Brain MRI Segmentation Research Articles

A Novel Segmentation Method for Brain MRI Using a Maximum Entropy Clustering Algorithm Based on Cluster Center Transfer

As the pace of life accelerates and stress increases, brain diseases begin to seriously threaten the quality of human life and survival. Effective segmentation of brain images is the key to diagnosing brain diseases. In this article, a maximum entropy clustering (MEC) algorithm is introduced to segment brain magnetic resonance imaging (MRI) images. Due to the imaging mechanism, noise is inevitably introduced when acquiring medical images, and the segmentation results of traditional image segmentation algorithms will be affected to some extent. To effectively increase the robustness of the algorithm to noise, this paper introduces a knowledge transfer mechanism based on a historical cluster center. After combining this mechanism with the MEC algorithm, an MEC algorithm based on cluster center transfer (CCT-MEC) is proposed. A series of comparative experiments show that the proposed CCT-MEC algorithm outperforms the other algorithms in brain MRI images with a better segmentation accuracy and noise reduction performance and has a certain reference value.

Brain Tumor Detection Based on Multilevel 2D Histogram Image Segmentation Using DEWO Optimization Algorithm

Brain tumor detection from magnetic resonance (MR)images is a tedious task but vital for early prediction of the disease which until now is solely based on the experience of medical practitioners. Multilevel image segmentation is a computationally simple and efficient approach for segmenting brain MR images. Conventional image segmentation does not consider the spatial correlation of image pixels and lacks better post-filtering efficiency. This study presents a Renyi entropy-based multilevel image segmentation approach using a combination of differential evolution and whale optimization algorithms (DEWO) to detect brain tumors. Further, to validate the efficiency of the proposed hybrid algorithm, it is compared with some prominent metaheuristic algorithms in recent past using between-class variance and the Tsallis entropy functions. The proposed hybrid algorithm for image segmentation is able to achieve better results than all the other metaheuristic algorithms in every entropy-based segmentation performed on brain MR images.

Enhanced N Cut and Watershed based Model for Brain MRI Segmentation

Segmentation of an image is most important and essential task in medical image processing, specifically while analyzing magnetic resonance (MR) image of brain clinically. during the clinical investigation of brain MRI images. Lot of research has been carried out for MRI segmentation but still it is challenging task. Hybrid approach which uses enhanced normalized cut and watershed transform to segment brain MRI images is developed in this paper. Watershed transform is used for the initial partitioning of the MRI, which creates primitive regions. In the next stage these primitive regions resembled for graph depiction and then the normalized cut method is used for segmenting an image. Variety of simulated and actual MR images are being segmented by using proposed algorithm to test its efficiency, in addition to it segmentation results are also compared with the other available techniques of brain MRI segmentation.

Tumor Segmentation by a Self-Organizing-Map based Active Contour Model (SOMACM) from the Brain MRIs

Segmentation of tumors from the brain Magnetic Resonance Images (MRIs) is very important for the analysis and right treatment. Tumors treated at early stages improve the survival time. This paper proposes an advanced method named SOMACM which is a combination of Self -Organizing -Map (SOM) and Active Contour Model (ACM) for the efficient segmentation of brain MRIs to detect tumors. ACM is an energy-based segmentation method and treats the segmentation as an optimization issue. It can model complex shapes and handles topological changes in the object boundary. The customary ACMs rely upon the intensities of the pixels and are very vulnerable to parameter tuning hence it is very difficult to segment the images of distinct pixel intensities. ACMs will evolve from the object boundary for the images consisting of Intensity Inhomogeneity (IIH). Neural Networks (NNs) are exceptionally compelling in processing the images of inhomogeneities. Furthermore, image segmentation can be done by NNs without the use of an objective function. The proposed SOMACM method works by precisely incorporating the global information extracted from the weights of the trained SOM neurons which helps in modeling complex shapes and distinct intensity distributions. It can handle images with noise, intensity similarity and IIH. The proposed segmentation technique is not sensitive to parameter tuning. The outcomes of the proposed SOMACM demonstrate the improved accuracy in the segmentation results of different types of tumor images, in contrast with the individual SOM, ACM, Fuzzy-C- Means (FCM), Particle Swarm Optimization (PSO) and Probabilistic Neural Networks (PNN) segmentation methods.

