Accelerated liver tumor segmentation in four-phase computed tomography images

Segmentation and volume measurement of liver tumor are important tasks for surgical planning and cancer follow-up. In this work, a segmentation method from four-phase computed tomography images is proposed. It is based on the combination of the Expectation-Maximization algorithm and the Hidden Markov Random Fields. The latter considers the spatial information given by voxel neighbors of two contrast phases. The segmentation algorithm is applied on a volume of interest that decreases the number of processed voxels. To accelerate the classification steps within the segmentation process, a Bootstrap resampling scheme is also adopted. It consists in selecting randomly an optimal representative set of voxels. The experimental results carried out on three clinical datasets show the performance of our liver tumor segmentation method. It has been notably observed that the computing time of the classification algorithm is reduced without any significant impact on the segmentation accuracy.     

A review of atlas-based segmentation for magnetic resonance brain images

Normal and abnormal brains can be segmented by registering the target image with an atlas. Here, an atlas is defined as the combination of an intensity image (template) and its segmented image (the atlas labels). After registering the atlas template and the target image, the atlas labels are propagated to the target image. We define this process as atlas-based segmentation. In recent years, researchers have investigated registration algorithms to match atlases to query subjects and also strategies for atlas construction. In this paper we present a review of the automated approaches for atlas-based segmentation of magnetic resonance brain images. We aim to point out the strengths and weaknesses of atlas-based methods and suggest new research directions. We use two different criteria to present the methods. First, we refer to the algorithms according to their atlas-based strategy: label propagation, multi-atlas methods, and probabilistic techniques. Subsequently, we classify the methods according to their medical target: the brain and its internal structures, tissue segmentation in healthy subjects, tissue segmentation in fetus, neonates and elderly subjects, and segmentation of damaged brains. A quantitative comparison of the results reported in the literature is also presented.     

White matter hyper-intensities automatic identification and segmentation in magnetic resonance images

A methodology for automatic identification and segmentation of white matter hyper-intensities appearing in magnetic resonance images of brain axial cuts is presented. To this end, a sequence of image processing technics is employed to form an image where the hyper-intensities in white matter differ notoriously from the rest of the objects. This pre-processing stage facilitates the posterior process of identification and segmentation of the hyper-intensity volumes. The proposed methodology was tested on 55 magnetic resonance images from six patients. These images were analysed by the proposed system and the resulted hyper-intensity images were compared with the images manually segmented by experts. The experimental results show the mean rate of true positives of 0.9, the mean rate of false positives of 0.7 and the similarity index of 0.7; it is worth commenting that the false positives are found mostly within the grey matter not causing problems in early diagnosis. The proposed methodology for magnetic resonance image processing and analysis may be useful in the early detection of white matter lesions.     

Abnormalities detection in serial computed tomography brain images using multi-level segmentation approach

Segmentation, where pixels are categorized by tissue types, is essential in medical image processing. This paper proposes a multi-level Fuzzy C-Means method to extract an intracranial from its background and skull. Then, a two-level Otsu multi-thresholding method is applied to segment the intracranial structure into cerebrospinal fluid, brain matters and other homogenous regions. Based on symmetrical properties in the intracranial structures, the left-half and right-half segmented intracranial regions are quantitatively compared with respect to the intracranial midline. The segmented regions are found to be very useful in providing information regarding normal and abnormal structures in the intracranial because any asymmetry that is detected would indicate a high probability of abnormalities. Additionally, pixel intensity information such as standard deviation and the maximum value of the pixels of the segmented regions are used to distinguish abnormalities such as bleeding and calcification from normal cases. This experimental work uses a medical image database consisting of 519 normal and 201 abnormal serial computed tomography (CT) brain images from 31 patients. The proposed multi-level segmentation approach proved to effectively isolate important homogenous regions in CT brain images. The extracted features of the regions would provide a strong basis for the application of content-based medical image retrieval (CMBIR).     

