Segment Boundaries Research Articles

Improved nested U-structure for accurate nailfold capillary segmentation

Changes in the structure and function of nailfold capillaries may be indicators of numerous diseases. Noninvasive diagnostic tools are commonly used for the extraction of morphological information from segmented nailfold capillaries to study physiological and pathological changes therein. However, current segmentation methods for nailfold capillaries cannot accurately separate capillaries from the background, resulting in issues such as unclear segmentation boundaries. Therefore, improving the accuracy of nailfold capillary segmentation is necessary to facilitate more efficient clinical diagnosis and research. Herein, we propose a nailfold capillary image segmentation method based on a U2-Net backbone network combined with a Transformer structure. This method integrates the U2-Net and Transformer networks to establish a decoder–encoder network, which inserts Transformer layers into the nested two-layer U-shaped architecture of the U2-Net. This structure effectively extracts multiscale features within stages and aggregates multilevel features across stages to generate high-resolution feature maps. The experimental results demonstrate an overall accuracy of 98.23 %, a Dice coefficient of 88.56 %, and an IoU of 80.41 % compared to the ground truth. Furthermore, our proposed method improves the overall accuracy by approximately 2 %, 3 %, and 5 % compared to the original U2-Net, Res-Unet, and U-Net, respectively. These results indicate that the Transformer–U2Net network performs well in nailfold capillary image segmentation and provides more detailed and accurate information on the segmented nailfold capillary structure, which may aid clinicians in the more precise diagnosis and treatment of nailfold capillary-related diseases.

Segmental and Syllabic Articulations: A Descriptive Approach.

This article reports on jaw articulation, in connection with the segmental articulations of tongue tip and lips. The jaw is considered a syllable articulator as it opens and closes for each syllable, and the amount of jaw opening is related to syllable strength, given the same phonemic vowel. Here, we investigate the syllabic and the segmental articulations relationships to the acoustic segments. We analyze electromagnetic articulography data of 18 Southern Swedish speakers by testing hypotheses based on the Descriptive Approach to Segmental Articulations. In this approach, articulatory movements are divided into fast intervals and steady states, and the crucial ("primary") articulators' deceleration and acceleration peaks align with the acoustic segment boundaries. Previous findings on the lips and the tongue tip are confirmed. New results are the jaw as noncrucial ("nonprimary") does not align with the acoustic segment boundaries: Its steady states are shorter than consonant and vowel segments. Moreover, place of articulation of the coda affects the jaw cycle, while syllable type only affects jaw closing. No such effects are found on the edges of the jaw cycle, instead only gender affects jaw deceleration at syllable onset. The jaw is not crucial for the timing of the acoustic segment boundaries; also, syllable borders seem to not be affected by place of segmental articulation. The results strengthen the view of the jaw as syllable articulator providing a frame and the other articulators (e.g., lips and tongue tip) as the segmental articulators providing the content.

On the characterization of rectangular duals

A rectangular partition is a partition of a rectangle into a finite number of rectangles. A rectangular partition is generic if no four of its rectangles meet at the same point. A plane graph G is called a rectangularly dualizable graph if G can be represented as a rectangular partition such that each vertex is represented by a rectangle in the partition and each edge is represented by a common boundary segment shared by the corresponding rectangles. Then the rectangular partition is called a rectangular dual of the RDG. In this paper, we have found a minor error in a characterization for rectangular duals given by Koźmiński and Kinnen in 1985 without formal proof, and we fix this characterization with formal proof.

FUSeg: The Foot Ulcer Segmentation Challenge

Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound and provide quantitative measurement for the treatment. Unfortunately, this process is very time-consuming and requires a high level of expertise, hence the need for automatic wound measurement methods. Recently, automatic wound segmentation methods based on deep learning have shown promising performance; yet, they heavily rely on large training datasets. A few wound image datasets were published including the Diabetic Foot Ulcer Challenge dataset, the Medetec wound dataset, and WoundDB. Existing public wound image datasets suffer from small size and a lack of annotation. There is a need to build a fully annotated dataset to benchmark wound segmentation methods. To address these issues, we propose the Foot Ulcer Segmentation Challenge (FUSeg), organized in conjunction with the 2021 International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). It contains 1210 pixel-wise annotated foot ulcer images collected over 2 years from 889 patients. The submitted algorithms are reviewed in this paper and the dataset can be accessed through the Foot Ulcer Segmentation Challenge website.