Multi-phase level set method for precise segmentation and correction of brain MRI

Medical image segmentation as an earlier application field in image segmentation is the key technology of medical image analysis and is also a key point and difficulty in clinical application. This paper proposes an accurate and robust active contour model based on the four-phase level set for medical MR images. First we define a new energy functional by combining the data term and the length term, where the data term is defined by transforming the energy functional of the multiplicative intrinsic component optimization (MICO) model into the level set framework after adding an edge detector function. Then, when we minimize the energy functional, we use the split Bregman method to improve the convergence speed. To test the performance of our model, we do lots of experiments according to the different brain MR images, which show that even under the severe influence of bias field or shadows, our model can still segment these images well, and our model is robust to the initial contours and noise. Moreover, our model is compared with the MICO model by experimental results and the numerical values, concluding that our model is better than the MICO model no matter in segmentation accuracy or in correction effect.

MRI Segmentation and Classification of Human Brain Using Deep Learning for Diagnosis of Alzheimer's Disease: A Survey.

Many neurological diseases and delineating pathological regions have been analyzed, and the anatomical structure of the brain researched with the aid of magnetic resonance imaging (MRI). It is important to identify patients with Alzheimer’s disease (AD) early so that preventative measures can be taken. A detailed analysis of the tissue structures from segmented MRI leads to a more accurate classification of specific brain disorders. Several segmentation methods to diagnose AD have been proposed with varying complexity. Segmentation of the brain structure and classification of AD using deep learning approaches has gained attention as it can provide effective results over a large set of data. Hence, deep learning methods are now preferred over state-of-the-art machine learning methods. We aim to provide an outline of current deep learning-based segmentation approaches for the quantitative analysis of brain MRI for the diagnosis of AD. Here, we report how convolutional neural network architectures are used to analyze the anatomical brain structure and diagnose AD, discuss how brain MRI segmentation improves AD classification, describe the state-of-the-art approaches, and summarize their results using publicly available datasets. Finally, we provide insight into current issues and discuss possible future research directions in building a computer-aided diagnostic system for AD.

AssemblyNet: A large ensemble of CNNs for 3D whole brain MRI segmentation

Whole brain segmentation of fine-grained structures using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a single convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called AssemblyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions, unseen problem and reaching a relevant consensus. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. During our validation, AssemblyNet showed competitive performance compared to state-of-the-art methods such as U-Net, Joint label fusion and SLANT. Moreover, we investigated the scan-rescan consistency and the robustness to disease effects of our method. These experiences demonstrated the reliability of AssemblyNet. Finally, we showed the interest of using semi-supervised learning to improve the performance of our method.

6-MONTH INFANT BRAIN MRI SEGMENTATION GUIDED BY 24-MONTH DATA USING CYCLE-CONSISTENT ADVERSARIAL NETWORKS.

Due to the extremely low intensity contrast between the white matter (WM) and the gray matter (GM) at around 6 months of age (the isointense phase), it is difficult for manual annotation, hence the number of training labels is highly limited. Consequently, it is still challenging to automatically segment isointense infant brain MRI. Meanwhile, the contrast of intensity images in the early adult phase, such as 24 months of age, is a relatively better, which can be easily segmented by the well-developed tools, e.g., FreeSurfer. Therefore, the question is how could we employ these high-contrast images (such as 24-month-old images) to guide the segmentation of 6-month-old images. Motivated by the above purpose, we propose a method to explore the 24-month-old images for a reliable tissue segmentation of 6-month-old images. Specifically, we design a 3D-cycleGAN-Seg architecture to generate synthetic images of the isointense phase by transferring appearances between the two time-points. To guarantee the tissue segmentation consistency between 6-month-old and 24-month-old images, we employ features from generated segmentations to guide the training of the generator network. To further improve the quality of synthetic images, we propose a feature matching loss that computes the cosine distance between unpaired segmentation features of the real and fake images. Then, the transferred of 24-month-old images is used to jointly train the segmentation model on the 6-month-old images. Experimental results demonstrate a superior performance of the proposed method compared with the existing deep learning-based methods.

Image Segmentation of Brain MRI Based on LTriDP and Superpixels of Improved SLIC.

Non-uniform gray distribution and blurred edges often result in bias during the superpixel segmentation of medical images of magnetic resonance imaging (MRI). To this end, we propose a novel superpixel segmentation algorithm by integrating texture features and improved simple linear iterative clustering (SLIC). First, a 3D histogram reconstruction model is used to reconstruct the input image, which is further enhanced by gamma transformation. Next, the local tri-directional pattern descriptor is used to extract texture features of the image; this is followed by an improved SLIC superpixel segmentation. Finally, a novel clustering-center updating rule is proposed, using pixels with gray difference with original clustering centers smaller than a predefined threshold. The experiments on the Whole Brain Atlas (WBA) image database showed that, compared to existing state-of-the-art methods, our superpixel segmentation algorithm generated significantly more uniform superpixels, and demonstrated the performance accuracy of the superpixel segmentation in both fuzzy boundaries and fuzzy regions.