Survey of denoising,segmentation and classification of magnetic resonance imaging for prostate cancer

Multimedia Tools and Applications - Prostate cancer (PCa) has become the second most dreadful cancer in men after lung cancer. Traditional approaches used for treatment of PCa were manual, time...     

A reinforcement agent for object segmentation in ultrasound images

The principal contribution of this work is to design a general framework for an intelligent system to extract one object of interest from ultrasound images. This system is based on reinforcement learning. The input image is divided into several sub-images, and the proposed system finds the appropriate local values for each of them so that it can extract the object of interest. The agent uses some images and their ground-truth (manually segmented) version to learn from. A reward function is employed to measure the similarities between the output and the manually segmented images, and to provide feedback to the agent. The information obtained can be used as valuable knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images. The experimental results for prostate segmentation in trans-rectal ultrasound images show high potential of this approach in the field of ultrasound image segmentation.     

Automatic brain tumor segmentation from magnetic resonance images using superpixel-based approach

Multimedia Tools and Applications - Cancer is the second leading cause of deaths worldwide, reported by World Health Organization (WHO). The abnormal growth of cells, which should die at the time...     

Fuzzy segmentation of endorrhachis in magnetic resonance images and its fuzzy maximum intensity projection

This paper describes a fuzzy segmentation approach and the rendering technique called fuzzy maximum intensity projection (FMIP) for the endorrhachis in magnetic resonance images. First, we propose a fuzzy segmentation procedure, which assigns the high fuzzy degree for the high possibility to the endorrhachis. Second, we describe FMIP, which projects higher fuzzy membership degrees to brighter values in the 2D plane for every voxel in the volume dataset. This enables us to visualize regions of interest with higher accuracy after the fuzzy segmentation is done in the dataset. The applicability of them is tested in the visualization of the endorrhachis in magnetic resonance images. A comparison between FMIP and MIP shows that FMIP visualizes it more effectively.     

Speeding up the EM algorithm for mixture model-based segmentation of magnetic resonance images

Mixture models implemented via the expectation-maximization (EM) algorithm are being increasingly used in a wide range of problems in pattern recognition such as image segmentation. However, the EM algorithm requires considerable computational time in its application to huge data sets such as a three-dimensional magnetic resonance (MR) image of over 10 million voxels. Recently, it was shown that a sparse, incremental version of the EM algorithm could improve its rate of convergence. In this paper, we show how this modified EM algorithm can be speeded up further by adopting a multiresolution kd-tree structure in performing the E-step. The proposed algorithm outperforms some other variants of the EM algorithm for segmenting MR images of the human brain.     

Neuro-levelset system based segmentation in dynamic susceptibility contrast enhanced and diffusion weighted magnetic resonance images

In this study, neuro-levelset method is proposed and evaluated for segmentation and grading of brain tumors on reconstructed images of dynamic susceptibility contrast (DSC) and diffusion weighted (DW) magnetic resonance images. The proposed neuro-levelset method comprises of two independent phases of processing. At first, reconstructed images have been independently processed by three different artificial neural network systems such as multilayer perceptron (MLP), self-organizing map (SOM), and radial basis function (RBF). The images used for these tasks were the cerebral blood volume (CBV), time to peak (TTP), percentage of base at peak (PBP) and apparent diffusion coefficient (ADC) images. This processing step ensued in formation of segmentation images of brain tumors. Further, in the second phase, these coarse segmented images of each artificial neural network system have been independently subjected as speed images to levelset method in order to optimize the segmentation performance. This has resulted in construction of three distinct neuro-levelset methods such as MLP-levelset, SOM-levelset and RBF-levelset method. Proposed neuro-levelset methods performed better in segmenting tumor, edema, necrosis, CSF and normal tissues as compared to independent artificial neural network systems. Among three neuro-levelset methods, RBF-levelset system has performed well with average sensitivity and specificity values of 91.43±2.94% and 94.43±1.90%, respectively.     

