, the atmosphere, filter systems, adaptive optics systems, astronomical catalogs, and image viewing/processing tools. We developed a survey informed by previous research validated assessments aimed to evaluate course feedback, course impact, student self-efficacy, student science identity and community values, and student sense of belonging. The survey was administered at the conclusion of the course to all eleven students yielding eight total responses. Although preliminary, the results of our analysis indicate that students’ confidence in utilizing the tools and skills taught in the course was significant. Students also felt a great sense of belonging to the astronomy community and increased confidence in conducting astronomical research in the future.

A three-stage framework for accurate detection of high-speed train body paint film defects

Detecting paint film defects on high-speed train (HST) body is a crucial step towards zero-defect manufacturing (ZDM). The effectiveness of defect detection in industrial environments, however, is significantly impacted by factors such as high reflection noise, weak defect features, small defect size, and various defect scales, resulting in unsatisfactory detection accuracy. To address these challenges, this paper proposes a technical framework for the accurate detection of paint film defects on HST body, encompassing three stages. A reflection detection removal method that takes into account the reflection transition region as well as the preservation of defect features is at first used to reduce reflection noise interference. Then a lightness-weighted adaptive image enhancement algorithm based on the fractional order differentiation is utilized to enhance the features of paint film defects while avoiding the introduction of reflection noise. Finally, an improved YOLOv5 algorithm, incorporating attention mechanism feature extraction and multi-scale feature fusion, is employed to detect and classify paint film defects. Experimental results demonstrate that the proposed framework effectively reduces the reflection in paint film images, and enhances the contrast between paint film defects and the background, with a mean average precision (mAP) for defect detection reaching up to 90.13%. This work serves as a valuable reference for the automated detection of defects arising in the painting process of HST body.

Incorporating patient-specific information for the development of rectal tumor auto-segmentation models for online adaptive magnetic resonance Image-guided radiotherapy

Background and purposeIn online adaptive magnetic resonance image (MRI)-guided radiotherapy (MRIgRT), manual contouring of rectal tumors on daily images is labor-intensive and time-consuming. Automation of this task is complex due to substantial variation in tumor shape and location between patients. The aim of this work was to investigate different approaches of propagating patient-specific prior information to the online adaptive treatment fractions to improve deep-learning based auto-segmentation of rectal tumors. Materials and methods243 T2-weighted MRI scans of 49 rectal cancer patients treated on the 1.5T MR-Linear accelerator (MR-Linac) were utilized to train models to segment rectal tumors. As benchmark, an MRI_only auto-segmentation model was trained. Three approaches of including a patient-specific prior were studied: 1. include the segmentations of fraction 1 as extra input channel for the auto-segmentation of subsequent fractions, 2. fine-tuning of the MRI_only model to fraction 1 (PSF_1) and 3. fine-tuning of the MRI_only model on all earlier fractions (PSF_cumulative). Auto-segmentations were compared to the manual segmentation using geometric similarity metrics. Clinical impact was assessed by evaluating post-treatment target coverage. ResultsAll patient-specific methods outperformed the MRI_only segmentation approach. Median 95th percentile Hausdorff (95HD) were 22.0 (range: 6.1–76.6) mm for MRI_only segmentation, 9.9 (range: 2.5–38.2) mm for MRI+prior segmentation, 6.4 (range: 2.4–17.8) mm for PSF_1 and 4.8 (range: 1.7–26.9) mm for PSF_cumulative. PSF_cumulative was found to be superior to PSF_1 from fraction 4 onward (p = 0.014). ConclusionPatient-specific fine-tuning of automatically segmented rectal tumors, using images and segmentations from all previous fractions, yields superior quality compared to other auto-segmentation approaches.

