Multiphase Level Set Research Articles

Three-dimensional topology optimization of Ni-YSZ anode for solid oxide fuel cells via multiphase level-set method

In the present study, numerical model is developed to optimize the 3D multiphase electrode microstructure for SOFC, e.g. nickel-yttria-stabilized zirconia (Ni-YSZ) anode. During the optimization, Ni-YSZ microstructure is deformed in order to maximize the total reaction current. Multiphase level-set (MLS) model is applied to represent the Ni-YSZ anode microstructure, and adjoint method is applied for the sensitivity analysis. In addition, in order to improve the computational accuracy and to make the optimized microstructure manufacturable, a radius constraint is imposed to ensure that the local particle radii are kept larger than a target value (Rtarget), where the interface is updated only when the local radius value is larger than Rtarget. It is also confirmed that the optimized microstructure and performance of the Ni-YSZ anode are independent of the initial structures and the phase division schemes. According to the optimization results, the optimized electrochemical performances are improved, and the particle and pore radii of the microstructure successfully remained larger than the target values. The optimized Ni-YSZ microstructures are composed of Ni particles embedded into a YSZ scaffold which has a pillar-like shape along the anode thickness direction.

Segmentation of mammogram images using level set with Cuckoo search optimisation

ABSTRACT Breast cancer is alone accounted for 30% of all new cancer diagnoses for women. Early identification of breast cancer is a key stage in the process of diagnosis and treatment. Segmenting of low contrast mammograms is not an easy task due to irregular mass form, speculated margins and variation in intensity levels. Most of the region-based technique works well for homogenous images but fails for intensity inhomogeneity. Multiphase level set segmentation is optimised by the cuckoo search approach for energy minimisation. The proposed multiphase level set with the cuckoo optimisation method performs well in segmenting homogeneous as well as inhomogeneous regions. The Chan Vese (CV) and the proposed method are applied to the Mammographic Image Analysis Society (MIAS) database to obtain the accurate contour of the masses. To validate the proposed approach using quantitative performance measures such as Jaccard coefficient (JC), dice coefficient (DC), Hausdorff distance (Hd), sensitivity, specificity and accuracy were used for the MIAS data set. The results indicate that the suggested method can successfully segment the breast mass in mammograms and more robust than the classical CV method.

A Computer Aided Breast Cancer Detection Using Unit-Linking Pulse Coupled Neural Network & Multiphase Level Set Method

Breast cancer is one of the lethal diseases with high mortality rates among women. An early detection and diagnosis of the disease can help increase the survival rate. Distinguishing a normal breast tissue from a cancerous one proves to be ambiguous for a Radiologist. A computer aided system can help a radiologist in better and efficient diagnosis. This paper aims at detection and classification of benign and malignant mammogram images with Unit-linking Pulse Coupled Neural Network combined with Multiphase level set Method. While Unit linking Pulse Coupled Neural Network (PCNN) helps in coarse feature extraction, Multi phase Level Set method helps in extracting minute details and hence, better classification. The proposed method is tested with images from MIAS open-source database. Performance of the proposed method is measured using sensitivity, accuracy, specificity and false positive rate. Experiments show that the proposed method gives satisfactory results when compared to the state-of-art methods. The sensitivity obtained by the proposed method is 95.16%, an accuracy of 96.76%, the False Positive Rate (FPR) is as less as 0.85% and specificity of 97.12%.

MRI Images Based on Semiautomatic Segmentation Algorithm for Prediction of Histological Grade of Breast Tumor

This study aimed to explore the effects of delayed enhanced magnetic resonance imaging (MRI) (DE-MRI) image features based on the semiautomatic circle-dependent (SCD)-based multiphase level set (MLS) (SCD-MLS) algorithm in predicting the histological grade of breast tumors. We explore the clinical effect of DE-MRI on the prediction of the histological grade of breast tumors (BTs). In this study, 264 breast tumor (BT) patients from The Second Affiliated Hospital of Soochow University were selected as the research objects, and DE-MRI examinations were performed. The SCD-MLS algorithm was compared with the Live-Wire algorithm for the segmentation effect and was applied to the DE-MRI image for prediction of the histological grade of BT. The results proved that the SCD-MLS algorithm in this study showed a more accurate segmentation effect with good stability. BT tissue showed a patchy low signal on T1WI and a high signal on T2WI. The number of patients with grade II was the highest (P < 0.05); the lesion diameters of grade II and grade III were concentrated at 1.5–2.5 cm and 2.5–3.5 cm, respectively (P < 0.05); the fractional anisotropy (FA) of patients with grade I was the largest (P < 0.05); and the apparent diffusion coefficient (ADC) of the patients with grade III was the highest (P < 0.05). In short, DE-MRI showed a good performance in the BT diagnosis, and the grading of BT tissue was related to lesion size, number of lesions, ADC, and FA.

