Global Image Research Articles

Diagnosing Necrotizing Enterocolitis via Fine-Grained Visual Classification.

Necrotizing Enterocolitis (NEC) is a devastating condition affecting prematurely born neonates. Reviewing Abdominal X-rays (AXRs) is a key step in NEC diagnosis, staging and treatment decision-making, but poses significant challenges due to the subtle, difficult-to-identify radiological signs of the disease. In this paper, we propose AIDNEC - AI Diagnosis of NECrotizing enterocolitis, a deep learning method to automatically detect and stratify the severity (surgical or medical) of NEC from no pathology in AXRs. The model is trainable end-to-end and integrates a Detection Transformer and Graph Convolution modules for localizing discriminative areas in AXRs, used to formulate subtle local embeddings. These are then combined with global image features to perform Fine-Grained Visual Classification (FGVC). We evaluate AIDNEC on our GOSH NEC dataset of 1153 images from 334 patients, achieving 79.7% accuracy in classifying NEC against No Pathology. AIDNEC outperforms the backbone by 2.6%, FGVC models by 2.5% and CheXNet by 4.2%, with statistically significant (two-tailed p 0.05) improvements, while providing meaningful discriminative regions to support the classification decision. Additional validation in the publicly available Chest X-ray14 dataset yields comparable performance to state-of-the-art methods, illustrating AIDNEC's robustness in a different X-ray classification task.

Does Reputation Matter? Explaining China’s Evolving Strategy in South China Sea Disputes

What drives China’s approach to disputes in the South China Sea? While conventional wisdom often attributes Beijing’s actions primarily to material interests, this overlooks the possible influence of non-material factors such as China’s desire to uphold its national reputation. Contrary to the assumptions of traditional prospect theory, China’s behavior is not driven solely by calculations of gains and losses but also by considerations for its international reputation. Beijing may temper its assertiveness when its reputation is declining but still manageable, as demonstrated by its increased willingness to resolve disputes multilaterally after its global image was tarnished following the outbreak of the COVID-19 pandemic. Contrarily, China may resort to more assertive actions when these do not significantly hurt its reputation or when the damage seems irreversible, as seen in its unwavering stance during the 2012 Scarborough Shoal standoff with the Philippines.

A dual encoder LDCT image denoising model based on cross-scale skip connections

LDCT image denoising is crucial in medical imaging as it aims to minimize patient radiation exposure while maintaining diagnostic image quality. However, current convolutional neural network-based denoising methods struggle to incorporate global contexts, often focusing solely on local features. This limitation poses a significant challenge. To address this, a dual encoder denoising model is introduced that utilizes the Transformer model’s proficiency in capturing long-range dependencies and global context. This model integrates the Transformer branch and the convolutional branch in the encoder. By concatenating the features of these two different branches, the model can capture both global and local image features, substantially enhancing denoising efficacy. A cross-scale skip connection mechanism is introduced to integrate the encoder’ s low-level features with the decoder’ s high-level features, enriching contextual information and preserving image details. In addition, to meet the requirements of multi-scale feature fusion, the decoder is equipped with different multi-scale convolution modules to optimize feature processing. The number of layers in these modules gradually decreases as the depth of the decoder increases. In order to enhance the discriminative ability of the model, a multi-scale discriminator is also introduced, which effectively improves the recognition ability of the image by extracting features from four different scales. Consequently, our approach demonstrates remarkable performance in reducing noise and improving LDCT image quality, as evidenced by the substantial improvements in PSNR (17.75%) and SSIM (7.31%) values.

Block-based color image encryption algorithm by a novel memristor chaotic system and new RNA computation

The security of images is closely related to the protection of information privacy. We proposed a novel 5D memory resistive chaotic system (5D-MRCS), which exhibits good chaotic characteristics. Therefore, we employed it to design an image encryption algorithm aimed at ensuring secure image transmission. To further enhance the complexity of the algorithm and obtain more chaotic sequences, we combine the 5D-MRCS with the Hodgkin-Huxley (HH) model and use this combination in algorithm design. Initially, we combine the plain image with the hash function SHA-384 to devise and generate the secret key. Subsequently, the algorithm determines whether to pad the plain image based on different block size requirements. Then, we use multiple chaotic sequences generated by the 5D-MRCS and HH model to perform the global image permutation operation. Our designed permutation algorithm includes two parts: Block-based permutation and a new pixel-level permutation. Next, the scrambled image undergoes block-based random RNA diffusion, incorporating two newly proposed methods in the RNA operations, ultimately resulting in the ciphertext image. The algorithm’s NPCR, UACI, information entropy, and other security performance metrics are very close to the ideal values, and it possess characteristics such as resistance to differential, cutting, chosen plaintext, and noise attacks. Compared with other algorithms, it still has some advantages across multiple images and demonstrates excellent image encryption performance.