A survey of shaped-based registration and segmentation techniques for cardiac images

Heart disease is the leading cause of death in the modern world. Cardiac imaging is routinely applied for assessment and diagnosis of cardiac diseases. Computerized image analysis methods are now widely applied to cardiac segmentation and registration in order to extract the anatomy and contractile function of the heart. The vast number of recent papers on this topic point to the need for an up to date survey in order to summarize and classify the published literature. This paper presents a survey of shape modeling applications to cardiac image analysis from MRI, CT, echocardiography, PET, and SPECT and aims to (1) introduce new methodologies in this field, (2) classify major contributions in image-based cardiac modeling, (3) provide a tutorial to beginners to initiate their own studies, and (4) introduce the major challenges of registration and segmentation and provide practical examples. The techniques surveyed include statistical models, deformable models/level sets, biophysical models, and non-rigid registration using basis functions. About 130 journal articles are categorized based on methodology, output, imaging system, modality, and validations. The advantages and disadvantages of the registration and validation techniques are discussed as appropriate in each section.     

Tissue segmentation in ultrasound images by using genetic algorithms

This paper presents a genetic based incremental neural network (GINeN) for the segmentation of tissues in ultrasound images. Performances of the GINeN and the Kohonen network are investigated for tissue segmentation in ultrasound images. Feature extraction is carried out by using continuous wavelet transform. Pixel intensities at the same spatial location on 12 wavelet planes and on the original image are considered as features, leading to 13-dimensional feature vectors. The same training set is used for the training of the Kohonen network and the GINeN.

This paper proposes the use of wavelet transform and genetic based incremental neural network together in order to increase the segmentation performance. It is observed that genetic based incremental neural network gives satisfactory segmentation performance for ultrasound images.     

A genetically optimized level set approach to segmentation of thyroid ultrasound images

This paper presents a novel framework for thyroid ultrasound image segmentation that aims to accurately delineate thyroid nodules. This framework, named GA-VBAC incorporates a level set approach named Variable Background Active Contour model (VBAC) that utilizes variable background regions, to reduce the effects of the intensity inhomogeneity in the thyroid ultrasound images. Moreover, a parameter tuning mechanism based on Genetic Algorithms (GA) has been considered to search for the optimal VBAC parameters automatically, without requiring technical skills. Experiments were conducted over a range of ultrasound images displaying thyroid nodules. The results show that the proposed GA-VBAC framework provides an efficient, effective and highly objective system for the delineation of thyroid nodules.     

A dynamic texture based segmentation method for ultrasound images with Surfacelet,HMT and parallel computing

To segment regions of interest (ROIs) from ultrasound images, one novel dynamic texture based algorithm is presented with surfacelet transform, hidden Markov tree (HMT) model and parallel computing. During surfacelet transform, the image sequence is decomposed by pyramid model, and the 3D signals with high frequency are decomposed by directional filter banks. During HMT modeling, distribution of coefficients is described with Gaussian mixture model (GMM), and relationship of scales is described with scale continuity model. From HMT parameters estimated through expectation maximization, the joint probability density is calculated and taken as feature value of image sequence. Then ROIs and non-ROIs in collected sample videos are used to train the support vector machine (SVM) classifier, which is employed to identify the divided 3D blocks from input video. To improve the computational efficiency, parallel computing is implemented with multi-processor CPU. Our algorithm has been compared with the existing texture based approaches, including gray level co-occurrence matrix (GLCM), local binary pattern (LBP), Wavelet, for ultrasound images, and the experimental results prove its advantages of processing noisy ultrasound images and segmenting higher accurate ROIs.

