Current methods in medical image segmentation

A robust fuzzy local information C-Means clustering algorithm

This paper presents a variation of fuzzy c-means (FCM) algorithm that provides image clustering. The proposed algorithm incorporates the local spatial information and gray level information in a novel fuzzy way. The new algorithm is called fuzzy local information C-Means (FLICM). FLICM can overcome the disadvantages of the known fuzzy c-means algorithms and at the same time enhances the clustering performance. The major characteristic of FLICM is the use of a fuzzy local (both spatial and gray level) similarity measure, aiming to guarantee noise insensitiveness and image detail preservation. Furthermore, the proposed algorithm is fully free of the empirically adjusted parameters (a, ¿(g), ¿(s), etc.) incorporated into all other fuzzy c-means algorithms proposed in the literature. Experiments performed on synthetic and real-world images show that FLICM algorithm is effective and efficient, providing robustness to noisy images.

Latent Stick-Breaking Processes

We develop a model for stochastic processes with random marginal distributions. Our model relies on a stick-breaking construction for the marginal distribution of the process, and introduces dependence across locations by using a latent Gaussian copula model as the mechanism for selecting the atoms. The resulting latent stick-breaking process (LaSBP) induces a random partition of the index space, with points closer in space having a higher probability of being in the same cluster. We develop an efficient and straightforward Markov chain Monte Carlo (MCMC) algorithm for computation and discuss applications in financial econometrics and ecology. This article has supplementary material online.

NEONATAL BRAIN MRI SEGMENTATION BY BUILDING MULTI-REGION-MULTI-REFERENCE ATLASES

Neonatal brain MRI segmentation is challenging due to the poor image quality. Existing population atlases used for guiding segmentation are usually constructed by averaging all images in a population with no preference. However, such approaches diminish the important local inter-subject structural variability. In this paper, we propose a multi-region-multi-reference strategy for atlas building from a population. In brief, the brain is first parcellated into multiple anatomical regions, and for each region, the population images are classified into different sub-populations. The exemplars in sub-populations serve as structural references when determining the most suitable regional atlas for a to-be-segmented image. A final atlas is generated by combining all selected regional atlases, and a joint registration-segmentation strategy is employed for tissue segmentation. Experimental results demonstrate that segmentation with our atlas achieves high average tissue overlap rates with manual golden standard of 0.86 (SD 0.02) for gray matter (GM) and 0.83 (SD 0.03) for white matter (WM), and outperforms other atlases in comparison.

Quantitative analysis of cryo-EM density map segmentation by watershed and scale-space filtering, and fitting of structures by alignment to regions

Cryo-electron microscopy produces 3D density maps of molecular machines, which consist of various molecular components such as proteins and RNA. Segmentation of individual components in such maps is a challenging task, and is mostly accomplished interactively. We present an approach based on the immersive watershed method and grouping of the resulting regions using progressively smoothed maps. The method requires only three parameters: the segmentation threshold, a smoothing step size, and the number of smoothing steps. We first apply the method to maps generated from molecular structures and use a quantitative metric to measure the segmentation accuracy. The method does not attain perfect accuracy, however it produces single or small groups of regions that roughly match individual proteins or subunits. We also present two methods for fitting of structures into density maps, based on aligning the structures with single regions or small groups of regions. The first method aligns centers and principal axes, whereas the second aligns centers and then rotates the structure to find the best fit. We describe both interactive and automated ways of using these two methods. Finally, we show segmentation and fitting results for several experimentally-obtained density maps.

Large-scale propagation of ultrasound in a 3-D breast model based on high-resolution MRI data

A 40 x 35 x 25-mm(3) specimen of human breast consisting mostly of fat and connective tissue was imaged using a 3-T magnetic resonance scanner. The resolutions in the image plane and in the orthogonal direction were 130 microm and 150 microm, respectively. Initial processing to prepare the data for segmentation consisted of contrast inversion, interpolation, and noise reduction. Noise reduction used a multilevel bidirectional median filter to preserve edges. The volume of data was segmented into regions of fat and connective tissue by using a combination of local and global thresholding. Local thresholding was performed to preserve fine detail, while global thresholding was performed to minimize the interclass variance between voxels classified as background and voxels classified as object. After smoothing the data to avoid aliasing artifacts, the segmented data volume was visualized using isosurfaces. The isosurfaces were enhanced using transparency, lighting, shading, reflectance, and animation. Computations of pulse propagation through the model illustrate its utility for the study of ultrasound aberration. The results show the feasibility of using the described combination of methods to demonstrate tissue morphology in a form that provides insight about the way ultrasound beams are aberrated in three dimensions by tissue.

Unified wavelet and Gaussian filtering for segmentation of CT images; application in segmentation of bone in pelvic CT images

Background

The analysis of pelvic CT scans is a crucial step for detecting and assessing the severity of Traumatic Pelvic Injuries. Automating the processing of pelvic CT scans could impact decision accuracy, decrease the time for decision making, and reduce health care cost. This paper discusses a method to automate the segmentation of bone from pelvic CT images. Accurate segmentation of bone is very important for developing an automated assisted-decision support system for Traumatic Pelvic Injury diagnosis and treatment.

