Delineation Of Boundaries Research Articles

Medical image segmentation with hybrid neural networks

Abstract Recent advancements in CNN and Transformer-based models have significantly advanced medical image segmentation. CNN-based models are less effective at capturing global contexts than Transformer-based models and Transformers have structural disadvantages that limit their ability to capture detailed spatial information. In this paper, we introduce an Dual-Encoder Fusion Model that incorporates a novel Correlation Fusion Module (CFM) for medical image segmentation tasks. This model leverages the strengths of Convolutional Neural Networks (CNN) for local context modeling and Transformers for comprehending long-range dependencies in pixel interactions. Experimental results demonstrate a substantial improvement over existing models on the Synapse dataset, achieving enhancements of 2.28% and 3.47% on the dice metric for Aorta and Pancreas organs respectively. Additionally, our model attains the highest mean HD95 score of 9.05 on the Synapse dataset while utilizing fewer parameters. When evaluated on the MSD datasets, our model outperforms a fine-tuned nnUNet in three out of five tumor detection tasks and maintains competitive performance in three out of four organ boundary delineation tasks. Notably, on the MSD-Lung dataset, our model surpasses a fine-tuned nnUNet on the dice metric by 6.4%. These results underscore the effectiveness of the CFM module within the dual-encoder architecture.

Agricultural surface water extraction in environmental remote sensing: A novel semantic segmentation model emphasizing contextual information enhancement and foreground detail attention

The intelligent and efficient analysis of agricultural surface water is essential for agricultural irrigation, flood prevention, and resource utilization. However, accurate extraction from high-resolution optical remote sensing images is challenging due to agricultural heterogeneous terrains, dynamic water body scales, and diverse surrounding vegetation. To address these challenges, this paper introduces a novel architecture called the Complex Rural Water Extraction Network (CRWENet). The CRWENet is designed to enhance the understanding of contextual information and suppress random background noise, which comprises four key components including feature encoder, feature decoder, context information enhancement module, and foreground detail attention module. The context information enhancement module harnesses the long-range dependency-capturing capabilities of Transformer, merging multi-scale features to enhance global information perception. Meanwhile, the foreground detail attention module facilitates adaptive suppression of intricate background noise and accurate delineation of agricultural surface water boundaries by harmonizing interactions across channel, height, and width dimensions. Extensive experimentation on the LoveDA dataset and the GLH-water dataset validates the effectiveness of CRWENet. The results demonstrate that the proposed CRWENet outperforms the existing classical semantic segmentation networks and the mainstream water body extraction methods, achieving Intersection over Union (IoU) scores of 70.93% and 80.55% respectively.

From Crown Detection to Boundary Segmentation: Advancing Forest Analytics with Enhanced YOLO Model and Airborne LiDAR Point Clouds

Individual tree segmentation is crucial to extract forest structural parameters, which is vital for forest resource management and ecological monitoring. Airborne LiDAR (ALS), with its ability to rapidly and accurately acquire three-dimensional forest structural information, has become an essential tool for large-scale forest monitoring. However, accurately locating individual trees and mapping canopy boundaries continues to be hindered by the overlapping nature of the tree canopies, especially in dense forests. To address these issues, this study introduces CCD-YOLO, a novel deep learning-based network for individual tree segmentation from the ALS point cloud. The proposed approach introduces key architectural enhancements to the YOLO framework, including (1) the integration of cross residual transformer network extended (CReToNeXt) backbone for feature extraction and multi-scale feature fusion, (2) the application of the convolutional block attention module (CBAM) to emphasize tree crown features while suppressing noise, and (3) a dynamic head for adaptive multi-layer feature fusion, enhancing boundary delineation accuracy. The proposed network was trained using a newly generated individual tree segmentation (ITS) dataset collected from a dense forest. A comprehensive evaluation of the experimental results was conducted across varying forest densities, encompassing a variety of both internal and external consistency assessments. The model outperforms the commonly used watershed algorithm and commercial LiDAR 360 software, achieving the highest indices (precision, F1, and recall) in both tree crown detection and boundary segmentation stages. This study highlights the potential of CCD-YOLO as an efficient and scalable solution for addressing the critical challenges of accuracy segmentation in complex forests. In the future, we will focus on enhancing the model’s performance and application.

