Robust Image Segmentation Research Articles

A hybrid method for generation of attenuation map for MR-based attenuation correction of PET data in prostate PET/MR imaging.

Recently introduced PET/MRI scanners present significant advantages in comparison with PET/CT. However, the lack of accurate method for generation of µmap from MR images for implementation of MRAC is hampering further development. In this study, we present a new method including short echo-time pulse sequence to detect bone signal along with a robust and automatic image segmentation method base on FCM, active contouring and shape analysis to provide a three-classes µmap. The proposed imaging protocol implemented on a 1.5T Avanto scanner. The acquisition parameters were 1.11 msec and 20 msec for TE and TR, respectively, with FA=20. The image-processing protocol includes five major steps: (I) intensity-inhomogeneity correction using non parametric method, which is an essential step for removing bias field; (II) separation of bone and air from other areas using active contouring based on gradient vector method; (III) FCM in order to segment the image into two clusters, one cluster is bone and air and another cluster is soft tissue; (IV) separation of bone and air areas using shape analysis; (V) generation of µmap. The accuracy of the proposed segmentation method was validated using comparison against manual segmentation. The corresponding segmentation images and generated µmap prove the validity of algorithm. Quantitative analysis on accuracy, sensitivity and specificity for 15 segmented images in comparison with manual segmentation performed by an expert radiologist. The proposed strategy shows that the three tissue class µmap can be successfully generated from MR images in pelvis region using STE pulse sequence following by the image processing steps. The method can be a potential alternative to UTE-based attenuation correction. The algorithm is still under development and will be validated in more details based on comparison with the µmaps generate from CT images. This study has been developed particularly for improving the accuracy of MRAC in prostate imaging.

Robust medical image segmentation using particle swarm optimization aided level set based global fitting energy active contour approach

The active contour models have been popularly employed for image segmentation for almost a decade now. Among these active contour models, the level set based Chan and Vese algorithm is a popular region-based model that inherently utilizes intensity homogeneity in each region under consideration. However, the Chan and Vese model often suffers from the possibility of getting trapped in a local minimum, if the contour is not properly initialized. This problem assumes greater importance in the context of medical images where the intensity variations may assume large varieties of local and global profiles. In this work we propose a robust version of the Chan and Vese algorithm which is expected to achieve satisfactory segmentation performance, irrespective of the initial choice of the contour. This work formulates the fitting energy minimization problem to be solved using a metaheuristic optimization algorithm and makes a successful implementation of our algorithm using particle swarm optimization (PSO) technique. Our algorithm has been developed for two-phase level set implementation of the Chan and Vese model and it has been successfully utilized for both scalar-valued and vector-valued images. Extensive experimentations utilizing different varieties of medical images demonstrate how our proposed method could significantly improve upon the quality of segmentation performance achieved by Chan and Vese algorithm with varied initializations of contours.

Adaptive scale fuzzy local Gaussian mixture model for brain MR image segmentation

The Gaussian mixture model (GMM) has been widely used in brain magnetic resonance (MR) image segmentation. However, due to the MR bias field effect, the implied stochastic assumption that the intensities of each tissue type are sampled from an identical distribution may not be valid. In this paper, we propose a novel adaptive scale fuzzy local GMM (AS-FLGMM) algorithm for accurate and robust brain MR image segmentation. We assume that the local image data within the neighborhood of each pixel follow the GMM, in which the difference of variance among Gaussian components can be ignored. Based on this assumption, we develop a local scale estimation method to adaptively calculate the variance in each distribution. The segmentation is then performed under the fuzzy clustering framework and the objective is defined as the integration of the weighted GMM energy of each pixel. The AS-FLGMM algorithm has been compared to five state-of-the-art segmentation approaches in both synthetic and clinical MR images. Our results show that the proposed algorithm can produce more accurate segmentation results and its performance is more robust to initialization.

