Clear Edges Research Articles

An improved subpixel measurement method for piezoelectric ceramic driving characteristics based on particle filter

Microscopic vision displacement calculation is crucial for its high precision and non-contact nature in measuring piezoelectric ceramic displacement. However, the inefficient global search limits its effectiveness. This paper proposes an improved sub-pixel algorithm (GKF-PFBM) based on particle filtering. Firstly, particle filtering (PF) is combined with block matching (BM) to enhance matching efficiency and accuracy by replacing global search with particle state prediction and update. Then, subpixel interpolation using a Gaussian kernel function (GKF) is better adapted to nonlinear variations, handling high-frequency variations while preserving clear edges, thereby improving interpolation accuracy. Finally, a high-precision experimental platform is used to measure the driving characteristics of piezoelectric ceramics. Experimental results show that the mean errors of the GKF-PFBM algorithm and the bilinear interpolation algorithm (BI-BM) are 0.0032pixels and 0.1269pixels, respectively. The average hysteresis displacement error was measured to be approximately 12 nm by this method, verifying its precise non-contact measurement capability.

LapUNet: a novel approach to monocular depth estimation using dynamic laplacian residual U-shape networks

Monocular depth estimation is an important but challenging task. Although the performance has been improved by adopting various encoder-decoder architectures, the estimated depth maps lack structure details and clear edges due to simple repeated upsampling. To solve this problem, this paper presents the novel LapUNet (Laplacian U-shape networks), in which the encoder adopts ResNeXt101, and the decoder is constructed with the novel DLRU (dynamic Laplacian residual U-shape) module. The DLRU module based on the U-shape structure can supplement high-frequency features by fusing dynamic Laplacian residual into the process of upsampling, and the residual is dynamically learnable due to the addition of convolutional operation. Also, the ASPP (atrous spatial pyramid pooling) module is introduced to capture image context at multiple scales though multiple parallel atrous convolutional layers, and the depth map fusion module is used for combining high and low frequency features from depth maps with different spatial resolution. Experiments demonstrate that the proposed model with moderate model size is superior to other previous competitors on the KITTI and NYU Depth V2 datasets. Furthermore, 3D reconstruction and target ranging by utilizing the estimated depth maps prove the effectiveness of our proposed method.

Conjugated Polymer-Based Photo-Crosslinker for Efficient Photo-Patterning of Polymer Semiconductors.

Photo-patterning of polymer semiconductors using photo-crosslinkers has shown potential for organic circuit fabrication via solution processing techniques. However, the performance of patterning, including resolution (R), UV light exposure dose, sensitivity (S), and contrast (γ), remains unsatisfactory. In this study, a novel conjugated polymer based photo-crosslinker (PN3, Figure 1a) is reported for the first time, which entails phenyl-substituted azide groups in its side chains. Due to the potential π-π interactions between the conjugated backbone of PN3 and those of polymer semiconductors, PN3 exhibits superior miscibility with polymer semiconductors compared to the commonly used small molecule photo-crosslinker 4Bx (Figure 1a). Consequently, photo-patterning of polymer semiconductors with PN3 demonstrates improved performance with much lower UV light exposure dose, higher S and higher γ compared to 4Bx. By utilizing electron beam lithography, patterned arrays of polymer semiconductors with resolutions down to 500nm and clearer edges are successfully fabricated using PN3. Furthermore, patterned arrays of PDPP4T, the p-type semiconductor (Figure 1b), after being doped, can function as source-drain electrodes for fabricating field-effect transistors (FETs) with comparable charge mobility and significantly lower sub-threshold swing value compared to those with gold electrodes.