Region-aware image-based human action retrieval with transformers

Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this paper, we focus on the neglected but important task of image-based action retrieval which aims to find images that depict the same action as a query image. We establish benchmarks for this task and set up important baseline methods for fair comparison. We present a Transformer-based model that learns rich action representations from three aspects: the anchored person, contextual regions, and the global image. A fusion transformer is designed to model the relationships among different features and effectively fuse them into an action representation. Experiments on both the Stanford-40 and PASCAL VOC 2012 Action datasets show that the proposed method significantly outperforms previous approaches for image-based action retrieval.

Benefits of Information Technology to the Development of Nigeria

The sustainability and development of businesses and organization solely rely on the geometric progression of the impact of information technology (IT); aside the significant impact on individual lives, many organizations globally have experienced increase in productivity, reduce costs, improvement on the quality of goods and services, enhance communication systems and promote good transportation systems. Every sector has direct impact of the information technology, and the level of development currently is directly proportional to the degree of the impact. In today`s world information technology has become pivotal element in the economic growth; many solutions to everyday challenges could not have been possible without the impact of information technology. Medical and surgical processes of restoring good health to many patients today would not exist, the possibility of travelling globally without difficulties, enhancing communications that has no limitation by location, and many more that makes lives meaningful and dreams achievable are made possible by the influence of information technology. This article will describe the influence of Information Technology in enhancing the growth and development of Nigeria in relation to various sectors such as; education, health, manufacturing industries, real estate, energy, utilities, to mention a few, which will promote business and global image

A virtual scene reconstruction algorithm for 3D digital images based on machine learning

In order to obtain a better quality image of virtual scene reconstruction of three-dimensional digital image, a virtual scene reconstruction algorithm of three-dimensional digital image based on machine learning is proposed. Firstly, the state information and presentation instructions of the scene are analyzed to obtain the distribution position of the vertices of the mesh model of the image reconstruction. The global image is approximately calculated by the local coordinate method, and the local details are corrected to complete the rendering of the three-dimensional digital image. Then, the space and scale are used as feature points to build a window detection template on the image, and the classifier is applied to suppress discrete feature points and remove redundant features. Finally, the smoothed three-dimensional coordinates are obtained according to the fitting function method to reconstruct the three-dimensional surface, and the local two-dimensional triangle is segmented and mapped to the three-dimensional space to realize the reconstruction of the virtual scene of the three-dimensional digital image. The experimental results show that the algorithm has a fast convergence speed, the reconstructed image details and edge contours are complete, and the overall effect is good.

Therapeutic Performance of Needle Injection Versus Needle-Free Jet Injector System for Polynucleotide Filler in Skin Rejuvenation.

Polynucleotide (PN) filler often causes pain and can lead to delivery inaccuracies when applied via intradermal injection using a traditional needle. To evaluate the efficacy of treatment and the pain during the procedure using conventional needle injection versus a needle-free jet system for intradermal PN filler application. In this split-face clinical trial, 10 Korean subjects were enrolled. Each subject received an intradermal injection of PN filler on one side of the face and a needle-free jet injection using CureJet on the other side. Assessments included global and 3D skin imaging at each visit. Pain intensity was evaluated using visual analogue scale (VAS) scores during the injection. Additionally, patient satisfaction and adverse events were documented. Findings revealed that Global Aesthetic Improvement Scale scores and patient satisfaction were significantly higher with the CureJet compared to the needle injection method. VAS scores were notably lower on the CureJet side. Improvements in both pore and wrinkle indices were observed from baseline, with a more pronounced improvement rate on the CureJet side compared to the needle injection side. Needle-free injection of PN for aging skin was found to be effective in enhancing pore and wrinkle improvement, while reducing associated discomfort.