UISS-Net: Underwater Image Semantic Segmentation Network for improving boundary segmentation accuracy of underwater images

UISS-Net: Underwater Image Semantic Segmentation Network for improving boundary segmentation accuracy of underwater images

Research of ordinal model fusion based apple grading

Near infrared spectrum has been applied for the rapid non-destructive prediction and classification of the internal soluble solids content (SSC) of apples, due to its rapid, non-destructive and non-polluting nature. However, current apple grading methods do not make full use of the orderliness relationship existing in the apple grading labels. Therefore, ordinal model is introduced in the issue of apples grading based on the internal SSC. In details, the orderliness in the classification model is considered and ordinal regression is combined with apple classification model to establish ordered partition neural network and ordinal regression extreme learning machine, respectively. Meanwhile, to address the problems of poor applicability of single prediction model and the grading uncertainty associated with compulsory segmentation of grading boundaries, a Gaussian mass function generating method is proposed based on the distance between the predicted ordinal class labels and the real grading boundaries, and the multiple models can be fused through the Dempster combination rule, making a fuller description of the uncertainty problem on ordinal class labels prediction, providing a research basis for online non destructive testing grading of apples. Finally, the multiple model fusion process is fully demonstrated by simulation examples, the grading accuracy of Yantai Red Fuji apples is also improved than single ordinal model.

Vascular changes of the choroid and their correlations with visual acuity in diabetic retinopathy.

To investigate changes in the choroidal vasculature and their correlations with visual acuity in diabetic retinopathy (DR). The cohort was composed of 225 eyes from 225 subjects, including 60 eyes from 60 subjects with healthy control, 55 eyes from 55 subjects without DR, 46 eyes from 46 subjects with nonproliferative diabetic retinopathy (NPDR), 21 eyes from 21 subjects with proliferative diabetic retinopathy (PDR), and 43 eyes from 43 subjects with clinically significant macular edema (CSME). Swept-source optical coherence tomography (SS-OCT) was used to image the eyes with a 12-mm radial line scan protocol. The parameters for 6-mm diameters of region centered on the macular fovea were analyzed. Initially, a custom deep learning algorithm based on a modified residual U-Net architecture was utilized for choroidal boundary segmentation. Subsequently, the SS-OCT image was binarized and the Niblack-based automatic local threshold algorithm was employed to calibrate subfoveal choroidal thickness (SFCT), luminal area (LA), and stromal area (SA) by determining the distance between the two boundaries. Finally, the ratio of LA and total choroidal area (SA + LA) was defined as the choroidal vascularity index (CVI). The choroidal parameters in five groups were compared, and correlations of the choroidal parameters with age, gender, duration of diabetes mellitus (DM), glycated hemoglobin (HbA1c), fasting blood sugar, SFCT and best-corrected visual acuity (BCVA) were analyzed. The CVI, SFCT, LA, and SA values of patients with DR were found to be significantly lower compared to both healthy patients and patients without DR (P< 0.05). The SFCT was significantly higher in NPDR group compared to the No DR group (P < 0.001). Additionally, the SFCT was lower in the PDR group compared to the NPDR group (P = 0.014). Furthermore, there was a gradual decrease in CVI with progression of diabetic retinopathy, reaching its lowest value in the PDR group. However, the CVI of the CSME group exhibited a marginally closer proximity to that of the NPDR group. The multivariate regression analysis revealed a positive correlation between CVI and the duration of DM as well as LA (P < 0.05). The results of both univariate and multivariate regression analyses demonstrated a significant positive correlation between CVI and BCVA (P = 0.003). Choroidal vascular alterations, especially decreased CVI, occurred in patients with DR. The CVI decreased with duration of DM and was correlated with visual impairment, indicating that the CVI might be a reliable imaging biomarker to monitor the progression of DR.