A Hybrid Segmentation Algorithm for Rheumatoid Arthritis Diagnosis Using X-ray Images

Rheumatoid Arthritis (RA) is a chronic autoimmune illness that occurs in the joints, resulting in inflammation, pain, and stiffness. X-ray examination is one of the most common diagnostic procedures for RA, but manual X-ray image analysis has limitations because it is a time-consuming procedure and is prone to errors. A specific algorithm aims to a lay stable and accurate segmenting of carpal bones from hand bone images, which is vitally important for identifying rheumatoid arthritis. The algorithm demonstrates several stages, starting with Carpal bone Region of Interest (CROI) specification, dynamic thresholding, and Gray Level Co-occurrence Matrix (GLCM) application for texture analysis. To get the clear edges of the image, the component is first converted to the greyscale function and thresholding is carried out to separate the hand from the background. The pad region is identified to obtain the contours of it, and the CROI is defined by the bounding box of the largest contour. The threshold value used in the CROI method is given a dynamic feature that can separate the carpal bones from the surrounding tissue. Then the GLCM texture analysis is carried out, calculating the number of pixel neighbors, with the specific intensity and neighbor relations of the pixels. The resulting feature matrix is then employed to extract features such as contrast and energy, which are later used to categorize the images of the affected carpal bone into inflamed and normal. The proposed technique is tested on a rheumatoid arthritis image dataset, and the results show its contribution to diagnosis of the disease. The algorithm efficiently divides carpal bones and extracts the signature parameters that are critical for correct classification of the inflammation in the cartilage images.

Electron microscopy of stable electrophoretic fractions of natural humic acids – the key to the understanding of their structural organization

Transmission electron microscopy (TEM) with contrast staining by uranyl acetate solution was used to study morphological differences between soil humic acids (HAs) and their A, B and C + D fractions obtained using coupling preparative low-pressure size exclusion chromatography and analytical polyacrylamide gel electrophoresis. The electrophoretic mobility of fractions varied in order C + D B A. The distribution of various morphological elements between fractions showed that large structures such as vesicle-like formations 70–150 nm long and 30–80 nm wide with clear edges were found exclusively in fraction A and occupied ~55% of the TEM image area. On the other hand, long fibrils with a length of 60–100 nm, a width of 4–6 nm and a thickness of 2–3 nm, as well as their bundles with a length of 150 nm and a diameter of 30–70 nm were identified only in the C + D fraction and occupied ~59 % area of TEM images. Smaller morphological elements such as point particles with a diameter of 2–3 nm, ring particles with a diameter of 4–6 nm, worm-shaped short particles with a length of 20–30 nm, and spheroids with a diameter of 10– 30 nm were observed in all samples, but in varying quantities. Significant morphological differences between the fractions can be explained by their composition, previously established by using a few physico-chemical methods. The ratio Car(165–108 ppm)/Calk(108–0 ppm), or aromaticity index, calculated from 13C-NMR, could be one of the indicators of the various morphological structures formation. The obtained TEM results clearly confirm the supramolecular organization of soil HAs.

SLN and chitosan nano-delivery systems for antibacterial effect of black seed (Nigella sativa) oil against S. aureus

ABSTRACT Staphylococcus aureus with current universal importance represents a main carrier of emerging antimicrobial resistance determinatives of global health concerns that have developed drug resistance mechanisms to the various available antibiotics. On the other hand, due to the antimicrobial potential of Nigella Sativa oil (NSO), it was hypothesized that incorporation of nano-carriers (NS-SLN and NS-chitosan (CH) nanoparticles) can enhance its antibacterial effects. This study evaluated the physico-chemical and antibacterial characteristics of NS-SLN and NS-CH. TEM images revealed a round shape with clear edges for both nanoparticles, and the average sizes were reported to be 196.4 and 446.6 nm for NS-SLN and NS-CH, respectively. The zeta potential and encapsulation efficiency were −28.9 and 59.4 mV and 73.22% and 88% for NS-SLN and NS-CH, respectively. The Minimum Inhibitory Concentrations for NSO, NS-SLN, and NS-CH against S. aureus were 480, 200, and 80 µg/mL, respectively. The results confirm significantly stronger antibacterial influences of NSO when loaded into chitosan nanoparticles as a potential candidate for nano-delivery of antimicrobial agents.