Single Cell Measurements of Intracellular Signalling, and Motility, in Macrophage Cells Sensing a Bacterial Infection

Macrophages are cells of the innate immune system in vertebrates. They are a cell type able to eat colloidal scale particles. In particular, these cells take up pathogenic bacteria, contributing to controlling a bacterial infection, and also acting to alarm the immune system and begin an inflammatory response.Macrophages are motile, move around tissues. When the presence of pathogens is detected, a complex network of signal pathways is triggered; in this particular state the macrophage is said to be activated. The aim of our research is the characterization of the activation process that takes place in macrophages on sensing the Salmonella bacteria. Working with cell culture systems, and exposing cells both to living bacteria, and to components of the bacteria, we investigate both the intracellular signalling, which feeds from a membrane receptor into the NF-kB signalling pathway, and also the phenotypic changes in cell motility and morphology.Regarding the intracellular signalling, we make use of cell lines in which two key components are fluorescently labelled, and through a robust image segmentation routine we detect NF-kB translocation within the cell (repeated cycles of cytoplasm to nucleus), at single cell level. This allows us to quantitatively measure the intracellular variability, and to identify commonalities and differences within the clonal population.Cell motility and shape are also affected by the detection of bacteria in the system: we quantify the migratory behaviour of macrophages, and how it changes depending on the different activation agents, linking the observations to putative biological functions. Experiments have been carried out observing cells behaviour after stimulation with Salmonella LPS (LPS is a molecule present on the outer membrane of gram-negative bacteria) and Interferon-γ (IFN-γ is a cytokine, expressed by macrophages as an intercellular signal).

Realization of an Automated Microassembly Task Involving Micro Adhesive Bonding

An automated approach is proposed for a microassembly task, which is to insert a 10 µm diameter glass tube into a 12 µm diameter hole in a silicon substrate, and bond them together with UV curable adhesive. Two three-degree-of-freedom micromanipulators are used to move the glass tube and the dispensing needle, respectively. Visual feedback is provided by an optical microscope. The angle of the microscope axis is precisely calibrated using an autofocus strategy. Robust image segmentation method and feature extraction algorithm are developed to obtain the features of the hole, the glass tube and the dispensing needle. Visual servo control is employed to achieve accurate aligning for the tube and the hole. Automated adhesive dispensing is used to bond the glass tube and the silicon substrate together after the insertion. Online monitoring ensures that the diameter of the adhesive spot is within a desired range. Experimental results demonstrate the effectiveness of the proposed strategy.

Robust information gain based fuzzy c-means clustering and classification of carotid artery ultrasound images

In this paper, a robust method is proposed for segmentation of medical images by exploiting the concept of information gain. Medical images contain inherent noise due to imaging equipment, operating environment and patient movement during image acquisition. A robust medical image segmentation technique is thus inevitable for accurate results in subsequent stages. The clustering technique proposed in this work updates fuzzy membership values and cluster centroids based on information gain computed from the local neighborhood of a pixel. The proposed approach is less sensitive to noise and produces homogeneous clustering. Experiments are performed on medical and non-medical images and results are compared with state of the art segmentation approaches. Analysis of visual and quantitative results verifies that the proposed approach outperforms other techniques both on noisy and noise free images. Furthermore, the proposed technique is used to segment a dataset of 300 real carotid artery ultrasound images. A decision system for plaque detection in the carotid artery is then proposed. Intima media thickness (IMT) is measured from the segmented images produced by the proposed approach. A feature vector based on IMT values is constructed for making decision about the presence of plaque in carotid artery using probabilistic neural network (PNN). The proposed decision system detects plaque in carotid artery images with high accuracy. Finally, effect of the proposed segmentation technique has also been investigated on classification of carotid artery ultrasound images.

