A modified probabilistic neural network for partial volume segmentation in brain MR image

Brain MR Image Classification Using Superpixel-Based Deep Transfer Learning

Nowadays, brain MR (Magnetic Resonance) images are widely used by clinicians to examine the brain's anatomy to look into various pathological conditions like cerebrovascular incidents and neuro-degenerative diseases. Generally, these diseases can be identified with the MR images as "normal" and "abnormal" brains in a two-class classification problem or as disease-specific classes in a multi-class problem. This article presents an ensemble transfer learning-inspired deep architecture that uses the simple linear iterative clustering (SLIC)-based superpixel algorithm along with convolutional neural network (CNN) to classify the MR images as normal or abnormal. Superpixel algorithm segments the input MR images into clusters of regions defined by similarity measures using perceptual feature space. These superpixel images are beneficial as they can provide a compact and meaningful role in computationally demanding applications. The superpixel images are then fed to the deep convolutional neural network (CNN) to classify the images. Three brain MR image datasets, NITR-DHH, DS-75, and DS-160, are used to conduct the experimentation. Through the use of deep transfer learning, the model achieves performance accuracy of 88.15% (NITR-DHH), 98.15% (DS-160), and 98.33% (DS-75) even with the small-scale medical image dataset. The experimentally obtained results demonstrate that the proposed method is promising and efficient for clinical applications for diagnosing different brain diseases via MR images.

Novel Probabilistic Neural Network Models Combined with Dissolved Gas Analysis for Fault Diagnosis of Oil-Immersed Power Transformers

Fault diagnosis technology of power transformers is essential for the stable operation of power systems. Fault diagnosis technology based on dissolved gas analysis (DGA) is one of the most commonly used methods. However, due to the lack of fault information, traditional DGA fault diagnosis techniques are difficult to meet increasing power demand in terms of accuracy and efficiency. To address this problem, this paper proposes a novel fault diagnosis model for oil-immersed transformers based on International Electrotechnical Commission (IEC) ratio methods and probabilistic neural network (PNN) optimized with the modified moth flame optimization algorithm (MMFO). PNN as a radial neural network has good utility and is often used in classification models, but its classification performance is easily affected by the smoothing factor (σ) of the hidden layer and is not stable. This paper addresses this issue using the MMFO to optimize the smoothing factor, which effectively improves the classification accuracy and robustness of PNN. The proposed method was validated by conducting the experiments with the real data collected from transformers. Experimental results show that the MMFO-PNN model improves the fault diagnosis accuracy rate from 70.65 to 99.04%, which is higher than other power transformer fault diagnosis models.

Transformer Fault Diagnosis Model Based on Improved Gray Wolf Optimizer and Probabilistic Neural Network

Dissolved gas analysis (DGA) based in insulating oil has become a more mature method in the field of transformer fault diagnosis. However, due to the complexity and diversity of fault types, the traditional modeling method based on oil sample analysis is struggling to meet the industrial demand for diagnostic accuracy. In order to solve this problem, this paper proposes a probabilistic neural network (PNN)-based fault diagnosis model for power transformers and optimizes the smoothing factor of the pattern layer of PNN by the improved gray wolf optimizer (IGWO) to improve the classification accuracy and robustness of PNN. The standard GWO easily falls into the local optimum because the update mechanism is too single. The update strategy proposed in this paper enhances the convergence ability and exploration ability of the algorithm, which greatly alleviates the dilemma that GWO is prone to fall into local optimum when dealing with complex data. In this paper, a reliability analysis of thirteen diagnostic methods is conducted using 555 transformer fault samples collected from Jiangxi Power Supply Company, China. The results show that the diagnostic accuracy of the IGWO-PNN model reaches 99.71%, which is much higher than that of the traditional IEC (International Electrotechnical Commission) three-ratio method. Compared with other neural network models, IGWO-PNN also has higher diagnostic accuracy and stability, and is more applicable to the field of transformer fault diagnosis.

