An Approach to Differentiate Alzheimer’s Conditions using MR Image–based Zernike Moments and Fractal Features
30 Jun 2018-IEIE Transactions on Smart Processing and Computing (The Institute of Electronics Engineers of Korea)-Vol. 7, Iss: 3, pp 175-183
About: This article is published in IEIE Transactions on Smart Processing and Computing.The article was published on 2018-06-30. It has received 1 citations till now. The article focuses on the topics: Zernike polynomials & Fractal.
Citations
More filters
[...]
TL;DR: In this paper , the shape features from each lung and mediastinum masks are extracted and analyzed. And the proposed segmentation methods are able to delineate lungs and mediASTinum from the CXR images.
Abstract: • Differentiation of Drug Sensitive and Resistant Tuberculosis using chest X-rays. • Both lungs and mediastinum are precisely segmented using active contour models. • Significant lung and mediastinum shape features are extracted for characterization. • Multilayer perceptron and support vector machine classifiers perform better. • Combination of mediastinum and lung features improves the diagnostic accuracy. The rise of Drug Resistant Tuberculosis (DR TB), particularly Multi DR (MDR), and Extensively DR (XDR) has reduced the rate of control of the disease. Computer aided diagnosis using Chest X-rays (CXRs) can help in mass screening and timely diagnosis of DR TB, which is essential to administer proper treatment regimens. In CXRs, lungs and mediastinum are two significant regions which contain the information about the likelihood of DR TB. The objective of this work is to analyze the shape characteristics of lungs and mediastinum to improve the diagnostics accuracy for differentiation of Drug Sensitive (DS), MDR and XDR TB using computer aided diagnostics system. The CXR images of DS and DR TB patients are obtained from a public database. The lung fields are segmented from the CXRs using Reaction Diffusion Level Set Evolution. Mediastinum is segmented from the delineated lung masks using Chan Vese model. The shape features from each lung and mediastinum masks are extracted and analysed. The discriminative power of individual and combination of both lung and mediastinum features are evaluated using machine learning techniques for classification of DS vs MDR, MDR vs XDR and DS vs XDR TB images. The performances of classifiers are compared using standard metrics. The proposed segmentation methods are able to delineate lungs and mediastinum from the CXR images. The extracted lung and mediastinum features are found to be statistically significant (p < 0.05) for differentiation of DS and DR TB conditions. Using the combination of both lung and mediastinum features, Multi-Layer Perceptron classifier achieves maximum F-measure of 82.4%, 81.0% and 87.0% for differentiation of DS vs MDR, MDR vs XDR and DS vs XDR, respectively. Analysis of mediastinum along with the lungs in chest X-rays could improve the diagnostic performance for differentiation of drug sensitive and resistant TB conditions. The proposed methodology is able to differentiate DS, MDR and XDR TB, and found to be clinically relevant. Hence, this work is useful for computer-based early detection of DS and DR TB conditions.
7 citations
[...]
TL;DR: In this article , a multiscale entropy-based texture analysis is proposed to quantify the textural variations in images at multiple scales and complexity indices are evaluated for each scale to study textural variation.
Abstract: Alzheimer’s Disease (AD) is a progressive fatal neurodegenerative disorder that causes cognitive decline in affected people. Image processing of brain MR images can aid in identifying significant imaging biomarkers for detection of AD and its prodromal stage Mild Cognitive Impairment (MCI). Bidimensional multiscale entropy-based texture analysis is a new approach to quantify the textural variations in images at multiple scales. This work is based on the application of bidimensional multiscale entropy for analyzing AD induced textural alterations in lateral ventricles of the brain MR images. For this T1 weighted MR brain images of normal, MCI and AD subjects are obtained from public database. Lateral ventricles (LV) are delineated using reaction–diffusion level set technique from transaxial image slice with high accuracy. Bidimensional multiscale entropy is then applied on segmented LV to extract entropy features at multiple image scales and complexity indices are evaluated for each scale to study textural variations. The parameters such as tolerance factor, window lengths and scales for computation of multiscale entropy for significant differentiation amongst the healthy and diseased subjects are experimentally evaluated. The obtained entropy values from healthy subjects are observed to be significantly lower from the pathological subjects across scales. Classification with extracted features using a linear discriminant classifier achieves an accuracy of 80.1% and 87.6% for Normal vs MCI and Normal vs AD classes, respectively. The proposed multiscale entropy-based approach captures the textural alterations in lateral ventricles of brain MR images and furthermore, can be used as automated tool for early diagnosis of AD.
6 citations
[...]
TL;DR: In this paper , an attempt has been made to analyze the effect of the Extreme Learning Machine (ELM) classifier and its variants in the differentiation of healthy controls (HC) and Alzheimer's disease (AD) using structural MR images.