A novel segmentation approach for implementation of MRAC in head PET/MRI employing Short-TE MRI and 2-point Dixon method in a fuzzy C-means framework

Quantitative PET image reconstruction requires an accurate map of attenuation coefficients of the tissue under investigation at 511keV (μ-map), and in order to correct the emission data for attenuation. The use of MRI-based attenuation correction (MRAC) has recently received lots of attention in the scientific literature. One of the major difficulties facing MRAC has been observed in the areas where bone and air collide, e.g. ethmoidal sinuses in the head area. Bone is intrinsically not detectable by conventional MRI, making it difficult to distinguish air from bone. Therefore, development of more versatile MR sequences to label the bone structure, e.g. ultra-short echo-time (UTE) sequences, certainly plays a significant role in novel methodological developments. However, long acquisition time and complexity of UTE sequences limit its clinical applications. To overcome this problem, we developed a novel combination of Short-TE (ShTE) pulse sequence to detect bone signal with a 2-point Dixon technique for water–fat discrimination, along with a robust image segmentation method based on fuzzy clustering C-means (FCM) to segment the head area into four classes of air, bone, soft tissue and adipose tissue.The imaging protocol was set on a clinical 3T Tim Trio and also 1.5T Avanto (Siemens Medical Solution, Erlangen, Germany) employing a triple echo time pulse sequence in the head area. The acquisition parameters were as follows: TE1/TE2/TE3=0.98/4.925/6.155ms, TR=8ms, FA=25 on the 3T system, and TE1/TE2/TE3=1.1/2.38/4.76ms, TR=16ms, FA=18 for the 1.5T system. The second and third echo-times belonged to the Dixon decomposition to distinguish soft and adipose tissues. To quantify accuracy, sensitivity and specificity of the bone segmentation algorithm, resulting classes of MR-based segmented bone were compared with the manual segmented one by our expert neuro-radiologist.Results for both 3T and 1.5T systems show that bone segmentation applied in several slices yields average accuracy, sensitivity and specificity higher than 90%. Results indicate that FCM is an appropriate technique for tissue classification in the sinusoidal area where there is air-bone interface. Furthermore, using Dixon method, fat and brain tissues were successfully separated.

A Robust Brain Image Segmentation Approach Using ABC with FPCM

In medical field, image processing plays a vital role in research and diagnosing disease. Segmentation of images is widely used for medical purpose such as pre-surgery and post- surgery decisions, which is required for planning treatment. The abnormal growth of tissues can be detected using computer aided detection and it is used for achieving maximum classification accuracy. Magnetic resonance imaging is widely used in computer aided design for the detection of abnormalities. Even though MRI is an efficient method, it is time consuming and needs reasonable amount of human resources. Many studies are going on in the medical field using Markov random fields in segmentation. In this paper, the MRI images are used as a dataset to the proposed algorithm, MRF-artificial bee colony optimization algorithm, with fuzzy possibility c- means is used to obtain the optimal solution. The main aim of the proposed algorithm is to reduce the computational complexity and achieving the higher accuracy. The performance of the proposed algorithm is calculated using region non uniformity, correlation and computation time. The experimental results were compared with the existing approaches such as simulated annealing and MRF with improved genetic algorithm (GA).

Type-2 Fuzzy C-Means Algorithm with Spatial Informations and Membership Constrains for Liver Segmentation

The Fuzzy C-Means algorithm with spatial informations and membership constrains is a very effective and efficient image segmentation method. However£¬it is founded with Type-1 fuzzy sets, which can not handle the uncertainties existing in liver image well.The type-2 fuzzy sets have better performance on handling uncertainties than Type-1 fuzzy set. In this paper, a new robust Type-2 FCM image segmentation algorithm is proposed aiming to improve the segmentation precision and robustness of liver image by introducing the type-2 fuzzy set into FCM with spatial information and membership constrains. We extend the type-1 fuzzy set of membership to interval type-2 fuzzy set using two fuzzifiers and which create a footprint of uncertainty (FOU). The experimental results show that the target area of the liver in CT images can be segmented well by the proposed method.

