scholarly journals Automatic Feature Selection for Stenosis Detection in X-ray Coronary Angiograms

Mathematics ◽  
2021 ◽  
Vol 9 (19) ◽  
pp. 2471
Author(s):  
Miguel-Angel Gil-Rios ◽  
Igor V. Guryev ◽  
Ivan Cruz-Aceves ◽  
Juan Gabriel Avina-Cervantes ◽  
Martha Alicia Hernandez-Gonzalez ◽  
...  
Keyword(s):  
Feature Selection ◽  
Learning Strategies ◽  
High Performance ◽  
State Of The Art ◽  
Search Space ◽  
Jaccard Index ◽  
Computational Time ◽  
X Ray ◽  
Coronary Angiograms ◽  
Automatic Feature Selection

The automatic detection of coronary stenosis is a very important task in computer aided diagnosis systems in the cardiology area. The main contribution of this paper is the identification of a suitable subset of 20 features that allows for the classification of stenosis cases in X-ray coronary images with a high performance overcoming different state-of-the-art classification techniques including deep learning strategies. The automatic feature selection stage was driven by the Univariate Marginal Distribution Algorithm and carried out by statistical comparison between five metaheuristics in order to explore the search space, which is O(249) computational complexity. Moreover, the proposed method is compared with six state-of-the-art classification methods, probing its effectiveness in terms of the Accuracy and Jaccard Index evaluation metrics. All the experiments were performed using two X-ray image databases of coronary angiograms. The first database contains 500 instances and the second one 250 images. In the experimental results, the proposed method achieved an Accuracy rate of 0.89 and 0.88 and Jaccard Index of 0.80 and 0.79, respectively. Finally, the average computational time of the proposed method to classify stenosis cases was ≈0.02 s, which made it highly suitable to be used in clinical practice.

scholarly journals A Novel Method for Detection of Tuberculosis in Chest Radiographs Using Artificial Ecosystem-Based Optimisation of Deep Neural Network Features

Symmetry ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 1146 ◽  
Author(s):  
Ahmed T. Sahlol ◽  
Mohamed Abd Elaziz ◽  
Amani Tariq Jamal ◽  
Robertas Damaševičius ◽  
Osama Farouk Hassan
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Computational Time ◽  
X Ray ◽  
Artificial Ecosystem ◽  
Benchmark Datasets ◽  
Chest X Ray ◽  
Medical Image Recognition ◽  
Novel Method ◽  
Tb Diagnostics

Tuberculosis (TB) is is an infectious disease that generally attacks the lungs and causes death for millions of people annually. Chest radiography and deep-learning-based image segmentation techniques can be utilized for TB diagnostics. Convolutional Neural Networks (CNNs) has shown advantages in medical image recognition applications as powerful models to extract informative features from images. Here, we present a novel hybrid method for efficient classification of chest X-ray images. First, the features are extracted from chest X-ray images using MobileNet, a CNN model, which was previously trained on the ImageNet dataset. Then, to determine which of these features are the most relevant, we apply the Artificial Ecosystem-based Optimization (AEO) algorithm as a feature selector. The proposed method is applied to two public benchmark datasets (Shenzhen and Dataset 2) and allows them to achieve high performance and reduced computational time. It selected successfully only the best 25 and 19 (for Shenzhen and Dataset 2, respectively) features out of about 50,000 features extracted with MobileNet, while improving the classification accuracy (90.2% for Shenzen dataset and 94.1% for Dataset 2). The proposed approach outperforms other deep learning methods, while the results are the best compared to other recently published works on both datasets.

scholarly journals Reducing the Computational Time for the Kemeny Method by Exploiting Condorcet Properties

Mathematics ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 1380
Author(s):  
Noelia Rico ◽  
Camino R. Vela ◽  
Raúl Pérez-Fernández ◽  
Irene Díaz
Keyword(s):  
Choice Theory ◽  
State Of The Art ◽  
Social Choice Theory ◽  
Real Life ◽  
Search Space ◽  
Exact Algorithms ◽  
Computational Time ◽  
Preference Aggregation ◽  
Life Problems ◽  
Ranking Aggregation