Efficient Segmentation of Brain Tumor Using FL-SNM with a Metaheuristic Approach to Optimization

Nowadays, automatic tumor detection from brain images is extremely significant for many diagnostic as well as therapeutic purposes, due to the unpredictable shape and appearance of tumors. In medical image analysis, the automatic segmentation of tumors from brain using magnetic resonance imaging (MRI) data is the most critical issue. Existing research has some limitations, such as high processing time and lower accuracy, because of the time required for the training process. In this research, a new automatic segmentation process is introduced using machine learning and a swarm intelligence scheme. Here, a fuzzy logic with spiking neuron model (FL-SNM) is proposed for segmenting the brain tumor region in MR images. Initially, input images are preprocessed to remove Gaussian and Poisson noise using a modified Kuan filter (MKF). In the MKF, the optimal selection of the minimum MSE of image pixels is achieved using a random search algorithm (RSA), which improves the peak signal-to-noise ratio (PSNR). Then, the image is smoothed using an anisotropic diffusion filter (ADF) to reduce the over-filtering problem. Afterwards, to extract statistical texture features, Fisher's linear-discriminant analysis (FLDA) is used. Finally, extracted features are transferred to the FL-SNM process and this scheme effectively segments the tumor region. In FL-SNM, the consequent parameters such as weight and bias play an important role in segmenting the region. Therefore, optimizing the weight parameter values using a chicken behavior-based swarm intelligence (CSI) algorithm, is proposed. The proposed (FL-SNM) scheme attained better performance in terms of high accuracy (94.87%), sensitivity (92.07%), specificity (99.34%), precision rate (89.36%), recall rate (88.39%), F-measure (95.06%), G-mean (95.63%), and DSC rate (91.2%), compared to existing convolutional neural networks (CNNs) and hierarchical self-organizing maps (HSOMs).

A fast stochastic framework for automatic MR brain images segmentation

This paper introduces a new framework for the segmentation of different brain structures (white matter, gray matter, and cerebrospinal fluid) from 3D MR brain images at different life stages. The proposed segmentation framework is based on a shape prior built using a subset of co-aligned training images that is adapted during the segmentation process based on first- and second-order visual appearance characteristics of MR images. These characteristics are described using voxel-wise image intensities and their spatial interaction features. To more accurately model the empirical grey level distribution of the brain signals, we use a linear combination of discrete Gaussians (LCDG) model having positive and negative components. To accurately account for the large inhomogeneity in infant MRIs, a higher-order Markov-Gibbs Random Field (MGRF) spatial interaction model that integrates third- and fourth- order families with a traditional second-order model is proposed. The proposed approach was tested and evaluated on 102 3D MR brain scans using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute brain volume difference. Experimental results show better segmentation of MR brain images compared to current open source segmentation tools.

Evolution-based hierarchical feature fusion for ultrasonic liver tissue characterization

This paper presents an evolution-based hierarchical feature fusion system that selects the dominant features among multiple feature vectors for ultrasonic liver tissue characterization. After extracting the spatial gray-level dependence matrices, multiresolution fractal feature vectors and multiresolution energy feature vectors, the system utilizes evolution-based algorithms to select features. In each feature space, features are selected independently to compile a feature subset. As the features of different feature vectors contain complementary information, a feature fusion process is used to combine the subsets generated from different vectors. Features are then selected from the fused feature vector to form a fused feature subset. The selected features are used to classify ultrasonic images of liver tissue into three classes: hepatoma, cirrhosis, and normal liver. Experiment results show that the classification accuracy of the fused feature subset is superior to that derived by using individual feature subsets. Moreover, the findings demonstrate that the proposed algorithm is capable of selecting discriminative features among multiple feature vectors to facilitate the early detection of hepatoma and cirrhosis via ultrasonic liver imaging.

Partial volume effect modeling for segmentation and tissue classification of brain magnetic resonance images: A review

Quantitative analysis of magnetic resonance (MR) brain images are facilitated by the development of automated segmentation algorithms. A single image voxel may contain of several types of tissues due to the finite spatial resolution of the imaging device. This phenomenon, termed partial volume effect (PVE), complicates the segmentation process, and, due to the complexity of human brain anatomy, the PVE is an important factor for accurate brain structure quantification. Partial volume estimation refers to a generalized segmentation task where the amount of each tissue type within each voxel is solved. This review aims to provide a systematic, tutorial-like overview and categorization of methods for partial volume estimation in brain MRI. The review concentrates on the statistically based approaches for partial volume estimation and also explains differences to other, similar image segmentation approaches.

Automatic MRI 2D brain segmentation using graph searching technique

Accurate and efficient segmentation of the whole brain in magnetic resonance (MR) images is a key task in many neuroscience and medical studies either because the whole brain is the final anatomical structure of interest or because the automatic extraction facilitates further analysis. The problem of segmenting brain MRI images has been extensively addressed by many researchers. Despite the relevant achievements obtained, automated segmentation of brain MRI imagery is still a challenging problem whose solution has to cope with critical aspects such as anatomical variability and pathological deformation. In the present paper, we describe and experimentally evaluate a method for segmenting brain from MRI images basing on two-dimensional graph searching principles for border detection. The segmentation of the whole brain over the entire volume is accomplished slice by slice, automatically detecting frames including eyes. The method is fully automatic and easily reproducible by computing the internal main parameters directly from the image data. The segmentation procedure is conceived as a tool of general applicability, although design requirements are especially commensurate with the accuracy required in clinical tasks such as surgical planning and post-surgical assessment. Several experiments were performed to assess the performance of the algorithm on a varied set of MRI images obtaining good results in terms of accuracy and stability.

