Schemes For Segmentation Research Articles

Pseudo-Label Guided Image Synthesis for Semi-Supervised COVID-19 Pneumonia Infection Segmentation.

Coronavirus disease 2019 (COVID-19) has become a severe global pandemic. Accurate pneumonia infection segmentation is important for assisting doctors in diagnosing COVID-19. Deep learning-based methods can be developed for automatic segmentation, but the lack of large-scale well-annotated COVID-19 training datasets may hinder their performance. Semi-supervised segmentation is a promising solution which explores large amounts of unlabelled data, while most existing methods focus on pseudo-label refinement. In this paper, we propose a new perspective on semi-supervised learning for COVID-19 pneumonia infection segmentation, namely pseudo-label guided image synthesis. The main idea is to keep the pseudo-labels and synthesize new images to match them. The synthetic image has the same COVID-19 infected regions as indicated in the pseudo-label, and the reference style extracted from the style code pool is added to make it more realistic. We introduce two representative methods by incorporating the synthetic images into model training, including single-stage Synthesis-Assisted Cross Pseudo Supervision (SA-CPS) and multi-stage Synthesis-Assisted Self-Training (SA-ST), which can work individually as well as cooperatively. Synthesis-assisted methods expand the training data with high-quality synthetic data, thus improving the segmentation performance. Extensive experiments on two COVID-19 CT datasets for segmenting the infections demonstrate our method is superior to existing schemes for semi-supervised segmentation, and achieves the state-of-the-art performance on both datasets. Code is available at: https://github.com/FeiLyu/SASSL.

A Study of Techniques for Segmenting the Spinal Cord

The spinal cord is one of the most important organs that controls communication between the brain and various parts of the body. It is highly susceptible to harmful infections and many diseases. An important criterion of clinical management is the appropriate localization and division of the spinal cord. Segmentation poses risks associated with variation in human anatomy and contrast variation in Magnetic Resonance Imaging. Therefore, an effective segmentation technique should be developed for effective division of the spinal cord and disc localization. In comparison, the survey contained here in provides an overview of different segmentation schemes for spinal cord segmentation. Now, there is an urgent need to develop an effective segmentation approach that is better than the current one segmentation methods. In this research article, a detailed survey of the various research activities presented by specific segmentation schemes based on the semi-automated, active contour model, Introduced partitioning, deformable model, probabilistic model and graph based partitioning. In addition, in-depth analysis and discussion are provided in accordance with the year of publication, evaluation dimensions, segmentation scheme, and magnetic Resonance Image Datasets, Dice Equivalence Coefficient (DSC), Accuracy.

A 3D image segmentation for lung cancer using V.Net architecture based deep convolutional networks

Lung segmentation of chest CT scan is utilised to identify lung cancer and this step is also critical in other diagnostic pathways. Therefore, powerful algorithms to accomplish this accurate segmentation task are highly needed in the medical imaging domain, where the tumours are required to be segmented with the lung parenchyma. Also, the lung parenchyma needs to be detached from the tumour regions that are often confused with the lung tissue. Recently, lung semantic segmentation is more suitable to allocate each pixel in the image to a predefined class based on fully convolutional networks (FCNs). In this paper, CT cancer scans from the Task06_Lung database were applied to FCN that was inspired by V.Net architecture for efficiently selecting a region of interest (ROI) using the 3D segmentation. This lung database is segregated into 64 training images and 32 testing images. The proposed system is generalised by three steps including data preprocessing, data augmentation and neural network based on the V-Net model. Then, it was evaluated by dice score coefficient (DSC) to calculate the ratio of the segmented image and the ground truth image. This proposed system outperformed other previous schemes for 3D lung segmentation with an average DCS of 80% for ROI and 98% for surrounding lung tissues. Moreover, this system demonstrated that 3D views of lung tumours in CT images precisely carried tumour estimation and robust lung segmentation.

