改善多通道相位陣列線圈之腦部磁振造影像組織分類 ICA+SVM 績效之研究

This report describes work done on Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT) based Image Fusion techniques for additional band generation of Brain MR Images and their Blind Source Separation. A technique widely adopted for source separation is Independent Component Analysis (ICA). One of the issues that have been overlooked and not investigated is lack of MR Images to be used to unmix signal sources of interest. Two new methods for generating more images were tried and their impact on the soft tissue contrast were recorded. This paper introduces PCA & DWT based image fusion techniques to generate an additional new set of images from the original MR images. These newly generated images are then combined with the original MR images to provide sufficient MR images for ICA analysis.

Day by day the new rate of brain tumor causes is diagnosed. To make use of technology, the standard of lifestyle for many patients was increased their survival rate. Medical imaging modalities were contributing more because the internal formation of the human brain is more complicated to diagnosis. In this field, various modalities are used to detect but the invention of magnetic resonance imaging (MRI) gives more attention, especially to detect brain tumor. The proposed work is focused on segmenting the tumor region in the MR images. The Discrete Wavelet Transform (DWT) is used to extract attributes from tumour images, which is then used with PCA to reduce the dimensionality of the attributes. Gray level co-occurrence method based different features are extracted in the MRI which is given as input to the classification learner such as ensemble, support vector machine, K-nearest neighbor, Naïve, and Fine Tree which are used to classify efficiently. The method is achieved 99% of accuracy according to that trained with 30 images and tested with 100 images. From that tumor images have been split up into benign or malignant. With this trouble-free method is used in MR images to give high accuracy.

Computer vision and pattern recognition systems play an important role in our lives by means of automated face detection, face and gesture recognition, and estimation of gender and age. We have developed a gender classifier with performance superior to existing gender classifiers. This paper addresses the problem of gender classification using frontal facial images. The testbed consists of 500 images (250 females and 250 males) randomly withdrawn from the FERET facial database. Independent component analysis (ICA) is used to represent each image as a feature vector in a low dimensional subspace. Different classifiers are studied in this lower dimensional subspace. Our experimental results show the best accuracy of 96% in gender classification by combining ICA and support vector machines (SVMs).

Brain tumor is the phenomenal growth of abnormal tissues in the human brain. A malignant tumor is known as a cancerous cell, and it is the major cause of death among people across the globe. Nowadays, the detection and classification of brain tumors from Magnetic Resonance Images (MRI) is a very crucial task. This chapter addresses various computing methods such as Edge Detection (ED), feature extraction, and classification techniques for the detection and classification of brain tumor regions from MRI datasets. Initially, MRI images are collected, and then various pre-processing steps such as filtering and edge detection are applied. Then, different edge detection methods such as Sobel ED, Robert’s ED, Prewitt ED, Canny ED, Laplacian ED, and Laplacian of Gaussian (LoG) with sigma 3 are applied for the MRI datasets. Subsequently, segmentation techniques are applied for detecting tumor regions from MRI, and essential features are extracted using Discrete Wavelet Transform (DWT) method. Otsu’s thresholding and K-means clustering segmentation methods are used for the investigation. Further, the support vector machines (SVMs), Naïve Bayes (NB), K-nearest neighbors (KNN), Back Propagation Neural Network (BPNN), and feedforward neural networks (FFNN) classifiers are employed for the MRI classification purpose. The experiments are 146conducted using the brain tumor dataset in the MATLAB 2019a software environment. The experimental results are analyzed in multiple dimensions, and it shows that the SVM with Otsu’s thresholding method exhibits better performance with 86.11% accuracy during the classification.