Ancient mural segmentation based on multiscale feature fusion and dual attention enhancement

To address the fuzzy segmentation boundaries, missing details, small target losses and low efficiency of traditional segmentation methods in ancient mural image segmentation scenarios, this paper proposes a mural segmentation model based on multiscale feature fusion and a dual attention-augmented segmentation model (MFAM). The model uses the MobileViT network, which integrates a coordinate attention mechanism, as the feature extraction backbone network. It attains global and local expression capabilities through self-attention, class convolution, and coordinate attention and focuses on location information to expand the receptive field and achieve improved feature extraction efficiency. An A_R_ASPP feature enhancement module is proposed for the attention-optimized residual atrous spatial pyramid pooling module. The module uses residual connections to solve the small target loss problem in murals caused by the excessive sampling rate of atrous convolution and uses a feature attention mechanism to adaptively adjust the feature map weight according to the channel importance levels. A dual attention-enhanced feature fusion module is proposed for multiscale decoder feature fusion to improve the mural segmentation effect. This module uses a cross-level aggregation strategy and an attention mechanism to weight the importance of different feature levels to obtain multilevel semantic feature representations. The model improves the mean intersection over union (MIoU) by 3.06% and the MPA by 1.81% on a mural dataset compared with other models. The model is proven to be effective at improving the segmentation details, efficiency and small target segmentation results produced for mural images, and a new method is proposed for segmenting ancient mural images.

DRANet: A semantic segmentation network for Chinese landscape paintings

With large-scale human-annotated pixel-level annotations, many deep learning-based methods have achieved impressive innovations in the field of semantic image segmentation. However, the lack of publicly available Chinese landscape paintings with pixel-level annotations seriously hinders the process of segmentation of Chinese landscape paintings. In addition, a prominent feature of Chinese landscape paintings is the extensive use of black ink, resulting in a lack of color-related information, and landscape paintings often use blank space to depict sky and water elements, which can lead to confusion about boundary information. These issues make the semantic segmentation of Chinese landscape paintings more challenging. To address these challenges, we construct a Segmented Chinese Landscape Paintings (SegCLP) dataset, which contains 709 images with pixel-level annotations belonging to 6 foreground object classes. Moreover, we propose a novel approach called Decrease Dilation Rate Residual Attention Network (DRANet) to enable accurate semantic segmentation of Chinese landscape paintings. DRANet integrates two primary modules: an attention mechanism and a residual module. The attention module alleviates the training burden associated with the spatial convolution pool pyramid, while the residual block enhances the granularity of the decoder, particularly at the segmentation boundary. Experimental findings corroborate the superior efficacy of DRANet in accurately segmenting Chinese landscape images.

Individual-Tree Segmentation from UAV–LiDAR Data Using a Region-Growing Segmentation and Supervoxel-Weighted Fuzzy Clustering Approach

Accurate individual-tree segmentation is essential for precision forestry. In previous studies, the canopy height model-based method was convenient to process, but its performance was limited owing to the loss of 3D information, and point-based methods usually had high computational costs. Although some hybrid methods have been proposed to solve the above problems, most canopy height model-based methods are used to detect subdominant trees in one coarse crown and disregard the over-segmentation and accurate segmentation of the crown boundaries. This study introduces a combined approach, tested for the first time, for treetop detection and tree crown segmentation using UAV–LiDAR data. First, a multiscale adaptive local maximum filter was proposed to detect treetops accurately, and a Dalponte region-growing method was introduced to achieve crown delineation. Then, based on the coarse-crown result, the mean-shift voxelization and supervoxel-weighted fuzzy c-means clustering method were used to identify the constrained region of each tree. Finally, accurate individual-tree point clouds were obtained. The experiment was conducted using a synthetic uncrewed aerial vehicle (UAV)–LiDAR dataset with 21 approximately 30 × 30 m plots and an actual UAV–LiDAR dataset. To evaluate the performance of the proposed method, the accuracy of the remotely sensed biophysical observations and retrieval frameworks was determined using the tree location, tree height, and crown area. The results show that the proposed method was efficient and outperformed other existing methods.

