Biomedical Engineering: Applications, Basis and Communications

Enhancement of image plays an important and vital role in preprocessing the magnetic resonance images (MRI). At the same time, image segmentation techniques are also essential to detect and remove the noise to enhance the quality of MRI to detect the infected regions of the brain tumor. This paper presents a novel image enhancement technique for preprocessing of brain tumor MRI by hybridizing the Water Cycle Algorithm (WCA) and Sine Cosine Algorithm (SCA). The WCA is based on the process of water cycle in rivers and streams flow in the ocean whereas the SCA follows the cyclic form of sine and cosine trigonometric functions, which permits a search agent to be transposed around the desired solution. In fact, the Fuzzy $c$ means-based segmentation algorithms have proved their ability in automatic detection of the tumor and help doctors and radiologist to diagnose the type of tumor from the MRI, but, some of the FCM-based algorithms fail to remove the required amount of noise from the MRI which restrict doctors to have better segmentation accuracy. A modified fast and robust FCM (MFRFCM) segmentation technique has been proposed to sharpen and remove noise from MRI to detect the brain tumor to have improved accuracy. In this research work, Dataset-255 is considered from the Harvard medical school. The results from the proposed hybrid WCA-SCA technique are compared with WCA, SCA and comparison results are presented. The hybrid WCA+SCA image enhancement technique attains an accuracy of 99.25% for benign tumor and 98.52% for malignant tumor. Further, the results of modified Fast and Robust FCM (MFRFCM) segmentation results are compared with the conventional FCM-based segmentation algorithms. It is observed that the proposed hybrid WCA-SCA image enhancement technique and modified FRFCM Segmentation outperform in terms of computational time and performance accuracy in contrast to the other algorithms.

Breast cancer is a common cancer in female. Accurate and early detection of breast cancer can play a vital role in treatment. This paper presents and evaluates a thermogram based Computer-Aided Detection (CAD) system for the detection of breast cancer. In this CAD system, the Random Subset Feature Selection (RSFS) algorithm and hybrid of minimum Redundancy Maximum Relevance (mRMR) algorithm and Genetic Algorithm (GA) with RSFS algorithm are utilized for feature selection. In addition, the Support Vector Machine (SVM) and k-Nearest Neighbors (kNN) algorithms are utilized as classifier algorithm. The proposed CAD system is verified using MATLAB 2017 and a dataset that is composed of breast images from 78 patients. The implementation results demonstrate that using RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 85.36% and 75%, and sensitivity of 94.11% and 79.31%, respectively. In addition, using hybrid GA and RSFS algorithm for feature selection and kNN and SVM algorithms as classifier have accuracy of 83.87% and 69.56%, and sensitivity of 96% and 81.81%, respectively, and using hybrid mRMR and RSFS algorithms for feature selection and kNN and SVM algorithms as classifier have accuracy of 77.41% and 73.07%, and sensitivity of 98% and 72.72%, respectively.

Background: An infant is an individual who possesses his/her own innate personality. Crying is a form of communication, an expression of emotions and temperament. Our study aims to predict an infant’s temperament in the early stage by analyzing the crying sound after painful stimulation of vaccination. Methods: We analyze three types of information: (i) the crying sounds caused by the pain stimuli from being injected with a Hepatitis B vaccine, (ii) the answers provided by the parents in a temperament assessment scale (TAS) questionnaire, and (iii) backend analyses of the audio signals of the crying sounds. These data are subjected to correlation analyses, T-tests, and normal distribution for deriving the relationship between crying and temperament. Results: The results show that the manifestations of an infant’s temperament may be affected by the living environment and feeding habits. A tendency exists for a group of infants with similar and focused crying sounds to have higher average scores for three of nine temperament traits: approach or withdrawal, intensity of reaction, and quality of mood. Conclusions: An infant’s crying sounds in response to a pain stimulus can be used to predict his/her temperament in terms of the three aforementioned traits.

Cardiac auscultation is a basic means of initial diagnosis of congenital heart disease (CHD). It is significant to analyze Phonocardiogram (PCG) by using signal processing and machine learning techniques for the purpose of machine-assisted diagnosis of CHD. A novel method of machine-assisted diagnosis of CHD was proposed in this paper. First, the duration of the hidden Markov model (DHMM) was applied to locate and segment PCG into each cardiac cycle. Then, the envelope of the PCG was extracted by using Viola integral. After that, the variant logic theory was applied to extract the features and convert the envelope data of the heart sound signal into visual analysis measurement data. Finally, the classifier of the support vector machine (SVM) was used to classify the normal and abnormal heart sounds. There were 1000 cases used in this study. It was divided into a training set of 600 cases, a test set of 200 cases, and validation set of 200 cases. An accuracy of 0.965, a specificity of 0.898, and a sensitivity of 0.937 were achieved using the novel signal processing techniques. The results showed that DHMM and variant logic theory models were suitable for heart sound classification.