Methods

The automated method for pelvic CT bone segmentation is a hierarchical approach that combines filtering and histogram equalization, for image enhancement, wavelet analysis and automated seeded region growing. Initial results of segmentation are used to identify the region where bone is present and to target histogram equalization towards the specific area. Speckle Reducing Anisotropic Didffusion (SRAD) filter is applied to accentuate the desired features in the region. Automated seeded region growing is performed to refine the initial bone segmentation results.

Results

The proposed method automatically processes pelvic CT images and produces accurate segmentation. Bone connectivity is achieved and the contours and sizes of bones are true to the actual contour and size displayed in the original image. Results are promising and show great potential for fracture detection and assessing hemorrhage presence and severity.

Conclusion

Preliminary experimental results of the automated method show accurate bone segmentation. The novelty of the method lies in the unique hierarchical combination of image enhancement and segmentation methods that aims at maximizing the advantages of the combined algorithms. The proposed method has the following advantages: it produces accurate bone segmentation with maintaining bone contour and size true to the original image and is suitable for automated bone segmentation from pelvic CT images.

A multidimensional segmentation evaluation for medical image data

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Photosynthetic redox imbalance governs leaf sectoring in the Arabidopsis thaliana variegation mutants immutans, spotty, var1, and var2

We hypothesized that chloroplast energy imbalance sensed through alterations in the redox state of the photosynthetic electron transport chain, measured as excitation pressure, governs the extent of variegation in the immutans mutant of Arabidopsis thaliana. To test this hypothesis, we developed a nondestructive imaging technique and used it to quantify the extent of variegation in vivo as a function of growth temperature and irradiance. The extent of variegation was positively correlated (R(2) = 0.750) with an increase in excitation pressure irrespective of whether high light, low temperature, or continuous illumination was used to induce increased excitation pressure. Similar trends were observed with the variegated mutants spotty, var1, and var2. Measurements of greening of etiolated wild-type and immutans cotyledons indicated that the absence of IMMUTANS increased excitation pressure twofold during the first 6 to 12 h of greening, which led to impaired biogenesis of thylakoid membranes. In contrast with IMMUTANS, the expression of its mitochondrial analog, AOX1a, was transiently upregulated in the wild type but permanently upregulated in immutans, indicating that the effects of excitation pressure during greening were also detectable in mitochondria. We conclude that mutations involving components of the photosynthetic electron transport chain, such as those present in immutans, spotty, var1, and var2, predispose Arabidopsis chloroplasts to photooxidation under high excitation pressure, resulting in the variegated phenotype.

Intensity Standardization Simplifies Brain MR Image Segmentation

Typically, brain MR images present significant intensity variation across patients and scanners. Consequently, training a classifier on a set of images and using it subsequently for brain segmentation may yield poor results. Adaptive iterative methods usually need to be employed to account for the variations of the particular scan. These methods are complicated, difficult to implement and often involve significant computational costs. In this paper, a simple, non-iterative method is proposed for brain MR image segmentation. Two preprocessing techniques, namely intensity inhomogeneity correction, and more importantly MR image intensity standardization, used prior to segmentation, play a vital role in making the MR image intensities have a tissue-specific numeric meaning, which leads us to a very simple brain tissue segmentation strategy.Vectorial scale-based fuzzy connectedness and certain morphological operations are utilized first to generate the brain intracranial mask. The fuzzy membership value of each voxel within the intracranial mask for each brain tissue is then estimated. Finally, a maximum likelihood criterion with spatial constraints taken into account is utilized in classifying all voxels in the intracranial mask into different brain tissue groups. A set of inhomogeneity corrected and intensity standardized images is utilized as a training data set. We introduce two methods to estimate fuzzy membership values. In the first method, called SMG (for simple membership based on a gaussian model), the fuzzy membership value is estimated by fitting a multivariate Gaussian model to the intensity distribution of each brain tissue whose mean intensity vector and covariance matrix are estimated and fixed from the training data sets. The second method, called SMH (for simple membership based on a histogram), estimates fuzzy membership value directly via the intensity distribution of each brain tissue obtained from the training data sets. We present several studies to evaluate the performance of these two methods based on 10 clinical MR images of normal subjects and 10 clinical MR images of Multiple Sclerosis (MS) patients. A quantitative comparison indicates that both methods have overall better accuracy than the k-nearest neighbors (kNN) method, and have much better efficiency than the Finite Mixture (FM) model based Expectation-Maximization (EM) method. Accuracy is similar for our methods and EM method for the normal subject data sets, but much better for our methods for the patient data sets.

Multiple sclerosis lesion detection using constrained GMM and curve evolution

This paper focuses on the detection and segmentation of Multiple Sclerosis (MS) lesions in magnetic resonance (MRI) brain images. To capture the complex tissue spatial layout, a probabilistic model termed Constrained Gaussian Mixture Model (CGMM) is proposed based on a mixture of multiple spatially oriented Gaussians per tissue. The intensity of a tissue is considered a global parameter and is constrained, by a parameter-tying scheme, to be the same value for the entire set of Gaussians that are related to the same tissue. MS lesions are identified as outlier Gaussian components and are grouped to form a new class in addition to the healthy tissue classes. A probability-based curve evolution technique is used to refine the delineation of lesion boundaries. The proposed CGMM-CE algorithm is used to segment 3D MRI brain images with an arbitrary number of channels. The CGMM-CE algorithm is automated and does not require an atlas for initialization or parameter learning. Experimental results on both standard brain MRI simulation data and real data indicate that the proposed method outperforms previously suggested approaches, especially for highly noisy data.