Magnetic Resonance Imaging-Based Target Volume Delineation in Radiation Therapy Treatment Planning for Brain Tumors Using Localized Region-Based Active Contour

To evaluate the clinical application of a robust semiautomatic image segmentation method to determine the brain target volumes in radiation therapy treatment planning. A local robust region-based algorithm was used on MRI brain images to study the clinical target volume (CTV) of several patients. First, 3 oncologists delineated CTVs of 10 patients manually, and the process time for each patient was calculated. The averages of the oncologists' contours were evaluated and considered as reference contours. Then, to determine the CTV through the semiautomatic method, a fourth oncologist who was blind to all manual contours selected 4-8 points around the edema and defined the initial contour. The time to obtain the final contour was calculated again for each patient. Manual and semiautomatic segmentation were compared using 3 different metric criteria: Dice coefficient, Hausdorff distance, and mean absolute distance. A comparison also was performed between volumes obtained from semiautomatic and manual methods. Manual delineation processing time of tumors for each patient was dependent on its size and complexity and had a mean (±SD) of 12.33 ± 2.47 minutes, whereas it was 3.254 ± 1.7507 minutes for the semiautomatic method. Means of Dice coefficient, Hausdorff distance, and mean absolute distance between manual contours were 0.84 ± 0.02, 2.05 ± 0.66 cm, and 0.78 ± 0.15 cm, and they were 0.82 ± 0.03, 1.91 ± 0.65 cm, and 0.7 ± 0.22 cm between manual and semiautomatic contours, respectively. Moreover, the mean volume ratio (=semiautomatic/manual) calculated for all samples was 0.87. Given the deformability of this method, the results showed reasonable accuracy and similarity to the results of manual contouring by the oncologists. This study shows that the localized region-based algorithms can have great ability in determining the CTV and can be appropriate alternatives for manual approaches in brain cancer.

Deformable templates guided discriminative models for robust 3D brain MRI segmentation.

Automatically segmenting anatomical structures from 3D brain MRI images is an important task in neuroimaging. One major challenge is to design and learn effective image models accounting for the large variability in anatomy and data acquisition protocols. A deformable template is a type of generative model that attempts to explicitly match an input image with a template (atlas), and thus, they are robust against global intensity changes. On the other hand, discriminative models combine local image features to capture complex image patterns. In this paper, we propose a robust brain image segmentation algorithm that fuses together deformable templates and informative features. It takes advantage of the adaptation capability of the generative model and the classification power of the discriminative models. The proposed algorithm achieves both robustness and efficiency, and can be used to segment brain MRI images with large anatomical variations. We perform an extensive experimental study on four datasets of T1-weighted brain MRI data from different sources (1,082 MRI scans in total) and observe consistent improvement over the state-of-the-art systems.

A robust medical image segmentation method using KL distance and local neighborhood information

In this paper, we propose an improved Chan–Vese (CV) model that uses Kullback–Leibler (KL) distances and local neighborhood information (LNI). Due to the effects of heterogeneity and complex constructions, the performance of level set segmentation is subject to confounding by the presence of nearby structures of similar intensity, preventing it from discerning the exact boundary of the object. Moreover, the CV model cannot usually obtain accurate results in medical image segmentation in cases of optimal configuration of controlling parameters, which requires substantial manual intervention. To overcome the above deficiency, we improve the segmentation accuracy by the usage of KL distance and LNI, thereby introducing the image local characteristics. Performance evaluation of the present method was achieved through experiments on the synthetic images and a series of real medical images. The extensive experimental results showed the superior performance of the proposed method over the state-of-the-art methods, in terms of both robustness and efficiency.

Multiscale Image Segmentation Using Energy Minimization

We consider the role of multiscale prior information of the object in the form of a Bayesian framework to address the posterior inference problem. The multiscale prior is implicitly estimated from the given image. We show how the multiscale prior effectively exploits the available image data for hierarchical modeling and exploiting posterior inference scheme to determine the posterior likelihood at each iteration with definite number of iteration steps. Extensive experiments show that this method achieves robust multiscale image segmentation results in the presence of dynamic Gaussian noises.