Preference aggregation and in particular ranking aggregation are mainly studied by the field of social choice theory but extensively applied in a variety of contexts. Among the most prominent methods for ranking aggregation, the Kemeny method has been proved to be the only one that satisfies some desirable properties such as neutrality, consistency and the Condorcet condition at the same time. Unfortunately, the problem of finding a Kemeny ranking is NP-hard, which prevents practitioners from using it in real-life problems. The state of the art of exact algorithms for the computation of the Kemeny ranking experienced a major boost last year with the presentation of an algorithm that provides searching time guarantee up to 13 alternatives. In this work, we propose an enhanced version of this algorithm based on pruning the search space when some Condorcet properties hold. This enhanced version greatly improves the performance in terms of runtime consumption.

scholarly journals A Survey on Evolutionary Computation Approaches to Feature Selection

2021 ◽  
Author(s):  
Bing Xue ◽  
Mengjie Zhang ◽  
William Browne ◽  
X Yao
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Evolutionary Computation ◽  
State Of The Art ◽  
Search Space ◽  
Mining Machine ◽  
Future Research ◽  
Selection Problems ◽  
Personal Use ◽  
Index Terms

Feature selection is an important task in data miningand machine learning to reduce the dimensionality of the dataand increase the performance of an algorithm, such as a clas-sification algorithm. However, feature selection is a challengingtask due mainly to the large search space. A variety of methodshave been applied to solve feature selection problems, whereevolutionary computation techniques have recently gained muchattention and shown some success. However, there are no compre-hensive guidelines on the strengths and weaknesses of alternativeapproaches. This leads to a disjointed and fragmented fieldwith ultimately lost opportunities for improving performanceand successful applications. This paper presents a comprehensivesurvey of the state-of-the-art work on evolutionary computationfor feature selection, which identifies the contributions of thesedifferent algorithms. In addition, current issues and challengesare also discussed to identify promising areas for future research. Index Terms—Evolutionary computation, feature selection,classification, data mining, machine learning. © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

scholarly journals A Survey on Evolutionary Computation Approaches to Feature Selection

2021 ◽  
Author(s):  
Bing Xue ◽  
Mengjie Zhang ◽  
William Browne ◽  
X Yao
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Evolutionary Computation ◽  
State Of The Art ◽  
Search Space ◽  
Mining Machine ◽  
Future Research ◽  
Selection Problems ◽  
Personal Use ◽  
Index Terms

Feature selection is an important task in data miningand machine learning to reduce the dimensionality of the dataand increase the performance of an algorithm, such as a clas-sification algorithm. However, feature selection is a challengingtask due mainly to the large search space. A variety of methodshave been applied to solve feature selection problems, whereevolutionary computation techniques have recently gained muchattention and shown some success. However, there are no compre-hensive guidelines on the strengths and weaknesses of alternativeapproaches. This leads to a disjointed and fragmented fieldwith ultimately lost opportunities for improving performanceand successful applications. This paper presents a comprehensivesurvey of the state-of-the-art work on evolutionary computationfor feature selection, which identifies the contributions of thesedifferent algorithms. In addition, current issues and challengesare also discussed to identify promising areas for future research. Index Terms—Evolutionary computation, feature selection,classification, data mining, machine learning. © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

scholarly journals BioSAXS on the SWING beamline at Synchrotron SOLEIL

2021 ◽  
Vol 54 (6) ◽  
Author(s):  
Aurélien Thureau ◽  
Pierre Roblin ◽  
Javier Pérez
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
Spectroscopic Techniques ◽  
Fibre Optics ◽  
X Ray ◽  
X Ray Scattering ◽  
Independent Determination ◽  
Scientific Disciplines ◽  
Reduction Methods

Small-angle X-ray scattering (SAXS) of proteins in solution has become a key tool for biochemists and structural biologists, thanks especially to the availability of beamlines with high-throughput capabilities at synchrotron sources. Despite the large spectrum of scientific disciplines tackled on the SWING beamline since its opening in 2008, there has always been a strong commitment to offering state-of-the-art biological SAXS (BioSAXS) instrumentation and data reduction methods to the scientific community. The extremely reliable in-vacuum EigerX-4M detector allows collection of an unlimited number of frames without noise. A small beamstop including a diamond diode-based monitor enables measurements of the transmitted intensity with 0.1% precision as well as a q max/q min ratio as large as 140 at a single distance. The parasitic scattering has been strongly reduced by the installation of new hybrid blades. A new thermally controlled in-vacuum capillary holder including fibre-optics-based spectroscopic functionalities allows the simultaneous use of three spectroscopic techniques in addition to SAXS measurements. The addition of a second high-performance liquid chromatography (HPLC) circuit has virtually eliminated the waiting time associated with column equilibration. The easy in-line connection of a multi-angle light scattering spectrometer and a refractometer allows for an independent determination of the molecular mass and of the concentration of low-UV-absorption samples such as detergents and sugars, respectively. These instrumental improvements are combined with important software developments. The HPLC injection Agilent software is controlled by the SAXS beamline acquisition software, allowing a virtually unlimited series of automated SAXS measurements to be synchronized with the sample injections. All data-containing files and reports are automatically stored in the same folders, with names related to both the user and sample. In addition, all raw SAXS images are processed automatically on the fly, and the analysed data are stored in the ISPyB database and made accessible via a web page.