Optical Coherence Tomography Image Enhancement and Layer Detection Using Cycle-GAN

Background/Objectives: Variations in image clarity across different OCT devices, along with the inconsistent delineation of RNFL boundaries, pose a challenge to achieving consistent diagnoses for glaucoma. Recently, deep learning methods such as GANs for image transformation have been gaining attention. This paper introduces deep learning methods to transform low-clarity images from one OCT device into high-clarity images from another, concurrently estimating the retinal nerve fiber layer (RNFL) segmentation lines in the enhanced images. Methods: We applied two deep learning methods, pix2pix and cycle-GAN, and provided a comparison of their performance by evaluating the similarity between the generated and actual images, as well as comparing the generated RNFL boundary delineation with the actual boundaries. Results: The image conversion performance was compared based on two criteria: Fréchet Inception Distance (FID) and curve dissimilarity. In the comparison of FID values, the cycle-GAN method showed significantly lower values than the pix2pix method (p-value < 0.001). In terms of curve similarity, the cycle-GAN method also demonstrated higher similarity to the actual curves compared to both manually annotated curves and the pix2pix method (p-value < 0.001). Conclusions: We demonstrated that the cycle-GAN method produces more consistent and precise outcomes in the converted images compared to the pix2pix method. The resulting segmented lines showed a high degree of similarity to those manually annotated by clinical experts in high-clarity images, surpassing the boundary accuracy observed in the original low-clarity scans.

Motion-Compensated Multishot Pancreatic Diffusion-Weighted Imaging With Deep Learning-Based Denoising.

Pancreatic diffusion-weighted imaging (DWI) has numerous clinical applications, but conventional single-shot methods suffer from off resonance-induced artifacts like distortion and blurring while cardiovascular motion-induced phase inconsistency leads to quantitative errors and signal loss, limiting its utility. Multishot DWI (msDWI) offers reduced image distortion and blurring relative to single-shot methods but increases sensitivity to motion artifacts. Motion-compensated diffusion-encoding gradients (MCGs) reduce motion artifacts and could improve motion robustness of msDWI but come with the cost of extended echo time, further reducing signal. Thus, a method that combines msDWI with MCGs while minimizing the echo time penalty and maximizing signal would improve pancreatic DWI. In this work, we combine MCGs generated via convex-optimized diffusion encoding (CODE), which reduces the echo time penalty of motion compensation, with deep learning (DL)-based denoising to address residual signal loss. We hypothesize this method will qualitatively and quantitatively improve msDWI of the pancreas. This prospective institutional review board-approved study included 22 patients who underwent abdominal MR examinations from August 22, 2022 and May 17, 2023 on 3.0 T scanners. Following informed consent, 2-shot spin-echo echo-planar DWI (b = 0, 800 s/mm2) without (M0) and with (M1) CODE-generated first-order gradient moment nulling was added to their clinical examinations. DL-based denoising was applied to the M1 images (M1 + DL) off-line. ADC maps were reconstructed for all 3 methods. Blinded pair-wise comparisons of b = 800 s/mm2 images were done by 3 subspecialist radiologists. Five metrics were compared: pancreatic boundary delineation, motion artifacts, signal homogeneity, perceived noise, and diagnostic preference. Regions of interest of the pancreatic head, body, and tail were drawn, and mean ADC values were computed. Repeated analysis of variance and post hoc pairwise t test with Bonferroni correction were used for comparing mean ADC values. Bland-Altman analysis compared mean ADC values. Reader preferences were tabulated and compared using Wilcoxon signed rank test with Bonferroni correction and Fleiss κ. M1 was significantly preferred over M0 for perceived motion artifacts and signal homogeneity (P < 0.001). M0 was significantly preferred over M1 for perceived noise (P < 0.001), but DL-based denoising (M1 + DL) reversed this trend and was significantly favored over M0 (P < 0.001). ADC measurements from M0 varied between different regions of the pancreas (P = 0.001), whereas motion correction with M1 and M1 + DL resulted in homogeneous ADC values (P = 0.24), with values similar to those reported for ssDWI with motion correction. ADC values from M0 were significantly higher than M1 in the head (bias 16.6%; P < 0.0001), body (bias 11.0%; P < 0.0001), and tail (bias 8.6%; P = 0.001). A small but significant bias (2.6%) existed between ADC values from M1 and M1 + DL. CODE-generated motion compensating gradients improves multishot pancreatic DWI as interpreted by expert readers and eliminated ADC variation throughout the pancreas. DL-based denoising mitigated signal losses from motion compensation while maintaining ADC consistency. Integrating both techniques could improve the accuracy and reliability of multishot pancreatic DWI.