89 Streamlining the acquisition and analysis of digital images for the assessment of horn fly abundance

Abstract Horn flies are one of the most prevalent ectoparasites on pasture raised cattle. Studies have shown reasonable evidence of a genetic basis for horn fly attraction in beef cattle. Current methods for assessing fly abundance-related phenotypes (e.g., subjective assessment and image-based counts) suffer from limited accuracy and logistic difficulties. Previous attempts to assess horn fly abundance using image-based methods were hindered by several factors including weather conditions, distance and angle between the image taker and the animal, and lighting during image acquisition. The aim of this study was to address these limitations through the development of practical guidance to optimize image acquisition and to develop an adaptive image analysis algorithm to enhance the accuracy of image-based assessment of fly abundance. Images of beef cattle on pasture over multiple horn fly seasons (late spring to early fall) were collected. For each animal, the best image (where the entire side of the animal was in view) was selected and cropped from the withers to the hooks and from the chest floor to the udder. For every image (n = 314), all the flies were manually counted using the ImageJ software. Several image enhancement and analysis techniques including adaptive thresholding, pixel region connection, and pixel classification were used. The images were then clustered into three quality classes based on quality metrics computed using several algorithms from the image processing toolbox in MATLAB (BRISQUE, NIQE, and PIQE). BRISQUE and NIQE use distortions of natural scene statistics to compute quality scores. PIQE uses image features and models of human perception to compute quality scores. Pearson correlation, mean squared error (MSE), and the coefficient of determination (R2) were used to evaluate the concordance between the manual (ground truth) and the image predicted counts. Across the different scenarios, the Pearson correlation and R2 ranged between 0.21 to 0.67 and 0.04 and 0.45, respectively (Table 1). When the images were first clustered in quality classes, all the assessment metrics showed a substantial increase (Table 2). In fact, the Pearson correlation ranged between 0.47 to 0.80 using the NIQE. When the images were classified as low or medium quality by BRISQUE, the correlation was greater (0.74 to 0.79) compared with NIQE (0.47 to 0.70) and PIQE (0.69 to 0.74). Similar patterns were observed for the other assessment criteria (MSE and R2). These results seem to indicate that NIQE, BRISQUE, or a combination of the two algorithms could be used to assess image quality and determine the appropriate combination of image parameters to maximize the predictive ability. The NIQE method could be used as a filter to detect low quality images that are unsuitable for counting and then BRISQUE could be used on the remaining images.

Anthropogenic and environmental risk factors of salmonid predation in a tidal freshwater delta

Abstract Water diversions that support agricultural and municipal use result in fish mortality through entrainment and impingement. Additionally, this infrastructure may attract both predators and prey fishes, thereby increasing predation rates and prey mortality near these anthropogenic contact points. The Sacramento–San Joaquin Delta (the Delta) in California's Central Valley is a tidal freshwater ecosystem that exports large volumes of water for municipal and agricultural use while at the same time providing valuable migratory and rearing habitat for imperilled fishes. Emigrating juvenile salmonids experience high mortality in the Delta, with predation by non‐native fishes contributing substantially. Therefore, this study had three main objectives. First, we determined if small water diversions aggregated piscivorous fishes like other similar structures in freshwater ecosystems. Second, we determined how small diversions may influence juvenile salmon predation risk in conjunction with other known predation risk factors (e.g. predator abundance, temperature and depth). Third, we assessed the predator assemblage, abundance and distribution to determine the likely predator composition in objectives one and two. Throughout the spring of 2021, we used ARIS (adaptive resolution imaging sonar; Sound Metrics) sonars to compare piscivore abundance at 30 water diversions in the north Delta to shorelines adjacent to diversions that did not contain these structures. We used predation event recorders (PERs) to assess the predation risk juvenile salmonids were exposed to, with linear distance (m) from diversions, and other predation risk factors in the north Delta. Finally, we used a boat electrofishing survey to determine the piscivore assemblage and compare spatial trends in black bass (Micropterus spp.) CPUE and relative abundance throughout these waterways. Piscivore abundance was greater near small water diversions than at adjacent shorelines and the predation risk of juvenile salmonids increased with diversion proximity. Additionally, predation risk increased with increasing piscivore abundance and decreasing water depth. The north Delta predator assemblage was dominated by black basses (Micropterus spp.), which likely drove the negative relationship of predation risk with water depth, given habitat requirements of these species. Furthermore, increasing smallmouth (Micropterus dolomieu) and spotted bass (Micropterus punctulatus) abundance in our northern study sites may have weakened temperature effects on predation, given metabolic requirements of these species. Our work demonstrated that small water diversions are likely to increase mortality of endangered salmonids, and that the north Delta predator assemblage was different than recorded by previous work in this system, changing predation risk factors. Although more work is needed to determine the population level impacts of diversions, the ubiquitous distribution of these structures warrants management solutions to reduce mortality from this source. These results indicate that in addition to entrainment and impingement, water diversions may increase mortality of small‐bodied fishes by attracting predators and elevating predation risk. Given the continual human demand for freshwater, predator–prey interactions should be considered along with entrainment and impingement when assessing intake infrastructure mitigation, especially when diversions co‐occur along migratory routes and essential habitat of imperilled fishes.