Isogeometric topology and shape optimization for composite structures using level-sets and adaptive Gauss quadrature

The Level-Set Method (LSM) with the smooth and distinct description of structural boundaries offers more superior benefits for topology optimization. However, the classic Finite Element Method (FEM) and ersatz material method in the LSM cause numerical deficiencies in the optimization, such as iterative instability and the crispness loss of boundaries. This work focuses on developing an Isogeometric Topology and Shape Optimization (ITSO) method for the design of composite structures, in which a Non-Uniform Rational B-splines (NURBS)-based Multi-phase Level-Sets (NM-LS) model is constructed to present the distribution of multiple materials. The NM-LS model consists of an immersed representation using level-sets, NURBS parameterized level-sets and its development. Isogeometric Analysis (IGA) with adaptive Gauss quadrature method are applied to solve unknown structural responses, which can effectively remove several numerical artifacts resulting from the linear interpolation of ersatz material model in both design and analysis. Three models of structural geometry, numerical analysis and topology description can be integrated by the same NURBS basis functions, which can effectively improve numerical precision and iterative stability. Finally, several 2D and 3D numerical examples are addressed to demonstrate the effectiveness and efficiency of the proposed ITSO method on the design of composite structures.

Speckle Tracking Algorithm-Based Cardiac Color Ultrasound in Diagnosis of Patients with Atrial Fibrillation Combined with Heart Failure

The study focused on the application of speckle tracking algorithm in the segmentation of cardiac color ultrasound images of patients with atrial fibrillation combined with heart failure. First, the optical flow method and block matching method were introduced on the basis of multiphase level set algorithm. Then, the pyramid block matching method was applied to build a pyramid model from bottom to top according to each image, and thus a new segmentation algorithm of cardiac color ultrasound image was constructed. The speckle tracking algorithm based on the pyramid block matching method was applied to segment cardiac color ultrasound images of 136 patients with atrial fibrillation and heart failure and compared with the traditional diagnosis for the sensitivity, specificity, and accuracy. It was found that the curve smoothness and accuracy of the algorithm in this study were better than the traditional level set algorithm, and it made up for the shortcomings of the traditional method. The proportion of patients of class III-IV cardiac function was significantly higher than that of non-atrial fibrillation patients, and the difference was statistically significant ( P < 0.05 ); patients of classes III-IV showed better left ventricular ejection fraction (LVEF) (42.4 ± 2.8%), left ventricular end-diastolic diameter (LVED) (58.7 ± 7.4 mm), left ventricular end-systolic diameter (LVSD) (49.3 ± 5.6 mm), and left atrial inner diameter (LAD) (55.0 ± 1.4 mm) versus those of classes I-II, of whom the corresponding indexes were 58.8 ± 3.3%, 48.5 ± 5.9 mm, 33.5 ± 4.5 mm, and 45.2 ± 2.0 mm. The accuracy of diagnosis based on the algorithm of this study (93.22%) was significantly higher than that of traditional method (79.23%), and the differences were statistically significant ( P < 0.05 ). In conclusion, the algorithm in this study improves the segmentation accuracy and smoothness of the curve, which is suggested in clinic.

Automated Computer Aided Diagnosis Using Altered Multi-Phase Level Sets in Application to Categorize the Breast Cancer Biopsy Images

As macroscopic Breast Cancer (BC) imaging diagnostics do not provide satisfied data, microscopic image analysis is used to get optimum cell-nuclei segmentation for image categorization. The paper presents a Novel Hybrid Segmentation Method which uses the energy detail coefficients attained from Non-Subsampled Contourlet Transform for cell-nuclei segmentation of BC histopathological images. NHSM solves the local inhomogeneities problem while preserving all necessary details. The system evaluation is done using training dataset of 98 BC histopathological images and testing dataset of 26 images. Total of 25 segmented features was extracted for classification using Decision Trees, k-Nearest Neighbor, multilayer perceptron, Multiclass-Support Vector Machine (M-SVM). The proposed NHSM segmentation results were undergone through both subjective and objective performance evaluation. Result evaluation proved that NHSM along with Multi Class-Support Vector Machine classifier provides highly precise and accurate classified result for BC tissue images compared to state-of-the-art segmentation methods. Also, the edge detection model initialization is highly robust and insensitive.