Statistical Model of Shape Moments with Active Contour Evolution for Shape Detection and Segmentation

Abstract This paper describes a novel method for shape representation and robust image segmentation. The proposed method combines two well known methodologies, namely, statistical shape models and active contours implemented in level set framework. The shape detection is achieved by maximizing a posterior function that consists of a prior shape probability model and image likelihood function conditioned on shapes. The statistical shape model is built as a result of a learning process based on nonparametric probability estimation in a PCA reduced feature space formed by the Legendre moments of training silhouette images. A greedy strategy is applied to optimize the proposed cost function by iteratively evolving an implicit active contour in the image space and subsequent constrained optimization of the evolved shape in the reduced shape feature space. Experimental results presented in the paper demonstrate that the proposed method, contrary to many other active contour segmentation methods, is highly resilient to severe random and structural noise that could be present in the data.

Tracking transcriptional activities with high-content epifluorescent imaging

High-content cell imaging based on fluorescent protein reporters has recently been used to track the transcriptional activities of multiple genes under different external stimuli for extended periods. This technology enhances our ability to discover treatment-induced regulatory mechanisms, temporally order their onsets and recognize their relationships. To fully realize these possibilities and explore their potential in biological and pharmaceutical applications, we introduce a new data processing procedure to extract information about the dynamics of cell processes based on this technology. The proposed procedure contains two parts: (1) image processing, where the fluorescent images are processed to identify individual cells and allow their transcriptional activity levels to be quantified; and (2) data representation, where the extracted time course data are summarized and represented in a way that facilitates efficient evaluation. Experiments show that the proposed procedure achieves fast and robust image segmentation with sufficient accuracy. The extracted cellular dynamics are highly reproducible and sensitive enough to detect subtle activity differences and identify mechanisms responding to selected perturbations. This method should be able to help biologists identify the alterations of cellular mechanisms that allow drug candidates to change cell behavior and thereby improve the efficiency of drug discovery and treatment design.

Robust image segmentation against complex color distribution

Color distribution is the most effective cue that is widely adopted in previous interactive image segmentation methods. However, it also may introduce additional errors in some situations, for example, when the foreground and background have similar colors. To address this problem, this paper proposes a novel method to learn the segmentation likelihoods. The proposed method is designed for high reliability, for which purpose it may choose to discard some unreliable likelihoods that may cause segmentation error. The reliability of likelihoods is estimated in a few Expectation–Maximization iterations. In each iteration, a novel multi-class transductive learning algorithm, namely, the Constrained Mapping, is proposed to learn likelihoods and identify unreliable likelihoods simultaneously. The resulting likelihoods then can be used as the input of any segmentation methods to improve their robustness. Experiments show that the proposed method is an effective way to improve both segmentation quality and efficiency, especially when the input image has complex color distribution.

Fast and robust image segmentation by small-world neural oscillator networks.

Inspired by the temporal correlation theory of brain functions, researchers have presented a number of neural oscillator networks to implement visual scene segmentation problems. Recently, it is shown that many biological neural networks are typical small-world networks. In this paper, we propose and investigate two small-world models derived from the well-known LEGION (locally excitatory and globally inhibitory oscillator network) model. To form a small-world network, we add a proper proportion of unidirectional shortcuts (random long-range connections) to the original LEGION model. With local connections and shortcuts, the neural oscillators can not only communicate with neighbors but also exchange phase information with remote partners. Model 1 introduces excitatory shortcuts to enhance the synchronization within an oscillator group representing the same object. Model 2 goes further to replace the global inhibitor with a sparse set of inhibitory shortcuts. Simulation results indicate that the proposed small-world models could achieve synchronization faster than the original LEGION model and are more likely to bind disconnected image regions belonging together. In addition, we argue that these two models are more biologically plausible.