PEGylated Ultrasmall Iron Oxide Nanoparticles as MRI Contrast Agents for Vascular Imaging and Real-Time Monitoring.

Accurate imaging evaluations of pre- and post-treatment of cardiovascular diseases are pivotal for effective clinical interventions and improved patient outcomes. However, current imaging methods lack real-time monitoring capabilities with a high contrast and resolution during treatments. This study introduces PEGylated ultrasmall iron oxide nanoparticles (PUSIONPs), which have undergone comprehensive safety evaluations, boasting an r1 value of 6.31 mM-1 s-1, for contrast-enhanced magnetic resonance angiography (MRA). Systematic comparisons against common clinical methods in rabbits reveal that PUSIONPs-enhanced MRA exhibited improved vascular contrast, clearer vascular boundaries, and superior vessel resolution. Moreover, owing to their nanosize, PUSIONPs demonstrate significantly prolonged blood circulation compared to small molecular contrast agents such as Magnevist and Ultravist. This extended circulation enables captivating real-time monitoring of thrombolysis treatment for up to 4 h in rabbit models postsingle contrast agent injection. Additionally, in larger animal models such as beagles and Bama minipigs, PUSIONPs-enhanced MRA also showcases superior contrast effects, boundary delineation, and microvessel visualization, underscoring their potential to transform cardiovascular imaging, particularly in real-time monitoring and high-resolution visualization during treatment processes.

Relating ecological diversity to genetic discontinuity across bacterial species

BackgroundGenetic discontinuity represents abrupt breaks in genomic identity among species. Advances in genome sequencing have enhanced our ability to track and characterize genetic discontinuity in bacterial populations. However, exploring the degree to which bacterial diversity exists as a continuum or sorted into discrete and readily defined species remains a challenge in microbial ecology. Here, we aim to quantify the genetic discontinuity (δ) and investigate how this metric is related to ecology.ResultsWe harness a dataset comprising 210,129 genomes to systematically explore genetic discontinuity patterns across several distantly related species, finding clear breakpoints which vary depending on the taxa in question. By delving into pangenome characteristics, we uncover a significant association between pangenome saturation and genetic discontinuity. Closed pangenomes are associated with more pronounced breaks, exemplified by Mycobacterium tuberculosis. Additionally, through a machine learning approach, we detect key features such as gene conservation patterns and functional annotations that significantly impact genetic discontinuity prediction.ConclusionsOur study clarifies bacterial genetic patterns and their ecological impacts, enhancing the delineation of species boundaries and deepening our understanding of microbial diversity.

Enhanced CATBraTS for Brain Tumour Semantic Segmentation.

The early and precise identification of a brain tumour is imperative for enhancing a patient's life expectancy; this can be facilitated by quick and efficient tumour segmentation in medical imaging. Automatic brain tumour segmentation tools in computer vision have integrated powerful deep learning architectures to enable accurate tumour boundary delineation. Our study aims to demonstrate improved segmentation accuracy and higher statistical stability, using datasets obtained from diverse imaging acquisition parameters. This paper introduces a novel, fully automated model called Enhanced Channel Attention Transformer (E-CATBraTS) for Brain Tumour Semantic Segmentation; this model builds upon 3D CATBraTS, a vision transformer employed in magnetic resonance imaging (MRI) brain tumour segmentation tasks. E-CATBraTS integrates convolutional neural networks and Swin Transformer, incorporating channel shuffling and attention mechanisms to effectively segment brain tumours in multi-modal MRI. The model was evaluated on four datasets containing 3137 brain MRI scans. Through the adoption of E-CATBraTS, the accuracy of the results improved significantly on two datasets, outperforming the current state-of-the-art models by a mean DSC of 2.6% while maintaining a high accuracy that is comparable to the top-performing models on the other datasets. The results demonstrate that E-CATBraTS achieves both high segmentation accuracy and elevated generalisation abilities, ensuring the model is robust to dataset variation.