Role of thermospheric winds on the generation of F-region irregularities over Indonesian sector during the solar minimum year 2020

Analysis of ionosonde observations over Chumpon (10.7°N, 99.4°E, 3.3° Mag. Lat.) and Kototabang (0.2° S, 100.3° E, 10° S Mag. Lat.) during the low solar activity year 2020 reveals that the occurrence of post-sunset spread-F maximises during winter (November-February), whereas that of post-midnight spread-F maximises during summer (May-August). The thermospheric winds observed by the Michelson Interferometer for Global High-Resolution Thermospheric Imaging (MIGHTI) on board the Ionospheric Connection Explorer (ICON) satellite over the Indonesian longitudes (95°E-115°E) are investigated to determine their impact on the generation of spread-F. The thermospheric winds at equatorial and low latitudes (10°N) are strongly eastward (> 50 m/s) around post-sunset hours (∼19:00 LST) in winter and equinox. The strong eastward wind is present only around midnight hours (after 22:00 LST) in summer. However, the present study reveals that the zonal wind does not contribute to the generation of plasma bubbles. Besides, the ICON-MIGHTI meridional wind at low latitude (10°N) is observed to be equatorward throughout the day during summer. Compared to the post-sunset hours, the intensity of trans-equatorial wind is stronger on the windward side (60–70 m/s) than on the leeward side (10–20 m/s) during midnight hours. The component of the equatorward meridional wind along the magnetic field lines can lift the F-layer to higher heights leading to a net decrease in the field line-integrated Pedersen conductivity thereby increasing the growth rate of the Rayleigh Taylor instability that can result in the generation of post-midnight spread F.

Use of strain imaging to detect subtle myocardial involvement in post COVID-19 patients: An Indian perspective

BackgroundThe study assessed Global longitudinal strain imaging (GLS) to detect subtle myocardial dysfunction among patients clinically recovered from COVID-19. MethodsAll patients (n = 101 76 % males, mean age 55.45 ± 11.14 years), and controls (n = 30), underwent clinical assessment and echocardiography, including GLS assessment. ResultsThe prevalence of diabetes mellitus, hypertension and dyslipidemia was comparable amongst patients and controls. The average GLS was significantly lesser in post COVID patients (−16.21 ± 1.96 vs −18.49 ± 1.64 respectively, p = 0.004) and significantly higher proportion of post COVID patients had GLS > -18 % (43 % vs 22.58 % respectively, p = 0.001) as compared to controls. The RV free wall longitudinal strain (RVFLS) was also lower in the patient group (22.35 ± 4.69 vs 24.19 ± 4.11, p = 0.004) and 21.7 % post COVID-19 patients had pathological RV FWLS (> −20 %) vs controls (6.6 %).Average GLS was significantly lesser in severe post COVID patients (viz −14.25 ± 1.92 vs −16.63 ± 1.61 vs −17.63 ± 1.91, p < 0.0001, respectively among severe, moderate and mild COVID-19 patients. On performing regression analysis, severity of COVID-19 (OR 7.762) was a significant predictor of impaired GLS. ConclusionDespite normal global LVEF, post COVID-19 recovered patients had significantly lower LV GLS and RV FWLS with severe COVID-19 infection, regardless of having a clinical recovery. This study reiterates the importance of speckle tracking echocardiography as an important imaging modality for detection of subclinical myocardial dysfunction in the post COVID-19 recovered patients.

Global-aware Fragment Representation Aggregation Network for image-text retrieval

Image-text retrieval is an important kind of cross-modal retrieval method and has recently attracted much attention. Existing image-text retrieval methods often ignore the relative importance of each fragment (region in an image or word in a sentence) on the global semantic of image or text when aggregating features of image or text fragments, resulting in the ineffectiveness of the learned image and text representations. To address this problem, we propose an image-text retrieval method named Global-aware Fragment Representation Aggregation Network (GFRAN). Specifically, it first designs a fine-grained multimodal information interaction module based on the self-attention mechanism to model both the intra-modality and inter-modality relationships between image regions and words. Then, with the guidance of the global image or text feature, it aggregates image or text fragment features conditioned on their attention weights over global feature, to highlight fragments that contribute more to the overall semantics of images and texts. Extensive experiments on two benchmark datasets Flickr30K and MS-COCO demonstrate the superiority of the proposed GFRAN model over several state-of-the-art baselines.