Phase-based thresholding schemes for segmentation of fetal thigh cross-sectional region in ultrasound images

Measurement of thigh circumference has been used as an indication of nutritional adequacy and fetal growth in the womb. Fractional thigh volume is one of the variables for estimating fetal weight that is also calculated using the fetal thigh circumference. This cross-section of the fetal thigh is an intricate part of detecting because it has a less clear boundary and sometimes attached to other tissue in the ultrasound image. This study aims to establish a detection scheme and segmentation of the fetal thigh cross-sectional area automatically on ultrasound images. We propose a segmentation framework that integrates two phase-based thresholding schemes and a gap connecting step. In the first scheme, we combine the phase congruency of the local phase features and the fuzzy entropy method. The second thresholding scheme is a combination of the phase symmetry method and the saliency visual attention model. The proposed framework has the advantage of being able to segment cross-sectional objects more precisely, even though there are other objects attached to them. This method also works well when applied to low-quality ultrasound images taken using a portable ultrasound scanner. This proposed segmentation method exhibits an average performance precision of 0.922 and a Dice similarity of 0.928.

The Development, Operation and Performance of the 5G Polar Codes

Since their inception in 2008, polar codes have been shown to offer near-capacity error correction performance across a wide range of block lengths and coding rates. Owing to this, polar codes have been selected to provide channel coding in the control channels of Third Generation Partnership Project (3GPP) New Radio (NR). The operation of the 3GPP NR polar codes is specified in the 3GPP standard TS 38.212, together with schemes for code block segmentation, Cyclic Redundancy Check (CRC) attachment, CRC scrambling, CRC interleaving, frozen and parity check bit insertion, sub-block interleaving, bit selection, channel interleaving and code block concatenation. The configuration of these components is different for the uplink, broadcast and downlink control channels. However, the lack of visualisations and diagrammatic explanations in TS 38.212 limits the accessibility of the standard to new readers. This motivates the aims of the paper, which provides detailed tutorials on the operation and motivation of the components of the 3GPP NR polar codes, as well as surveys of the 3GPP discussions that led to their specification. Furthermore, we comprehensively characterize the error correction and error detection performance of the 3GPP NR polar codes in the uplink, broadcast and downlink control channels.

A novel local contrast fusion-based fuzzy model for color image multilevel thresholding using grasshopper optimization

The segmentation process is considered the significant step of an image processing system due to its extreme inspiration on the subsequent image analysis. Out of various approaches, thresholding is one of the most popular schemes for image segmentation. In segmentation, image pixels are arranged in various regions based on their intensity levels. In this paper, a straightforward and efficient fusion-based fuzzy model for multilevel color image segmentation using grasshopper optimization algorithm (GOA) has been proposed. Thresholding based segmentation lacks accuracy in segmenting the ambiguous images due to their complex characteristics, uncertainties and inherent fuzziness. However, the fuzzy entropy resolves these problems, but it is unable for segmenting at higher levels and also the complexity level for selecting suitable thresholds is high. The selection of metaheuristic GOA reduces this problem by selecting optimal threshold values. Therefore, to increase the quality of the segmented image, a simple and effective multilevel thresholding method is exploited by using the concept of fusion which is based on the local contrast. Experimental outputs demonstrate that fusion-based multilevel thresholding is better than most specific segmentation methods and can be validated by comparing the different numerical parameters. Experiments on standard daily-life color and satellite images are conducted to prove the effectiveness of the proposed scheme.

Evaluation of flood season segmentation using seasonal exceedance probability measurement after outlier identification in the Three Gorges Reservoir

Flood season segmentation, which partitions an entire flood season into multiple subseasons, constitutes a considerable water resources management task. Moreover, the risks associated with various schemes for flood season segmentation should be evaluated. Preliminary analysis in this study used the principal component based outlier detection (PCOut) algorithm to identify possible outlying observations to reduce the uncertainty involved in flood season segmentation. Then, a quantitative measurement, the seasonal exceedance probability (SEP), was proposed to evaluate various segmentation schemes. The SEP quantifies the risk that the maximum observation occurs outside the main flood season. Several findings were derived based on a case study of China’s Three Gorges Reservoir (TGR) and daily streamflow records (1882–2010). (1) The PCOut algorithm was found effective in identifying outliers, and the estimation uncertainty of the segmentation evaluation due to outliers decreased when the end date of main flood season (EDMFS) was postponed. (2) The proposed SEP measurement was shown capable of supporting quantitative evaluation of the segmentation schemes in the flood season. (3) The current flood segmentation scheme based on an EDMFS of September 10 is sufficiently safe for the TGR. The findings of this study could help in the proper operation of the TGR.