Linked multi-component mobile robots: Modeling, simulation and control

The Linked Multi-Component Robotic Systems (L-MCRS) consists of a group of mobile robots carrying a passive uni-dimensional object (a hose or a wire). It is a recently identified unexplored and unexploited category of multi-robot systems. In this paper we report the first effort on the modeling, control and visual servoing of L-MCRS. Modeling has been tackled from geometrical and dynamical points of view. The passive element is modeled by splines, and the dynamical modeling is achieved by the appropriate extension of Geometrically Exact Dynamic Splines (GEDS). The system’s modeling allows realistic simulation, which can be used as a test bed for the evaluation of control strategies. In this paper we evaluate two such control strategies: a baseline global controller, and a fuzzy local controller based on the observation of the hose segment between two robots. Finally, we have performed physical experiments on a team of robots carrying a wire under a visual servoing scheme that provides the perceptual information about the hose for the fuzzy local controller. Visual servoing robust image segmentation is grounded in the Dichromatic Reflection Model (DRM).

A novel fuzzy C‐means algorithm for unsupervised heterogeneous tumor quantification in PET

Accurate and robust image segmentation was identified as one of the most challenging issues facing PET quantification in oncological imaging. This difficulty is compounded by the low spatial resolution and high noise characteristics of PET images. The fuzzy C-means (FCM) clustering algorithm was largely used in various medical image segmentation approaches. However, the algorithm is sensitive to both noise and intensity heterogeneity since it does not take into account spatial contextual information. To overcome this limitation, a new fuzzy segmentation technique adapted to typical noisy and low resolution oncological PET data is proposed. PET images smoothed using a nonlinear anisotropic diffusion filter are added as a second input to the proposed FCM algorithm to incorporate spatial information (FCM-S). In addition, a methodology was developed to integrate the a trous wavelet transform in the standard FCM algorithm (FCM-SW) to allow handling of heterogeneous lesions' uptake. The algorithm was applied to the simulated data of the NCAT phantom, incorporating heterogeneous lesions in the lung and clinical PET/CT images of 21 patients presenting with histologically proven nonsmall-cell lung cancer (NSCLC) and 7 patients presenting with laryngeal squamous cell carcinoma (LSCC) to assess its performance for segmenting tumors with arbitrary size, shape, and tracer uptake. For NSCLC patients, the maximal tumor diameters measured from the macroscopic examination of the surgical specimen served as the ground truth for comparison with the maximum diameter estimated by the segmentation technique, whereas for LSCC patients, the 3D macroscopic tumor volume was considered as the ground truth for comparison with the corresponding PET-based volume. The proposed algorithm was also compared to the classical FCM segmentation technique. There is a good correlation (R2 = 0.942) between the actual maximal diameter of primary NSCLC tumors estimated using the proposed PET segmentation procedure and those measured from the macroscopic examination, and the regression line agreed well with the line of identity (slope = 1.08) for the group analysis of the clinical data. The standard FCM algorithm seems to underestimate actual maximal diameters of the clinical data, resulting in a mean error of -4.6 mm (relative error of -10.8 +/- 23.1%) for all data sets. The mean error of maximal diameter estimation was reduced to 0.1 mm (0.9 +/- 14.4%) using the proposed FCM-SW algorithm. Likewise, the mean relative error on the estimated volume for LSCC patients was reduced from 21.7 +/- 22.0% for FCM to 8.6 +/- 28.3% using the proposed FCM-SW technique. A novel unsupervised PET image segmentation technique that allows the quantification of lesions in the presence of heterogeneity of tracer uptake was developed and evaluated. The technique is being further refined and assessed in clinical setting to delineate treatment volumes for the purpose of PET-guided radiation therapy treatment planning but could find other applications in clinical oncology such as the assessment of response to treatment.

A Nonconservative Flow Field for Robust Variational Image Segmentation

We introduce a robust image segmentation method based on a variational formulation using edge flow vectors. We demonstrate the nonconservative nature of this flow field, a feature that helps in a better segmentation of objects with concavities. A multiscale version of this method is developed and is shown to improve the localization of the object boundaries. We compare and contrast the proposed method with well known state-of-the-art methods. Detailed experimental results are provided on both synthetic and natural images that demonstrate that the proposed approach is quite competitive.