An Adaptive X‐Ray Dynamic Image Estimation Method Based on OMNI Solar Wind Parameters and SXI Simulated Observations

AbstractObservations of the overall interactions between solar wind and the Earth's magnetosphere are crucial for space weather monitoring. Upcoming missions like the Solar Wind Magnetosphere Ionosphere Link Explorer (SMILE) and the Lunar Environment heliosphere X‐ray Imager (LEXI) aim to make comprehensive global imaging of Earth's magnetosphere using soft X‐ray imager (SXI) in order to understand its dynamic response to solar wind impact. Short‐duration X‐ray images have a low signal‐to‐noise ratio (SNR), limited by cosmic background and Poisson noise. Longer integration times provide better SNR of magnetospheric structures but fail to capture the short‐term dynamics during the integration. Our study introduces a neural network method which is able to estimate the short‐term dynamics during a long integration, driven by OMNI solar wind data and simulated soft X‐ray images. Specifically, an adaptive X‐ray image estimator and a spatio‐temporal discriminator are used. It leverages X‐ray models like Magnetohydrodynamic (MHD) and Jorgensen &amp; Sun model, driven by OMNI data to provide high‐temporal‐resolution prior information on magnetosphere motion, with SXI observation images acting as a posterior constraint on the magnetosphere's state. Experimental validation demonstrates apparent improvements in Peak signal‐to‐noise ratio (PSNR) and Structural Similarity (SSIM) compared to traditional linear and optical flow interpolation methods. The method's flexibility, considering input‐output consistency, enables easy extension to any interval (&gt;3 min), meeting diverse application needs. In conclusion, our study presents a new approach to soft X‐ray image estimation based on neural networks, providing insights into magnetospheric dynamics as observed in soft X‐rays.

Optical Characterization of Coastal Waters with Atmospheric Correction Errors: Insights from SGLI and AERONET-OC

This study identifies the characteristics of water regions with negative normalized water-leaving radiance (nLw(λ)) values in the satellite observations of the Second-generation Global Imager (SGLI) sensor aboard the Global Change Observation Mission–Climate (GCOM-C) satellite. SGLI Level-2 data, along with atmospheric and in-water optical properties measured by the sun photometers in the AErosol RObotic NETwork-Ocean Color (AERONET-OC) from 26 sites globally, are utilized in this study. The focus is particularly on Tokyo Bay and the Ariake Sea, semi-enclosed water regions in Japan where previous research has pointed out the occurrence of negative nLw(λ) values due to atmospheric correction with SGLI. The study examines the temporal changes in atmospheric and in-water optical properties in these two regions, and identifies the characteristics of regions prone to negative nLw(λ) values due to atmospheric correction by comparing the optical properties of these regions with those of 24 other AERONET-OC sites. The time series results of nLw(λ) and the single-scattering albedo (ω(λ)) obtained by the sun photometers at the two sites in Tokyo Bay and Ariake Sea, along with SGLI nLw(λ), indicate the occurrence of negative values in SGLI nLw(λ) in blue band regions, which are mainly attributed to the inflow of absorptive aerosols. However, these negative values are not entirely explained by ω(λ) at 443 nm alone. Additionally, a comparison of in situ nLw(λ) measurements in Tokyo Bay and the Ariake Sea with nLw(λ) values obtained from 24 other AERONET-OC sites, as well as the inherent optical properties (IOPs) estimated through the Quasi-Analytical Algorithm version 5 (QAA_v5), identified five sites—Gulf of Riga, Long Island Sound, Lake Vanern, the Tokyo Bay, and Ariake Sea—as regions where negative nLw(λ) values are more likely to occur. These regions also tend to have lower nLw(λ) values at shorter wavelengths. Furthermore, relatively high light absorption by phytoplankton and colored dissolved organic matter, plus non-algal particles, was confirmed in these regions. This occurs because atmospheric correction processing excessively subtracts aerosol light scattering due to the influence of aerosol absorption, increasing the probability of the occurrence of negative nLw(λ) values. Based on the analysis of atmospheric and in-water optical measurements derived from AERONET-OC in this study, it was found that negative nLw(λ) values due to atmospheric correction are more likely to occur in water regions characterized by both the presence of absorptive aerosols in the atmosphere and high light absorption by in-water substances.