Features of the chemical composition of fine suspended particles in the atmospheric air of residential and industrial zones of the city of Sibay, Republic of Bashkortostan

Introduction. Atmospheric particulate matter as a negative environmental factor can be a significant hazard depending on their size, morphometric and physicochemical characteristics. The purpose of the study. To investigate the elemental composition of finely dispersed suspended particles in the atmospheric air of the industrial zones of the mining center of the Bashkir Trans-Urals - the city of Sibay. Materials and methods. Air sampling was carried out in the industrial area of ​​Sibay using an AVA-3-240/180-01 automatic three-channel air aspirator with AFA-VP-20 filters. Microscopy of samples and determination of the elemental composition of dust emissions were carried out at the Interdisciplinary Center “Analytical Microscopy” of the Kazan Federal University (Kazan) on a universal analytical complex for scanning field emission electron microscopy Merlin (Carl Zeiss). Results. On electron micrographs, there were identified particles of various sizes, mostly round in shape with clear edges, located solitary. In the automatic mode of processing the spectra, the peaks of the elements in the spectrum were automatically recognized and identified. In addition to carbon and oxygen, the calcium, iron, silicon, potassium, aluminium, copper, sulphur, sodium and magnesium are main chemical constituents of particulate matter encountered at all sampling points. Zinc was present in dust samples at three points, scandium, titanium, cobalt, barium, and manganese – only at one point. The possibility of the relation between the content of fine particles in the air and the increased incidence of cardiovascular, bronchopulmonary diseases, including asthma, in the population of Sibay is discussed. Limitations. The study of the elemental composition of fine dust in the city of Sibay was carried out using atmospheric air samples taken at 5 points located in residential and industrial areas. Conclusion. The increased content of fine particles in the atmospheric air of the city of Sibay increases the risks of respiratory and cardiovascular diseases, as well as other health abnormalities, in the population permanently residing near industrial zones. The obtained data on the parameters of dust particles are the basis for assessing the share contribution of industrial enterprises to air pollution and making management decisions to improve the environmental situation in the industrial center of the mining region.

Super-resolution of digital rock images with hybrid attention multi-branch neural network

High-resolution digital rock images are vital in studying microstructure and fluid flow characterization of oil and gas reservoirs. Computed tomography (CT) is currently the primary tool to acquire digital rock images because of its non-destructiveness and three-dimensional imaging capability. However, the restriction of imaging capability of CT sets a compromise between image resolution and field of view (FOV). The Hybrid Attention Multi-branch Super-Resolution Network (HAMSR) proposed in this study aims to remedy this deficiency. HAMSR employs a limited discrete distribution to capture all possible high-order information and generate reliable high-resolution images. The network is built to prioritize the recovery of pores, cracks, and textures in digital rock images by introducing channel and spatial attention mechanisms. The structure together with modules of HAMSR have been designed and optimized to yield superior performance with fewer parameters and less training time. HAMSR and several contemporary advanced models are trained on the DeepRock-SR 2D dataset which contains lots of sandstone and carbonate images. It is evident that HAMSR-generated images have minimal noise, clearer edges, and more micropores. Quantitative calculations show that compared to traditional bicubic interpolation, HAMSR acquires a 2.669 dB and 1.376 dB increase in peak signal-to-noise ratio (PSNR) respectively on the test sets (27%–38% reduction in relative error). Furthermore, the high-resolution (HR) images reconstructed by HAMSR are generally consistent with real HR images concerning statistical characteristics such as porosity, pore size distribution, shape factor distribution, and two-point correlation function. This work provides a new super-resolution model to generate high-quality digital rock images for further analysis.