Computerized characterization of prostate cancer by fractal analysis in MR images

PURPOSE

To explore the potential of computerized characterization of prostate MR images by extracting the fractal features of texture and intensity distributions as indices in the differential diagnosis of prostate cancer.

MATERIALS AND METHODS

MR T2-weighted images (T2WI) of 55 patients with pathologic results detected by ultrasound guided biopsy were collected and then divided in two groups, 27 with prostate cancer (PCa) and 28 with no histological abnormality. Texture fractal dimension (TFD) and histogram fractal dimension (HFD) were calculated to analyze complexity features of regions of Interest (ROIs) selected from the peripheral zone. Two-sample t-tests were performed to evaluate group differences for both parameters. Receiver operating characteristic (ROC) analysis was used to estimate the performance of TFD and HFD for discriminating PCa.

RESULTS

Significant differences were found in both TFD and HFD between the two patient groups. The areas under the ROC curves of TFD and HFD were 0.691 and 0.966, respectively, in distinguishing prostatic carcinoma from normal peripheral zone. As characterized by the fractal indices, cancerous prostatic tissue exhibited smoother texture and lower variation in intensity distribution than normal prostatic tissue.

CONCLUSION

The study suggests that TFD and HFD depict the changes in texture and intensity distribution associated with prostate cancer on T2WI. Both TFD and HFD provide promising quantitative indices for cancer identification. HFD performs better than TFD offering a more robust MR-based indicator in the diagnosis of prostatic carcinoma.

Segmentation of center brains and optic lobes in 3D confocal images of adult fruit fly brains

Automatic alignment (registration) of 3D images of adult fruit fly brains is often influenced by the significant displacement of the relative locations of the two optic lobes (OLs) and the center brain (CB). In one of our ongoing efforts to produce a better image alignment pipeline of adult fruit fly brains, we consider separating CB and OLs and align them independently. This paper reports our automatic method to segregate CB and OLs, in particular under conditions where the signal to noise ratio (SNR) is low, the variation of the image intensity is big, and the relative displacement of OLs and CB is substantial. We design an algorithm to find a minimum-cost 3D surface in a 3D image stack to best separate an OL (of one side, either left or right) from CB. This surface is defined as an aggregation of the respective minimum-cost curves detected in each individual 2D image slice. Each curve is defined by a list of control points that best segregate OL and CB. To obtain the locations of these control points, we derive an energy function that includes an image energy term defined by local pixel intensities and two internal energy terms that constrain the curve's smoothness and length. Gradient descent method is used to optimize this energy function. To improve both the speed and robustness of the method, for each stack, the locations of optimized control points in a slice are taken as the initialization prior for the next slice. We have tested this approach on simulated and real 3D fly brain image stacks and demonstrated that this method can reasonably segregate OLs from CBs despite the aforementioned difficulties.

Non-convex polyhedral volume of interest selection

We introduce a novel approach to specify and edit volumes of interest (VOI for short) interactively. Enhancing the capabilities of standard systems we provide tools to edit the VOI by defining a not necessarily convex polyhedral bounding object. We suggest to use low-level editing interactions for moving, inserting and deleting vertices, edges and faces of the polyhedron. The low-level operations can be used as building blocks for more complex higher order operations fitting the application demands. Flexible initialization allows the user to select within a few clicks convex VOI that in the classical clipping plane model need the specification of a large number of cutting planes. In our model it is similarly simple to select non-convex VOI. Boolean combinations allow to select non-connected VOI of arbitrary complexity. The polyhedral VOI selection technique enables the user to define VOI with complex boundary structure interactively, in an easy to comprehend and predictable manner.

Computational morphometry for detecting changes in brain structure due to development, aging, learning, disease and evolution

The brain, like any living tissue, is constantly changing in response to genetic and environmental cues and their interaction, leading to changes in brain function and structure, many of which are now in reach of neuroimaging techniques. Computational morphometry on the basis of Magnetic Resonance (MR) images has become the method of choice for studying macroscopic changes of brain structure across time scales. Thanks to computational advances and sophisticated study designs, both the minimal extent of change necessary for detection and, consequently, the minimal periods over which such changes can be detected have been reduced considerably during the last few years. On the other hand, the growing availability of MR images of more and more diverse brain populations also allows more detailed inferences about brain changes that occur over larger time scales, way beyond the duration of an average research project. On this basis, a whole range of issues concerning the structures and functions of the brain are now becoming addressable, thereby providing ample challenges and opportunities for further contributions from neuroinformatics to our understanding of the brain and how it changes over a lifetime and in the course of evolution.