Extraction and Evaluation of Corpus Callosum from 2D Brain MRI Slice: A Study with Cuckoo Search Algorithm.

The work proposes a computer-based diagnosis method (CBDM) to delineate and assess the corpus callosum (CC) segment from the 2-dimensional (2D) brain magnetic resonance images (MRI). The proposed CBDM consists of two parts: (1) preprocessing and (2) postprocessing sections. The preprocessing tools have a multithreshold technique with the chaotic cuckoo search (CCS) algorithm and a preferred threshold procedure. The postprocessing employs a delineation process for extracting the CC section. The proposed CBDM finally extracts the vital CC parameters, such as total brain area (TBA) and CC area (CCA) to classify the considered 2D MRI slices into the control and autism spectrum disorder (ASD) groups. This attempt considers the benchmark brain MRI database which includes ABIDE and MIDAS for the experimental investigation. The results obtained with ABIDE dataset are further confirmed against the fuzzy C-means driven level set (FCM + LS) and multiphase level set (MLS) technique and the proposed CBDM with Shannon entropy along with active contour (SE + AC) presented improved result in comparison to the existing methodologies. Further, the performance of CBDM is confirmed on MIDAS and clinical dataset. The experimental outcomes approve that the proposed CBDM extracts the CC section from the 2D MR brain images that have higher accuracy compared to alternative techniques.

CT Image Segmentation of Liver Tumor with Deep Convolutional Neural Network

The liver is the largest substantial organ in the abdominal cavity of the human body. Its structure is complex, the incidence of vascular abundance is high, and it has been seriously ribbed, human health and life. In this study, an automatic segmentation method based on deep convolutional neural network is proposed. Image data blocks of different sizes are extracted as training data and different network structures are designed, and features are automatically learned to obtain a segmentation structure of the tumor. Secondly, in order to further refine the segmentation boundary, we establish a multi-region segmentation model with region mutual exclusion constraints. The model combines the image grayscale, gradient and prior probability information, and overcomes the problem that the boundary point attribution area caused by boundary blur and regional adhesion is difficult to determine. Finally, the model is solved quickly using the time-invisible multi-phase level set. Compared with the traditional multi-organ segmentation method, this method does not require registration or model initialization. The experimental results show that the model can segment the liver, kidney and spleen quickly and effectively, and the segmentation accuracy reaches the advanced level of current methods.

Adaptive segmentation model for liver CT images based on neural network and level set method

Accurate segmentation is difficult for liver computed tomography (CT) images, since the liver CT images do not always have obvious and smooth boundaries. The location of the tumor is not specified and the image intensity is similar to that of the liver. Although manual and automatic segmentation methods, traditional and deep learning models currently exist, none can be specifically and effectively applied to segment liver CT images. In this paper, we propose a new model based on a level set framework for liver CT images in which the energy functional contains three terms including the data fitting term, the length term and the bound term. Then we apply the split Bregman method to minimize the energy functional that leads the energy functional to converge faster. The proposed model is robust to initial contours and can segment liver CT images with intensity inhomogeneity and unclear boundaries. In the bound term, we use the U-Net to get constraint information which has a considerable influence on effective and accurate segmentation. We improve a multi-phase level set of our model to get contours of tumor and liver at the same time. Finally, a parallel algorithm is proposed to improve segmentation efficiency. Results and comparisons of experiments are shown to demonstrate the merits of the proposed model including robustness, accuracy, efficiency and intelligence.

A locally conservative multiphase level set method for capillary-controlled displacements in porous media

We present a multiphase level set method with local volume conservation for capillary-controlled displacement in porous structures. Standard numerical formulations of the level set method for capillary-controlled (or, curvature-driven) motions assume phase pressures and interface properties are spatially uniform and disregard the fact that separate phase ganglia typically have distinct pressures. This is a major problem for the suitability of such methods to simulate capillary trapping in porous rocks as it will lead to severe mass loss. The method presented here preserves volumes of individual phase ganglia, while it predicts capillary pressures between ganglia and surrounding phases. A conservative volume redistribution algorithm handles ganglia breakup and coalescence. The method distinguishes between three-phase systems, where separate level set functions describe the different phases, and two-phase systems, where one level set function represents interfaces. We present sequential and parallel algorithms for the new method and emphasize important aspects specific to the patch-based parallel implementation.We validate the method numerically by applying local volume conservation to simulations of two and three phase systems in both two and three spatial dimensions. The model is tested for both saturation and pressure controlled systems and handles both merging and splitting of phase ganglia.