MORPHOLOGY AND EVOLUTION OF ALVEOLAR WEATHERING CAVITIES ON SANDSTONE TORS OF THE UKRAINIAN BESKIDS

The paper systematizes morphological forms of alveolar weathering cavities and presents patterns of their evolution. We have studied the forms of tafoni (cavities 2–10 cm in size), which are found in the crags in the Ukrainian Beskydy. The factors that caused the formation of tafoni in our latitudes are humidity and the inherent specificity of selective weathering in sandstones due to structural and textural features formed during the formation of sediments. In winter periods, the role of frost weathering increases. The crags are composed of sandstones of the Yamna suite of the Palaeocene of the Lower Paleogene age. The lithological composition of the sandstones is represented by quartz and feldspar, which allows us to classify them as typical feldspar-quartz sandstones. The cement is clay-siliceous, sometimes with chlorite, of the basal or contact cementation type. In research region tafoni are distributed on rock surfaces in two ways: locally in small areas or covering large areas e.g. whole crag surface of particular aspect. In the first case, the forms are located in small groups of 10–30 pieces in separate parts of a tor wall. In the second case, they occupy the entire plane of the tor surface or half of the surface of particular exposure. Local groups of tafoni can be divided into three shape varieties: 1) vertical bands, 2) horizontal bands, and 3) lenticular bands. Tafoni concentrations that occupy the entire one plane of the tor can be located on it: a) chaotically, b) in a chain-like manner. The following shapes of particular cavities can be distinguished in the Ukrainian Beskydy: 1) rounded, 2) ellipsoid, 3) vertically elongated, and 4) subtriangular. In the Beskyds, the largest length of ellipsoidal cavities is 20–30 cm, the diameter of rounded cavities reaches 10 cm, and the greatest depth is 15 cm. Investigating the morphology of tafoni in the Beskydy, we distinguished the following stages of their evolution: emergence – deepening – expansion – merging – degradation – re-emergence. On the walls of the Beskydy tors, one can observe tafonic forms at various stages of evolution. We identified morpho-evolutionary varieties of tafoni: A) with all four clear edges, B) with three clear and one leveled wall, C) with all unclear walls. The confinement of cavities to slope exposures was also investigated. Cavities in the Carpathians develop more actively on walls of warm exposures than on cold ones. Tafoni forms on tors, their morphology, evolution and formation factors can be the subject of expert interpretations during geotourism excursions. Key words: cavities, tafoni; morphology, evolution, alveolar weathering; tors; Beskydy, Ukrainian Carpathians.

GAN‐Based Multi‐Decomposition Photo Cartoonization

AbstractBackgroundCartoon images play a vital role in film production, scientific and educational animation, video games, and other fields, and are one of the key visual expressions of artistic creation. However, since hand‐crafted cartoon images often require a great deal of time and effort on the part of professional artists, it is necessary to be able to automatically transform real‐world images into different styles of cartoon images. Although cartoon images vary from artist to artist, cartoon images generally have the unique characteristics of being highly simplified and abstract, with clear edges, smooth color shading, and relatively simple textures. However, existing image cartoonization methods tend to create a number of problems when performing style transfer, which mainly include: (1) the resulting generated images do not have obvious cartoon‐style textures; and (2) the generated images are prone to structural confusion, color artifacts, and loss of the original image content. Therefore, it is also a great challenge in the field of image cartoonization to be able to make a good balance between style transfer and content keeping.MethodsIn this paper, we propose a GAN‐based multi‐attention mechanism for image cartoonization to address the above issues. The method combines the residual block used to extract deep network features in the generator with the attention mechanism, and further strengthens the perceptual ability of the generative model to cartoon images through the adaptive feature correction of the attention module to improve the cartoon features of the generated images. At the same time, we also introduce the attention mechanism in the convolution block of the discriminator, which is used to further reduce the image visual quality problem caused by the style transfer process. By introducing the attention mechanism into the generator and discriminator models of the generative adversarial network, our method enables the generated images to have obvious cartoon‐style features while effectively improving the image's visual quality.ResultsA large number of quantitative, qualitative, and ablation experiments are conducted to demonstrate the advantages of our method in the field of image cartoonization and the role of each module in the method.

A cardiac MRI motion artifact reduction method based on edge enhancement network

Cardiac magnetic resonance imaging (MRI) usually requires a long acquisition time. The movement of the patients during MRI acquisition will produce image artifacts. Previous studies have shown that clear MR image texture edges are of great significance for pathological diagnosis. In this paper, a motion artifact reduction method for cardiac MRI based on edge enhancement network is proposed. Firstly, the four-plane normal vector adaptive fractional differential mask is applied to extract the edge features of blurred images. The four-plane normal vector method can reduce the noise information in the edge feature maps. The adaptive fractional order is selected according to the normal mean gradient and the local Gaussian curvature entropy of the images. Secondly, the extracted edge feature maps and blurred images are input into the de-artifact network. In this network, the edge fusion feature extraction network and the edge fusion transformer network are specially designed. The former combines the edge feature maps with the fuzzy feature maps to extract the edge feature information. The latter combines the edge attention network and the fuzzy attention network, which can focus on the blurred image edges. Finally, extensive experiments show that the proposed method can obtain higher peak signal-to-noise ratio and structural similarity index measure compared to state-of-art methods. The de-artifact images have clear texture edges.