Neonatal brain image segmentation in longitudinal MRI studies

In the study of early brain development, tissue segmentation of neonatal brain MR images remains challenging because of the insufficient image quality due to the properties of developing tissues. Among various brain tissue segmentation algorithms, atlas-based brain image segmentation can potentially achieve good segmentation results on neonatal brain images. However, their performances rely on both the quality of the atlas and the spatial correspondence between the atlas and the to-be-segmented image. Moreover, it is difficult to build a population atlas for neonates due to the requirement of a large set of tissue-segmented neonatal brain images. To combat these obstacles, we present a longitudinal neonatal brain image segmentation framework by taking advantage of the longitudinal data acquired at late time-point to build a subject-specific tissue probabilistic atlas. Specifically, tissue segmentation of the neonatal brain is formulated as two iterative steps of bias correction and probabilistic-atlas-based tissue segmentation, along with the longitudinal atlas reconstructed by the late time image of the same subject. The proposed method has been evaluated qualitatively through visual inspection and quantitatively by comparing with manual delineations and two population-atlas-based segmentation methods. Experimental results show that the utilization of a subject-specific probabilistic atlas can substantially improve tissue segmentation of neonatal brain images.

An adaptive mean-shift framework for MRI brain segmentation

An automated scheme for magnetic resonance imaging (MRI) brain segmentation is proposed. An adaptive mean-shift methodology is utilized in order to classify brain voxels into one of three main tissue types: gray matter, white matter, and Cerebro-spinal fluid. The MRI image space is represented by a high-dimensional feature space that includes multimodal intensity features as well as spatial features. An adaptive mean-shift algorithm clusters the joint spatial-intensity feature space, thus extracting a representative set of high-density points within the feature space, otherwise known as modes. Tissue segmentation is obtained by a follow-up phase of intensity-based mode clustering into the three tissue categories. By its nonparametric nature, adaptive mean-shift can deal successfully with nonconvex clusters and produce convergence modes that are better candidates for intensity based classification than the initial voxels. The proposed method is validated on 3-D single and multimodal datasets, for both simulated and real MRI data. It is shown to perform well in comparison to other state-of-the-art methods without the use of a preregistered statistical brain atlas.

Active mask segmentation of fluorescence microscope images

We propose a new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns. It combines the (a) flexibility offered by active-contour methods, (b) speed offered by multiresolution methods, (c) smoothing offered by multiscale methods, and (d) statistical modeling offered by region-growing methods into a fast and accurate segmentation tool. The framework moves from the idea of the "contour" to that of "inside and outside," or masks, allowing for easy multidimensional segmentation. It adapts to the topology of the image through the use of multiple masks. The algorithm is almost invariant under initialization, allowing for random initialization, and uses a few easily tunable parameters. Experiments show that the active mask algorithm matches the ground truth well and outperforms the algorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively.

Three-dimensional neuron tracing by voxel scooping

Tracing the centerline of the dendritic arbor of neurons is a powerful technique for analyzing neuronal morphology. In the various neuron tracing algorithms in use nowadays, the competing goals of computational efficiency and robustness are generally traded off against each other. We present a novel method for tracing the centerline of a neuron from confocal image stacks, which provides an optimal balance between these objectives. Using only local information, thin cross-sectional layers of voxels ('scoops') are iteratively carved out of the structure, and clustered based on connectivity. Each cluster contributes a node along the centerline, which is created by connecting successive nodes until all object voxels are exhausted. While data segmentation is independent of this algorithm, we illustrate the use of the ISODATA method to achieve dynamic (local) segmentation. Diameter estimation at each node is calculated using the Rayburst Sampling algorithm, and spurious end nodes caused by surface irregularities are then removed. On standard computing hardware the algorithm can process hundreds of thousands of voxels per second, easily handling the multi-gigabyte datasets resulting from high-resolution confocal microscopy imaging of neurons. This method provides an accurate and efficient means for centerline extraction that is suitable for interactive neuron tracing applications.

Automated voxel-based 3D cortical thickness measurement in a combined Lagrangian-Eulerian PDE approach using partial volume maps

Accurate cortical thickness estimation is important for the study of many neurodegenerative diseases. Many approaches have been previously proposed, which can be broadly categorised as mesh-based and voxel-based. While the mesh-based approaches can potentially achieve subvoxel resolution, they usually lack the computational efficiency needed for clinical applications and large database studies. In contrast, voxel-based approaches, are computationally efficient, but lack accuracy. The aim of this paper is to propose a novel voxel-based method based upon the Laplacian definition of thickness that is both accurate and computationally efficient. A framework was developed to estimate and integrate the partial volume information within the thickness estimation process. Firstly, in a Lagrangian step, the boundaries are initialized using the partial volume information. Subsequently, in an Eulerian step, a pair of partial differential equations are solved on the remaining voxels to finally compute the thickness. Using partial volume information significantly improved the accuracy of the thickness estimation on synthetic phantoms, and improved reproducibility on real data. Significant differences in the hippocampus and temporal lobe between healthy controls (NC), mild cognitive impaired (MCI) and Alzheimer's disease (AD) patients were found on clinical data from the ADNI database. We compared our method in terms of precision, computational speed and statistical power against the Eulerian approach. With a slight increase in computation time, accuracy and precision were greatly improved. Power analysis demonstrated the ability of our method to yield statistically significant results when comparing AD and NC. Overall, with our method the number of samples is reduced by 25% to find significant differences between the two groups.

