Previous Segmentation Methods Research Articles

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique.

Abdominal multi-organ segmentation is one of the most important topics in the field of medical image analysis, and it plays an important role in supporting clinical workflows such as disease diagnosis and treatment planning. In this study, an efficient multi-organ segmentation method called Swin-PSAxialNet based on the nnU-Net architecture is proposed. It was designed specifically for the precise segmentation of 11 abdominal organs in CT images. The proposed network has made the following improvements compared to nnU-Net. Firstly, Space-to-depth (SPD) modules and parameter-shared axial attention (PSAA) feature extraction blocks were introduced, enhancing the capability of 3D image feature extraction. Secondly, a multi-scale image fusion approach was employed to capture detailed information and spatial features, improving the capability of extracting subtle features and edge features. Lastly, a parameter-sharing method was introduced to reduce the model's computational cost and training speed. The proposed network achieves an average Dice coefficient of 0.93342 for the segmentation task involving 11 organs. Experimental results indicate the notable superiority of Swin-PSAxialNet over previous mainstream segmentation methods. The method shows excellent accuracy and low computational costs in segmenting major abdominal organs.

Reliable segmentation of multiple lesions from medical images.

Focusing on the complicated pathological features, such as blurred boundaries, severe scale differences between symptoms, and background noise interference, we aim to enhance the reliability of multiple lesions joint segmentation from medicalimages. Propose a novel reliable multi-scale wavelet-enhanced transformer network, which can provide accurate segmentation results with reliabilityassessment. Focusing on enhancing the model's capability to capture intricate pathological features in medical images, this work introduces a novel segmentation backbone. The backbone integrates a wavelet-enhanced feature extractor network and incorporates a multi-scale transformer module developed within the scope of this work. Simultaneously, to enhance the reliability of segmentation outcomes, a novel uncertainty segmentation head is proposed. This segmentation head is rooted in the SL, contributing to the generation of final segmentation results along with an associated overall uncertainty evaluation scoremap. Comprehensive experiments are conducted on the public database of AI-Challenge 2018 for retinal edema lesions segmentation and the segmentation of Thoracic Organs at Risk in CT images. The experimental results highlight the superior segmentation accuracy and heightened reliability achieved by the proposed method in comparison to other state-of-the-art segmentationapproaches. Unlike previous segmentation methods, the proposed approach can produce reliable segmentation results with an estimated uncertainty and higher accuracy, enhancing the overall reliability of the model. The code will be release on https://github.com/LooKing9218/ReMultiSeg.

A novel Deep Learning architecture for lung cancer detection and diagnosis from Computed Tomography image analysis

Timely identification of lung nodules, which are precursors to lung cancer, and their evaluation can significantly reduce the incidence rate. Computed Tomography (CT) is the primary technique used for lung cancer screening due to its high resolution. Identifying white, spherical shadows as lung nodules in CT images is essential for accurately detecting lung cancer. Convolutional Neural Network (CNN)-based methods have performed better than traditional techniques in various medical image applications. However, challenges still need to be addressed due to insufficient annotated datasets, significant intra-class variations, and substantial inter-class similarities, which hinder their practical use. Manually labeling the position of nodules on CT slices is critical for distinguishing between benign and malignant cases, but it is an unreliable and time-consuming process. Insufficient data and class imbalance are the primary factors that may result in overfitting and below-par performance. The paper presents a novel Deep Learning (DL) framework to detect and classify lung cancer in input CT images. It introduces a 3D-VNet architecture for accurate segmentation of pulmonary nodules and a 3D-ResNet architecture designed for their classification. The segmentation model achieves a Dice Similarity Coefficient (DSC) of 99.34% on the LUNA16 dataset while reducing false positives to 0.4%. The classification model shows performance metrics with accuracy, sensitivity, and specificity of 99.2%, 98.8%, and 99.6%, respectively. The 3D-VNet network outperforms previous segmentation methods by accurately calibrating lung nodules of various sizes and shapes with excellent robustness. The classification model’s metrics show that the suggested method outperforms current approaches regarding accuracy, specificity, sensitivity and F1-Score.

