DCS-SVM: a novel semi-automated method for human brain MR image segmentation

2017 ◽  
Vol 62 (6) ◽  
pp. 581-590 ◽  
Author(s):  
Ali Ahmadvand ◽  
Mohammad Reza Daliri ◽  
Mohammadtaghi Hajiali
Keyword(s):  
Image Segmentation ◽  
Computational Cost ◽  
Three Dimensional ◽  
Feature Space ◽  
Support Vector ◽  
Brain Images ◽  
Automated Method ◽  
Classifier Selection ◽  
Novel Method ◽  
Mr Brain

AbstractIn this paper, a novel method is proposed which appropriately segments magnetic resonance (MR) brain images into three main tissues. This paper proposes an extension of our previous work in which we suggested a combination of multiple classifiers (CMC)-based methods named dynamic classifier selection-dynamic local training local Tanimoto index (DCS-DLTLTI) for MR brain image segmentation into three main cerebral tissues. This idea is used here and a novel method is developed that tries to use more complex and accurate classifiers like support vector machine (SVM) in the ensemble. This work is challenging because the CMC-based methods are time consuming, especially on huge datasets like three-dimensional (3D) brain MR images. Moreover, SVM is a powerful method that is used for modeling datasets with complex feature space, but it also has huge computational cost for big datasets, especially those with strong interclass variability problems and with more than two classes such as 3D brain images; therefore, we cannot use SVM in DCS-DLTLTI. Therefore, we propose a novel approach named “DCS-SVM” to use SVM in DCS-DLTLTI to improve the accuracy of segmentation results. The proposed method is applied on well-known datasets of the Internet Brain Segmentation Repository (IBSR) and promising results are obtained.

A New Image Segmentation Method Based on Three-Dimensional Neural Network

2012 ◽  
Vol 490-495 ◽  
pp. 157-161
Author(s):  
Guo Fu Lin
Keyword(s):  
Image Segmentation ◽  
Classification Accuracy ◽  
Probabilistic Approach ◽  
Three Dimensional ◽  
Training Method ◽  
Segmentation Method ◽  
Brain Images ◽  
Feature Sets ◽  
Mr Brain Images ◽  
Mr Brain

In this paper, a three-dimensional probabilistic approach for MR brain image segmentation is proposed. Based on the noise-free representative reference vectors provided by SOM, the results of the 3D-PNN method are superior to other traditional algorithms. In addition to the 3D-PNN architecture, a fast three-step training method is proposed. The proposed approach also incorporates structure tensor to find appropriate feature sets for the 3D-PNN with respect to resulting classification accuracy. Computational results with simulated MR brain images have shown the promising performance of the proposed method.

AUTOMATION OF MR BRAIN IMAGE CLASSIFICATION FOR MALIGNANCY DETECTION

2019 ◽  
Vol 19 (01) ◽  
pp. 1940002 ◽  
Author(s):  
K. V. AHAMMED MUNEER ◽  
K. PAUL JOSEPH
Keyword(s):  
Brain Tumor ◽  
Nearest Neighbor ◽  
Statistical Significance ◽  
Principal Component ◽  
Feature Reduction ◽  
Brain Atlas ◽  
Significant Feature ◽  
Support Vector ◽  
Brain Images ◽  
Mr Brain

Magnetic resonance imaging (MRI) plays an integral role among the advanced techniques for detecting a brain tumor. The early detection of brain tumor with proper automation algorithm results in assisting oncologists to make easy decisions for diagnostic purposes. This paper presents an automatic classification of MR brain images in normal and malignant conditions. The feature extraction is done with gray-level co-occurrence matrix, and we proposed a feature reduction technique based on statistical test which is preceded by principal component analysis (PCA). The main focus of the work is to establish the statistical significance of the features obtained after PCA, thereby selecting significant feature values for subsequent classification. For that, a [Formula: see text]-test is performed which yielded a [Formula: see text]-value of 0.05. Finally, a comparative study using [Formula: see text]-nearest neighbor (kNN), support vector machine and artificial neural network (ANN)-based supervised classifiers is performed. In this work, we could achieve reasonably good sensitivity, specificity and accuracy for all the classifiers. The ANN classifier gives better performance with sensitivity of 97.33%, specificity of 97.42% and accuracy of 98.66% on the whole brain atlas database. The experimental results obtained are comparable to the other recent state-of-the-art.