Adaptive weighted total variation expansion and Gaussian curvature guided low-dose CT image denoising network

The denoising task of low-dose CT images is a highly complex and uncertain inverse problem. Previous studies have primarily relied on convolutional neural network to reduce noise by learning the mapping from LDCT images to normal dose CT images. However, simply increasing the network depth alone is not an optimal choice due to the limited performance improvement and significant computational cost. In contrast, integrating prior knowledge of images with a model to assist in image reconstruction is a more efficient approach. This study proposes a new framework for denoising LDCT images, named Noise-Optimized Edge Feature Guided Network (NEFGN). The task of NEFGN is to integrate the noise optimization model of adaptive weighted total variation expansion, the edge detection model guided by Gaussian curvature, and image reconstruction into an end-to-end CNN framework. In order to achieve this goal, the noise optimization model is first constructed by learning the parameters in the adaptive weighted total variation regularization model to approximate the noise level in the NDCT image. The edge detection network is constructed using Gaussian curvature, predicting clear edges directly from the noise image. Finally, under the guidance of the noise optimization model and the edge detail model, NEFGN is more capable of suppressing artifact noise, demonstrating good accuracy and robustness, and can restore finer details. Numerous experimental studies demonstrate that the NEFGN denoising framework effectively restores the structure of LDCT images with limited image details and outperforms other methods in terms of performance.

Combined positron emission tomography‐guided modified black phosphorus nanosheet‐based photothermal therapy and anti programmed cell death protein ligand 1 therapy

AbstractBackgroundPatients with cold tumors gain limited benefits from immune checkpoint blockade (ICB) therapy owing to low programmed cell death protein ligand 1 (PD‐L1) expression and minimal immune cell infiltration. Mild photothermal therapy (PTT) using black phosphorus nanosheets (BPNSs) is a promising approach to enhance the efficacy of ICB therapy. However, to ensure that BPNS‐based PTT‐enhanced ICB therapy is clinically adaptable, a noninvasive, bedside‐accessible imaging tool capable of monitoring the status of PD‐L1 is imperative. We demonstrated that positron emission tomography (PET) using [64Cu]HKP2202 precisely delineated PD‐L1 expression in tumors receiving PTT.MethodsBPNSs were modified with polyethylene glycol to prepare BPNS@PEG, which were then characterized. MC38 cells and tumor allografts were treated with BPNS@PEG followed by 808 nm near‐infrared light exposure. PET using [64Cu]HKP2202 was performed to monitor PD‐L1 expression in vivo. We also evaluated whether the efficacy of ICB therapy improved after delivering BPNS@PEG‐based PTT.ResultsBPNS@PEG had a well‐defined lamellar structure with clear edges and an average size of 150 nm. PET and Western blotting assays indicated that PD‐L1 expression was upregulated after BPNS@PEG and NIR‐light treatment. Notably, the antitumor effect of anti PD‐L1 therapy was enhanced in mice treated with BPNS@PEG‐based PTT.ConclusionsBPNS@PEG had the capacity to convert cold tumors into hot tumors to facilitate the efficacy of ICB therapy. Importantly, the complementary diagnostic PET radiotracer targeting PD‐L1 allowed real‐time monitoring of PD‐L1 expression in the tumor microenvironment to guide ICB administration, holding great potential to achieve efficient and precise tumor immunotherapy.