Conceptual Foundations of Digital Newsdiscourseology as a Fundamental Subdiscipline of Newslinguistics: Overcoming Outdated Scientific-Theoretical Models

The study primarily focuses on identifying the limitations and inadequacies of media linguistics and internet linguistics, which can no longer comprehensively address the specifics of the modern informational landscape due to outdated scientific and theoretical frameworks. There arises a need for clear delineation of the conceptual boundaries of the aforementioned disciplines to prevent methodological ambivalence. Additionally, in response to these challenges, the development of a distinct discipline – newslinguistics, exclusively dedicated to the study of the news landscape – is proposed. Within this framework, its specialised subdiscipline, newsdiscourseology, is introduced to encompass the exploration of all aspects of digital news discourse. A central construct of this subdiscipline is the concept of the hypernews – a type of inclusive text characteristic exclusively of next-generation news platforms. Consequently, the establishment of newsdiscourseology is regarded as a critical response to the demands of the contemporary informational paradigm, characterised by hypertextual, interactive, polycoded, and multimodal structures. Further investigation of this issue entails the creation of a new scientific and practical foundation, including the identification and structured representation of implicit linguistic patterns embedded within contemporary digital news platforms. Assigning these patterns explicitness and specificity will contribute to enhancing users’ cultural and intellectual levels, fostering their critical thinking, and advancing related scientific practices. These developments will also enable the creation of sophisticated software utilities, integrated into browser-based linguistic applications and automated analytical-statistical linguistic databases. These innovations will furnish the foundation for the synchronous and automated analysis of hypernews, the formulation of strategies for optimising news content consumption, and ensure accessibility for a broad spectrum of users, ranging from system administrators to the general public. Pursuant to the proposed paradigm shift, continued exploration within the domain of digital informational communications offers significant transformative potential for addressing the complex challenges of the information age.

ETiSeg-Net: edge-aware self attention to enhance tissue segmentation in histopathological images

AbstractDigital pathology employing Whole Slide Images (WSIs) plays a pivotal role in cancer detection. Nevertheless, the manual examination of WSIs for the identification of various tissue regions presents formidable challenges due to its labor-intensive nature and subjective interpretation. Convolutional Neural Network (CNN) based semantic segmentation algorithms have emerged as valuable tools for assisting in this task by automating ROI delineation. The incorporation of attention modules and carefully designed loss functions has shown promise in further augmenting the performance of these algorithms. However, there exists a notable gap in research regarding the utilization of attention modules specifically for tissue segmentation, thereby constraining our comprehension and application of these modules in this context. This study introduces ETiSeg-Net (Edge-aware self attention to enhance Tissue Segmentation), a CNN-based semantic segmentation model that uses a novel edge-based attention module to achieve effective delineation of class boundaries. In addition, an innovative iterative training strategy is devised to efficiently optimize the model parameters. The study also conducts a comprehensive investigation into the impact of attention modules and loss functions on the efficacy of semantic segmentation models. Qualitative and quantitative evaluations of these semantic segmentation models are conducted using publicly available datasets. The findings underscore the potential of attention modules in enhancing the accuracy and effectiveness of tissue semantic segmentation.