     

An incremental neural network for tissue segmentation in ultrasound images

This paper presents an incremental neural network (INeN) for the segmentation of tissues in ultrasound images. The performances of the INeN and the Kohonen network are investigated for ultrasound image segmentation. The elements of the feature vectors are individually formed by using discrete Fourier transform (DFT) and discrete cosine transform (DCT). The training set formed from blocks of 4x4 pixels (regions of interest, ROIs) on five different tissues designated by an expert is used for the training of the Kohonen network. The training set of the INeN is formed from randomly selected ROIs of 4x4 pixels in the image. Performances of both 2D-DFT and 2D-DCT are comparatively examined for the segmentation of ultrasound images.     

Geometric techniques for 3D tracking of ultrasound sensor,tumor segmentation in ultrasound images,and 3D reconstruction

This paper presents different methods, some based on geometric algebra, for ultrasound probe tracking in endoscopic images, 3D allocation of the ultrasound probe, ultrasound image segmentation (to extract objects like tumors), and 3D reconstruction of the surface defined by a set of points. The tracking of the ultrasound probe in endoscopic images is done with a particle filter and an auxiliary method based on thresholding in the HSV space. The 3D pose of the ultrasound probe is calculated using conformal geometric algebra (to locate each slide in 3D space). Each slide (ultrasound image) is segmented using two methods: the level-set method and the morphological operators approach in order to obtain the object we are interested in. The points on the object of interest are obtained from the segmented ultrasound images, and then a 3D object is obtained by refining the convex hull. To do that, a peeling process with an adaptive radius is applied, all of this in the geometric algebra framework. Results for points from ultrasound images, as well as for points from objects from the AimatShape Project, are presented (A.I.M.A.T.S.H.A.P.E. – Advanced an Innovative Models And Tools for the development of Semantic-based systems for Handling, Acquiring, and Processing knowledge Embedded in multidimensional digital objects).     

Topologically controlled segmentation of 3D magnetic resonance images of the head by using morphological operators

This paper proposes a new data-driven segmentation technique of 3D T1-weighted magnetic resonance scans of human head. This technique serves to the construction of individual head models. Several structures of the head are extracted. The morphology-oriented approach combined with an extensive use of topological constraints provides a robust and automatic method requiring minimum user intervention. This new approach is suitable to applications where the topology is one of the main constraints. The originality of the approach lies in the satisfaction of such constraints and in an effort towards robustness.     

Software for interactive segmentation of the carotid artery from 3D black blood magnetic resonance images

A semiautomatic algorithm for segmenting organ surfaces from 3D medical images is presented in this work. The algorithm is based on a deformable model, and allows the user to initialize the model by combining and molding primitive shapes such as cylinders and spheres to form an initial approximate model of the organ surface. The initial model is automatically deformed to better fit organ boundaries. The algorithm was applied to segment the carotid bifurcation from 3D black blood magnetic resonance (MR) images of 5 subjects. The algorithm-segmented surfaces were compared to surfaces segmented manually by an experienced user. On average, approximately 3 min were required to segment an image using the algorithm, whereas 1h was required for manual segmentation. The average distance between corresponding points on the manually and algorithm-segmented surfaces was 0.37 mm, whereas the average maximum distance was 2.03 mm. Moreover, algorithm-segmented surfaces exhibited less intra-operator variability than those segmented manually.     

Automatic classification of computed tomography brain images using ANN,k-NN and SVM

Computed tomography images are widely used in the diagnosis of intracranial hematoma and hemorrhage. This paper presents a new approach for automated diagnosis based on classification of the normal and abnormal images of computed tomography. The computed tomography images used in the classification consists of non-enhanced computed tomography images. The proposed method consists of four stages namely pre-processing, feature extraction, feature reduction and classification. The discrete wavelet transform coefficients are the features extracted in this method. The essential coefficients are selected by the principal component analysis. The features derived are used to train the binary classifier, which infer automatically whether the image is that of a normal brain or a pathological brain, suffering from brain lesion. The proposed method has been evaluated on a dataset of 80 images. A classification with a success of 92, 97 and 98 % has been obtained by artificial neural network, k-nearest neighbor and support vector machine, respectively. This result shows that the proposed technique is robust and effective.