The role of upscale restaurants in destination image formation: a semiotic perspective on gastronomy tourism

PurposeHigh-end gastronomic tourism is currently trending and significantly impacts a destination’s image. This research aims to demonstrate the importance of high-level local gastronomy in forming the destination image from a semiotic perspective.Design/methodology/approachTo achieve this objective, the three phases of the upscale dining experience – pre-visit, in situ and post-visit – are examined from a descriptive (informative use), appraisive (valuative use) and prescriptive (incitive use) semiotic perspective. This conceptual model includes six constructs: restaurant image, consumer need for status, consumer expectations, consumer satisfaction, restaurant loyalty and destination loyalty. The study is based on a survey of high-end restaurant customers (N = 421).FindingsThe research findings highlight that the characteristics of upscale dining establishments influence customer expectations, while customer satisfaction plays a crucial role in fostering loyalty towards both the restaurant and the destination. Additionally, the study reveals that individuals' social status or reputation moderates their expectations and satisfaction levels.Originality/valueAlthough studies relate gastronomic image to global destination image, this relationship from a semiotic perspective has not been demonstrated through surveys. This proposed three-phase model based on the Peircean semiotic triad and Morris semiotic trichotomies not only addresses a gap in the existing literature but also offers valuable insights for destination managers and restaurant owners.

SwinDenoising: A Local and Global Feature Fusion Algorithm for Infrared Image Denoising

Infrared image denoising is a critical task in various applications, yet existing methods often struggle with preserving fine details and managing complex noise patterns, particularly under high noise levels. To address these limitations, this paper proposes a novel denoising method based on the Swin Transformer architecture, named SwinDenoising. This method leverages the powerful feature extraction capabilities of Swin Transformers to capture both local and global image features, thereby enhancing the denoising process. The proposed SwinDenoising method was tested on the FLIR and KAIST infrared image datasets, where it demonstrated superior performance compared to state-of-the-art methods. Specifically, SwinDenoising achieved a PSNR improvement of up to 2.5 dB and an SSIM increase of 0.04 under high levels of Gaussian noise (50 dB), and a PSNR increase of 2.0 dB with an SSIM improvement of 0.03 under Poisson noise (λ = 100). These results highlight the method’s effectiveness in maintaining image quality while significantly reducing noise, making it a robust solution for infrared image denoising.

Global and local feature extraction based on convolutional neural network residual learning for MR image denoising.

Given the different noise distribution information of global and local magnetic resonance (MR) images, this study aims to extend the current work on convolutional neural networks that preserve global structure and local details in MR image denoising tasks. This study proposed a parallel and serial network for denoising 3D MR images, called 3D-PSNet. We use the residual depthwise separable convolution block to learn the local information of the feature map, reduce the network parameters, and thus improve the training speed and parameter efficiency. In addition, we consider the feature extraction of the global image and utilize residual dilated convolution to process the feature map to expand the receptive field of the network and avoid the loss of global information. Finally, we combine both of them to form a parallel network. What's more, we integrate reinforced residual convolution blocks with dense connections to form serial network branches, which can remove redundant information and refine features to further obtain accurate noise information. The peak signal-to-noise ratio, structural similarity index measure, and root mean square error metrics of 3D-PSNet are as high as 47.79%, 99.81%, and 0.40%, respectively, achieving competitive denoising effect on three public datasets. The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets. The proposed 3D-PSNet takes advantage of multi-scale receptive fields, local feature extraction and residual dense connections to more effectively restore the global structure and local fine features in MR images, and is expected to help doctors quickly and accurately diagnose patients' conditions.

Method for Augmenting Side-Scan Sonar Seafloor Sediment Image Dataset Based on BCEL1-CBAM-INGAN.