A novel fuzzy clustering algorithm by minimizing global and spatially constrained likelihood-based local entropies for noisy 3D brain MR image segmentation

In this paper, we propose a novel fuzzy clustering algorithm by minimizing global and spatially constrained likelihood-based local entropies (FCMGsLE) for segmenting noisy 3D brain magnetic resonance (MR) image volumes. For each voxel, in order to measure uncertainties that arise while identifying its class, two different entropies are defined. In particular, they measure the amount of uncertainties in terms of global entropy using fuzzifier weighted global membership function and spatially constrained likelihood-based local entropy using fuzzifier weighted local membership function. To mitigate the effect of noise and intensity inhomogeneity (IIH) or radio frequency (RF) inhomogeneity, the local membership function is induced by spatially constrained likelihood measure. These entropies are minimized through a fuzzy objective function to obtain the cluster prototypes and membership functions. The final membership function is obtained by integrating these global and local membership functions using weighted parameters. The algorithm is assessed both qualitatively and quantitatively on ten 3D volumes of simulated and clinical brain MR image data having high levels of noise and intensity inhomogeneity and a synthetic 3D image volume with Rician noise. The simulation results reveal that the proposed algorithm outperforms several state-of-the-art algorithms devised in recent past when evaluated in terms of segmentation accuracy, Dice similarity coefficient, partition coefficient, and partition entropy

Segmentation of Magnetic Resonance Brain Images Using the Advanced Ant Colony Optimization Technique

MR Brain Image Segmentation is an important step in brain image analysis. It facilitates the automatic interpretation or diagnosis that helps in surgical planning, estimating the changes in the brain’s volume for various types of tissues, and recognizing different neural disorders. Many neurological disorders like epilepsy, Alzheimer’s, tumor, and cancer can be effectively quantified and analyzed by finding the volume of the brain tissues such as White Matter (WM), Gray Matter (GM), and Cerebro Spinal Fluids (CSF). In manual segmentation of brain MRIs physicians manually determines the boundaries of different objects of interest and it is time-consuming and difficult. Thus, several accurate automatic brain MRI segmentation techniques with different levels of complexity have been proposed. This paper proposes an advanced thresholding technique for the segmentation of brain MRIs based on the biologically inspired Ant Colony Optimization (ACO) algorithm. Here the texture features are assumed as heuristic data. The experimental results for the T1-weighted brain MRIs have shown high accuracy than the conventional such as Fuzzy C-Means (FCM), Expectation-Maximization (EM), Improved Bacterial Foraging Algorithm (IBFA), and Improved Particle Swarm Optimization (IPSO).

Analysis On Efficient Brain MRI Detection And Classification Strategy Using Medical Image Segmentation Techniques

During last few years, segmentation of brain MRI based images has gaining more popular research topic in medical image processing research domain. The segmentation, detection and extraction of the tumour affected region of MR images are very much difficult and time consuming task for the medical professional and radiologists. Their experience are very much important for enhancing accuracy. So, using computer based segmentation and classification, the performance become more better , hazards of manual work is eliminated and accuracy is more enhanced . In this work, Computer based detection is done based on efficient algorithm consisting stages are edge detection, segmentation, thresholding. After that, for improvement of the accuracy with quality factor and the Fuzzy-C-Means based classifier, are used for the classification and feature extraction of each segmented tumour. The work consisting of several segmentation methodology as edge based, threshold based and this approach for segmenting the accurate region of disease. The experimental performance of our proposed approach have been demonstrated here for quality and performance analysis on brain tumour MR images, based on accuracy, sensitivity, specificity, False Positive Rate(FPR).The experimental results achieved more than eighty percent of classifier accuracy, for the technique for classification of the tumor in MR images with accurately with analysing the effectiveness of the methodology. Also for experimental study, the image quality parameters as PSNR and MSE values are producing better outcomes than the other approaches.

Segmentation of MR Brain Images Through Hidden Markov Random Field and Hybrid Metaheuristic Algorithm.