Spatial Constraints of Rectangular Hydrogel Microgrooves Regulate the Morphology and Arrangement of Human Umbilical Vein Endothelial Cells

To construct microscale rectangular hydrogel grooves and to investigate the morphology and alignment of human umbilical vein endothelial cells (HUVECs) under spatial constraints. Vascular endothelial cell morphology and alignment are important factors in vascular development and the maintenance of homeostasis. A 4-arm polyethylene glycol-acrylate (PEG-acrylate) hydrogel was used to fabricate rectangular microgrooves of the widths of 60 μm, 100 μm, and 140 μm. The sizes and the fibronectin (FN) adhesion of these hydrogel microgrooves were measured. HUVECs were seeded onto the FN-coated microgrooves, while the flat surface without micropatterns was used as the control. After 48 hours of incubation, the morphology and orientation of the cells were examined. The cytoskeleton was labelled with phalloidine and the orientation of the cytoskeleton in the hydrogel microgrooves was observed by laser confocal microscopy. The hydrogel microgrooves constructed exhibited uniform and well-defined morphology, a complete structure, and clear edges, with the width deviation being less than 3.5%. The depth differences between the hydrogel microgrooves of different widths were small and the FN adhesion is uniform, providing a micro-patterned growth interface for cells. In the control group, the cells were arranged haphazardly in random orientations and the cell orientation angle was (46.9±1.8)°. In contrast, the cell orientation angle in the hydrogel microgrooves was significantly reduced (P<0.001). However, the cell orientation angles increased with the increase in hydrogel microgroove width. For the 60 μm, 100 μm, and 140 μm hydrogel microgrooves, the cell orientation angles were (16.4±2.8)°, (24.5±3.2)°, and (30.3±3.5)°, respectively. Compared to that of the control group (35.7%), the number of cells with orientation angles <30° increased significantly in the hydrogel microgrooves of different widths (P<0.001). However, as the width of the hydrogel microgrooves increased, the number of cells with orientation angles <30° gradually decreased (79.9%, 62.3%, 54.7%, respectively), while the number of cells with orientation angles between 60°-90° increased (P<0.001). The cell bodies in the microgrooves were smaller and more rounded in shape. The cells were aligned along the direction of the microgrooves and corresponding changes occurred in the arrangement of the cell cytoskeleton. In the control group, cytoskeletal filaments were aligned in random directions, presenting an orientation angle of (45.5±3.7)°. Cytoskeletal filaments were distributed evenly within various orientation angles. However, in the 60 μm, 100 μm, and 140 μm hydrogel microgrooves, the orientation angles of the cytoskeletal filaments were significantly decreased, measuring (14.4±3.1)°, (24.7±3.5)°, and (31.9±3.3)°, respectively. The number of cytoskeletal filaments with orientation angles <30° significantly increased in hydrogel microgrooves of different widths (P<0.001). However, as the width of the hydrogel microgrooves increased, the number of cytoskeletal filaments with orientation angles <30° gradually decreased, while the number of cytoskeletal filaments with orientation angles between 60°-90° gradually increased (P<0.001). Hydrogel microgrooves can regulate the morphology and orientation of HUVECs and mimic to a certain extent the in vivo microenvironment of vascular endothelial cells, providing an experimental model that bears better resemblance to human physiology for the study of the unique physiological functions of vascular endothelial cells. Nonetheless, the molecular mechanism of spatial constraints on the morphology and the assembly of vascular endothelial cell needs to be further investigated.

Advanced magnetic resonance imaging for glioblastoma: Oncology-radiology integration.

Aggressive brain tumors like glioblastoma multiforme (GBM) pose a poor prognosis. While magnetic resonance imaging (MRI) is crucial for GBM management, distinguishing it from other lesions using conventional methods can be difficult. This study explores advanced MRI techniques better to understand GBM properties and their link to patient outcomes. We studied MRI scans of 157 GBM surgery patients from January 2020 to March 2024 to extract radiomic features and analyze the impact of fluid-attenuated inversion recovery (FLAIR) resection on survival using statistical methods, proportional hazards regression, and Kaplan-Meier survival analysis. Predictive models achieved high accuracy (area under the curve of 0.902) for glioma-grade prediction. FLAIR abnormality resection significantly improved survival, while diffusion-weighted image best-depicted tumor infiltration. Glioblastoma infiltration was best seen with advanced MRI compared to metastasis. Glioblastomas showed distinct features, including irregular shape, margins, and enhancement compared to metastases, which were oval or round, with clear edges and even contrast, and extensive peritumoral changes. Advanced radiomic and machine learning analysis of MRI can provide noninvasive glioma grading and characterization of tumor properties with clinical relevance. Combining advanced neuroimaging with histopathology may better integrate oncology and radiology for optimized glioblastoma management. However, further studies are needed to validate these findings with larger datasets and assess additional MRI sequences and radiomic features.