In this paper, a method for augmenting samples of side-scan sonar seafloor sediment images based on CBAM-BCEL1-INGAN is proposed, aiming to address the difficulties in acquiring and labeling datasets, as well as the insufficient diversity and quantity of data samples. Firstly, a Convolutional Block Attention Module (CBAM) is integrated into the residual blocks of the INGAN generator to enhance the learning of specific attributes and improve the quality of the generated images. Secondly, a BCEL1 loss function (combining binary cross-entropy and L1 loss functions) is introduced into the discriminator, enabling it to focus on both global image consistency and finer distinctions for better generation results. Finally, augmented samples are input into an AlexNet classifier to verify their authenticity. Experimental results demonstrate the excellent performance of the method in generating images of coarse sand, gravel, and bedrock, as evidenced by significant improvements in the Frechet Inception Distance (FID) and Inception Score (IS). The introduction of the CBAM and BCEL1 loss function notably enhances the quality and details of the generated images. Moreover, classification experiments using the AlexNet classifier show an increase in the recognition rate from 90.5% using only INGAN-generated images of bedrock to 97.3% using images augmented using our method, marking a 6.8% improvement. Additionally, the classification accuracy of bedrock-type matrices is improved by 5.2% when images enhanced using the method presented in this paper are added to the training set, which is 2.7% higher than that of the simple method amplification. This validates the effectiveness of our method in the task of generating seafloor sediment images, partially alleviating the scarcity of side-scan sonar seafloor sediment image data.

Pseudo‐CT synthesis in adaptive radiotherapy based on a stacked coarse‐to‐fine model: Combing diffusion process and spatial‐frequency convolutions

AbstractBackgroundCone beam computed tomography (CBCT) provides critical anatomical information for adaptive radiotherapy (ART), especially for tumors in the pelvic region that undergo significant deformation. However, CBCT suffers from inaccurate Hounsfield Unit (HU) values and lower soft tissue contrast. These issues affect the accuracy of pelvic treatment plans and implementation of the treatment, hence requiring correction.PurposeA novel stacked coarse‐to‐fine model combining Denoising Diffusion Probabilistic Model (DDPM) and spatial‐frequency domain convolution modules is proposed to enhance the imaging quality of CBCT images.MethodsThe enhancement of low‐quality CBCT images is divided into two stages. In the coarse stage, the improved DDPM with U‐ConvNeXt architecture is used to complete the denoising task of CBCT images. In the fine stage, the deep convolutional network model jointly constructed by fast Fourier and dilated convolution modules is used to further enhance the image quality in local details and global imaging. Finally, the accurate pseudo‐CT (pCT) images consistent with the size of the original data are obtained. Two hundred fifty paired CBCT‐CT images from cervical and rectal cancer, combined with 200 public dataset cases, were used collectively for training, validation, and testing.ResultsTo evaluate the anatomical consistency between pCT and real CT, we have used the mean(std) of structure similarity index measure (SSIM), peak signal to noise ratio (PSNR), and normalized cross‐correlation (NCC). The numerical results for the above three metrics comparing the pCT synthesized by the proposed model against real CT for cervical cancer cases were 87.14% (2.91%), 34.02 dB (1.35 dB), and 88.01% (1.82%), respectively. For rectal cancer cases, the corresponding results were 86.06% (2.70%), 33.50 dB (1.41 dB), and 87.44% (1.95%). The paired t‐test analysis between the proposed model and the comparative models (ResUnet, CycleGAN, DDPM, and DDIM) for these metrics revealed statistically significant differences (p &lt; 0.05). The visual results also showed that the anatomical structures between the real CT and the pCT synthesized by the proposed model were closer. For the dosimetric verification, mean absolute error of dosimetry (MAEdoes) values for the maximum dose (Dmax), the minimum dose (Dmin), and the mean dose (Dmean) in the planning target volume (PTV) were analyzed, with results presented as mean (lower quartile, upper quartile). The experimental results show that the values of the above three dosimetry indexes (Dmin, Dmax, and Dmean) for the pCT images synthesized by the proposed model were 0.90% (0.48%, 1.29%), 0.82% (0.47%, 1.17%), and 0.57% (0.44%, 0.67%). Compared with 10 cases of the original CBCT image by Mann–Whitney test (p &lt; 0.05), it also proved that pCT can significantly improve the accuracy of HU values for the dose calculation.ConclusionThe pCT synthesized by the proposed model outperforms the comparative models in numerical accuracy and visualization, promising for ART of pelvic cancers.

Evaluation of the geometric and dosimetric accuracies of deformable image registration of targets and critical organs in prostate CBCT-guided adaptive radiotherapy.

