Search

Human brain MRI images are complex, and matters present in the brain exhibit non-spherical shape. There exits uncertainty in the overlapping structure of brain tissue, i.e. a lack of distinctness in the class definition. Soft clustering methods can efficiently handle the uncertainty, and plane-based clustering methods are found to be more efficient for non-spherical shape data. Fuzzy k-plane clustering (FkPC) method is a soft plane-based clustering algorithms that can handle the uncertainty in medical images, but its performance degraded in the presence of noise. In this research work, we incorporated local spatial information in the FkPC clustering method to handle the noise present in the image. This spatial regularization term included in the proposed FkPC_S method refines the membership value of noisy pixel with the help of immediate neighbour pixels information. To show the effectiveness of the proposed FkPC_S method, extensive experiments are performed on one synthetic image and two publicly available human brain MRI datasets. The performance of the proposed method is compared with 10 related methods in terms of average segmentation accuracy and dice score. The experiments result shows that the proposed FkPC_S method is superior in comparison with 10 related methods in the presence of noise. Statistically significance difference and superior performance of the proposed method in comparison with other methods are also found using Friedman test. [ABSTRACT FROM AUTHOR]

Spinocerebellar ataxia type 12 (SCA12) is a neurodegenerative genetic disorder triggered by abnormal CAG repeat expansion at locus 5q32. MRI recognises dissimilarities in affected areas of SCA12 patients and healthy subjects. But manual diagnosis is time-consuming and prone to subjective errors. This has motivated us in developing a systematic and authentic decision model for computer-aided diagnosis (CAD) of SCA12. Four different feature extraction techniques are examined in this research work, such as First Order Statistics, GLRLM, GLCM, and GLGCM, to obtain distinguishable characteristics for differentiating SCA12 patients from healthy subjects. The model's performance is measured using sensitivity, specificity, accuracy and F1-score with leave-one-out cross-validation scheme. Our experimental results show that features based on the GLRLM can distinguish SCA12 from healthy subjects with a maximum classification accuracy of 85% among all the different function extraction techniques used. [ABSTRACT FROM AUTHOR]

In this paper, classification of mental task-root brain–computer interfaces (BCIs) is being investigated. The mental tasks are dominant area of investigations in BCI, which utmost interest as these system can be augmented life of people having severe disabilities. The performance of BCI model primarily depends on the construction of features from brain, electroencephalography (EEG), signal, and the size of feature vector, which are obtained through multiple channels. The availability of training samples to features are minimal for mental task classification. The feature selection is used to increase the ratio for the mental task classification by getting rid of irrelevant and superfluous features. This paper suggests an approach to augment the performance of a learning algorithm for the mental task classification on the utility of power spectral density (PSD) using feature selection. This paper also deals a comparative analysis of multivariate and univariate feature selection for mental task classification. After applying the above stated method, the findings demonstrate substantial improvements in the performance of learning model for mental task classification. Moreover, the efficacy of the proposed approach is endorsed by carrying out a robust ranking algorithm and Friedman’s statistical test for finding the best combinations and compare various combinations of PSD and feature selection methods. [ABSTRACT FROM AUTHOR]

Background: The detection of Alzheimer's Disease (AD) in its formative stages, especially in Mild Cognitive Impairments (MCI), has the potential of helping the clinicians in understanding the condition. The literature review shows that the classification of MCI-converts and MCI-non-converts has not been explored profusely and the maximum classification accuracy reported is rather low. Thus, this paper proposes a Machine Learning approach for classifying patients of MCI into two groups one who converted to AD and the others who are not diagnosed with any signs of AD. The proposed algorithm is also used to distinguish MCI patients from controls (CN). This work uses the Structural Magnetic Resonance Imaging data.Methods: This work proposes a 3-D variant of Local Binary Pattern (LBP), called LBP-20 for extracting features. The method has been compared with 3D-Discrete Wavelet Transform (3D-DWT). Subsequently, a combination of 3D-DWT and LBP-20 has been used for extracting features. The relevant features are selected using the Fisher Discriminant Ratio (FDR) and finally the classification has been carried out using the Support Vector Machine.Results: The combination of 3D-DWT with LBP-20 results in a maximum accuracy of 88.77. Similarly, the proposed combination of methods is also applied to distinguish MCI from CN. The proposed method results in the classification accuracy of 90.31 in this data.Conclusion: The proposed combination is able to extract relevant distribution of microstructures from each component, obtained with the use of DWT and thereby improving the classification accuracy. Moreover, the number of features used for classification is significantly less as compared to those obtained by 3D-DWT. The performance of the proposed method is measured in terms of accuracy, specificity and sensitivity and is found superior in comparison to the existing methods. Thus, the proposed method may contribute to effective diagnosis of MCI and may prove advantageous in clinical settings. [ABSTRACT FROM AUTHOR]

The Internet is a place where a vast amount of information is flowing. With the deeper penetration of social media, everybody is participating in spreading information. Often we find ourselves confused with competing information on the same topic. In this work, we present a novel model for competitive information diffusion on the scale-free network. The proposed model is an extension of the classical DK model of rumour spreading. Most of previous competitive information diffusion models consider a different type of stiflers to be similar. In our model we have two separate compartments for different types of stiflers. We present a detailed analysis about the effect of infection rate on the prevalence of rumour in the network. To capture the large chunk of population one requires relatively higher spreading rate. Relative impact of spreading rate and stifler rate on the final population in different compartments is also presented. In our analysis, we find that if stifler rate is higher than the spreading rate, a large portion of population remains unaware of rumours. We also find that if the information source is a popular person than people have a bias towards that information and information coming from less popular persons lose its grip on the network and lose the competition. This analysis illustrates that why big companies hire famous celebrities to promote their products. We also demonstrate rumour spreading analysis with numerical solution, network simulation and real network topology of Facebook. [ABSTRACT FROM AUTHOR]