Since the introduction of image pattern recognition and computer vision processing, the classification of cancer tissues has been a challenge at pixel-level, slide-level, and patient-level. Conventional machine learning techniques have given way to Deep Learning (DL), a contemporary, state-of-the-art approach to texture classification and localization of cancer tissues. Colorectal Cancer (CRC) is the third ranked cause of death from cancer worldwide. This paper proposes image-level texture classification of a CRC dataset by deep convolutional neural networks (CNN). Simple DL techniques consisting of transfer learning and fine-tuning were exploited. VGG-16, a Keras pre-trained model with initial weights by ImageNet, was applied. The transfer learning architecture and methods responding to VGG-16 are proposed. The training, validation, and testing sets included 5000 images of 150 × 150 pixels. The application set for detection and localization contained 10 large original images of 5000 × 5000 pixels. The model achieved F1-score and accuracy of 0.96 and 0.99, respectively, and produced a false positive rate of 0.01. AUC-based evaluation was also measured. The model classified ten large previously unseen images from the application set represented in false color maps. The reported results show the satisfactory performance of the model. The simplicity of the architecture, configuration, and implementation also contributes to the outcome this work.

Epileptic seizure in the brain affects the day-to-day life of any individual due to its unexpected nature of occurrence. It has affected more than 50 million people worldwide. Drug resistance of patients is an important factor which leads to failure of epilepsy treatments using medications in 30% of patients. Surgery is also not a viable option in a substantial number of patients. In such cases, a new kind of seizure forecasting system is necessary to help those people. In our work, various sub-frequency bands of EEG signals are produced from the originally recorded Intracranial Electroencephalogram (IEEG) signals of five canines and two persons to identify possible low complex and less intense EEG features from each sub-band of the entire spectrum. Support Vector Machine (SVM) with different Kernel-based classifiers are used to categorize features into preictal and interictal data. Epileptic Seizures forecasting accuracy of 99% has been achieved for data from canine and human. Employed wavelet filter for noise removal and found that it improved the seizure prediction accuracy in some subjects and reduced the accuracy in some subjects. Similarly, the feature selection technique also improved the preictal detection accuracy in some patients/subjects and reduced the accuracy in some data. From this work, we identified that seizure prediction is possible in at least one sub-frequency band especially in high gamma sub-band generated from the originally recorded signal using a high-pass filter. This work demonstrates an algorithm for seizure forecasting or identifying the preictal region which identifies the suitable best sub-frequency band for predicting the seizure of the originally recorded EEG data by using the computationally less intense EEG features and employing the best classifying SVM kernel.

Mathematical modeling of biological processes has bridged the fields of experimental as well as theoretical research and has carried forward remarkable innovation. Sclerostin is a fundamental communication element for bone remodeling and its activity regulates the reabsorption and deposition of new bone tissue. During this research, we have presented several studies, which illustrate the function of sclerostin in communication with the Wnt signaling pathways. This article features the sclerostin-based pathological patterns related to diseases such as bone cancer. To have a good remodeling process, the osteocytes must recruit the pre-osteoblast cells from the mesenchymal stem cells with the help of the signal mechanism given by the Wnt pathway. The Wnt signal pathway is a complex transduction of a pool of well-conserved genes whose expression regulates various activities like gene translation, cell adhesion, cell differentiation, mitogenic stimulation and polarity cell. The complexity of the interaction of the Wnt pathway is due to the ligands of Wnt itself, to the proteins R-spondin and norrin. The receptors on the surface of the cell, then, activate a process of transduction of the intracellular signal that initiates gene transduction. The hypothesis of a sort of “steady state” has therefore proved indispensable to establish a sort of common base on which the two phases. This paper seeks to give a qualitative view of the action of sclerostin through a simple mathematical model. We use a logic related to stimulation and inhibition signals of new tissue production and illustrate the role of sclerostin in the mechanical and biochemical interaction during the bone remodeling process.

The energetic pattern of the foot–ankle system is critical in human walking gait. While some of the mechanical energy was dissipated due to foot segment deformation in walking stance phase. Increasing footwear insole bending stiffness was reported to restrict foot segment bending behavior and this was reported to reduce foot segment energy dissipation. While little is known whether increasing footwear insole bending stiffness would alter foot–ankle system mechanical work generation and absorption patterns. Two healthy subjects (one female, one male; age $26.5\pm 6.4$ years, height $168.5\pm 2.1$cm, weight $64.9\pm 5.4$kg) participated in this study and they were asked to walk at self-selected normal speed with the same footwear (Nike Free RN Flyknit, 2017) in two different insole stiffness conditions: (i) normal shoe insole (NSI); (ii) carbon fiber insole (CFI). Paired sample $t$-test was conducted between NSI and CFI for all outcome measures. No statistically significant differences in the outcome variables were found between the two insole conditions. While foot segment positive work and mechanical work ratio were 45.54% and 68.43% higher in CFI than in NSI condition, respectively; foot negative work was 25.02% lower in CFI than in NSI condition. However, ankle joint positive work and work ratio were around more than 10% higher in NSI than in CFI condition, and ankle peak positive power in NSI was 23.93% higher than in CFI condition. Additionally, foot–ankle system overall positive work and mechanical work ratio were both similar between NSI and CFI conditions. The findings indicate increasing footwear insole bending stiffness may influence foot segment and ankle joint energetic patterns in walking stance phase. And the mechanical energy generation compensatory mechanism may exist between foot segment and ankle joint. Specifically, a decreased foot segment energy generation tended to result in a higher amount of ankle joint positive work and peak power generation. This will be beneficial for maintaining a relatively consistent foot–ankle system overall energy generation and work ratio in response to altered insole stiffness and foot segment work during gait.