LD-UNet: A long-distance perceptual model for segmentation of blurred boundaries in medical images

The blurriness of boundaries in medical image target regions hinders further improvement in automatic segmentation accuracy and is a challenging problem. To address this issue, we propose a model called long-distance perceptual UNet (LD-UNet), which has a powerful long-‍distance perception ability and can effectively perceive the semantic context of an entire image. Specifically, LD-UNet utilizes global and local long-distance induction modules, which endow the model with contextual semantic induction capabilities for long-distance feature dependencies. The modules perform long-distance semantic perception at the high and low stages of LD-UNet, respectively, effectively improving the accuracy of local blurred information assessment. We also propose a top-down deep supervision method to enhance the ability of the model to fit data. Then, extensive experiments on four types of tumor data with blurred boundaries are conducted. The dataset includes nasopharyngeal carcinoma, esophageal carcinoma, pancreatic carcinoma, and colorectal carcinoma. The dice similarity coefficient scores obtained by LD-UNet on the four datasets are 73.35%, 85.93%, 70.04%, and 82.71%. Experimental results demonstrate that LD-UNet is more effective in improving the segmentation accuracy of blurred boundary regions than other methods with long-distance perception, such as transformers. Among all models, LD-UNet achieves the best performance. By visualizing the feature dependency field of the models, we further explore the advantages of LD-UNet in segmenting blurred boundaries.

A Hybrid of Fuzzy C-Means for the segmentation in CT scan and X-ray images for screening the COVID-19 patients

In this paper, using CT scan and X-ray images, we present a hybrid approach, based on combining fuzzy C-means with k-means clustering, to evaluate and determine pneumonia infection caused by the coronavirus disease (COVID-19). To achieve this objective, we introduce a hybrid method that combines fuzzy C-means clustering with K-means clustering. This hybrid approach is designed to effectively segment object boundaries within medical images, enabling the precise identification of pneumonia-related features. In addition to our hybrid method, we compare its performance with two other segmentation approaches: the Expectation Maximization (EM) algorithm and 2D Entropy segmentation. Which, the method we propose uses a comparison between the performances of the based on a database of medical imaging test. Experimental results showed that the proposed approach outperforms, it was found that the hybrid fuzzy C-means algorithm segmentation images methods give better performance in terms of accuracy, precision, and F-measure, which is effective in boundaries segmentation. Comparative results of the accuracy and image quality index demonstrate the robustness of AI. It also helps to improve work efficiency with accurate analysis of COVID-19 infection on CT scan and X-rays. In addition, the approach helps radiologists make clinical decisions for diagnosis, follow-up, and prognosis.

A Novel Technique Based on Machine Learning for Detecting and Segmenting Trees in Very High Resolution Digital Images from Unmanned Aerial Vehicles

The present study proposes a technique for automated tree crown detection and segmentation in digital images derived from unmanned aerial vehicles (UAVs) using a machine learning (ML) algorithm named Detectron2. The technique, which was developed in the python programming language, receives as input images with object boundary information. After training on sets of data, it is able to set its own object boundaries. In the present study, the algorithm was trained for tree crown detection and segmentation. The test bed consisted of UAV imagery of an agricultural field of tangerine trees in the city of Palermo in Sicily, Italy. The algorithm’s output was the accurate boundary of each tree. The output from the developed algorithm was compared against the results of tree boundary segmentation generated by the Support Vector Machine (SVM) supervised classifier, which has proven to be a very promising object segmentation method. The results from the two methods were compared with the most accurate yet time-consuming method, direct digitalization. For accuracy assessment purposes, the detected area efficiency, skipped area rate, and false area rate were estimated for both methods. The results showed that the Detectron2 algorithm is more efficient in segmenting the relevant data when compared to the SVM model in two out of the three indices. Specifically, the Detectron2 algorithm exhibited a 0.959% and 0.041% fidelity rate on the common detected and skipped area rate, respectively, when compared with the digitalization method. The SVM exhibited 0.902% and 0.097%, respectively. On the other hand, the SVM classification generated better false detected area results, with 0.035% accuracy, compared to the Detectron2 algorithm’s 0.056%. Having an accurate estimation of the tree boundaries from the Detectron2 algorithm, the tree health assessment was evaluated last. For this to happen, three different vegetation indices were produced (NDVI, GLI and VARI). All those indices showed tree health as average. All in all, the results demonstrated the ability of the technique to detect and segment trees from UAV imagery.