Kilovoltage cone beam computed tomography (kVCBCT)-guided adaptive radiation therapy (ART) uses daily deformed CT (dCT), which is generated automatically through deformable registration methods. These registration methods may perform poorly in reproducing volumes of the target organ, rectum, and bladder during treatment. We analyzed the registration errors between the daily kVCBCTs and corresponding dCTs for these organs using the default optical flow algorithm and two registration procedures. We validated the effectiveness of these registration methods in replicating the geometry for dose calculation on kVCBCT for ART. We evaluated three deformable image registration (DIR) methods to assess their registration accuracy and dose calculation effeciency in mapping target and critical organs. The DIR methods include (1) default intensity-based deformable registration, (2) hybrid deformable registration, and (3) a two-step deformable registration process. Each technique was applied to a computerized imaging reference system (CIRS) phantom (Model 062M) and to five patients who received volumetric modulated arc therapy to the prostate. Registration accuracy was assessed using the 95% Hausdorff distance (HD95) and Dice similarity coefficient (DSC), and each method was compared with the intensity-based registration method. The improvement in the dCT image quality of the CIRS phantom and five patients was assessed by comparing dCT with kVCBCT. Image quality quantitative metrics for the phantom included the signal-to-noise ratio (SNR), uniformity, and contrast-to-noise ratio (CNR), whereas those for the patients included the mean absolute error (MAE), mean error, peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). To determine dose metric differences, we used a dose-volume histogram (DVH) and 3.0%/0.3mm gamma analysis to compare planning computed tomography (pCT) and kVCBCT recalculations with restimulated CT images used as a reference. The dCT images generated by the hybrid (dCTH) and two-step (dCTC) registration methods resulted in significant improvements compared to kVCBCT in the phantom model. Specifically, the SNR improved by 107% and 107.2%, the uniformity improved by 90% and 75%, and the CNR improved by 212.2% and 225.6 for dCTH and dCTC methods, respectively. For the patient images, the MAEs improved by 98% and 94%, the PSNRs improved by 16.3% and 22.9%, and the SSIMs improved by 1% and 1% in the dCTH and dCTC methods, respectively. For the geometric evaluation, only the two-step registration method improved registration accuracy. The dCTH method yielded an average HD95 of 12mm and average DSC of 0.73, whereas dCTC yielded an average HD95 of 2.9mm and average DSC of 0.902. The DVH showed that the dCTC-based dose calculations differed by <2% from the expected results for treatment targets and volumes of organs at risk. Additionally, gamma indices for dCTC-based treatment plans were >95% at all points, whereas they were <95% for kVCBCT-based treatment plans. The two-step registration method outperforms the intensity-based and hybrid registration methods. While the hybrid and two-step-based methods improved the image quality of kVCBCT in a linear accelerator, only the two-step method improved the registration accuracy of the corresponding structures among the pCT and kVCBCT datasets. A two-step registration process is recommended for applying kVCBCT to ART, which achieves better registration accuracy for local and global image structures. This method appears to be beneficial for radiotherapy dose calculation in patients with pelvic cancer.

Exploring Guilin's Destination Image Via User-Generated Content: A Computational Methods

This study quantify mainland China's destination image through international tourists' user-generated content (UGC), with a specific focus on Guilin, utilizing advanced computational techniques such as Latent Dirichlet Allocation (LDA) for topic modeling and sentiment analysis. It systematically evaluates online travel reviews to distill key themes and emotional sentiments that shape Guilin's image, uncovering a rich tapestry of cognitive perceptions and affective reactions related to its natural scenery, cultural engagements, service standards, and logistical facets. The application of topic modeling and sentiment analysis provides a nuanced understanding of the cognitive and affective dimensions defining Guilin's destination image. While positive sentiments largely highlight the region's aesthetic and experiential allure, negative sentiments reveal critical areas for improvement, such as perceived value and infrastructure, which are vital for enhancing tourist satisfaction and reinforcing Guilin's appeal in the global tourism market. This research applies LDA and sentiment analysis to interpret UGC offer a calculable methodological approach for broader application in destination image studies. By aligning perceptual and emotional insights with destination marketing strategies, the findings offer actionable intelligence to optimize tourist experiences and enhance destination loyalty. This approach not only enriches the academic understanding of destination images but also provides practical frameworks for destination managers to harness the full potential of UGC in shaping and refining the global image of tourism locales.