Multi-scale differential network for landslide extraction from remote sensing images with different scenarios

ABSTRACT Landslides are major geological hazards globally, causing significant economic losses each year. Accurate landslide detection is essential for disaster prevention, risk assessment, and timely emergency response. Current extraction methods struggle to distinguish landslides from their surroundings and precisely define their boundaries. To address these challenges, we introduce the Multi-Scale Difference Enhancement Network (MSDENet), a framework for landslide extraction through time-based change detection. MSDENet incorporates three core components: the Difference Guided Attention Module (DGAM) for enhanced focus on landslide-specific changes, the Multi-Scale Feature Fusion Module (MSFFM) for improved boundary delineation, and the Multi-Scale Sensory Module (MSSM) to boost generalization by integrating multi-scale features. We validate MSDENet’s effectiveness on the Global Very-High-Resolution Landslide Mapping (GVLM) dataset, covering 17 diverse landslide events, and further assess its applicability on high-resolution Nepal and Wenchuan datasets. MSDENet outperforms six contemporary frameworks, achieving IoU improvements of 1.42% and 1.08% for the Kaikoura and Tbilisi datasets and demonstrating gains of 3.97% and 4.79% for the Nepal and Wenchuan datasets, confirming its effectiveness in varied conditions.

A Fast Coding Unit Partitioning Decision Algorithm for Versatile Video Coding Based on Gradient Feedback Hierarchical Convolutional Neural Network and Light Gradient Boosting Machine Decision Tree

Video encoding technology is a foundational component in the advancement of modern technological applications. The latest standard in universal video coding, H.266/VVC, features a quad-tree with nested multi-type tree (QTMT) partitioning structure, which represents an improvement over its predecessor, High-Efficiency Video Coding (H.265/HEVC). This configuration facilitates adaptable block segmentation, albeit at the cost of heightened encoding complexity. In view of the aforementioned considerations, this paper puts forth a deep learning-based approach to facilitate CU partitioning, with the aim of supplanting the intricate CU partitioning process observed in the Versatile Video Coding Test Model (VTM). We begin by presenting the Gradient Feedback Hierarchical CNN (GFH-CNN) model, an advanced convolutional neural network derived from the ResNet architecture, enabling the extraction of features from 64 × 64 coding unit (CU) blocks. Following this, a hierarchical network diagram (HND) is crafted to depict the delineation of partition boundaries corresponding to the various levels of the CU block’s layered structure. This diagram maps the features extracted by the GFH-CNN model to the partitioning at each level and boundary. In conclusion, a LightGBM-based decision tree classification model (L-DT) is constructed to predict the corresponding partition structure based on the prediction vector output from the GFH-CNN model. Subsequently, any errors in the partitioning results are corrected in accordance with the encoding constraints specified by the VTM, which ultimately determines the final CU block partitioning. The experimental results demonstrate that, in comparison with VTM-10.0, the proposed algorithm achieves a 48.14% reduction in complexity with only a 0.83% increase in bitrate under the top-three configuration, which is negligible. In comparison, the top-two configuration resulted in a higher complexity reduction of 63.78%, although this was accompanied by a 2.08% increase in bitrate. These results demonstrate that, in comparison to existing solutions, our approach provides an optimal balance between encoding efficiency and computational complexity.

A novel network with enhanced edge information for left atrium segmentation from LGE-MRI

IntroductionAutomatic segmentation of the left atrium (LA) constitutes a crucial pre-processing step in evaluating heart structure and function during clinical interventions, such as image-guided radiofrequency ablation of atrial fibrillation. Despite prior research on LA segmentation, the low contrast in medical images exacerbates the challenge of distinguishing various tissues, rendering accurate boundary delineation of the target area formidable. Moreover, class imbalance due to the small target size further complicates segmentation.MethodsThis study aims to devise an architecture that augments edge information for LA segmentation from late gadolinium enhancement magnetic resonance imaging. To intensify edge information within image features, this study introduces an Edge Information Enhancement Module (EIEM) to the foundational network. The design of EIEM is grounded in exploring edge details within target region features learned from images. Additionally, it incorporates a Spatially Weighted Cross-Entropy loss function tailored for EIEM, introducing constraints on different regions based on the importance of pixels to edge segmentation, while also mitigating class imbalance through weighted treatment of positive and negative samples.ResultsThe proposed method is validated on the 2018 Atrial Segmentation Challenge dataset. Compared with other state-of-the-art algorithms, the proposed algorithm demonstrated a significant improvement with an average symmetric surface distance of 0.684 mm and achieved a commendable Dice coefficient of 0.924, implicating the effectiveness of enhancing edge information.DiscussionThe method offers a practical framework for precise LA localization and segmentation, particularly strengthening the algorithm’s effectiveness in improving segmentation outcomes for irregular protrusions and discrete multiple targets. Additionally, the generalizability of our model was evaluated on the heart dataset from the Medical Segmentation Decathlon (MSD) challenge, confirming its robustness across different clinical scenarios involving LA segmentation.