Medical image segmentation using genetic algorithms

Genetic algorithms (GAs) have been found to be effective in the domain of medical image segmentation, since the problem can often be mapped to one of search in a complex and multimodal landscape. The challenges in medical image segmentation arise due to poor image contrast and artifacts that result in missing or diffuse organ/tissue boundaries. The resulting search space is therefore often noisy with a multitude of local optima. Not only does the genetic algorithmic framework prove to be effective in coming out of local optima, it also brings considerable flexibility into the segmentation procedure. In this paper, an attempt has been made to review the major applications of GAs to the domain of medical image segmentation.

The optimal linear transformation-based fMRI feature space analysis

This paper proposes a method of extending the optimal linear transformation (OLT), an image analysis technique of feature space, from magnetic resonance imaging (MRI) to functional magnetic resonance imaging (fMRI) so as to improve the activation detection performance over conventional approaches of fMRI analysis. The method was: (1) ideal hemodynamic responses for different stimuli were generated by convolving the theoretical hemodynamic response model with the stimulus timing, (2) considering the ideal hemodynamic responses as hypothetical signature vectors for different activity patterns of interest, OLT was used to extract the features of fMRI data. The resultant feature space had particular geometric clustering properties. It was then classified into different groups, each pertaining to an activity pattern of interest; the applied signature vector for each group was obtained by averaging, (3) using the applied signature vectors, OLT was applied again to generate fMRI composite images with high SNRs for the desired activity patterns. Simulations and a blocked fMRI experiment were employed to validate the proposed method. The simulation and the experiment results indicated the proposed method was capable of improving some conventional methods to be more sensitive to activations, having strong contrast between activations and inactivations, and being more valid for complex activity patterns.

Evaluation of automated brain MR image segmentation and volumetry methods

We compare three widely used brain volumetry methods available in the software packages FSL, SPM5, and FreeSurfer and evaluate their performance using simulated and real MR brain data sets. We analyze the accuracy of gray and white matter volume measurements and their robustness against changes of image quality using the BrainWeb MRI database. These images are based on "gold-standard" reference brain templates. This allows us to assess between- (same data set, different method) and also within-segmenter (same method, variation of image quality) comparability, for both of which we find pronounced variations in segmentation results for gray and white matter volumes. The calculated volumes deviate up to >10% from the reference values for gray and white matter depending on method and image quality. Sensitivity is best for SPM5, volumetric accuracy for gray and white matter was similar in SPM5 and FSL and better than in FreeSurfer. FSL showed the highest stability for white (<5%), FreeSurfer (6.2%) for gray matter for constant image quality BrainWeb data. Between-segmenter comparisons show discrepancies of up to >20% for the simulated data and 24% on average for the real data sets, whereas within-method performance analysis uncovered volume differences of up to >15%. Since the discrepancies between results reach the same order of magnitude as volume changes observed in disease, these effects limit the usability of the segmentation methods for following volume changes in individual patients over time and should be taken into account during the planning and analysis of brain volume studies.

3D SEGMENTATION OF THE LIVER USING FREE-FORM DEFORMATION BASED ON BOOSTING AND DEFORMATION GRADIENTS

This paper presents a novel automatic 3D hybrid segmentation approach based on free-form deformation. The algorithms incorporate boosting and deformation gradients to achieve reliable liver segmentation of Computed Tomography (CT) scans. A free-form deformable model is deformed under the forces originating from boosting and deformation gradients. The basic idea of the scheme is to combine information from intensity and shape prior knowledge to calculate desired displacements to the liver boundary on vertices of deformable surface. Boosting classifies the 3D image into a binary mask and the edgeflow generates a force field from the mask. The deformable surface deforms iteratively according to the force field. Deformation gradients cast restriction at each deformation step. The deformation converges to a stable status to achieve the final segmentation surface.

Automated segmentation of tissue structures in optical coherence tomography data

Segmentation of optical coherence tomography (OCT) images provides useful information, especially in medical imaging applications. Because OCT images are subject to speckle noise, the identification of structures is complicated. Addressing this issue, two methods for the automated segmentation of arbitrary structures in OCT images are proposed. The methods perform a seeded region growing, applying a model-based analysis of OCT A-scans for the seed's acquisition. The segmentation therefore avoids any user-intervention dependency. The first region-growing algorithm uses an adaptive neighborhood homogeneity criterion based on a model of an OCT intensity course in tissue and a model of speckle noise corruption. It can be applied to an unfiltered OCT image. The second performs region growing on a filtered OCT image applying the local median as a measure for homogeneity in the region. Performance is compared through the quantitative evaluation of artificial data, showing the capabilities of both in terms of structures detected and leakage. The proposed methods were tested on real OCT data in different scenarios and showed promising results for their application in OCT imaging.