How does abusive supervision differentiation affect employee work-family conflict? A moderated chain mediation model

PurposeThis study aims to explore the mechanism of abusive supervision differentiation on employee work-family conflict, and examine the chain mediating role of work-related rumination and organizational citizenship behavior/deviant workplace behavior, as well as the moderating role of work-family boundary segmentation preference.Design/methodology/approachThe authors designed two studies: Study 1 was a scenario experiment with 120 Master of Business Administration students. To further explore this finding, the authors conducted a multiwave survey in Study 2 with 345 employees from various organizations.FindingsThe results of Study 1 showed that abusive supervision differentiation had a positive effect on work-related rumination, and work-related rumination mediated the relationship between differentiated abusive supervision and organizational citizenship behavior/deviant workplace behavior. The results of Study 2 not only confirmed the conclusions of Study 1 but also revealed that organizational citizenship behavior/deviant workplace behavior significantly affected work-family conflict. Abusive supervision differentiation had a positive effect on work-family conflict through work-related rumination and organizational citizenship behavior/deviant workplace behavior. In addition, work-family boundary segmentation preference negatively moderated the relationship between organizational citizenship behavior and work-family conflict.Originality/valueFirst, to the best of the authors’ knowledge, this study is the first paper to test the spillover effect of abusive supervision differentiation on the family domain through a chain mediation model. It extends the research on abusive supervision differentiation from the work domain to the family domain. Second, previous research has highlighted role conflict or role insufficiency as significant factors contributing to work-family conflict. However, this study suggests that abusive supervision differentiation from workplace managers can also trigger work-family conflict, providing a new perspective in the study of precursors to work-family conflict.

Wavelet-based saturated absorption line detection for laser frequency locking

Owing to the presence of noise and the Doppler background, accurate saturated absorption (SA) peak automatic identification technology poses a significant challenge for laser frequency tuning and locking. To address this issue, a novel peak identification algorithm for the SA spectrum is proposed. First, a Gaussian filter based on a Gaussian continuous wavelet transform is proposed to mitigate the spectral high-frequency noise. Subsequently, a hybrid method combining a first-order Gaussian continuous wavelet transformation and adaptive threshold judgment was designed for multi-peak boundary segmentation. Finally, we obtained the target peak and its sweeping voltage based on an adaptive nonlinear fitting algorithm, which was almost unaffected by the peak asymmetry caused by the Doppler background.

Geometry, kinematics, and mechanics of the interaction between strike-slip and normal faults in active rifts: An example from the Quaternary-active Kane Springs Wash fault zone, Nevada, USA

Abstract The interactions among dip-slip and strike-slip faults are critical features in rift segmentation, including strain and slip transfer between faults of different rift segments. Here, we focused on the influence of factors such as fault and fracture geometries, kinematics, and local stress fields on the interaction and linkage of synchronous strike-slip and normal faults. Well-exposed faults along the tectonically active boundary between the central and northern Basin and Range provided for both reliable geometric data and consideration of rift segment development. We documented relative ages and distributions of Quaternary deposits, scarps, and geometries of three ~20–65-km-long Quaternary faults: the N-striking, normal Coyote Spring fault; the ENE-striking, left-lateral Kane Springs Wash fault; and the N-striking, normal Wildcat Wash fault. The normal faults bend to accommodate slip-type differences across linkage zones, with the strike-slip fault and local processes influencing interactions. Influenced by the local stress field of the Kane Springs Wash fault, the Coyote Spring fault bends SE as it approaches and links to the Kane Springs Wash fault. Influenced by the off-fault or process-zone fractures of the Kane Springs Wash fault, the Wildcat Wash fault bends NE and links with the Kane Springs Wash fault. The Kane Springs Wash fault continues beyond the normal fault terminations, suggesting slip transfer between them via the Kane Springs Wash fault. These relations and the ages of offset units suggest that activity on the faults was approximately synchronous despite slip-type differences. Consequently, in slip transfer, the local strike-slip stress environment and off-fault fractures influenced the geometry of the normal fault terminations; the strike-slip fault formed a boundary to dip-slip fault propagation; and this boundary facilitated kinematic and geodetic segmentation, forming a Basin and Range rift segment boundary.