Image segmentation is challenging task in field of medical image processing. Magnetic resonance imaging is helpful to doctor for detection of human brain tumor within three sources of images (axil, corneal, sagittal). MR images are nosier and detection of brain tumor location as feature is more complicated. Level set methods have been applied but due to human interaction they are affected so appropriate contour has been generated in discontinuous regions and pathological human brain tumor portion highlighted after applying binarization, removing unessential objects; therefore contour has been generated. Then to classify tumor for segmentation hybrid Fuzzy K Mean-Self Organization Mapping (FKM-SOM) for variation of intensities is used. For improved segmented accuracy, classification has been performed, mainly features are extracted using Discrete Wavelet Transformation (DWT) then reduced using Principal Component Analysis (PCA). Thirteen features from every image of dataset have been classified for accuracy using Support Vector Machine (SVM) kernel classification (RBF, linear, polygon) so results have been achieved using evaluation parameters like Fscore, Precision, accuracy, specificity and recall.

Not alike to principal component analysis (PCA) based monitoring statistics (T2 and SPE), the control limits for independent component analysis (ICA) monitoring statistics (I2 , Ie 2 and SPE) cannot be determined directly from a particular approximation distribution due to latent variables do not follow Gaussian distribution. Lee et al. (2004) proposed to use kernel density estimation (KDE) to obtain the control limits. However, the KDE method is very sensitive to the choice of smoothing parameter. Therefore, this study utilizes the support vector machine (SVM) for process fault detection by taking information of ICA extracted statistics as inputs of SVM. The proposed method (named, ICA-SVM) will be implemented in the Tennessee Eastman Process. In which, several multivariate monitoring schemes such as PCA, ICA, modified ICA and ICA- PCA will be also compared to demonstrate the efficiency of proposed method.

Here, a brain tumor classification method using the support vector machine (SVM) algorithm by utilizing discrete wavelet transform (DWT) transformation and feature extraction of gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) has been implemented using the magnetic resonance imaging (MRI) image belong to the low-grade glioma (LGG) or high-grade glioma (HGG) group. SVM algorithm used as a classification method has been widely used in research that raises the topic of classification. Through the formation of a hyperplane between 2 data classes, the SVM algorithm can be said to be a reliable method but does not require complicated computations. The DWT transformation is intended to provide clearer feature details from the MRI image, so that when the feature extraction algorithm is applied, it is expected that the extracted features will differ between benign tumor MRI images and malignant tumor MRI images. In 1 level DWT using high-low (HL) sub-band yield the highest specificity, sensitivity, and accuracy than using 3 levels using HL or low-high (LH) sub-band in LGG MRI image.Compared with another research, our proposed method is slightly better in terms of accuracy to classify the brain tumor image with achieved the accuracy of 98.6486%.

Background: Machine learning is now a powerful tool to help improve medical disorders diagnosis. One of its critical applications is the classification or clustering of neurodegenerative disease by pattern recognition methods based on biomedical signals and medical images. Early detection of these diseases is always useful and vital. In this study, we focused on Alzheimer’s disease (AD) as a type of dementia leading to problems with memory, thinking, and behavior. This disease was named after Dr. Alois Alzheimer in 1906 when he inspected a female patient who died of an unusual mental illness. According to recent studies, four stages are introduced for AD, including pre-dementia, early AD, moderate AD, and advanced AD. There are several methods for AD diagnosis that include mental status evaluation, physical exam, and neurological exam, based on different imaging techniques such as magnetic resonance imaging (MRI). Several methods have been introduced until now for the classification and detection of AD using machine learning algorithms, such as the classification of AD with discrete wavelet transform (DWT) and single linear discriminant analysis (LDA) classifiers and differentiation of AD from normal based on T2-weighted MRI with shearlet transform (ST) and K-nearest neighbors (KNN) classifiers. Objectives: In this work, we proposed a methodology based on DWT with three-level decomposition feature extraction (Figure 1). Methods: Based on statistics (mean, variance, skewness) of features and principal component analysis (PCA) for dimension reduction, we used five classifiers, including multi-layer perceptron neural network (MLPNN) (Figure 2), KNN, support vector machine (SVM) (Figure 3), and naive Bayesian (NB) with the majority vote method to fuse them into one ensemble classifier. Results: The proposed methodology was evaluated using 100 T2-weighted MRI of AD and cognitive normal (CN) subjects, which were chosen from the Harvard Medical School website. The accuracy, specificity, and sensitivity achieved from our methodology were 95%, 90%, and 100%, respectively by using a 10-fold cross-validation strategy. Conclusion: Our study showed that the stacking method for classification of AD and CN was better than using one classifier and comparable with state-of-the-art methods.