Automatic cropping of MRI rat brain volumes using pulse coupled neural networks

The Pulse Coupled Neural Network (PCNN) was developed by Eckhorn to model the observed synchronization of neural assemblies in the visual cortex of small mammals such as a cat. In this paper we show the use of the PCNN as an image segmentation strategy to crop MR images of rat brain volumes. We then show the use of the associated PCNN image 'signature' to automate the brain cropping process with a trained artificial neural network. We tested this novel algorithm on three T2 weighted acquisition configurations comprising a total of 42 rat brain volumes. The datasets included 40 ms, 48 ms and 53 ms effective TEs, acquisition field strengths of 4.7 T and 9.4 T, image resolutions from 64x64 to 256x256, slice locations ranging from +6 mm to -11 mm AP, two different surface coil manufacturers and imaging protocols. The results were compared against manually segmented gold standards and Brain Extraction Tool (BET) V2.1 results. The Jaccard similarity index was used for numerical evaluation of the proposed algorithm. Our novel PCNN cropping system averaged 0.93 compared to BET scores circa 0.84.

Performance measure characterization for evaluating neuroimage segmentation algorithms

Characterizing the performance of segmentation algorithms in brain images has been a persistent challenge due to the complexity of neuroanatomical structures, the quality of imagery and the requirement of accurate segmentation. There has been much interest in using the Jaccard and Dice similarity coefficients associated with Sensitivity and Specificity for evaluating the performance of segmentation algorithms. This paper addresses the essential characteristics of the fundamental performance measure coefficients adopted in evaluation frameworks. While exploring the properties of the Jaccard, Dice and Specificity coefficients, we propose new measure coefficients Conformity and Sensibility for evaluating image segmentation techniques. It is indicated that Conformity is more sensitive and rigorous than Jaccard and Dice in that it has better discrimination capabilities in detecting small variations in segmented images. Comparing to Specificity, Sensibility provides consistent and reliable evaluation scores without the incorporation of image background properties. The merits of the proposed coefficients are illustrated by extracting neuroanatomical structures in a wide variety of brain images using various segmentation techniques.

A combined region growing and deformable model method for extraction of closed surfaces in 3D CT and MRI scans

Image segmentation of 3D medical images is a challenging problem with several still not totally solved practical issues, such as noise interference, variable object structures and image artifacts. This paper describes a hybrid 3D image segmentation method which combines region growing and deformable models to obtain accurate and topologically preserving surface structures of anatomical objects of interest. The proposed strategy starts by determining a rough but robust approximation of the objects using a region-growing algorithm. Then, the closed surface mesh that encloses the region is constructed and used as the initial geometry of a deformable model for the final refinement. This integrated strategy provides an alternative solution to one of the flaws of traditional deformable models, achieving good refinements of internal surfaces in few steps. Experimental segmentation results of complex anatomical structures on both simulated and real data from MRI scans are presented, and the method is assessed by comparing with standard reference segmentations of head MRI. The evaluation was mainly based on the average overlap measure, which was tested on the segmentation of white matter, corresponding to a simulated brain data set, showing excellent performance exceeding 90% accuracy. In addition, the algorithm was applied to the detection of anatomical head structures on two real MRI and one CT data set. The final reconstructions resulting from the deformable models produce high quality meshes suitable for 3D visualization and further numerical analysis. The obtained results show that the approach achieves high quality segmentations with low computational complexity.

Oriented active shape models

Active shape models (ASM) are widely employed for recognizing anatomic structures and for delineating them in medical images. In this paper, a novel strategy called oriented active shape models (OASM) is presented in an attempt to overcome the following five limitations of ASM: 1) lower delineation accuracy, 2) the requirement of a large number of landmarks, 3) sensitivity to search range, 4) sensitivity to initialization, and 5) inability to fully exploit the specific information present in the given image to be segmented. OASM effectively combines the rich statistical shape information embodied in ASM with the boundary orientedness property and the globally optimal delineation capability of the live wire methodology of boundary segmentation. The latter characteristics allow live wire to effectively separate an object boundary from other nonobject boundaries with similar properties especially when they come very close in the image domain. The approach leads to a two-level dynamic programming method, wherein the first level corresponds to boundary recognition and the second level corresponds to boundary delineation, and to an effective automatic initialization method. The method outputs a globally optimal boundary that agrees with the shape model if the recognition step is successful in bringing the model close to the boundary in the image. Extensive evaluation experiments have been conducted by utilizing 40 image (magnetic resonance and computed tomography) data sets in each of five different application areas for segmenting breast, liver, bones of the foot, and cervical vertebrae of the spine. Comparisons are made between OASM and ASM based on precision, accuracy, and efficiency of segmentation. Accuracy is assessed using both region-based false positive and false negative measures and boundary-based distance measures. The results indicate the following: 1) The accuracy of segmentation via OASM is considerably better than that of ASM; 2) The number of landmarks can be reduced by a factor of 3 in OASM over that in ASM; 3) OASM becomes largely independent of search range and initialization becomes automatic. All three benefits of OASM ensue mainly from the severe constraints brought in by the boundary-orientedness property of live wire and the globally optimal solution found by the 2-level dynamic programming algorithm.