Abstract: In this study, an attempt has been made to analyze the effect of the Extreme Learning Machine (ELM) classifier and its variants in the differentiation of Healthy Controls (HC) and Alzheimer's Disease (AD) using structural MR images. For this, sub-anatomic brain structures, namely Corpus Callosum (CC) and Lateral Ventricles (LV) are segmented and characterized using morphometric features. Significant features from these regions are subjected to ELM, online sequential ELM, and Self-adaptive Differential Evolution ELM (SaDE-ELM) classifiers for the differentiation of HC and AD. The activation functions and the number of hidden neurons in ELM classifiers are tuned by evaluating the performance using standard metrics. Results indicate that ELM and its variant classifiers are able to identify AD using morphometric features from CC and LV. ELM classifiers achieve an accuracy greater than 90% using the sigmoid activation function for both regions. Among the ELM variants, SaDE-ELM attains a maximum sensitivity of 97% and 94% using LV and CC features respectively with the lowest number of hidden neurons. The extracted features from LV demonstrate higher discriminative power than CC in AD classification. However, a specificity greater than 95% is observed in ELM for CC features. As the proposed approach is able to characterize and differentiate the morphometric alterations in CC and LV due to AD, the study seems to be clinically significant for the differentiation of HC and AD.
3 citations
[...]
TL;DR: Efficiency of the KDE-based texture analysis confirms that the proposed computer assisted technique can be used for mass screening of MCI, which can aid in handling the disease severity.
Abstract: Objectives Mild Cognitive Impairment (MCI) is the prodromal stage of Alzheimer's disease (AD), which is a progressive and fatal neurodegenerative disorder. Detection of MCI condition can enable early diagnosis resulting in timely intervention to delay the disease progression. Onset of MCI causes tissue alterations in Corpus Callosum (CC) of the brain. Texture analysis of brain Magnetic Resonance (MR) images aids in characterising these imperceptible changes. In this study, Kernel Density Estimation (KDE) technique is used to analyse the textural variations in CC to detect MCI condition. Materials and method The pre-processed brain MR images are obtained from a public access database. Reaction Diffusion level set is employed to segment CC from sagittal slices of the images. Kernel density estimation method is applied to study the local intensity variations within the segmented CC. Statistical features quantifying these variations are extracted from the KDE values. These features are used to differentiate MCI condition using linear classifiers based on discriminant analysis and support vector machine. The results are compared with conventional Grey Level Co-occurrence Matrix (GLCM) features for validation. Results The KDE-based texture features extracted from CC show significant variation between normal and MCI classes. Results demonstrate that this approach can differentiate MCI condition with high accuracy and specificity of 81.3% and 82.7%, respectively. The KDE-based features perform better when compared with GLCM features for distinguishing MCI. Conclusions The KDE-based texture features are able to capture the subtle changes occurring in CC at the MCI stage. This technique achieves comparable performance to other state-of-the-art methods with reduced number of features. Efficiency of the KDE-based texture analysis confirms that the proposed computer assisted technique can be used for mass screening of MCI, which can aid in handling the disease severity.
2 citations
[...]
TL;DR: In this article , geometric shape descriptors to evaluate the toxicity effects of a particular drug in cell images are formulated, and Statistical analysis is performed to find the significant features, and classification is performed using Support Vector Machine (SVM) to differentiate drug untreated with treated cells at different concentrations.
Abstract: Investigation of drug-induced structural changes in cell lines at different concentrations using microscopic images is essential to understand their cytotoxic effects. In this study, geometric shape descriptors to evaluate the toxicity effects of a particular drug in cell images are formulated. For this, fluorescence microscopic images of drug-untreated and drug-treated mouse cardiac muscle HL1 cells are considered. Ratiometric index of cellular to non-cellular area and, Zernike moment measures are calculated for three different thresholds at different drug concentrations namely 0.6, 1.2, 2.5, 5, and 10[Formula: see text][Formula: see text]M. Statistical analysis is performed to find the significant features. Classification is performed using Support Vector Machine (SVM) to differentiate drug untreated with treated cells at different concentrations. Results demonstrate that the proposed features are able to characterize the shape variations in cell images at different concentrations, and validates the efficacy of segmentation. Mean cellular area ratio is found to decrease from drug-untreated to drug-treated at various concentrations. Significant shape alterations in cellular structures are also obtained using Zernike moment measures for these cases. The machine learning approach using SVM provides better performance in classifying the drug untreated with progressively increasing drug concentrations. Hence, the proposed pipeline of methods could be clinically used to determine the maximum permissible drug tolerance levels during the development of new drugs.
Related Papers (5)
[...]
[...]