A Model for Defining the Boundaries of Complex Sentences and Clauses in English Translation Based on the Huffman Tree and Objective Function

To address the issues of high redundancy in sentence features and poor semantic similarity analysis in English translation, a boundary definition model for complex sentence clauses in English translation based on the Huffman tree and objective function is proposed. This model analyzes the boundary structure of complex sentences and clauses in English translation, determines the mathematical expected value of the probability distribution of boundary features, introduces the maximum entropy model to assess the key degree of different features, and utilizes conditional random fields to mine hidden features. Additionally, by employing a hierarchical clustering algorithm to analyze the distance between boundary features of complex sentences and clauses in English translation, similar images are merged based on the minimum distance between data points. Feature redundancy scores are obtained through an attention mechanism, and the weight of boundary features of complex sentences and clauses in English translation is calculated. By using the edit distance in semantic similarity to determine the boundary distance of clauses, and then using cosine similarity to calculate the similarity between the boundary features of complex clauses in English translation, a Huffman tree and objective function are introduced to construct a model for defining the boundary of complex clauses in English translation. Input the boundary feature values of complex sentences and clauses in English translation to complete the final definition. The experimental results show that the proposed method performs well in the task of defining the boundaries of complex sentences and clauses in English translation, with semantic similarity analysis results remaining above 95% and reaching up to 99%, significantly better than the comparative methods. Meanwhile, the recall curve obtained by the proposed method is closest to the ideal curve and has a small fluctuation range, stable between 90% and 98%, further verifying its accuracy and robustness in boundary delineation. In addition, when the sample data size is 1000, the confidence level of the proposed method is as high as 99.6%, which is higher than the 95.6% and 95.1% of the comparison methods. As the sample size increased to 2500, the confidence level of the proposed method remained at a high level of 99.4%, while the confidence level of the comparative method decreased to 94.2% and 94.1%, respectively. These data results fully demonstrate the effectiveness of the proposed method in reducing redundant interference and improving confidence. In summary, the proposed method has improved the performance of defining the boundaries of complex sentences and clauses in English translation.

National Park Double Boundary Delimitation: A Synergy-Based Approach Integrating Biodiversity and Ecosystem Services—An Example of Proposed Ailaoshan–Wuliangshan National Parks in China

The demarcation of national park boundaries is crucial for comprehensive planning, effective management, and maintaining the integrity of ecosystems and biodiversity. This research uses the proposed ‘Ailaoshan–Wuliangshan’ National Park (AWNP) in Yunnan Province, China, as the study area and adheres to the principles of systematic conservation planning (SCP). It employs the Marxan 2.43, MaxEnt 3.4.4, and InVEST 3.14.2 models to predict suitable distribution areas for key endangered species within the AWNP, identifies core ecological source areas, priority conservation areas, and conservation gaps, and constructs a double boundary protection framework. The study’s findings indicate that the potentially suitable habitats for the major rare and endangered species, as predicted by the MaxEnt model, are predominantly located in the Ailaoshan and Wuliangshan areas, with a smaller portion distributed in the Konglonghe area. The InVEST model assessment of habitat quality revealed that the total area of the core ecological source areas is 4775.26 km2, accounting for 35.34% of the total study area. The Marxan model identified a total area of 1064.22 km2 as priority conservation areas, constituting 7.90% of the total study area. Additionally, it revealed conservation gaps of 302.1 km2, which represent 2.20% of the total area. Ultimately, by integrating biodiversity conservation and ecosystem services, the boundaries of the AWNP were optimized into a double boundary delineation model: the inner boundary, characterized by rigid control, spans an area of 1076.20 km2, while the outer boundary, characterized by elastic management, covers an area of 3056.92 km2. Corresponding management recommendations are proposed for the different areas. The double boundary delineation method proposed in this study can, to a certain extent, reconcile the conflict between biodiversity conservation and resource utilization, providing an appropriate reference for the demarcation and dynamic management of national park boundaries in China.