High-resolution SAR optoelectronic processor based on sensor-less adaptive optics

Studying phase error is central to synthetic aperture radar (SAR) research. Phase error due to the real motion status of the SAR platform and propagation effects can reduce the utility of high-resolution SAR images even with theoretical estimation-based phase error correction. Adaptive optics (AO) can be used to correct optical aberrations. This study proposes an advanced, high-resolution SAR optoelectronic processor by integrating conventional processors with sensor-less AO techniques. This processor provides accurate adaptive phase error correction capabilities. The processing results of SAR echo data demonstrate the effectiveness of the proposed system in adaptive phase error correction and imaging improvement.

Advanced petrographic thin section segmentation through deep learning-integrated adaptive GLFIF

In geological research, precise segmentation of sandstone thin sections is crucial for detailed subsurface material analysis. Traditional methods often fall short in accurately capturing the complexities of these samples. This study presents an innovative segmentation approach that integrates an adaptive Global and Local Fuzzy Image Fitting (GLFIF) algorithm with Otsu's thresholding, significantly enhancing segmentation accuracy and efficiency. Our method combines deep learning and traditional image processing techniques. The adaptive GLFIF algorithm, powered by deep learning, automates parameter tuning, thereby reducing manual intervention and improving precision. Unlike conventional methods that learn fixed parameters, our model dynamically adjusts the segmentation process to achieve accurate results. The dual-phase segmentation strategy effectively isolates small features and handles intricate boundaries, ensuring high-quality outcomes. Experimental results demonstrate that our approach improves segmentation accuracy by 11.2% (from 82.6% to 93.8%), the Jaccard index by 15.4% (from 76.8% to 92.2%), and the Dice coefficient by 9% (from 86.9% to 95.9%) compared to traditional methods. This technique bridges the gap between conventional image analysis and deep learning, combining precise segmentation with the automation and computational power of advanced algorithms. Our segmentation algorithm represents a significant advancement in automated petrographic thin section analysis. Traditional image processing methods, such as thresholding and level sets, excel in handling small objects and complex boundaries but require significant manual intervention and cannot achieve full automation. Recent deep learning methods, particularly semantic segmentation, offer end-to-end automation but struggle with small targets and intricate boundaries. Our approach effectively combines the strengths of both methodologies, providing a comprehensive and efficient solution for geological image analysis that ensures both high accuracy and full automation.

Biometry study of foveal isoplanatic patch variation for adaptive optics retinal imaging.

The change in ocular wavefront aberrations with visual angle determines the isoplanatic patch, defined as the largest field of view over which diffraction-limited retinal imaging can be achieved. Here, we study how the isoplanatic patch at the foveal center varies across 32 schematic eyes, each individualized with optical biometry estimates of corneal and crystalline lens surface topography, assuming a homogeneous refractive index for the crystalline lens. The foveal isoplanatic patches were calculated using real ray tracing through 2, 4, 6 and 8 mm pupil diameters for wavelengths of 400-1200 nm, simulating five adaptive optics (AO) strategies. Three of these strategies, used in flood illumination, point-scanning, and line-scanning ophthalmoscopes, apply the same wavefront correction across the entire field of view, resulting in almost identical isoplanatic patches. Two time-division multiplexing (TDM) strategies are proposed to increase the isoplanatic patch of AO scanning ophthalmoscopes through field-varying wavefront correction. Results revealed substantial variation in isoplanatic patch size across eyes (40-500%), indicating that the field of view in AO ophthalmoscopes should be adjusted for each eye. The median isoplanatic patch size decreases with increasing pupil diameter, coarsely following a power law. No statistically significant correlations were found between isoplanatic patch size and axial length. The foveal isoplanatic patch increases linearly with wavelength, primarily due to its wavelength-dependent definition (wavefront root-mean-squared, RMS <λ/14), rather than aberration chromatism. Additionally, ray tracing reveals that in strongly ametropic eyes, induced aberrations can result in wavefront RMS errors as large as λ/3 for an 8-mm pupil, with implications for wavefront sensing, open-loop ophthalmic AO, spectacle prescription and refractive surgery.