scholarly journals A Novel Multiscale Gaussian-Matched Filter Using Neural Networks for the Segmentation of X-Ray Coronary Angiograms

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Ivan Cruz-Aceves ◽  
Fernando Cervantes-Sanchez ◽  
Maria Susana Avila-Garcia
Keyword(s):  
Neural Networks ◽  
Matched Filter ◽  
State Of The Art ◽  
Ground Truth ◽  
Detection Methods ◽  
Test Set ◽  
X Ray ◽  
Accuracy Measure ◽  
Segmentation Methods ◽  
Coronary Angiograms

The accurate and efficient segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis. This paper presents a new multiscale Gaussian-matched filter (MGMF) based on artificial neural networks. The proposed method consists of two different stages. In the first stage, MGMF is used for detecting vessel-like structures while reducing image noise. The results of MGMF are compared with those obtained using six GMF-based detection methods in terms of the area (Az) under the receiver operating characteristic (ROC) curve. In the second stage, ten thresholding methods of the state of the art are compared in order to classify the magnitude of the multiscale Gaussian response into vessel and nonvessel pixels, respectively. The accuracy measure is used to analyze the segmentation methods, by comparing the results with a set of 100 X-ray coronary angiograms, which were outlined by a specialist to form the ground truth. Finally, the proposed method is compared with seven state-of-the-art vessel segmentation methods. The vessel detection results using the proposed MGMF method achieved an Az=0.9357 with a training set of 50 angiograms and Az=0.9362 with the test set of 50 images. In addition, the segmentation results using the intraclass variance thresholding method provided a segmentation accuracy of 0.9568 with the test set of coronary angiograms.

scholarly journals Utility metric for unsupervised feature selection

2021 ◽  
Vol 7 ◽  
pp. e477
Author(s):  
Amalia Villa ◽  
Abhijith Mundanad Narayanan ◽  
Sabine Van Huffel ◽  
Alexander Bertrand ◽  
Carolina Varon
Keyword(s):  
Feature Selection ◽  
Manifold Learning ◽  
State Of The Art ◽  
High Dimensional Data ◽  
Subset Selection ◽  
The State ◽  
Computational Time ◽  
High Dimensional ◽  
Learning Stage ◽  
Unsupervised Feature Selection

Feature selection techniques are very useful approaches for dimensionality reduction in data analysis. They provide interpretable results by reducing the dimensions of the data to a subset of the original set of features. When the data lack annotations, unsupervised feature selectors are required for their analysis. Several algorithms for this aim exist in the literature, but despite their large applicability, they can be very inaccessible or cumbersome to use, mainly due to the need for tuning non-intuitive parameters and the high computational demands. In this work, a publicly available ready-to-use unsupervised feature selector is proposed, with comparable results to the state-of-the-art at a much lower computational cost. The suggested approach belongs to the methods known as spectral feature selectors. These methods generally consist of two stages: manifold learning and subset selection. In the first stage, the underlying structures in the high-dimensional data are extracted, while in the second stage a subset of the features is selected to replicate these structures. This paper suggests two contributions to this field, related to each of the stages involved. In the manifold learning stage, the effect of non-linearities in the data is explored, making use of a radial basis function (RBF) kernel, for which an alternative solution for the estimation of the kernel parameter is presented for cases with high-dimensional data. Additionally, the use of a backwards greedy approach based on the least-squares utility metric for the subset selection stage is proposed. The combination of these new ingredients results in the utility metric for unsupervised feature selection U2FS algorithm. The proposed U2FS algorithm succeeds in selecting the correct features in a simulation environment. In addition, the performance of the method on benchmark datasets is comparable to the state-of-the-art, while requiring less computational time. Moreover, unlike the state-of-the-art, U2FS does not require any tuning of parameters.