Assessing Intracavitary Three-Dimensional Ultrasound for Endometrial Polyps Diagnosis

Objective: To discuss the clinical effectiveness of intracavitary three-dimensional ultrasound in diagnosing endometrial polyps and evaluate its detection status. Methods: A total of 155 patients with suspected endometrial polyps underwent examination using the GE-Voluson-E10 three-dimensional ultrasound diagnostic instrument at the Department of Ultrasound Medicine in Lijiang People’s Hospital. Among them, 92 cases underwent intracavitary three-dimensional ultrasound examination between November 1, 2022, and June 2, 2023. Using histopathological results as the diagnostic criteria, a retrospective analysis was conducted on the clinical effects of intracavitary three-dimensional ultrasound diagnosis in patients with endometrial polyps. Results: Intracavitary three-dimensional ultrasound examination of 92 patients with suspected endometrial diseases revealed that 32 patients were diagnosed with endometrial polyps, including 9 with single lesions and 23 with multiple lesions, with a polyp diameter range of 3–16 mm. The examination displayed clear arc-shaped edges of the polyps in the endometrium. The section diameter was less than 16 mm, and the echo was relatively strong. The base of the uterine cavity was relatively narrow, and the endometrium line was neat. Color Doppler revealed strip-like or dot-like colored blood flow signals in the center and base. Among the 92 patients with suspected endometrial polyps, 30 cases were confirmed by histopathology, and 32 cases were confirmed by intracavitary three-dimensional ultrasound. The sensitivity of intracavitary three-dimensional ultrasound in diagnosing endometrial polyps was 100.00% (30/30), the specificity was 96.77% (60/62), and the accuracy was 97.83% (90/92). Conclusion: The application of intracavitary three-dimensional ultrasound in the diagnosis of endometrial polyps yielded significant diagnostic results. It provided detailed morphology of the endometrium, delivering vivid and three-dimensional imaging images. The diagnostic efficiency was high and consistent with pathological and histological diagnoses.

A pluggable single-image super-resolution algorithm based on second-order gradient loss

Convolutional neural networks for single-image super-resolution have been widely used with great success. However, most of these methods use L1 loss to guide network optimization, resulting in blurry restored images with sharp edges smoothed. This is because L1 loss limits the optimization goal of the network to the statistical average of all solutions within the solution space of that task. To go beyond the L1 loss, this paper designs an image super-resolution algorithm based on second-order gradient loss. We impose additional constraints by considering the high-order gradient level of the image so that the network can focus on the recovery of fine details such as texture during the learning process. This helps to alleviate the problem of restored image texture over-smoothing to some extent. During network training, we extract the second-order gradient map of the generated image and the target image of the network by minimizing the distance between them, this guides the network to pay attention to the high-frequency detail information in the image and generate a high-resolution image with clearer edge and texture. Besides, the proposed loss function has good embeddability and can be easily integrated with existing image super-resolution networks. Experimental results show that the second-order gradient loss can significantly improve both Learned Perceptual Image Patch Similarity (LPIPS) and Frechet Inception Distance score (FID) performance over other image super-resolution deep learning models.

DSRNet: Depth Super-Resolution Network guided by blurry depth and clear intensity edges

Although high resolution (HR) depth images are required in many applications such as virtual reality and autonomous navigation, their resolution and quality generated by consumer depth cameras fall short of the requirements. Existing depth upsampling methods focus on extracting multiscale features of HR color image to guide low resolution (LR) depth upsampling, thus causing blurry and inaccurate edges in depth. In this paper, we propose a depth super-resolution (SR) network guided by blurry depth and clear intensity edges, called DSRNet. DSRNet differentiates effective edges from a number of HR edges with the guidance of blurry depth and clear intensity edges. First, we perform global residual estimation based on an encoder–decoder architecture to extract edge structure from HR color image for depth SR. Then, we distinguish effective edges from HR edges in the decoder side with the guidance of LR depth upsampling. To maintain edges for depth SR, we use intensity edge guidance that extracts clear intensity edges from HR image. Finally, we use residual loss to generate accurate high frequency (HF) residual and reconstruct HR depth maps. Experimental results show that DSRNet successfully reconstructs depth edges in SR results as well as outperforms the state-of-the-art methods in terms of visual quality and quantitative measurements.11The proposed model with some test image pairs are available in https://github.com/lanhui-123/DSRNet.