Topology Preserving Discretization Schemes for Digital Image Segmentation and Digital Models of the Plane

In this paper, discretization schemes are defined and studied that allow us to build digital models of 2-dimensional continuous objects with the same topological properties as their continuous counterparts. In particular, it is shown that the digital model of the plane is necessarily the digital 2-surface defined and studied in the context of digital topology. It is shown that in proposed discretization schemes, any required resolution can be used in any area of the object of interest. Finally, we describe a method, which transforms regions of interest produced by the image acquisition process into digital spaces with topological features of the regions.

Effective elliptic fitting for iris normalization

Having an accurate parametric description of the iris borders is a critical issue for iris recognition systems based on Daugman’s rubber sheet normalization. Many methods in the literature use very powerful and effective schemes for iris segmentation but often apply a simple estimator procedure, such as the Hough Transform or Least Square Fitting to get this parametric description. Those fitting methods are very sensitive to the segmentation quality as inaccuracies will provoke large errors in the resulting contour.In this article we propose an effective way to find optimal parameters for ellipses in order to proceed the normalization. Our method is based on a variational formulation of the well-known Active Contour techniques leading to a compact formulation for elliptic contours. We show improvements compared to an Elliptic Hough Transform and a Direct Least Square Fitting on the following databases: ICE2005, ND-Iris and Casia-Lamp. We also demonstrate that our scheme can be paired effectively with different segmentation algorithms. Significant improvements of the recognition results were obtained when adding our algorithm after the segmentation stage of VASIR and OSIRIS, two open source packages for iris recognition.

Microarray Image Processing and Quality Control

Image processing is an important stage of every microarray experiment. Reliability of this stage strongly influences the results of data analysis performed on extracted gene expressions. Multiple methods related to array recognition, spot segmentation and measurement extraction have emerged in this area over past several years. Currently there are various commercial and freeware packages available, which perform microarray image analysis. This paper attempts to review microarray image analysis as a whole and to make some experimental comparison of several computational schemes for signal segmentation and measurement extraction. Also we provide a detailed discussion of automated image quality control for use with microarray images.

Globally convergent iterative numerical schemes for nonlinear variational image smoothing and segmentation on a multiprocessor machine

We investigate several iterative numerical schemes for nonlinear variational image smoothing and segmentation implemented in parallel. A general iterative framework subsuming these schemes is suggested for which global convergence irrespective of the starting point can be shown. We characterize various edge-preserving regularization methods from the image processing literature involving auxiliary variables as special cases of this general framework. As a by-product, global convergence can be proven under conditions slightly weaker than these stated in the literature. Efficient Krylov subspace solvers for the linear parts of these schemes have been implemented on a multiprocessor machine. The performance of these parallel implementations has been assessed and empirical results concerning convergence rates and speed-up factors are reported.

A Compression-based Algorithm for Chinese Word Segmentation

Chinese is written without using spaces or other word delimiters. Although a text may be thought of as a corresponding sequence of words, there is considerable ambiguity in the placement of boundaries. Interpreting a text as a sequence of words is beneficial for some information retrieval and storage tasks: for example, full-text search, word-based compression, and keyphrase extraction. We describe a scheme that infers appropriate positions for word boundaries using an adaptive language model that is standard in text compression. It is trained on a corpus of presegmented text, and when applied to new text, interpolates word boundaries so as to maximize the compression obtained. This simple and general method performs well with respect to specialized schemes for Chinese language segmentation.

Sonar image segmentation using an unsupervised hierarchical MRF model

This paper is concerned with hierarchical Markov random field (MRP) models and their application to sonar image segmentation. We present an original hierarchical segmentation procedure devoted to images given by a high-resolution sonar. The sonar image is segmented into two kinds of regions: shadow (corresponding to a lack of acoustic reverberation behind each object lying on the sea-bed) and sea-bottom reverberation. The proposed unsupervised scheme takes into account the variety of the laws in the distribution mixture of a sonar image, and it estimates both the parameters of noise distributions and the parameters of the Markovian prior. For the estimation step, we use an iterative technique which combines a maximum likelihood approach (for noise model parameters) with a least-squares method (for MRF-based prior). In order to model more precisely the local and global characteristics of image content at different scales, we introduce a hierarchical model involving a pyramidal label field. It combines coarse-to-fine causal interactions with a spatial neighborhood structure. This new method of segmentation, called the scale causal multigrid (SCM) algorithm, has been successfully applied to real sonar images and seems to be well suited to the segmentation of very noisy images. The experiments reported in this paper demonstrate that the discussed method performs better than other hierarchical schemes for sonar image segmentation.