의미론적 분할 기반 모델을 이용한 조선소 사외 적치장 객체 자동 관리 기술

In the shipyard, aerial images are acquired at regular intervals using Unmanned Aerial Vehicles (UAVs) for the management of external storage yards. These images are then investigated by humans to manage the status of the storage yards. This method requires a significant amount of time and manpower especially for large areas. In this paper, we propose an automated management technology based on a semantic segmentation foundation model to address these challenges and accurately assess the status of external storage yards. In addition, as there is insufficient publicly available dataset for external storage yards, we collected a small-scale dataset for external storage yards objects and equipment. Using this dataset, we fine-tune an object detector and extract initial object candidates. They are utilized as prompts for the Segment Anything Model(SAM) to obtain precise semantic segmentation results. Furthermore, to facilitate continuous storage yards dataset collection, we propose a training data generation pipeline using SAM. Our proposed method has achieved 4.00%p higher performance compared to those of previous semantic segmentation methods on average. Specifically, our method has achieved 5.08% higher performance than that of SegFormer.

Fruit tree canopy segmentation from UAV orthophoto maps based on a lightweight improved U-Net

Segmenting fruit tree canopies from drone remote sensing images is a prerequisite for achieving accurate agricultural monitoring and precision aerial spraying at the individual tree (instance) level. However, current instance segmentation algorithms for canopy segmentation require repeated sampling of digital orthophoto maps (DOMs), resulting in high computational complexity and poor performance in densely planted orchards. Therefore, we propose a canopy labeling method suitable for U-Net and a lightweight segmentation network, where a lightweight backbone network, an attention mechanism, and a focal loss function are introduced to improve the U-Net decoder, greatly reducing the computational complexity required for large-scale canopy segmentation. The feasibility and effectiveness of the proposed method were validated using datasets from two seasons of two different lychee orchards. The average recognition rate of the improved U-Net was 90.98 %, 28.59 % higher than the basic model U-Net, and the floating-point operations (FLOPs) amounted to 50.86 GFLOPS, 27.67 % lower than the basic model U-Net. Under the same experimental conditions, the proposed model outperformed mainstream semantic segmentation models such as Deeplabv3 + and ResNet50-U-Net, and it was more efficient than previous instance segmentation methods based on YOLACT, as it does not require repeated sampling of the same region. For the same area, the number of sampled small images decreased from 194 to 78, resulting in a 148 % overall efficiency improvement while achieving better segmentation results. Thus, the proposed model can be used to extract and locate the crown of a lychee orchard, aiding in accurate management of a lychee orchard and in a differentiated agricultural analysis and decision-making for individual lychee trees.

Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures.

Segmenting highly-overlapping image objects is challenging, because there is typically no distinction between real object contours and occlusion boundaries on images. Unlike previous instance segmentation methods, we model image formation as a composition of two overlapping layers, and propose Bilayer Convolutional Network (BCNet), where the top layer detects occluding objects (occluders) and the bottom layer infers partially occluded instances (occludees). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We investigate the efficacy of bilayer structure using two popular convolutional network designs, namely, Fully Convolutional Network (FCN) and Graph Convolutional Network (GCN). Further, we formulate bilayer decoupling using the vision transformer (ViT), by representing instances in the image as separate learnable occluder and occludee queries. Large and consistent improvements using one/two-stage and query-based object detectors with various backbones and network layer choices validate the generalization ability of bilayer decoupling, as shown by extensive experiments on image instance segmentation benchmarks (COCO, KINS, COCOA) and video instance segmentation benchmarks (YTVIS, OVIS, BDD100 K MOTS), especially for heavy occlusion cases.

