Brain MR image segmentation with spatial constrained K-mean algorithm and dual-tree complex wavelet transform

Comparison of Tongue Characteristics Classified According to Ultrasonographic Features Using a K-Means Clustering Algorithm

The precise correlations among tongue function and characteristics remain unknown, and no previous studies have attempted machine learning-based classification of tongue ultrasonography findings. This cross-sectional observational study aimed to investigate relationships among tongue characteristics and function by classifying ultrasound images of the tongue using a K-means clustering algorithm. During 2017–2018, 236 healthy older participants (mean age 70.8 ± 5.4 years) were enrolled. The optimal number of clusters determined by the elbow method was 3. After analysis of tongue thickness and echo intensity plots, tongues were classified into three groups. One-way ANOVA was used to compare tongue function, tongue pressure, and oral diadochokinesis for /ta/ and /ka/ in each group. There were significant differences in all tongue functions among the three groups. The worst function was observed in patients with the lowest values for tongue thickness and echo intensity (tongue pressure [P = 0.023], /ta/ [P = 0.007], and /ka/ [P = 0.038]). Our results indicate that ultrasonographic classification of tongue characteristics using K-means clustering may aid clinicians in selecting the appropriate treatment strategy. Indeed, ultrasonography is advantageous in that it provides real-time imaging that is non-invasive, which can improve patient follow-up both in the clinic and at home.

Analysis of athletes’ stadium stress source based on improved layered K-means algorithm

Most of the research on stressors is in the medical field, and there are few analysis of athletes’ stressors, so it can not provide reference for the analysis of athletes’ stressors. Based on this, this study combines machine learning algorithms to analyze the pressure source of athletes’ stadium. In terms of data collection, it is mainly obtained through questionnaire survey and interview form, and it is used as experimental data after passing the test. In order to improve the performance of the algorithm, this paper combines the known K-Means algorithm with the layering algorithm to form a new improved layered K-Means algorithm. At the same time, this paper analyzes the performance of the improved hierarchical K-Means algorithm through experimental comparison and compares the clustering results. In addition, the analysis system corresponding to the algorithm is constructed based on the actual situation, the algorithm is applied to practice, and the user preference model is constructed. Finally, this article helps athletes find stressors and find ways to reduce stressors through personalized recommendations. The research shows that the algorithm of this study is reliable and has certain practical effects and can provide theoretical reference for subsequent related research.

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

Classification of Brain Hemorrhages in MRI Using Naïve Bayes- Probabilistic Kernel Approach

A brain hemorrhage is one type of stroke, which is caused due to artery burst in the brain, killing the brain cells due to bleeding. Therefore, to reduce the criticality among the patients, for treatment, the doctors depend on accurate reports on the location of hemorrhage. Magnetic resonance imaging (MRI) is one of the best imaging modality when functional and structural abnormalities need to be found. To aid the identification of presence of abnormality, a novel NB-PKC algorithm for effective recognition of brain hemorrhages in MRI is proposed. A series of preprocessing is done, then the image undergoes binary thresholding process for applying an image mask on the hemorrhage region. Then for segmentation a modified multi-level segmenting algorithm is applied, using minimal local binary pattern and GLCM, combined features are extracted and finally for classification a novel Naïve Bayes- Probabilistic Kernel Classification is applied. These techniques designed could accurately identify the position and classified whether the image had an abnormality or not and could reduce human errors.

Detection of Cardiac Abnormalities from Multilead ECG using Multiscale Phase Alternation Features

The cardiac activities such as the depolarization and the relaxation of atria and ventricles are observed in electrocardiogram (ECG). The changes in the morphological features of ECG are the symptoms of particular heart pathology. It is a cumbersome task for medical experts to visually identify any subtle changes in the morphological features during 24 hours of ECG recording. Therefore, the automated analysis of ECG signal is a need for accurate detection of cardiac abnormalities. In this paper, a novel method for automated detection of cardiac abnormalities from multilead ECG is proposed. The method uses multiscale phase alternation (PA) features of multilead ECG and two classifiers, k-nearest neighbor (KNN) and fuzzy KNN for classification of bundle branch block (BBB), myocardial infarction (MI), heart muscle defect (HMD) and healthy control (HC). The dual tree complex wavelet transform (DTCWT) is used to decompose the ECG signal of each lead into complex wavelet coefficients at different scales. The phase of the complex wavelet coefficients is computed and the PA values at each wavelet scale are used as features for detection and classification of cardiac abnormalities. A publicly available multilead ECG database (PTB database) is used for testing of the proposed method. The experimental results show that, the proposed multiscale PA features and the fuzzy KNN classifier have better performance for detection of cardiac abnormalities with sensitivity values of 78.12 %, 80.90 % and 94.31 % for BBB, HMD and MI classes. The sensitivity value of proposed method for MI class is compared with the state-of-art techniques from multilead ECG.