Automated Visceral Adipose Tissue Segmentation and Quantification from Abdominal MRI using an Enhanced U-Net and Region-growing

The study focuses on enhancing the accuracy and reliability of visceral adipose tissue (VAT) segmentation and quantification from abdominal MRI images. Accurate segmentation of VAT is crucial for assessing obesity-related health risks, as traditional methods struggle with irregular shapes and varying intensities. The research utilizes a methodology consisting of three key modules: homomorphic filtering for intensity inhomogeneity correction, a U-Net architecture with attention mechanisms for primary segmentation, and a region-growing algorithm for refining segmentation. Homomorphic filtering effectively separates bias fields, enhancing image quality by transforming multiplicative artifacts into additive ones and removing them with high-pass filtering. This process ensures precise segmentation by maintaining high-frequency anatomical details. The U-Net model incorporates attention mechanisms and skip connections to focus on VAT regions, utilizing both local and global image contexts.The Combined Healthy Abdominal Organ Segmentation (CHAOS) challenge dataset and the Cancer Imaging Archive (TCIA) dataset are used to train and evaluate the model. It achieves a Dice Similarity Coefficient (DSC) of up to 0.985 on the CHAOS dataset and 0.972 on the TCIA dataset, outperforming existing methods in terms of segmentation accuracy. The region-growing algorithm further refines the segmentation by expanding VAT regions from high-confidence seed points, ensuring accurate boundary delineation and reducing noise. The study's results, evaluated using k-fold cross-validation, show that the proposed methodology significantly improves VAT segmentation efficiency, achieving a median DSC of 0.96 for the CHAOS dataset and 0.95 for the TCIA dataset in the most comprehensive experimental scenario. Comparative analysis indicates that the proposed approach outperforms other models, with higher sensitivity and specificity values, highlighting its potential for clinical applications in obesity management..

Segmentation of Low-Grade Brain Tumors Using Mutual Attention Multimodal MRI.

Early detection and precise characterization of brain tumors play a crucial role in improving patient outcomes and extending survival rates. Among neuroimaging modalities, magnetic resonance imaging (MRI) is the gold standard for brain tumor diagnostics due to its ability to produce high-contrast images across a variety of sequences, each highlighting distinct tissue characteristics. This study focuses on enabling multimodal MRI sequences to advance the automatic segmentation of low-grade astrocytomas, a challenging task due to their diffuse and irregular growth patterns. A novel mutual-attention deep learning framework is proposed, which integrates complementary information from multiple MRI sequences, including T2-weighted and fluid-attenuated inversion recovery (FLAIR) sequences, to enhance the segmentation accuracy. Unlike conventional segmentation models, which treat each modality independently or simply concatenate them, our model introduces mutual attention mechanisms. This allows the network to dynamically focus on salient features across modalities by jointly learning interdependencies between imaging sequences, leading to more precise boundary delineations even in regions with subtle tumor signals. The proposed method is validated using the UCSF-PDGM dataset, which consists of 35 astrocytoma cases, presenting a realistic and clinically challenging dataset. The results demonstrate that T2w/FLAIR modalities contribute most significantly to the segmentation performance. The mutual-attention model achieves an average Dice coefficient of 0.87. This study provides an innovative pathway toward improving segmentation of low-grade tumors by enabling context-aware fusion across imaging sequences. Furthermore, the study showcases the clinical relevance of integrating AI with multimodal MRI, potentially improving non-invasive tumor characterization and guiding future research in radiological diagnostics.