A hybrid geometric-statistical deformable model for automated 3-D segmentation in brain MRI

We present a novel 3-D deformable model-based approach for accurate, robust, and automated tissue segmentation of brain MRI data of single as well as multiple magnetic resonance sequences. The main contribution of this study is that we employ an edge-based geodesic active contour for the segmentation task by integrating both image edge geometry and voxel statistical homogeneity into a novel hybrid geometric-statistical feature to regularize contour convergence and extract complex anatomical structures. We validate the accuracy of the segmentation results on simulated brain MRI scans of both single T1-weighted and multiple T1/T2/PD-weighted sequences. We also demonstrate the robustness of the proposed method when applied to clinical brain MRI scans. When compared to a current state-of-the-art region-based level-set segmentation formulation, our white matter and gray matter segmentation resulted in significantly higher accuracy levels with a mean improvement in Dice similarity indexes of 8.55% ( p < 0.0001) and 10.18% ( p < 0.0001), respectively.

Investigation of the neural correlates underlying action observation in multiple sclerosis patients

Recent fMRI evidence indicates that both the execution and the observation of hand actions in multiple sclerosis (MS) patients increase recruitment of a portion of the so-called mirror neuron system. However, it remains unclear whether this is the expression of a compensatory mechanism for the coding of observed action or whether such a mechanism represents a rather unspecific functional adaptation process. Here we used fMRI on early relapsing remitting MS (RRMS) patients to clarify this issue. Functional images of 15 right-handed early RRMS patients and of 15 sex- and age-matched right-handed healthy controls were acquired using a 1.5 T scanner. During scanning, participants simply observed images depicting a human hand either grasping an object or resting alongside an object. As shown by a between-group analysis, when compared to controls, RRMS patients revealed a robust increase of activation in an extensive network of brain regions including frontal, parietal, temporal and visual areas usually activated during action observation. However, this pattern of hemodynamic activity was completely independent of the type of observed hand-object interaction as revealed by the lack of any significant between-group interaction. Our findings are in line with previous fMRI evidence demonstrating cortical reorganization in MS patients during action observation. However, based on our findings we go one step further and suggest that such functional cortical changes may be the expression of a generalized and unspecific compensatory mechanism, that is not necessarily involved in action understanding.

The emerging discipline of Computational Functional Anatomy

Computational Functional Anatomy (CFA) is the study of functional and physiological response variables in anatomical coordinates. For this we focus on two things: (i) the construction of bijections (via diffeomorphisms) between the coordinatized manifolds of human anatomy, and (ii) the transfer (group action and parallel transport) of functional information into anatomical atlases via these bijections. We review advances in the unification of the bijective comparison of anatomical submanifolds via point-sets including points, curves and surface triangulations as well as dense imagery. We examine the transfer via these bijections of functional response variables into anatomical coordinates via group action on scalars and matrices in DTI as well as parallel transport of metric information across multiple templates which preserves the inner product.

Brain Tissue Segmentation of Neonatal MR Images Using a Longitudinal Subject-specific Probabilistic Atlas

Brain tissue segmentation of neonate MR images is a challenging task in study of early brain development, due to low signal contrast among brain tissues and high intensity variability especially in white matter. Among various brain tissue segmentation algorithms, the atlas-based segmentation techniques can potentially produce reasonable segmentation results on neonatal brain images. However, their performance on the population-based atlas is still limited due to the high variability of brain structures across different individuals. Moreover, it may be impossible to generate a reasonable probabilistic atlas for neonates without tissue segmentation samples. To overcome these limitations, we present a neonatal brain tissue segmentation method by taking advantage of the longitudinal data available in our study to establish a subject-specific probabilistic atlas. In particular, tissue segmentation of the neonatal brain is formulated as two iterative steps of bias correction and probabilistic atlas based tissue segmentation, along with the guidance of brain tissue segmentation resulted from the later time images of the same subject which serve as a subject-specific probabilistic atlas. The proposed method has been evaluated qualitatively through visual inspection and quantitatively by comparing with manual delineation results. Experimental results show that the utilization of a subject-specific probabilistic atlas can substantially improve tissue segmentation of neonatal brain images.

K-Bayes reconstruction for perfusion MRI. I: concepts and application

Despite the continued spread of magnetic resonance imaging (MRI) methods in scientific studies and clinical diagnosis, MRI applications are mostly restricted to high-resolution modalities, such as structural MRI. While perfusion MRI gives complementary information on blood flow in the brain, its reduced resolution limits its power for detecting specific disease effects on perfusion patterns. This reduced resolution is compounded by artifacts such as partial volume effects, Gibbs ringing, and aliasing, which are caused by necessarily limited k-space sampling and the subsequent use of discrete Fourier transform (DFT) reconstruction. In this study, a Bayesian modeling procedure (K-Bayes) is developed for the reconstruction of perfusion MRI. The K-Bayes approach (described in detail in Part II: Modeling and Technical Development) combines a process model for the MRI signal in k-space with a Markov random field prior distribution that incorporates high-resolution segmented structural MRI information. A simulation study was performed to determine qualitative and quantitative improvements in K-Bayes reconstructed images compared with those obtained via DFT. The improvements were validated using in vivo perfusion MRI data of the human brain. The K-Bayes reconstructed images were demonstrated to provide reduced bias, increased precision, greater effect sizes, and higher resolution than those obtained using DFT.