Investigation of brain tissue segmentation error and its effect on EEG source localization

Surgical therapy has become an important therapeutic alternative for patients with medically intractable epilepsy. Correct and anatomically precise localization of the epileptic focus, preferably with non-invasive methods, is the main goal of the pre-surgical epilepsy diagnosis to decide if resection of brain tissue is possible. For evaluating the performance of the source localization algorithms in an actual clinical situation, realistic patient-specific human head models that incorporate the heterogeneity nature of brain tissues is required. In this paper, performance of two of the most widely used software packages for brain segmentation, namely FSL and FreeSurfer has been analyzed. Then a segmented head model from a package with better performance is used to investigate the effects of brain tissue segmentation in EEG source localization.

Automatic segmentation of brain white matter and white matter lesions in normal aging: comparison of five multispectral techniques

White matter loss, ventricular enlargement and white matter lesions are common findings on brain scans of older subjects. Accurate assessment of these different features is therefore essential for normal aging research. Recently, we developed a novel unsupervised classification method, named 'Multispectral Coloring Modulation and Variance Identification' (MCMxxxVI), that fuses two different structural magnetic resonance imaging (MRI) sequences in red/green color space and uses Minimum Variance Quantization (MVQ) as the clustering technique to segment different tissue types. Here we investigate how this method performs compared with several commonly used supervised image classifiers in segmenting normal-appearing white matter, white matter lesions and cerebrospinal fluid in the brains of 20 older subjects with a wide range of white matter lesion load and brain atrophy. The three tissue classes were segmented from T(1)-, T(2)-, T(2)⁎- and fluid attenuation inversion recovery (FLAIR)-weighted structural MRI data using MCMxxxVI and the four supervised multispectral classifiers available in the Analyze package, namely, Back-Propagated Neural Networks, Gaussian classifier, Nearest Neighbor and Parzen Windows. Bland-Altman analysis and Jaccard index values indicated that, in general, MCMxxxVI performed better than the supervised multispectral classifiers in identifying the three tissue classes, although final manual editing was still required to deliver radiologically acceptable results. These analyses show that MVQ, as implemented in MCMxxxVI, has the potential to provide quick and accurate white matter segmentations in the aging brain, although further methodological developments are still required to automate fully this technique.

Hybrid genetic and variational expectation-maximization algorithm for gaussian-mixture-model-based brain MR image segmentation

The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.

Comparison of tissue segmentation algorithms in neuroimage analysis software tools

Accurate segmentation of different brain tissues is of much importance in magnetic resonance imaging. This paper presents a comparison of the existing segmentation algorithms that are deployed in the neuroimaging community as part of two widely used software packages. The results obtained in this comparison can be used to select the appropriate segmentation algorithm for the neuroimaging application of interest. In addition to the entire brain area, a comparison is carried out for the subcortical region of the brain in terms of its gray matter composition.

A neural model for compensation of sensory abnormalities in autism through feedback from a measure of global perception

Sensory abnormalities and weak central coherence (WCC), a processing bias for features and local information, are important characteristics associated with autism. This paper introduces a self-organizing map (SOM)-based computational model of sensory abnormalities in autism, and of a feedback system to compensate for them. Feedback relies on a measure of balance of coverage over four (sensory) domains. Different methods to compute this measure are discussed, as is the flexibility to configure the system using different control mechanisms. Statistically significant improvements throughout training are demonstrated for compensation of a simple (i.e., monotonically decreasing) hypersensitivity in one of the domains. Fine-tuning control parameters can lead to further gains, but a standard setup results in good performance. Significant improvements are also shown for complex hypersensitivities (i.e., increasing and decreasing through time) in two domains. Although naturally best suited to compensate hypersensitivities--stimuli filtering may mitigate neuron migration to a hypersensitive domain--the system is also shown to perform effectively when compensating hyposensitivities. With poor coverage balance in the model akin to poor global perception, WCC would be consistent with inadequate feedback, resulting in uncontrolled hyper- and/or hyposensitivities characteristic of autism, as seen in the topologies of the resulting SOMs.