DCUFormer: Enhancing pavement crack segmentation in complex environments with dual-cross/upsampling attention

Efficient road inspection and maintenance are essential to extend pavement lifespan and enhance safety. However, automated crack detection remains challenging due to varied environmental conditions and differences in image collection equipment, making robust algorithm development a critical need. Vision Transformers, with their capacity to capture long-range dependencies, offer significant advantages for crack detection in complex scenarios by effectively extracting global features. Nevertheless, existing Transformer-based methods encounter difficulties in boundary delineation due to decoder design limitations, which lead to suboptimal fusion of low-level and high-level features. To address this issue, we propose a comprehensive approach that integrates semantic preservation, detail refinement, and detail delineation. These concepts are realized through our novel Dual-Cross Attention Module (DCA) and Upsampling Attention Module (UA). The DCA module progressively filters redundant details from low-level feature layers using high-level semantic information, while preserving boundary details to refine high-level feature boundaries. In addition, the UA module employs progressive local cross-attention in upsampling, facilitating more precise boundary definitions and surpassing conventional dynamic upsampling methods. Our approach, utilizing both lightweight (MiT-B0, LVT) and middle-weight (Swin-T) backbones, demonstrates state-of-the-art performance on three diverse datasets—Crack500, CrackSC, and UAV-Crack500—highlighting its robustness across varied conditions. This work contributes to advancing Transformer-based architectures for defect segmentation in complex engineering contexts, underscoring the critical role of improved feature fusion in crack detection. The code is available at: https://github.com/SHAN-JH/DCUFormer.

Medical Image Segmentation

Medical image segmentation is a critical component in the development of computer-aided diagnosis and treatment planning systems. This paper provides a comprehensive survey of recent advances in segmentation techniques applied to various imaging modalities, including Magnetic Resonance Imaging (MRI). Traditional methods such as thresholding, region-growing, and active contours are reviewed alongside contemporary machine learning-based approaches, particularly deep learning models. The survey emphasizes the growing dominance of convolutional neural networks (CNNs) and their variants, including U-Net and Fully Convolutional Networks (FCNs), which have shown remarkable success in handling complex medical imaging challenges. Additionally, the paper discusses hybrid methods that combine classical techniques with artificial intelligence to improve accuracy and robustness in segmentation tasks. Key challenges such as class imbalance, boundary delineation, and computational efficiency are also highlighted. Future directions, including the integration of multi-modal data and advancements in self-supervised learning, are explored as potential solutions to overcome current limitations in medical image segmentation.

Improvement of Coal Mining-Induced Subsidence-Affected (MISA) Zone Irregular Boundary Delineation by MT-InSAR Techniques, UAV Photogrammetry, and Field Investigation

Coal mining-induced ground subsidence is a severe hazard that can damage property, infrastructure, and the environment in the vicinity when the deformation is not negligible. The boundary of a mining-induced subsidence-affected zone refers to the area beyond which the ground subsidence is less concerned. Accurately measuring mining-induced ground deformation is essential for delineating the irregular boundary of the impacted area. This study employs multitemporal interferometric synthetic aperture radar (MT-InSAR) techniques, including differential InSAR (DInSAR), InSAR stacking, and interferometric point target analysis (IPTA), to analyze coal mine subsidence and delineate the boundaries of the mining-impacted zones. DInSAR accurately reconstructs, locates, and detects the trend in mining-induced subsidence and correlates well with documented mining operations. The InSAR stacking method maps the spatial variation of the ground’s average line-of-sight (LOS) velocity over the mining area, delineating the boundary of the impacted zone. IPTA analysis combining multilook and single-pixel phases achieves millimeter-level surface measurement above tunnel alignments and measures unevenly distributed deformation fields. This study considers an average of 4 cm per year of surface deformation in the LOS direction as the subsidence threshold value for delineating the boundary of the mining-induced subsidence-affected (MISA) zone during the active coal mining stage. Interestingly, there are twin transportation tunnels near the mining area. The twin tunnels completed before the coal mining activities started were functioning well, but damage was observed after the mining began. Our study reveals the tunnels are located within the InSAR-derived MISA zone, although the tunnels approach the MISA boundary. As direct signs of subsidence, ground fissures have been identified near the tunnels via field investigations and UAV photogrammetry. Furthermore, the derived distribution of ground fissures validates and verifies InSAR measurements. The integrated approach of MT-InSAR, UVA photogrammetry, and field investigation developed in this study can be applied to delineate the irregular boundary of the MISA zone and study the accumulating effects of mining-induced subsidence on the performance of infrastructure in areas proximate to coal mining activities.