Efficient and Low Color Information Dependency Skin Segmentation Model

Skin segmentation involves segmenting the human skin region in an image. It is a preprocessing technique mainly used in many applications such as face detection, hand gesture recognition, and remote biosignal measurements. As the performance of skin segmentation directly affects the performance of these applications, precise skin segmentation methods have been studied. However, previous skin segmentation methods are unsuitable for real-world environments because they rely heavily on color information. In addition, deep-learning-based skin segmentation methods incur high computational costs, even though skin segmentation is mainly used for preprocessing. This study proposes a lightweight skin segmentation model with a high performance. Additionally, we used data augmentation techniques that modify the hue, saturation, and values, allowing the model to learn texture or contextual information better without relying on color information. Our proposed model requires 1.09M parameters and 5.04 giga multiply-accumulate. Through experiments, we demonstrated that our proposed model shows high performance with an F-score of 0.9492 and consistent performance even for modified images. Furthermore, our proposed model showed a fast processing speed of approximately 68 fps, based on 3 × 512 × 512 images and an NVIDIA RTX 2080TI GPU (11GB VRAM) graphics card.

Realistic CT data augmentation for accurate deep-learning based segmentation of head and neck tumors in kV images acquired during radiation therapy.

Using radiation therapy (RT) to treat head and neck (H&N) cancers requires precise targeting of the tumor to avoid damaging the surrounding healthy organs. Immobilisation masks and planning target volume margins are used to attempt to mitigate patient motion during treatment, however patient motion can still occur. Patient motion during RT can lead to decreased treatment effectiveness and a higher chance of treatment related side effects. Tracking tumor motion would enable motion compensation during RT, leading to more accurate dose delivery. The purpose of this paper is to develop a method to detect and segment the tumor in kV images acquired during RT. Unlike previous tumor segmentation methods for kV images, in this paper a process for generating realistic and synthetic CT deformations was developed to augment the training data, and make the segmentation method robust to patient motion. Detecting the tumor in 2D kV images is a necessary step towards 3D tracking of the tumor position during treatment. In this paper a conditional generative adversarial network (cGAN) is presented that can detect and segment the gross tumor volume (GTV) in kV images acquired during H&N RT. Retrospective data from 15 H&N cancer patients obtained from the Cancer Imaging Archive were used to train and test patient-specific cGANs. The training data consisted of digitally reconstructed radiographs (DRRs) generated from each patient's planning CT and contoured GTV. Training data was augmented by using synthetically deformed CTs to generate additional DRRs (in total 39600 DRRs per patient or 25200 DRRs for nasopharyngeal patients) containing realistic patient motion. The method for deforming the CTs was a novel deformation method based on simulating head rotation and internal tumor motion. The testing dataset consisted of 1080 DRRs for each patient, obtained by deforming the planning CT and GTV at different magnitudes to the training data. The accuracy of the generated segmentations was evaluated by measuring the segmentation centroid error, Dice similarity coefficient (DSC) and mean surface distance (MSD). This paper evaluated the hypothesis that when patient motion occurs, using a cGAN to segment the GTV would create a more accurate segmentation than no-tracking segmentations from the original contoured GTV, the current standard-of-care. This hypothesis was tested using the 1-tailed Mann-Whitney U-test. The magnitude of our cGAN segmentation centroid error was (mean ± standard deviation) 1.1 ± 0.8 millimeters and the DSC and MSD values were 0.90 ± 0.03 and 1.6 ± 0.5 millimeters respectively. Our cGAN segmentation method reduced the segmentation centroid error (p<0.001), and MSD (p = 0.031) when compared to the no-tracking segmentation, but did not significantly increase the DSC (p = 0.294). The accuracy of our cGAN segmentation method demonstrates the feasibility of this method for H&N cancer patients during RT. Accurate tumor segmentation of H&N tumors would allow for intrafraction monitoring methods to compensate for tumor motion during treatment, ensuring more accurate dose delivery and enabling better H&N cancer patient outcomes. This article is protected by copyright. All rights reserved.