Multi-phase level set method for precise segmentation and correction of brain MRI

Medical image segmentation as an earlier application field in image segmentation is the key technology of medical image analysis and is also a key point and difficulty in clinical application. This paper proposes an accurate and robust active contour model based on the four-phase level set for medical MR images. First we define a new energy functional by combining the data term and the length term, where the data term is defined by transforming the energy functional of the multiplicative intrinsic component optimization (MICO) model into the level set framework after adding an edge detector function. Then, when we minimize the energy functional, we use the split Bregman method to improve the convergence speed. To test the performance of our model, we do lots of experiments according to the different brain MR images, which show that even under the severe influence of bias field or shadows, our model can still segment these images well, and our model is robust to the initial contours and noise. Moreover, our model is compared with the MICO model by experimental results and the numerical values, concluding that our model is better than the MICO model no matter in segmentation accuracy or in correction effect.

Deep Multiphase Level Set for Scene Parsing.

Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to predict semantic labels around the object boundaries, thus FCN-based methods usually produce parsing results with inaccurate boundaries. Meanwhile, many works have demonstrate that level set based active contours are superior to the boundary estimation in sub-pixel accuracy. However, they are quite sensitive to initial settings. To address these limitations, in this paper we propose a novel Deep Multiphase Level Set (DMLS) method for semantic scene parsing, which efficiently incorporates multiphase level sets into deep neural networks. The proposed method consists of three modules, i.e., recurrent FCNs, adaptive multiphase level set, and deeply supervised learning. More specifically, recurrent FCNs learn multi-level representations of input images with different contexts. Adaptive multiphase level set drives the discriminative contour for each semantic class, which makes use of the advantages of both global and local information. In each time-step of the recurrent FCNs, deeply supervised learning is incorporated for model training. Extensive experiments on three public benchmarks have shown that our proposed method achieves new state-of-the-art performances. The source codes will be released at https://github.com/Pchank/DMLS-for-SSP.

Hybrid Active Contours Driven by Improved Laplace Adaptive Energy in Multiphase Level Set Framework

This paper presents a novel multiphase level set framework and its corresponding algorithms for image segmentation. The region fitting energies are described with the combination of the global and local distributions. An improved image Laplace term enhances the ability to locate the weak boundary. In order to better deal with the inhomogeneity, the adaptive segmentation energy is proposed to replace the fixed threshold and local Gaussian means and variances are added to get better precision of segmentation results. Experiment shows the proposed model is effective with application to MR images with intensity inhomogeneity.

Multi-phase level set algorithm based on fully convolutional networks (FCN-MLS) for retinal layer segmentation in SD-OCT images with central serous chorioretinopathy (CSC).

As a function of the spatial position of the optical coherence tomography (OCT) image, retinal layer thickness is an important diagnostic indicator for many retinal diseases. Reliable segmentation of the retinal layer is necessary for extracting useful clinical information. However, manual segmentation of these layers is time-consuming and prone to bias. Furthermore, due to speckle noise, low image contrast, retinal detachment, and also irregular morphological features make the automatic segmentation task challenging. To alleviate these challenges, in this paper, we propose a new coarse-fine framework combining the full convolutional network (FCN) with a multiphase level set (named FCN-MLS) for automatic segmentation of nine boundaries in retinal spectral OCT images. In the coarse stage, FCN is used to learn the characteristics of specific retinal layer boundaries and achieve classification of four retinal layers. The boundaries are then extracted and the remaining boundaries are initialized based on a priori information about the thickness of the retinal layer. In order to prevent the overlapping of the segmentation interfaces, a regional restriction technique is used in the multi-phase level to evolve the boundaries to achieve fine nine retinal layers segmentation. Experimental results on 1280 B-scans show that the proposed method can segment nine retinal boundaries accurately. Compared with the manual delineation, the overall mean absolute boundary location difference and the overall mean absolute thickness difference were 5.88 ± 2.38μm and 5.81 ± 2.19μm, which showed a good consistency with manual segmentation by the physicians. Our experimental results also outperform state-of-the-art methods.