scholarly journals Support Vector Regression for the Modeling and Synthesis of Near-Field Focused Antenna Arrays

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1352 ◽  
Author(s):  
Rafael González Ayestarán
Keyword(s):  
Support Vector Regression ◽  
Antenna Arrays ◽  
Near Field ◽  
Computational Cost ◽  
Support Vector ◽  
Analysis Tool ◽  
Training Samples ◽  
Learning Capabilities ◽  
Novel Method ◽  
The Individual

The powerful support vector regression framework is proposed in a novel method for near-field focusing using antenna arrays. By using this machine-learning method, the set of weights required in the elements of an array can be calculated to achieve an assigned near-field distribution focused on one or more positions. The computational cost is concentrated in an initial training process so that the trained system is fast enough for applications where moving devices are involved. The increased learning capabilities of support vector machines allow using a reduced number of training samples. Thus, these training samples may be generated with a prototype or a convenient electromagnetic analysis tool, and hence realistic effects, such as coupling or the individual radiation patterns of the elements of the arrays, are accounted for. Illustrative examples are presented.

Three-dimensional anatomical model-based segmentation of MR brain images through principal axes registration

1995 ◽  
Vol 42 (11) ◽  
pp. 1069-1078 ◽  
Author(s):  
L.K. Arata ◽  
A.P. Dhawan ◽  
J.P. Broderick ◽  
M.F. Gaskil-Shipley ◽  
A.V. Levy ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Brain Images ◽  
Anatomical Model ◽  
Model Based ◽  
Principal Axes ◽  
Mr Brain Images ◽  
Mr Brain

The Research on Image Segmentation Based on the Minimum Error Probability Bayesian Decision Theory

2011 ◽  
Vol 121-126 ◽  
pp. 1151-1155
Author(s):  
Zhi Yuan Chen ◽  
Gang Luo ◽  
Zhi Gen Fei
Keyword(s):  
Image Segmentation ◽  
Em Algorithm ◽  
Mixture Model ◽  
Error Probability ◽  
Feature Space ◽  
Image Feature ◽  
Bayesian Decision ◽  
Minimum Error ◽  
Novel Method ◽  
Image Edge

The image segmentation technology has been extensively applied in many fields. As the foundation of image identification, the effective image segmentation plays a significant role during the course of subsequent image processing. Many theories and methods have been presented and discussed about image segmentation, such as K-means and fuzzy C-means methods, method based on regions information, method based on image edge detection, etc. In this work, it is proposed to apply Bayesian decision-making theory based on minimum error probability to gray image segmentation. The approach to image segmentation can guarantee the segmentation error probability minimum, which is generally what we desire. On the assumption that the gray values accord with the probability distribution of Gaussian finite mixture model in image feature space, EM algorithm is used to estimate the parameters of mixture model. In order to improve the convergence speed of EM algorithm, a novel method called weighted equal interval sampling is presented to obtain the contracted sample set. Consequently, the computation burden of EM algorithm is greatly reduced. The final experiments demonstrate the feasibility and high effectiveness of the method.

scholarly journals Security Challenges and Application for Underwater Wireless Sensor Network

10.29007/ctsn ◽  
2018 ◽  
Author(s):  
Sarvesh Kumar Kumar ◽  
Bersha Kumari ◽  
Harshita Chawla
Keyword(s):  
Ct Images ◽  
Kernel Functions ◽  
Support Vector ◽  
Svm Classifier ◽  
Second Phase ◽  
Normal Brain ◽  
Brain Images ◽  
Brain Ct ◽  
Automated Method ◽  
Occurrence Matrix

Automated detection of the abnormalities in brain image analysis is very important and it is prerequisite for planning and treatment of the disease. Computed tomography scan is an imaging technique used for studying brain images. Classification of brain images is important in order to distinguish between normal brain images and those having the abnormalities in brain like hematomas, tumor, edema, concussion etc. The proposed automated method identifies the abnormalities in brain CT images and classifies them using support vector machine. The proposed method consists of three important phases, First phase is preprocessing, second phase consists of feature extraction and final phase is classification. In the first phase preprocessing is performed on brain CT images to remove artifacts and noise. In second phase features are extracted from brain CT images using gray level co-occurrence matrix (GLCM). In the final stage, extracted features are fed as input to SVM classifier with different kernel functions that classifies the images into normal and abnormal with different accuracy levels.