Improved Fracture Segmentation from Unwrapped Drill-Core Images Using an Innovative Two-Stage Segmentation Approach

While machine learning (ML) provides a great tool for image analysis, obtaining accurate fracture segmentation from high-resolution core images is challenging. A major reason is that the segmentation quality of large and detailed objects, such as fractures, is limited by the capacity of the segmentation branch. This challenge can be seen in the Mask Region-based Convolutional Neural Network (Mask R-CNN), which is a common and well-validated instance segmentation model. This study proposes a two-stage segmentation approach using Mask R-CNN to improve fracture segmentation from unwrapped-core images. Two CNN models are used: the first model processes full-size unwrapped-core images to detect and segment fractures; the second model performs a more detailed segmentation by processing smaller regions of the images that include the fractures detected by the first model. In addition, the procedure uses a new architecture of Mask R-CNN with a point-based rendering (PointRend) neural network module that can increase segmentation accuracy. The method is evaluated on approximately 47 m of core from four boreholes and results in an improvement to previous fracture segmentation methods. It achieves an increase in the average intersection over union of approximately 27% from the baseline (one-stage segmentation with standard Mask R-CNN). The enhanced fracture segmentation provides a mean for obtaining an accurate fracture aperture with an average error of less than 1 mm, which represents a reduction of 0.5 mm from the baseline method. This work presents a novel contribution towards developing an ML-based workflow for core-image analysis.

Interpretable machine learning-based approach for customer segmentation for new product development from online product reviews

For new product development, previous segmentation methods based on demographic, psychographic, and purchase behavior information cannot identify a group of customers with unsatisfied needs. Moreover, segmentation is limited to sales promotions in marketing. Although needs-based segmentation considering customer sentiments on product features can be conducted to develop a new product concept, it cannot identify commonalities among customers owing to their diverse preferences. Therefore, this paper proposes an interpretable machine learning-based approach for customer segmentation for new product development based on the importance of product features from online product reviews. The technical challenges of determining the importance of product features in each review are identifying and interpreting the nonlinear relations between satisfaction with product features and overall customer satisfaction. In this study, interpretable machine learning is used to identify these nonlinear relations with high performance and transparency. A case study on a wearable device is conducted to validate the proposed approach. Customer segmentation using the proposed approach based on importance is compared with that employing a previous approach based on sentiments. The results show that the proposed approach presents a higher clustering performance than the previous approach and offers opportunities to identify new product concepts.

An Efficient Framework for Accurate Liver Segmentation in Abdominal CT Images with Low Knowledge Requirement

Liver segmentation from abdominal computed tomography (CT) images is a primary step in the diagnosis and treatment of liver cancer, but previous liver segmentation methods have the problems of excessive demand for prior knowledge, under- and oversegmentation, and boundary leakage. To solve these problems, this paper proposes a new method of liver segmentation to assist doctors in medical judgment. Firstly, a liver reconstruction algorithm is proposed to obtain the approximate initial region of the liver, which reduces the requirement of prior knowledge and can reconstruct the liver region closer to the liver boundary. Then, we refine the edge of the liver region based on the reaction diffusion level set (RD level set). This edge refinement method can effectively deal with the weak boundary problem, prevent under- and oversegmentation, and obtain a more accurate liver region. Our method is verified on the clinical and public datasets, respectively. The segmentation results in terms of mean VOE, RVD, ASD, RMSD, and MSD on dataset Sliver07 are 5.1%, −0.1%, 1.0 mm, 2.0 mm, and 18.2 mm, and on dataset 3Dircadb are 8.1%, −0.2%, 1.5 mm, 2.4 mm, and 20.8 mm, respectively. Compared with the previous algorithms, the experiment results show that this method has a great improvement in accuracy with less prior knowledge. The liver reconstruction algorithm proposed in this paper can obtain a more accurate initial liver region, reduce the requirement for prior knowledge, and reduce time costs compared with the level set algorithm.