Parasagittal Meningioma Brain Tumor Classification System Based on Mri Images and Multi Phase Level Set Formulation

The most common type of brain tumor known as Meningioma arises from the meninges and encloses the spine and the brain inside the skull. It accounts for 30% of all types of brain tumor. Meningioma’s can occur in many parts of the brain and accordingly it is named. In this paper, we propose Meningioma brain tumor classification system using MRI image is developed . Firstly, based on the characteristics of MRI image and Chan-Vese model, we use multiphase level set method to get the interesting region. Therefore, we obtain two matrixes, in which one contains the whole cell's boundary, and the other contains the boundary of some cells. Secondly, with respect to the cells' boundary, it is necessary to further processing, which ensures the boundary of some cells is a discrete region. Mathematical Morphology brings a fancy result during the discrete processing. At last, we consider every discrete region according to the tumor's features to judge whether a tumor appears in the image or not. Our method has a desirable performance in the presence of common tumors. For some non-convex tumors, we utilized a traditional way (SVM and LBP) as a second processing, which increased the coverage and accuracy. Experiments show that our method has a high coverage without any learning-based classifiers for most common tumors, which saves a lot time and reduces a lot workload. Therefore, the proposed method has a good practical application for assisting physicians in detecting Meningiom tumors using MRI images.

A multiphase level set approach to motion of disconnected fluid ganglia during capillary-dominated three-phase flow in porous media: Numerical validation and applications

We present a multiphase level set (MLS) approach to capillary-controlled, three-phase displacement in porous media, and use it to simulate displacements of disconnected fluid ganglia surrounded by two other fluid phases (i.e., double displacements), which are important pore-scale mechanisms for oil recovery and CO2 storage. After a comprehensive model validation on several new benchmark cases, including 3-D simulations of double displacements in a straight angular tube, we show two new applications of the MLS method. First, we simulate three-phase capillary pressure curves for gas invasion along constant oil saturation paths in sandstone. The results show significant oil redistribution by double displacements, which leads to fluctuations of gas/oil capillary pressure due to oil volume preservation, whereas oil/water capillary pressure increases mostly monotonically, yet the pressure level is lower than in the corresponding two-phase oil/water system. Further, gas/water capillary pressure is lower when mobile oil is present in the sample. The second application demonstrates the suitability of MLS method to describe foam dynamics both with and without oil present in the pore space. MLS method successfully describes well-known foam interfacial properties, and it also captures the rise of displacement capillary pressure when adding gas bubbles between continuous gas and water inside a pore channel.

Segmentation of Weld Defects Using Multiphase Level Set by the Piecewise-Smooth Mumford-Shah Model

This paper deals with the problem of the X-ray image segmentation used to detect weld defects for a non-destructive testing task. In this work we have implemented a multiphase method using the Mumford and Shah piecewise smooth model to extract the size and the texture information of defect and its region. Using this model which is more robust to the noise and less sensitive to the position of the initial curve, we have obtained a maximum of information for several regions in the X-ray image (the geometry of weld beads and defects). Our results show that the model developed can do at the same time the image segmentation and restoration.

Image Automatic Categorisation using Selected Features Attained from Integrated Non-Subsampled Contourlet with Multiphase Level Sets

A framework of automatic detection and categorization of Breast Cancer (BC) biopsy images utilizing significant interpretable features is initially considered in discussed work. Appropriate efficient techniques are engaged in layout steps of the discussed framework. Different steps include 1.To emphasize the edge particulars of tissue structure; the distinguished Non-Subsampled Contourlet (NSC) transform is implemented. 2. For the demarcation of cells from background, k-means, Adaptive Size Marker Controlled Watershed, two proposed integrated methodologies were discussed. Proposed Method-II, an integrated approach of NSC and Multiphase Level Sets is preferred to other segmentation practices as it proves better performance 3. In feature extraction phase, extracted 13 shape morphology, 33 textural (includes 6 histogram, 22 Haralick’s, 3 Tamura’s, 2 Graylevel Run-Length Matrix,) and 2 intensity features from partitioned tissue images for 96 trained images

PCSeg: Color model driven probabilistic multiphase level set based tool for plasma cell segmentation in multiple myeloma.

Plasma cell segmentation is the first stage of a computer assisted automated diagnostic tool for multiple myeloma (MM). Owing to large variability in biological cell types, a method for one cell type cannot be applied directly on the other cell types. In this paper, we present PCSeg Tool for plasma cell segmentation from microscopic medical images. These images were captured from bone marrow aspirate slides of patients with MM. PCSeg has a robust pipeline consisting of a pre-processing step, the proposed modified multiphase level set method followed by post-processing steps including the watershed and circular Hough transform to segment clusters of cells of interest and to remove unwanted cells. Our modified level set method utilizes prior information about the probability densities of regions of interest (ROIs) in the color spaces and provides a solution to the minimal-partition problem to segment ROIs in one of the level sets of a two-phase level set formulation. PCSeg tool is tested on a number of microscopic images and provides good segmentation results on single cells as well as efficient segmentation of plasma cell clusters.