scholarly journals An Automated Method for Surface Ice/Snow Mapping Based on Objects and Pixels from Landsat Imagery in a Mountainous Region

2020 ◽  
Vol 12 (3) ◽  
pp. 485 ◽  
Author(s):  
Xuecheng Wang ◽  
Xing Gao ◽  
Xiaoyan Zhang ◽  
Wei Wang ◽  
Fei Yang
Keyword(s):  
Image Segmentation ◽  
Large Scale ◽  
Near Infrared ◽  
Landsat Imagery ◽  
Object Oriented ◽  
Infrared Band ◽  
Automated Method ◽  
Novel Method ◽  
Surface Ice ◽  
Karakoram Mountains

Surface ice/snow is a vital resource and is sensitive to climate change in many parts of the world. The accurate and timely measurement of the spatial distribution of ice/snow is critical for managing water resources. Object-oriented and pixel-oriented methods often have some limitations due to the image segmentation scale, the determination of the optimal threshold and background heterogeneity. Therefore, this study proposes a method for automatically extracting large-scale surface ice/snow from Landsat series images, which takes advantage of the combination of image segmentation, the watershed algorithm and a series of ice/snow indices. We tested our novel method in three different regions in the Karakoram Mountains, and the experimental results show that the produced ice/snow map obtained a user’s accuracy greater than 90%, a producer’s accuracy greater than 97%, an overall accuracy greater than 98% and a kappa coefficient greater than 0.93. Comparing the extraction results under segmentation scales of 10, 15, 20 and 25, the user’s accuracy and producer’s accuracy from the proposed method are very similar, which indicates that the proposed method is more reliable and stable for extracting ice/snow objects than the object-oriented method. Due to the different reflectivity values in the near-infrared band in the snow and water categories, the normalized difference forest snow index (NDFSI) is suitable for Landsat TM and ETM+ images. This study can serve as a reliable, scientific reference for rapidly and accurately extracting ice/snow objects.

scholarly journals Identification of stable adsorption sites and diffusion paths on nanocluster surfaces: an automated scanning algorithm

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Tibor Szilvási ◽  
Benjamin W. J. Chen ◽  
Manos Mavrikakis
Keyword(s):  
Potential Energy ◽  
Potential Energy Surfaces ◽  
Rational Design ◽  
Computational Cost ◽  
Three Dimensional ◽  
Adsorption Sites ◽  
Automated Method ◽  
Diffusion Paths ◽  
Energy Surfaces ◽  
And Diffusion

Abstract The diverse coordination environments on the surfaces of discrete, three-dimensional (3D) nanoclusters contribute significantly to their unique catalytic properties. Identifying the numerous adsorption sites and diffusion paths on these clusters is however tedious and time-consuming, especially for large, asymmetric nanoclusters. Here, we present a simple, automated method for constructing approximate 2D potential energy surfaces for the adsorption of atomic species on the surfaces of 3D nanoclusters with minimal human intervention. These potential energy surfaces fully characterize the important adsorption sites and diffusion paths on the nanocluster surfaces with accuracies similar to current approaches and at comparable computational cost. Our method can treat complex nanoclusters, such as alloy nanoclusters, and accounts for cluster relaxation and adsorbate-induced reconstruction, important for obtaining accurate energetics. Moreover, its highly parallelizable nature is ideal for modern supercomputer architectures. We showcase our method using two clusters: Au18 and Pt55. For Au18, diffusion of atomic hydrogen between the most stable sites occurs via non-intuitive paths, underlining the necessity of exploring the complete potential energy surface. By enabling the rapid and unbiased assessment of adsorption and diffusion on large, complex nanoclusters, which are particularly difficult to handle manually, our method will help advance materials discovery and the rational design of catalysts.

Sign in / Sign up

Export Citation Format

Share Document