Full 3-D modulation transfer function estimation of tomosynthesis system using modified Richardson-Lucy deconvolution.

Tomosynthesis systems are three-dimensional (3-D) medical imaging devices that operate over limited acquisition angles using low radiation dosages. To measure the spatial resolution performance of a tomosynthesis system, the modulation transfer function (MTF) is widely used as a quantitative evaluationmetric. We previously introduced a method to estimate the full 3-D MTF of a cone-beam computed tomography system using two-dimensional (2-D) Richardson-Lucy (RL) deconvolution with Tikhonov-Miller regularization. However, this method can not be applied directly to estimate the 3-D MTF of a tomosynthesis system, since the unique artifacts (i.e., shadow artifacts, spreading tails, directional blurring, and high-level noise) of the system produce several errors that lower the estimation performance. Varying positions of the negative pixels due to shadow artifacts and spreading tails cause inconsistent deconvolution performances at each of the directional projections, and the severe noise in the reconstructed images cause noise amplification during estimation. This work proposes several modifications to the previous method to resolve the inconsistent performance and noise amplification errors to increase the full 3-D MTF estimationaccuracy. Three modifications were introduced to the 2-D RL deconvolution to prevent estimation errors and improve MTF estimation performance: non-negativity relaxation function, cost function to terminate the iterative process of RL deconvolution, and regularization strength for noise control. To validate the effectiveness of the proposed modifications, we reconstructed sphere phantoms from simulation and experimental tomosynthesis studies in the iso-center and offset-center positions as well as estimated the full 3-D MTFs using the previous and proposed methods. We compared the 3-D render images, central plane images, and center profiles of the estimated 3-D MTFs and calculated the full widths at half and tenth maximum for quantitativeevaluation. The previous method cannot estimate the full 3-D MTF of a tomosynthesis system; its inaccurate negative pixel relaxation produces circular-shaped errors, and the mean squared error based simple cost function for termination causes inconsistent estimation at each directional projection to diminish the clear edges of the low-frequency drop and missing sample regions. Noise amplification from lack of noise regularization is also seen in the previous method results. Compared to the previous method, the proposed method shows superior estimation performance at reducing errors in both the simulation and experimental studies regardless of object position. The proposed method preserves the low-frequency drop, missing sample regions from the limited acquisition angles, and missing cone region from the offset-center position; the estimated MTFs also show FWHM and FWTM values close to those of the ideal MTFs than with the previousmethod. This work presents a method to estimate the full 3-D MTF of a tomosynthesis system. The proposed modifications prevent circular-shaped errors and noise amplification due to the geometry for limited acquisition angles and high noise levels. Compared to our previous method, the proposed scheme show better performance for estimating the 3-D MTF of the tomosynthesissystem.

Asymmetric CycleGANs for inverse design of photonic metastructures

Using deep learning to develop nanophotonic structures has been an active field of research in recent years to reduce the time intensive iterative solutions found in finite-difference time-domain simulations. Existing work has primarily used a specific type of generative network: conditional deep convolutional generative adversarial networks. However, these networks have issues with producing clear optical structures in image files; for example, a large number of images show speckled noise, which often results in non-manufacturable structures. Here, we report the first use of cycle-consistent generative adversarial networks to design nanophotonic structures. This approach significantly reduces the amount of speckled noise present in generated geometric structures and allows shapes to have clear edges. We demonstrate that for a given input reflectance spectra, the system generates designs in the form of images, and a complementary network generates reflectance spectra if an image containing a shape is provided as an input. The results show a higher Frechet Inception Distance score than previous approaches, which indicates that the generated structures are of higher quality and are able to learn nonlinear relationships between both datasets. This method of designing nanophotonics provides alternative avenues for development that are more noise robust while still adhering to desired optical properties.