A new procedure for lung region segmentation from computed tomography images

&lt;span lang="EN-US"&gt;Lung cancer is the leading cause of cancer death among people worldwide. The primary aim of this research is to establish an image processing method for lung cancer detection. This paper focuses on lung region segmentation from computed tomography (CT) scan images. In this work, a new procedure for lung region segmentation is proposed. First, the lung CT scan images will undergo an image thresholding stage before going through two morphological reconstruction and masking stages. In between morphological and masking stages, object extraction, border change, and object elimination will occur. Finally, the lung field will be annotated. The outcomes of the proposed procedure and previous lung segmentation methods i.e., the modified watershed segmentation method is compared with the ground truth images for performance evaluation that will be carried out both in qualitative and quantitative manners. Based on the analyses, the new proposed procedure for lung segmentation, denotes better performance, an increment by 0.02% to 3.5% in quantitative analysis. The proposed procedure produced better-segmented images for qualitative analysis and became the most frequently selected method by the 22 experts. This study shows that the outcome from the proposed method outperforms the existing modified watershed segmentation method.&lt;/span&gt;

Research on Semantic Segmentation Method of Macular Edema in Retinal OCT Images Based on Improved Swin-Unet

Optical coherence tomography (OCT), as a new type of tomography technology, has the characteristics of non-invasive, real-time imaging and high sensitivity, and is currently an important medical imaging tool to assist ophthalmologists in the screening, diagnosis, and follow-up treatment of patients with macular disease. In order to solve the problem of irregular occurrence area of diabetic retinopathy macular edema (DME), multi-scale and multi-region cluster of macular edema, which leads to inaccurate segmentation of the edema area, an improved Swin-Unet networks model was proposed for automatic semantic segmentation of macular edema lesion areas in OCT images. Firstly, in the deep bottleneck of the Swin-Unet network, the Resnet network layer was used to increase the extraction of pairs of sub-feature images. Secondly, the Swin Transformer block and skip connection structure were used for global and local learning, and the regions after semantic segmentation were morphologically smoothed and post-processed. Finally, the proposed method was performed on the macular edema patient dataset publicly available at Duke University, and was compared with previous segmentation methods. The experimental results show that the proposed method can not only improve the overall semantic segmentation accuracy of retinal macular edema, but also further to improve the semantic segmentation effect of multi-scale and multi-region edema regions.

Fuzzy-Based Approach for Clustering Data with Multivalued Features

In analysis of data, objects have mostly been characterized by a set of characteristics known as attributes, which together contained only one value for each object. Besides that, a few attributes in reality could include with more than a single value; such as from a human beside multiple profession characterizations, practises, communication methods, and capabilities, in addition to shipping addresses, of that kind of attributes are referred to as multivalued attributes and are typically regarded as null attributes when data is processed employing machine learning procedures. Throughout this article, another similarity mechanism is introduced that is defined around including multivalued characteristics which can be used for grouping. We propose a model to analyse each factor’s relative prominence for different data collection challenges in order to enable the selection among the most suited multivalued elements. The suggested methodology is a clustering technique for development and evolution that employs fuzzy c-means clustering and retains the new and more effective membership component by implementing the proposed similarity metric. Clustering of multivalued variables using fuzzy c-means is the efficient grouping criteria that results; any methodology to group-related data appears viable. The results show that our assessment not only improves previous segmentation methods on the multivalued cluster-based architecture but also helps in the improvement of the standard similarity metrics.