ITAC volume assessment through a Gaussian hidden Markov random field model-based algorithm

In this paper, a semi-automatic segmentation method for volume assessment of Intestinal-type adenocarcinoma (ITAC) is presented and validated. The method is based on a Gaussian hidden Markov random field (GHMRF) model that represents an advanced version of a finite Gaussian mixture (FGM) model as it encodes spatial information through the mutual influences of neighboring sites. To fit the GHMRF model an expectation maximization (EM) algorithm is used. We applied the method to a magnetic resonance data sets (each of them composed by T1-weighted, Contrast Enhanced T1-weighted and T2-weighted images) for a total of 49 tumor-contained slices. We tested GHMRF performances with respect to FGM by both a numerical and a clinical evaluation. Results show that the proposed method has a higher accuracy in quantifying lesion area than FGM and it can be applied in the evaluation of tumor response to therapy.

Evaluating the cancer detection and grading potential of prostatic-zinc imaging: a simulation study

The present work deals with the analysis of prostatic-zinc-concentration images. The goal is to evaluate potential clinically relevant information that can be extracted from such images. In the absence of experimental images, synthetic ones are produced from clinically measured zinc-concentration distributions in certified benign and cancerous tissue samples, classified by the lesion grade. We describe the method for producing the images and model the effect of counting statistics noise. We present in detail the image analysis, which is based on a combination of standard image processing and segmentation tools, optimized for this particular application. The information on lowest zinc value obtained from the image analysis is translated to clinical data such as tumour presence, location, size and grade. Their confidence is evaluated with the help of standard statistical tools such as receiver operating characteristic analysis. The present work predicts a potential for detecting small prostate-cancer lesions, of grade (4+3) and above, with very good specificity and sensitivity. The present analysis further provides data on the pixel size and image counting statistics requested from the trans-rectal probe that will record in vivo prostatic-zinc maps in patients.

Cross modality deformable segmentation using hierarchical clustering and learning

Segmentation of anatomical objects is always a fundamental task for various clinical applications. Although many automatic segmentation methods have been designed to segment specific anatomical objects in a given imaging modality, a more generic solution that is directly applicable to different imaging modalities and different deformable surfaces is desired, if attainable. In this paper, we propose such a framework, which learns from examples the spatially adaptive appearance and shape of a 3D surface (either open or closed). The application to a new object/surface in a new modality requires only the annotation of training examples. Key contributions of our method include: (1) an automatic clustering and learning algorithm to capture the spatial distribution of appearance similarities/variations on the 3D surface. More specifically, the model vertices are hierarchically clustered into a set of anatomical primitives (sub-surfaces) using both geometric and appearance features. The appearance characteristics of each learned anatomical primitive are then captured through a cascaded boosting learning method. (2) To effectively incorporate non-Gaussian shape priors, we cluster the training shapes in order to build multiple statistical shape models. (3) To our best knowledge, this is the first time the same segmentation algorithm has been directly employed in two very diverse applications: (a) Liver segmentation (closed surface) in PET-CT, in which CT has very low-resolution and low-contrast; (b) Distal femur (condyle) surface (open surface) segmentation in MRI.

A Scalable Framework For Segmenting Magnetic Resonance Images

A fast, accurate and fully automatic method of segmenting magnetic resonance images of the human brain is introduced. The approach scales well allowing fast segmentations of fine resolution images. The approach is based on modifications of the soft clustering algorithm, fuzzy c-means, that enable it to scale to large data sets. Two types of modifications to create incremental versions of fuzzy c-means are discussed. They are much faster when compared to fuzzy c-means for medium to extremely large data sets because they work on successive subsets of the data. They are comparable in quality to application of fuzzy c-means to all of the data. The clustering algorithms coupled with inhomogeneity correction and smoothing are used to create a framework for automatically segmenting magnetic resonance images of the human brain. The framework is applied to a set of normal human brain volumes acquired from different magnetic resonance scanners using different head coils, acquisition parameters and field strengths. Results are compared to those from two widely used magnetic resonance image segmentation programs, Statistical Parametric Mapping and the FMRIB Software Library (FSL). The results are comparable to FSL while providing significant speed-up and better scalability to larger volumes of data.

Image Segmentation for Evaluating Axillary Lymph Nodes

A review is provided of the literature that has been published on image segmentation relative to sonography. Manual and automatic techniques for partitioning a sonogram are highlighted. In addition, a preliminary set of results is provided on the interrater reliability of the manual segmentation of axillary lymph nodes that have been sonographically imaged. A correlation between sonographers conducting manual segmentation is very high ( r = 0.9 with P < .00 at the .01 alpha level). This work is set to provide additional information on lymph node cubic volume and the agreement between manual and automatic segmentation of axillary lymph nodes.

Quantitative imaging of musculoskeletal tissue

Quantitative imaging of musculoskeletal tissue, including radiography, computed tomography (CT), and magnetic resonance imaging (MRI), has become the essential methodology in clinical practice for diagnosis and monitoring of various musculoskeletal conditions. Furthermore, quantitative imaging technologies have become indispensable for research and development in diseases of the human skeleton. Standardized methods of image analysis have been developed through the years to quantify measurements on bone and cartilage with high precision and accuracy. Key areas of musculoskeletal disease where quantitative imaging is currently employed are osteoporosis and arthritis.