Image segmentation is one of the most critical tasks in Magnetic Resonance (MR) images analysis. Since the performance of most current image segmentation methods is suffered by noise and intensity non-uniformity artifact (INU), a precise and artifact resistant method is desired. In this work, we propose a new segmentation method combining a new Hidden Markov Random Field (HMRF) model and a novel hybrid metaheuristic method based on Cuckoo search (CS) and Particle swarm optimization algorithms (PSO). The new model uses adaptive parameters to allow balancing between the segmented components of the model. In addition, to improve the quality of searching solutions in the Maximum a posteriori (MAP) estimation of the HMRF model, the hybrid metaheuristic algorithm is introduced. This algorithm takes into account both the advantages of CS and PSO algorithms in searching ability by cooperating them with the same population in a parallel way and with a solution selection mechanism. Since CS and PSO are performing exploration and exploitation in the search space, respectively, hybridizing them in an intelligent way can provide better solutions in terms of quality. Furthermore, initialization of the population is carefully taken into account to improve the performance of the proposed method. The whole algorithm is evaluated on benchmark images including both the simulated and real MR brain images. Experimental results show that the proposed method can achieve satisfactory performance for images with noise and intensity inhomogeneity, and provides better results than its considered competitors.

Image Segmentation of Brain MR Images Using Otsu’s based Hybrid WCMFO Algorithm

In this study, a novel hybrid Water Cycle Moth-Flame Optimization (WCMFO) algorithm is proposed for multilevel thresholding brain image segmentation in Magnetic Resonance (MR) image slices. WCMFO constitutes a hybrid between the two techniques, comprising the water cycle and moth-flame optimization algorithms. The optimal thresholds are obtained by maximizing the between class variance (Otsu’s function) of the image. To test the performance of threshold searching process, the proposed algorithm has been evaluated on standard benchmark of ten axial T₂-weighted brain MR images for image segmentation. The experimental outcomes infer that it produces better optimal threshold values at a greater and quicker convergence rate. In contrast to other state-of-the-art methods, namely Adaptive Wind Driven Optimization (AWDO), Adaptive Bacterial Foraging (ABF) and Particle Swarm Optimization (PSO), the proposed algorithm has been found to be better at producing the best objective function, Peak Signal-to-Noise Ratio (PSNR), Standard Deviation (STD) and lower computational time values. Further, it was observed thatthe segmented image gives greater detail when the threshold level increases. Moreover, the statistical test result confirms that the best and mean values are almost zero and the average difference between best and mean value 1.86 is obtained through the 30 executions of the proposed algorithm.Thus, these images will lead to better segments of gray, white and cerebrospinal fluid that enable better clinical choices and diagnoses using a proposed algorithm.

A Novel Hybrid Method for Segmentation and Analysis of Brain MRI for Tumor Diagnosis

A Novel Hybrid Method for Segmentation and Analysis of Brain MRI for Tumor Diagnosis

Robust FCM clustering algorithm with combined spatial constraint and membership matrix local information for brain MRI segmentation

This paper presents a robust fuzzy clustering algorithm for the segmentation of brain tissues in magnetic resonance imaging (MRI). The proposed method incorporates context-aware spatial constraint and local information of the membership matrix into the fuzzy c-means (FCM) clustering algorithm. Based upon this approach, an FCM clustering algorithm with joint spatial constraint and membership matrix local information (FCMS-MLI) for brain MRI segmentation is presented, which is more robust against noise and other artifacts. The proposed spatial constraint considers both local spatial and gray-level information adaptively, and to the best of the authors’ knowledge for the first time, the membership matrix local information (MLI) of fuzzy clustering is extracted to be utilized besides the spatial constraint. The proposed method solves two significant drawbacks of spatial constraint-based FCM approaches, which are ineffectiveness in preserving image details as well as confronting noise and intensity non-uniformity (INU) simultaneously. These problems are caused due to utilizing spatial constraints solely. The presented context-aware spatial constraint makes the method robust against a high level of noise while preserving image details. Furthermore, employing the MLI technique improves segmentation results in the presence of noise concurrently with INU. In contrast to spatial constraint-based methods, which just use local information in the image domain, the FCMS-MLI technique utilizes information in both image and coefficient domains. Hence, the proposed method benefits from two different sources of information. Finally, several types of images, including synthetic images, simulated and real brain MR images are utilized to make a comparison among the performances of popular FCMS types (i.e. FCM algorithms with spatial constraint), some new methods and the proposed algorithm. Experimental results prove efficiency and robustness of the FCMS-MLI algorithm confronting different levels of noise and INU.