In this research work, we proposed a medical image analysis framework with two separate releases whether or not Synovial Sarcoma (SS) is the cell structure for cancer. Within this framework the histopathology images are decomposed into a third-level sub-band using a two-dimensional Discrete Wavelet Transform. Subsequently, the structure features (SFs) such as Principal Components Analysis (PCA), Independent Components Analysis (ICA) and Linear Discriminant Analysis (LDA) were extracted from this sub-band image representation with the distribution of wavelet coefficients. These SFs are used as inputs of the Support Vector Machine (SVM) classifier. Also, classification of PCA + SVM, ICA + SVM, and LDA + SVM with Radial Basis Function (RBF) kernel the efficiency of the process is differentiated and compared with the best classification results. Furthermore, data collected on the internet from various histopathological centres via the Internet of Things (IoT) are stored and shared on blockchain technology across a wide range of image distribution across secure data IoT devices. Due to this, the minimum and maximum values of the kernel parameter are adjusted and updated periodically for the purpose of industrial application in device calibration. Consequently, these resolutions are presented with an excellent example of a technique for training and testing the cancer cell structure prognosis methods in spindle shaped cell (SSC) histopathological imaging databases. The performance characteristics of cross-validation are evaluated with the help of the receiver operating characteristics (ROC) curve, and significant differences in classification performance between the techniques are analyzed. The combination of LDA + SVM technique has been proven to be essential for intelligent SS cancer detection in the future, and it offers excellent classification accuracy, sensitivity, specificity.

This thesis focuses on finding ways to differentiate the gray matter (GM) and white matter (WM) in magnetic resonance (MR) images of the human spinal cord (SC). The aim of this project is to quantify tissue loss in these compartments to study their implications on the progression of multiple sclerosis (MS). To this end, we propose segmentation algorithms that we evaluated on MR images of healthy volunteers. Segmentation of GM and WM in MR images can be done manually by human experts, but manual segmentation is tedious and prone to intra- and inter-rater variability. Therefore, a deterministic automation of this task is necessary. On axial 2D images acquired with a recently proposed MR sequence, called AMIRA, we experiment with various automatic segmentation algorithms. We first use variational model-based segmentation approaches combined with appearance models and later directly apply supervised deep learning to train segmentation networks. Evaluation of the proposed methods shows accurate and precise results, which are on par with manual segmentations. We test the developed deep learning approach on images of conventional MR sequences in the context of a GM segmentation challenge, resulting in superior performance compared to the other competing methods. To further assess the quality of the AMIRA sequence, we apply an already published GM segmentation algorithm to our data, yielding higher accuracy than the same algorithm achieves on images of conventional MR sequences. On a different topic, but related to segmentation, we develop a high-order slice interpolation method to address the large slice distances of images acquired with the AMIRA protocol at different vertebral levels, enabling us to resample our data to intermediate slice positions. From the methodical point of view, this work provides an introduction to computer vision, a mathematically focused perspective on variational segmentation approaches and supervised deep learning, as well as a brief overview of the underlying project's anatomical and medical background.

The human right is to live a healthy life free of serious diseases. Cancer is the most serious disease facing humans and possibly leading to death. So, a definitive solution must be done to these diseases, to eliminate them and also to protect humans from them. Breast cancer is considered being one of the dangerous types of cancers that face women in particular. Early examination should be done periodically and the diagnosis must be more sensitive and effective to preserve the women lives. There are various types of breast cancer images but magnetic resonance imaging (MRI) has become one of the important ways in breast cancer detection. In this work, a new method is done to detect the breast cancer using the MRI images that is preprocessed using a 2D Median filter. The features are extracted from the images using discrete wavelet transform (DWT). These features are reduced to 13 features. Then, support vector machine (SVM) is used to detect if there is a tumor or not. Simulation results have been accomplished using the MRI images datasets. These datasets are extracted from the standard Breast MRI database known as the “Reference Image Database to Evaluate Response (RIDER)”. The proposed method has achieved an accuracy of 98.03 % using the available MRIs database. The processing time for all processes was recorded as 0.894 seconds. The obtained results have demonstrated the superiority of the proposed system over the available ones in the literature.