scholarly journals Introduction: a brief overview of iterative algorithms in X-ray computed tomography

2015 ◽  
Vol 373 (2043) ◽  
pp. 20140399 ◽  
Author(s):  
M. Soleimani ◽  
T. Pengpen
Keyword(s):  
Computed Tomography ◽  
High Performance ◽  
Large Scale ◽  
Krylov Subspace ◽  
Iterative Algorithms ◽  
Computational Time ◽  
X Ray ◽  
Reconstruction Software ◽  
X Ray Computed ◽  
Linear Systems Of Equations

This paper presents a brief overview of some basic iterative algorithms, and more sophisticated methods are presented in the research papers in this issue. A range of algebraic iterative algorithms are covered here including ART, SART and OS-SART. A major limitation of the traditional iterative methods is their computational time. The Krylov subspace based methods such as the conjugate gradients (CG) algorithm and its variants can be used to solve linear systems of equations arising from large-scale CT with possible implementation using modern high-performance computing tools. The overall aim of this theme issue is to stimulate international efforts to develop the next generation of X-ray computed tomography (CT) image reconstruction software.

scholarly journals Automatic Cephalometric Landmark Detection on X-ray Images Using a Deep-Learning Method

2020 ◽  
Vol 10 (7) ◽  
pp. 2547 ◽  
Author(s):  
Yu Song ◽  
Xu Qiao ◽  
Yutaro Iwamoto ◽  
Yen-wei Chen
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Region Of Interest ◽  
Computational Time ◽  
Grand Challenge ◽  
Step Method ◽  
Classification Rate ◽  
X Ray ◽  
Training Images ◽  
Time Issue

Accurate automatic quantitative cephalometry are essential for orthodontics. However, manual labeling of cephalometric landmarks is tedious and subjective, which also must be performed by professional doctors. In recent years, deep learning has gained attention for its success in computer vision field. It has achieved large progress in resolving problems like image classification or image segmentation. In this paper, we propose a two-step method which can automatically detect cephalometric landmarks on skeletal X-ray images. First, we roughly extract a region of interest (ROI) patch for each landmark by registering the testing image to training images, which have annotated landmarks. Then, we utilize pre-trained networks with a backbone of ResNet50, which is a state-of-the-art convolutional neural network, to detect each landmark in each ROI patch. The network directly outputs the coordinates of the landmarks. We evaluate our method on two datasets: ISBI 2015 Grand Challenge in Dental X-ray Image Analysis and our own dataset provided by Shandong University. The experiments demonstrate that the proposed method can achieve satisfying results on both SDR (Successful Detection Rate) and SCR (Successful Classification Rate). However, the computational time issue remains to be improved in the future.

scholarly journals COVID-19 image classification using deep features and fractional-order marine predators algorithm

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Ahmed T. Sahlol ◽  
Dalia Yousri ◽  
Ahmed A. Ewees ◽  
Mohammed A. A. Al-qaness ◽  
Robertas Damasevicius ◽  
...  
Keyword(s):  
Feature Selection ◽  
Image Classification ◽  
Fractional Order ◽  
Classification Accuracy ◽  
High Performance ◽  
Computational Cost ◽  
X Ray ◽  
Marine Predators ◽  
Hybrid Classification ◽  
Selection Algorithms

Abstract Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. Although convolutional neural networks (CNNs) is considered the current state-of-the-art image classification technique, it needs massive computational cost for deployment and training. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm-based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. A combination of fractional-order and marine predators algorithm (FO-MPA) is considered an integration among a robust tool in mathematics named fractional-order calculus (FO). The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance and reduction of computational complexity. The two datasets consist of X-ray COVID-19 images by international Cardiothoracic radiologist, researchers and others published on Kaggle. The proposed approach selected successfully 130 and 86 out of 51 K features extracted by inception from dataset 1 and dataset 2, while improving classification accuracy at the same time. The results are the best achieved on these datasets when compared to a set of recent feature selection algorithms. By achieving 98.7%, 98.2% and 99.6%, 99% of classification accuracy and F-Score for dataset 1 and dataset 2, respectively, the proposed approach outperforms several CNNs and all recent works on COVID-19 images.

Sign in / Sign up

Export Citation Format

Share Document