Brain Image Segmentation Based on the Hybrid of Back Propagation Neural Network and AdaBoost System

The segmentation of brain magnetic resonance (MR) images can provide more detailed anatomical information, which can be of great help for the proper diagnosis of brain diseases. Therefore, the study of medical image segmentation technology is crucial and necessary. Owing to the presence of equipment noise and the complexity of the brain structure, the existing methods have various shortcomings and their performances are not ideal. In this study, we propose a new method based on back propagation (BP) neural networks and the AdaBoost algorithm. The BP neural network that we created has a 1–7-1 structure. We trained the system using a gravitational search algorithm. (In this algorithm, we use segmented images, which were obtained by state-of-the-art methods, as ideal output data.) Based on this, we established and trained 10 groups of back propagation neural networks (BPNNs) by applying 10 groups of different data. Subsequently, we adopted the AdaBoost algorithm to obtain the weight of each BPNN. Finally, we updated the BPNNs by training the gravitational search and AdaBoost algorithms. In this experiment, we used one group of brain magnetic resonance imaging (MRI) datasets. A comparison with four state-of-the-art segmentation methods through subjective observation and objective evaluation indexes reveals that the proposed method achieved better results for brain MR image segmentation.

A novel hybrid atlas-free hierarchical graph-based segmentation of newborn brain MRI using wavelet filter banks

Objective: The newborn brain MRI (magnetic resonance imaging) tissue segmentation plays a vital part in assessment of primary brain growth. In the newborn stage (nearly less than 28 days old), in T1- as well as T2-weighted MR images similar levels of intensity are exhibited by WM and GM, makes segmentation of the tissue extremely challenging. In this newborn stage for tissue segmentation, very few methods are developed. Hence the development of accurate brain tissue segmentation of neonate is prime objective of this paper.Methods: In this research work, we propose a novel hybrid atlas-free hierarchical graph-based tissue segmentation method for newborn infants. Wavelet filter banks are a class of deep models wherein filters and local neighborhood processes are used alternately for efficient segmentation on the raw input images, and fuzzy-based SVM (support vector machine) is used for precise tissue classification.Results: Specifically, from T1, T2 images multimodality information are used as inputs and then as outputs the segmentation maps are generated. The proposed approach considerably outperforms preceding methods of tissue segmentation as reflected in results. With this approach, the newborn MRI images that are even suffered from noise, poor resolution or the low contrasted images are also segmented more effectively with precision of 90% and sensitivity 98%.Conclusion: In addition, our findings indicate that the incorporation of multi-modality image led to significant improvements in performance. Thus, the proposed work effectively tackles the unreliability as well as the other issues faced with the prior methodologies with an interactive accurate segmentation outline.

Segmentation of Brain MRI with Tumor by Image Overlapping using Cellular Automata

In order to improve the health care reach, we need efficient and fast computer aided simulation processes or algorithms. When some change is found in pathological reports and biomedical quantities, the person is susceptible to diseases. If the diseases are detected earlier then there can be increase in the rate of mortality. Tumor is one such disease which has been seen to be one of the most fatal for human beings. Detecting and removing tumor is big challenge for medical practitioners. Medical image processing can be used through cellular automata has proven to be one of the fast and reliable method for detection of tumor cells. To study the capabilities of medical science CA’s are being used extensively, as they are useful in studying the self-reproducing biological systems. Purpose: This paper presents an algorithm for segmentation of MRI image through cellular automata, using Conway’s Game of Life. A new approach is being used in this paper, first the image is converted into gray level image. Then edge detection is done for this image using Game of Life. This edge detected image is overlapped with the gray scale image to get the resulted segmented image as an output. Materials and Methods: In order to run the proposed algorithm MATLAB2019b is used and the images are obtained. Results: Algorithm was used on different MRI’s and the results were taken.

Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation

Precise 3D segmentation of infant brain tissues is an essential step towards comprehensive volumetric studies and quantitative analysis of early brain development. However, computing such segmentations is very challenging, especially for 6-month infant brain, due to the poor image quality, among other difficulties inherent to infant brain MRI, e.g., the isointense contrast between white and gray matter and the severe partial volume effect due to small brain sizes.This study investigates the problem with an ensemble of semi-dense fully convolutional neural networks (CNNs), which employs T1-weighted and T2-weighted MR images as input. We demonstrate that the ensemble agreement is highly correlated with the segmentation errors. Therefore, our method provides measures that can guide local user corrections. To the best of our knowledge, this work is the first ensemble of 3D CNNs for suggesting annotations within images. Our quasi-dense architecture allows the efficient propagation of gradients during training, while limiting the number of parameters, requiring one order of magnitude less parameters than popular medical image segmentation networks such as 3D U-Net (Çiçek, et al.). We also investigated the impact that early or late fusions of multiple image modalities might have on the performances of deep architectures. We report evaluations of our method on the public data of the MICCAI iSEG-2017 Challenge on 6-month infant brain MRI segmentation, and show very competitive results among 21 teams, ranking first or second in most metrics.