A Semi-Supervised Semantic Segmentation Method for Blast-Hole Detection

The goal of blast-hole detection is to help place charge explosives into blast-holes. This process is full of challenges, because it requires the ability to extract sample features in complex environments, and to detect a wide variety of blast-holes. Detection techniques based on deep learning with RGB-D semantic segmentation have emerged in recent years of research and achieved good results. However, implementing semantic segmentation based on deep learning usually requires a large amount of labeled data, which creates a large burden on the production of the dataset. To address the dilemma that there is very little training data available for explosive charging equipment to detect blast-holes, this paper extends the core idea of semi-supervised learning to RGB-D semantic segmentation, and devises an ERF-AC-PSPNet model based on a symmetric encoder–decoder structure. The model adds a residual connection layer and a dilated convolution layer for down-sampling, followed by an attention complementary module to acquire the feature maps, and uses a pyramid scene parsing network to achieve hole segmentation during decoding. A new semi-supervised learning method, based on pseudo-labeling and self-training, is proposed, to train the model for intelligent detection of blast-holes. The designed pseudo-labeling is based on the HOG algorithm and depth data, and proved to have good results in experiments. To verify the validity of the method, we carried out experiments on the images of blast-holes collected at a mine site. Compared to the previous segmentation methods, our method is less dependent on the labeled data and achieved IoU of 0.810, 0.867, 0.923, and 0.945, at labeling ratios of 1/8, 1/4, 1/2, and 1.

Automatic 3-D segmentation and volumetric light fluence correction for photoacoustic tomography based on optimal 3-D graph search.

Preclinical imaging with photoacoustic tomography (PAT) has attracted wide attention in recent years since it is capable of providing molecular contrast with deep imaging depth. The automatic extraction and segmentation of the animal in PAT images is crucial for improving image analysis efficiency and enabling advanced image post-processing, such as light fluence (LF) correction for quantitative PAT imaging. Previous automatic segmentation methods are mostly two-dimensional approaches, which failed to conserve the 3-D surface continuity because the image slices were processed separately. This discontinuity problem further hampers LF correction, which, ideally, should be carried out in 3-D due to spatially diffused illumination. Here, to solve these problems, we propose a volumetric auto-segmentation method for small animal PAT imaging based on the 3-D optimal graph search (3-D GS) algorithm. The 3-D GS algorithm takes into account the relation among image slices by constructing a 3-D node-weighted directed graph, and thus ensures surface continuity. In view of the characteristics of PAT images, we improve the original 3-D GS algorithm on graph construction, solution guidance and cost assignment, such that the accuracy and smoothness of the segmented animal surface were guaranteed. We tested the performance of the proposed method by conducting in vivo nude mice imaging experiments with a commercial preclinical cross-sectional PAT system. The results showed that our method successfully retained the continuous global surface structure of the whole 3-D animal body, as well as smooth local subcutaneous tumor boundaries at different development stages. Moreover, based on the 3-D segmentation result, we were able to simulate volumetric LF distribution of the entire animal body and obtained LF corrected PAT images with enhanced structural visibility and uniform image intensity.

Enhanced Automatic Segmentation for Superficial White Matter Fiber Bundles for Probabilistic Tractography Datasets.

This paper presents an enhanced algorithm for automatic segmentation of superficial white matter (SWM) bundles from probabilistic dMRI tractography datasets, based on a multi-subject bundle atlas. Previous segmentation methods use the maximum Euclidean distance between corresponding points of the subject fibers and the atlas centroids. However, this scheme might include noisy fibers. Here, we propose a three step approach to discard noisy fibers improving the identification of fibers. The first step applies a fiber clustering and the segmentation is performed between the centroids of the clusters and the atlas centroids. This step removes outliers and enables a better identification of fibers with similar shapes. The second step applies a fiber filter based on two different fiber similarities. One is the Symmetrized Segment-Path Distance (SSPD) over 2D ISOMAP and the other is an adapted version of SSPD for 3D space. The last step eliminates noisy fibers by removing those that connect regions that are far from the main atlas bundle connections. We perform an experimental evaluation using ten subjects of the Human Connectome (HCP) database. The evaluation only considers the bundles connecting precentral and postcentral gyri, with a total of seven bundles per hemisphere. For comparison, the bundles of the ten subjects were manually segmented. Bundles segmented with our method were evaluated in terms of similarity to manually segmented bundles and the final number of fibers. The results show that our approach obtains bundles with a higher similarity score than the state-of-the-art method and maintains a similar number of fibers.Clinical relevance-Many brain pathologies or disorders can occur in specific regions of the SWM automatic segmentation of reliable SWM bundles would help applications to clinical research.

