Search results

Brain tumor is one of the most dangerous and life-threatening disease. In order to decide the type of tumor, devising a treatment plan and estimating the overall survival time of the patient, accurate segmentation of tumor region from images is extremely important. The process of manual segmentation is very time-consuming and prone to errors; therefore, this paper aims to provide a deep learning based method, that automatically segment the tumor region from MR images.

In this paper, the authors propose a deep neural network for automatic brain tumor (Glioma) segmentation. Intensity normalization and data augmentation have been incorporated as pre-processing steps for the images. The proposed model is trained on multichannel magnetic resonance imaging (MRI) images. The model outputs high-resolution segmentations of brain tumor regions in the input images.

The proposed model is evaluated on benchmark BRATS 2013 dataset. To evaluate the performance, the authors have used Dice score, sensitivity and positive predictive value (PPV). The superior performance of the proposed model is validated by training very popular UNet model in the similar conditions. The results indicate that proposed model has obtained promising results and is effective for segmentation of Glioma regions in MRI at a clinical level.

The model can be used by doctors to identify the exact location of the tumorous region.

The proposed model is an improvement to the UNet model. The model has fewer layers and a smaller number of parameters in comparison to the UNet model. This helps the network to train over databases with fewer images and gives superior results. Moreover, the information of bottleneck feature learned by the network has been fused with skip connection path to enrich the feature map.

Decision support systems developed using machine learning classifiers have become a valuable tool in predicting various diseases. However, the performance of these systems is adversely affected by the missing values in medical datasets. Imputation methods are used to predict these missing values. In this paper, a new imputation method called hybrid imputation optimized by the classifier (HIOC) is proposed to predict missing values efficiently.

The proposed HIOC is developed by using a classifier to combine multivariate imputation by chained equations (MICE), K nearest neighbor (KNN), mean and mode imputation methods in an optimum way. Performance of HIOC has been compared to MICE, KNN, and mean and mode methods. Four classifiers support vector machine (SVM), naive Bayes (NB), random forest (RF) and decision tree (DT) have been used to evaluate the performance of imputation methods.

The results show that HIOC performed efficiently even with a high rate of missing values. It had reduced root mean square error (RMSE) up to 17.32% in the heart disease dataset and 34.73% in the breast cancer dataset. Correct prediction of missing values improved the accuracy of the classifiers in predicting diseases. It increased classification accuracy up to 18.61% in the heart disease dataset and 6.20% in the breast cancer dataset.

The proposed HIOC is a new hybrid imputation method that can efficiently predict missing values in any medical dataset.

The purpose of this paper is to study the axisymmetric problem in a micropolar porous thermoelastic circular plate with dual phase lag model by employing eigenvalue approach subjected to thermomechanical sources.

The Laplace and Hankel transforms are employed to obtain the expressions for displacements, microrotation, volume fraction field, temperature distribution and stresses in the transformed domain. A numerical inversion technique has been carried out to obtain the resulting quantities in the physical domain. Effect of porosity and phase lag on the resulting quantities has been presented graphically. The results obtained for Lord Shulman theory (L-S, 1967) and coupled theory of thermoelasticity are presented as the particular cases.

The variation of temperature distribution is similar for micropolar thermoelastic with dual (MTD) phase lag model and coupled theory of thermoelasticity. The variation is also similar for tangential couple stress for MTD and L-S theory but opposite to couple theory. The behavior of volume fraction field and tangential couple stress for L-S theory and coupled theory are observed opposite. The values of all the resulting quantities are close to each other away from the sources. The variation in tangential stress, tangential couple stress and temperature distribution is more uniform.

The results are original and new because the authors presented an eigenvalue approach for two dimensional problem of micropolar porous thermoelastic circular plate with dual phase lag model. A comparison of porosity, L-S theory and coupled theory of micropolar thermoelasticity is made. Such problem has applications in material science, industries and earthquake problems.

A dynamical two‐dimensional problem of a homogeneous transversely isotropic fibre‐reinforced generalized thermoelastic solid with an overlying acoustic fluid layer has been considered to investigate disturbance due to mechanical load. Laplace and Fourier transform techniques are applied to solve the problem. Uniformly distributed and linearly distributed forces are applied to illustrate the utility of the approach. A numerical inversion technique has been applied to obtain the solution in the physical domain. Numerical results are obtained and presented graphically to show the effect of anisotropy along with the comparison of homogeneous transversely isotropic fibre‐reinforced generalized thermoelastic solid and isotropic elastic solid.

The Laplace and Fourier transforms have been employed to find the general solution to the fields equations in porous generalized thermoelastic medium subjected to thermomechanical boundary conditions permeated with various heat sources; in the transformed form. On the boundary surface, the distributed sources have been taken. To get the solution in the physical form, a numerical inversion technique has been used. The effect of continuous and moving heat sources with the thermomechanical boundary conditions; and the response of boundary sources (concentrated and continuous) with heat source varying with depth; on the normal stress component, change in volume fraction field and temperature distribution have been depicted graphically for a particular model. A particular case is also deduced from the present formulation.

The purpose of this paper is to investigate a two dimensional problem in magneto-micropolar thermoelastic half-space with fractional order derivative in the presence of combined effects of hall current and rotation subjected to ramp-type heating.

The fractional order theory of thermoelasticity with one relaxation time derived by Sherief et al. (2010) has been used to investigate the problem. Laplace and Fourier transform technique has been used to solve the resulting non-dimensional coupled field equations to obtain displacement, stress components and temperature distribution. A numerical inversion technique has been applied to obtain the solution in the physical domain.

Numerical computed results of all the considered variables have been shown graphically to depict the combined effect of hall current and rotation. Some particular cases of interest are also deduced from the present study.

Comparison are made in the presence and absence of hall current and rotation in a magneto-micropolar thermoelastic solid with fractional order derivative.

The paper's aim is to investigate a two‐dimensional deformation of homogeneous, anisotropic generalized thermoelastic diffusion as a result of an inclined load by applying Laplace and Fourier transforms. The inclined load is assumed to be a linear combination of a normal load and a tangential load.

As an application, concentrated and distributed loads have been taken to illustrate the utility of the approach. The transformed solutions are inverted numerically, using a numerical inversion technique.

The variations of normal displacement, temperature distribution and chemical potential distribution due to different sources for different angle of inclinations with distance have been shown graphically to depict the effect of diffusion and anisotropy. A special case is also deduced from the present investigation.

It can contribute to the theoretical consideration of the seismic and volcanic sources since it can account for the deformation fields in the entire volume surrounding the sources region.

The purpose of this paper is to investigate the thermoelastic functionally graded beam in a modified couple stress theory subjected to a dual-phase-lag model.

The governing equations are solved by using the Euler-Bernoulli beam assumption and the Laplace transform technique. The lateral deflection, temperature change, displacement component, axial stress and thermal moment of the beam are obtained by ramp type heating in the transformed domain. A general algorithm of the inverse Laplace transform is developed to recover the results in a physical domain.

The lateral deflection, temperature change, displacement component, axial stress and thermal moment of the beam are computed numerically and presented graphically to show the effect of ramp time parameter and phase lags of heating.

Comparisons are made in the absence and presence of coupled dual-phase-lag thermoelastic and coupled thermoelastic L-S theories and also different values of ramp type parameter.