This Dissertation dealt with the development of computational methods for the diagnosis and estimation of fetal condition. The proposed methods analyzed and extracted information from the Fetal Heart Rate (FHR) signal, since this is one of the few available tools for the estimation of fetal oxygenation and the assessment of fetal condition during labor. For the evaluation of the proposed methods the correlation of the FHR signal with short term indices were employed and to be more specific, its correlation with the pH values of fetal blood, which is an indirect sign of the development of fetal hypoxia during labor. In the context of this Dissertation, Independent Component Analysis (ICA) for feature extraction from the FHR signal was used for the first time. Moreover we used Hidden Markov Models in an attempt to “capture” the evolution in time of the fetal condition. Furthermore, new features based on the Discrete Wavelet Transform were proposed and used. Using a new hybrid method based on grammatical evolution new features were constructed based on already extracted features by conventional methods. Moreover, for the first (and only) time, Support Vector Machine (SVM) classifiers were employed in the field of FHR processing and the Particle Swarm Optimization (PSO) method was proposed for tuning their parameters. Finally, a new family of neural networks, the Wavelet Neural Networks (WNN) was proposed and used, trained using the PSO method. By conducting a number of experiments we managed to show that the FHR signal conveys valuable information, which by the use of advanced data processing and classification techniques can be associated with fetal pH, something which was not regarded feasible during the 90’s.

Describes a pattern classification approach for detecting frontal-view faces via learning a decision boundary. The classification can be achieved either by explicit estimation of density functions of two classes, face and non-face or by direct learning of a classification function (decision boundary). The latter is a more effective approach, when the number of training available examples is small, compared to the dimensionality of image space. The proposed method consists of a implicit modeling of both face and near-face classes using Independent Component Analysis (ICA), and a subsequent classification stage based on the decision boundary estimation using Support Vector Machine (SVM). Multiple nonlinear SVMs are trained for local subspaces, considering the general non-Gaussian and multi-modal characteristic of face space. This parallelization of SVMs reduces computational cost of on-line classification, since the locally trained SVM has small number of support vectors compared to the SVM trained on entire data space. We showed that the proposed algorithm is superior to the simple combination of ICA and SVM, both in accuracy and computational burden.

Electroencephalogram (EEG) is a highly sensitive instrument and is frequently corrupted with eye blinks. Methods based on adaptive noise cancellation (ANC) and discrete wavelet transform (DWT) have been used as a standard technique for removal of eye blink artefacts. However, these methods often require visual inspection and appropriate thresholding for identifying and removing artefactual components from the EEG signal. The proposed work describes an automated windowed method with a window size of 0.45 s that is slid forward and fed to a support vector machine (SVM) classifier for identification of artefacts, after the identification of artefacts, it is fed to an autoencoder for correction of artefacts. The proposed method is evaluated on the data collected from the project entitled ‘Analysis of Brain Waves and Development of Intelligent Model for Silent Speech Recognition’. From the results it is observed that the proposed method performs better in identifying and removing artefactual components from EEG data than existing wavelet and ANC based methods. The proposed method does not require the application of independent component analysis (ICA) before processing and can be applied to multiple channels in parallel.

In order to improve the generalization performance of support vector machine (SVM), a support vector machine ensembling method based on independent component analysis (ICA) and fuzzy kernel clustering (FKC) was proposed. The ICA emphasizes the independence between the data characteristics and can effectively obtain a series of independent features, the performance of single SVM can be improved when the SVM was trained on these independent features; The FKC method uses kernel function to expand the feature space, so that the clustering is more accurate and the diversity between sub-SVMs can also be guaranteed. Simulation results on UCI datasets show that the proposed ensembling method can improve the classification precision of SVM and make the ensemble SVM has better generalization property.