An Automatic Knee Osteoarthritis Diagnosis Method Based on Deep Learning: Data from the Osteoarthritis Initiative.

Osteoarthritis (OA) is the most common form of arthritis. According to the evidence presented on both sides of the knee bones, radiologists assess the severity of OA based on the Kellgren–Lawrence (KL) grading system. Recently, computer-aided methods are proposed to improve the efficiency of OA diagnosis. However, the human interventions required by previous semiautomatic segmentation methods limit the application on large-scale datasets. Moreover, well-known CNN architectures applied to the OA severity assessment do not explore the relations between different local regions. In this work, by integrating the object detection model, YOLO, with the visual transformer into the diagnosis procedure, we reduce human intervention and provide an end-to-end approach to automatic osteoarthritis diagnosis. Our approach correctly segments 95.57% of data at the expense of training on 200 annotated images on a large dataset that contains more than 4500 samples. Furthermore, our classification result improves the accuracy by 2.5% compared to the traditional CNN architectures.

Edge and neighborhood guidance network for 2D medical image segmentation

Accurate automatic image segmentation is important in medical image analysis. A perfect segmentation using fully convolutional network (FCN) means an accurate classification of each pixel. However, it is still a great challenge to accurately differentiate edge pixels from neighborhood pixels in weak edge regions. Many previous segmentation methods have focused on edge information to mitigate weak edge problems, but the more important neighborhood information is undervalued. To tackle this problem, in this paper, we propose a novel yet effective Edge and Neighborhood Guidance Network (ENGNet). Specifically, instead of just utilizing the edge information as the shape constraints, the edge and neighborhood guidance (ENG) module is designed to exploit the edge information and fine-grained neighborhood spatial information simultaneously, so as to improve the ability of network to classify edge pixels and neighborhood pixels in weak edge regions. Moreover, the ENG modules are adopted in different scales to learn sufficient feature representations of edge and neighborhood. To extract complementary features more effectively in channel dimension, we also design a multi-scale adaptive selection (MAS) module at channel-wise to extract multi-scale context information and adaptively fuse different-scale features. Two 2D public segmentation datasets including skin lesion dataset and endoscopic polyp dataset are used to evaluate the performance of the proposed ENGNet. Experimental results demonstrated that by exploiting edge information and neighborhood spatial information in different scales simultaneously, the proposed ENGNet can effectively alleviate the misclassification in weak edge regions and achieve better performance than other state-of-the-art methods.

Development of a Gold-standard Pashto Dataset and a Segmentation App

The article aims to introduce a gold-standard Pashto dataset and a segmentation app. The Pashto dataset consists of 300 line images and corresponding Pashto text from three selected books. A line image is simply an image consisting of one text line from a scanned page. To our knowledge, this is one of the first open access datasets which directly maps line images to their corresponding text in the Pashto language. We also introduce the development of a segmentation app using textbox expanding algorithms, a different approach to OCR segmentation.&#x0D; The authors discuss the steps to build a Pashto dataset and develop our unique approach to segmentation. The article starts with the nature of the Pashto alphabet and its unique diacritics which require special considerations for segmentation. Needs for datasets and a few available Pashto datasets are reviewed. Criteria of selection of data sources are discussed and three books were selected by our language specialist from the Afghan Digital Repository. The authors review previous segmentation methods and introduce a new approach to segmentation for Pashto content. The segmentation app and results are discussed to show readers how to adjust variables for different books. Our unique segmentation approach uses an expanding textbox method which performs very well given the nature of the Pashto scripts.&#x0D; The app can also be used for Persian and other languages using the Arabic writing system. The dataset can be used for OCR training, OCR testing, and machine learning applications related to content in Pashto.