Semi-supervised learning for concrete defect segmentation from images

Deep learning-based concrete defect detection has emerged as a promising technology to overcome the limitations of manual visual inspection, which is often subjective, laborious, and time-consuming. However, most existing methods rely heavily on manual labels and adopt a fully supervised learning approach, which hinders their practical application in engineering. To tackle these concerns, we proposed a semi-supervised learning model, termed Semi-SegDefect. Our proposal utilizes a mean teacher architecture to assign pseudo-labels to the pixels of unlabeled images and performs pixel-level contrastive learning on a sparse set of hard negative pixels to achieve segmentation boundaries with the highest possible accuracy. Test results demonstrate that Semi-SegDefect outperforms fully supervised models significantly, especially when trained with limited labeled data. This method shows great promise for enhancing the accuracy and scalability of concrete defect segmentation and can contribute to the advancement of the construction industry.

Widespread fracture movements during a volcano-tectonic unrest: the Reykjanes Peninsula, Iceland, from 2019–2021 TerraSAR-X interferometry

Tectonic controls on dyke emplacements, eruption dynamics and locations have been observed in multiple volcanic areas worldwide. Mapping of active structures is therefore key for assessing potential tectonic and volcanic hazards in active regions. We used wrapped interferograms from the TerraSAR-X satellite to map active fracture movements over a 2-year period of a volcano-tectonic unrest at the onshore Reykjanes Peninsula plate boundary in SW Iceland. As of 1 December 2023, the unrest has included at least six inflation events and five dyke injections resulting in three eruptions of the Fagradalsfjall volcanic segment. In addition to the deformation associated with the 2019–2021 inflation events and intrusions, the interferograms reveal fracture movements over a wide area surrounding the active plate boundary segment. This first-order mapping of active fractures complements previously mapped structures, as InSAR allows for the detection of subtle ground movements, even in areas where young lava flows cover older structures. Our fracture data therefore fill in some of the apparent voids in previous fracture and fault maps of SW Iceland. Furthermore, our investigation reveals aseismic movement on previously unknown fractures directly beneath the town of Grindavík, as well as a N45∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^\\circ $$\\end{document} E striking fracture co-located with the longest lasting volcanic vent of the subsequent 2021 eruption. The mapping method we present in this study is relevant for active volcano-tectonic regions where InSAR can be applied to detect small-scale fracture movements to advance understanding of ongoing unrest and volcano-tectonic hazards.

Transform-Equivariant Consistency Learning for Temporal Sentence Grounding

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the dataset distribution bias. To alleviate these limitations, we introduce a novel Equivariant Consistency Regulation Learning (ECRL) framework to learn more discriminative query-related frame-wise representations for each video, in a self-supervised manner. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted under various video-level transformations. Concretely, we first design a series of spatio-temporal augmentations on both foreground and background video segments to generate a set of synthetic video samples. In particular, we devise a self-refine module to enhance the completeness and smoothness of the augmented video. Then, we present a novel self-supervised consistency loss (SSCL) applied on the original and augmented videos to capture their invariant query-related semantic by minimizing the KL-divergence between the sequence similarity of two videos and a prior Gaussian distribution of timestamp distance. At last, a shared grounding head is introduced to predict the transform-equivariant query-guided segment boundaries for both the original and augmented videos. Extensive experiments on three challenging datasets (ActivityNet, TACoS, and Charades-STA) demonstrate both effectiveness and efficiency of our proposed ECRL framework.

Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy

Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy