Abstract: Characterizing the performance of image segmentation approaches has been a persistent challenge. Performance analysis is important since segmentation algorithms often have limited accuracy and precision. Interactive drawing of the desired segmentation by human raters has often been the only acceptable approach, and yet suffers from intra-rater and inter-rater variability. Automated algorithms have been sought in order to remove the variability introduced by raters, but such algorithms must be assessed to ensure they are suitable for the task. The performance of raters (human or algorithmic) generating segmentations of medical images has been difficult to quantify because of the difficulty of obtaining or estimating a known true segmentation for clinical data. Although physical and digital phantoms can be constructed for which ground truth is known or readily estimated, such phantoms do not fully reflect clinical images due to the difficulty of constructing phantoms which reproduce the full range of imaging characteristics and normal and pathological anatomical variability observed in clinical data. Comparison to a collection of segmentations by raters is an attractive alternative since it can be carried out directly on the relevant clinical imaging data. However, the most appropriate measure or set of measures with which to compare such segmentations has not been clarified and several measures are used in practice. We present here an expectation-maximization algorithm for simultaneous truth and performance level estimation (STAPLE). The algorithm considers a collection of segmentations and computes a probabilistic estimate of the true segmentation and a measure of the performance level represented by each segmentation. The source of each segmentation in the collection may be an appropriately trained human rater or raters, or may be an automated segmentation algorithm. The probabilistic estimate of the true segmentation is formed by estimating an optimal combination of the segmentations, weighting each segmentation depending upon the estimated performance level, and incorporating a prior model for the spatial distribution of structures being segmented as well as spatial homogeneity constraints. STAPLE is straightforward to apply to clinical imaging data, it readily enables assessment of the performance of an automated image segmentation algorithm, and enables direct comparison of human rater and algorithm performance.

Abstract: Vessel segmentation algorithms are the critical components of circulatory blood vessel analysis systems. We present a survey of vessel extraction techniques and algorithms. We put the various vessel extraction approaches and techniques in perspective by means of a classification of the existing research. While we have mainly targeted the extraction of blood vessels, neurosvascular structure in particular, we have also reviewed some of the segmentation methods for the tubular objects that show similar characteristics to vessels. We have divided vessel segmentation algorithms and techniques into six main categories: (1) pattern recognition techniques, (2) model-based approaches, (3) tracking-based approaches, (4) artificial intelligence-based approaches, (5) neural network-based approaches, and (6) tube-like object detection approaches. Some of these categories are further divided into subcategories. We have also created tables to compare the papers in each category against such criteria as dimensionality, input type, preprocessing, user interaction, and result type.

Abstract: We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure- ground segmentation is available prior to recognition. However, in contrast to most standard approaches for object class recognition, our approach automati- cally segments the object as a result of the categorization. This combination of recognition and segmentation into one process is made pos- sible by our use of an Implicit Shape Model, which integrates both into a common probabilistic framework. In addition to the recognition and segmentation result, it also generates a per-pixel confidence measure specifying the area that supports a hypothesis and how much it can be trusted. We use this confidence to derive a nat- ural extension of the approach to handle multiple objects in a scene and resolve ambiguities between overlapping hypotheses with a novel MDL-based criterion. In addition, we present an extensive evaluation of our method on a standard dataset for car detection and compare its performance to existing methods from the literature. Our results show that the proposed method significantly outper- forms previously published methods while needing one order of magnitude less training examples. Finally, we present results for articulated objects, which show that the proposed method can categorize and segment unfamiliar objects in differ- ent articulations and with widely varying texture patterns, even under significant partial occlusion.

Abstract: This paper explores a statistical basis for a process often described in computer vision: image segmentation by region merging following a particular order in the choice of regions. We exhibit a particular blend of algorithmics and statistics whose segmentation error is, as we show, limited from both the qualitative and quantitative standpoints. This approach can be efficiently approximated in linear time/space, leading to a fast segmentation algorithm tailored to processing images described using most common numerical pixel attribute spaces. The conceptual simplicity of the approach makes it simple to modify and cope with hard noise corruption, handle occlusion, authorize the control of the segmentation scale, and process unconventional data such as spherical images. Experiments on gray-level and color images, obtained with a short readily available C-code, display the quality of the segmentations obtained.

Abstract: In this work we compare the performance of a number of vessel segmentation algorithms on a newly constructed retinal vessel image database. Retinal vessel segmentation is important for the detection of numerous eye diseases and plays an important role in automatic retinal disease screening systems. A large number of methods for retinal vessel segmentation have been published, yet an evaluation of these methods on a common database of screening images has not been performed. To compare the performance of retinal vessel segmentation methods we have constructed a large database of retinal images. The database contains forty images in which the vessel trees have been manually segmented. For twenty of those forty images a second independent manual segmentation is available. This allows for a comparison between the performance of automatic methods and the performance of a human observer. The database is available to the research community. Interested researchers are encouraged to upload their segmentation results to our website (http://www.isi.uu.nl/Research/Databases). The performance of five different algorithms has been compared. Four of these methods have been implemented as described in the literature. The fifth pixel classification based method was developed specifically for the segmentation of retinal vessels and is the only supervised method in this test. We define the segmentation accuracy with respect to our gold standard as the performance measure. Results show that the pixel classification method performs best, but the second observer still performs significantly better.

Abstract: The watershed transform has interesting properties that make it useful for many different image segmentation applications: it is simple and intuitive, can be parallelized, and always produces a complete division of the image. However, when applied to medical image analysis, it has important drawbacks (oversegmentation, sensitivity to noise, poor detection of thin or low signal to noise ratio structures). We present an improvement to the watershed transform that enables the introduction of prior information in its calculation. We propose to introduce this information via the use of a previous probability calculation. Furthermore, we introduce a method to combine the watershed transform and atlas registration, through the use of markers. We have applied our new algorithm to two challenging applications: knee cartilage and gray matter/white matter segmentation in MR images. Numerical validation of the results is provided, demonstrating the strength of the algorithm for medical image segmentation.

Abstract: Chinese word segmentation is a difficult, important and widely-studied sequence modeling problem. This paper demonstrates the ability of linear-chain conditional random fields (CRFs) to perform robust and accurate Chinese word segmentation by providing a principled framework that easily supports the integration of domain knowledge in the form of multiple lexicons of characters and words. We also present a probabilistic new word detection method, which further improves performance. Our system is evaluated on four datasets used in a recent comprehensive Chinese word segmentation competition. State-of-the-art performance is obtained.

Abstract: We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body pans in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. For the main regression, we evaluate both regularized least squares and relevance vector machine (RVM) regressors over both linear and kernel bases. The RVM's provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. For realism and good generalization with respect to viewpoints, we train the regressors on images resynthesized from real human motion capture data, and test it both quantitatively on similar independent test data, and qualitatively on a real image sequence. Mean angular errors of 6-7 degrees are obtained - a factor of 3 better than the current state of the art for the much simpler upper body problem.

Abstract: Reliable and efficient optic disk localization and segmentation are important tasks in automated retinal screening. General-purpose edge detection algorithms often fail to segment the optic disk due to fuzzy boundaries, inconsistent image contrast or missing edge features. This paper presents an algorithm for the localization and segmentation of the optic nerve head boundary in low-resolution images (about 20 /spl mu//pixel). Optic disk localization is achieved using specialized template matching, and segmentation by a deformable contour model. The latter uses a global elliptical model and a local deformable model with variable edge-strength dependent stiffness. The algorithm is evaluated against a randomly selected database of 100 images from a diabetic screening programme. Ten images were classified as unusable; the others were of variable quality. The localization algorithm succeeded on all bar one usable image; the contour estimation algorithm was qualitatively assessed by an ophthalmologist as having Excellent-Fair performance in 83% of cases, and performs well even on blurred images.

Abstract: In this work we show how to combine bottom-up and top-down approaches into a single figure-ground segmentation process. This process provides accurate delineation of object boundaries that cannot be achieved by either the top-down or bottom-up approach alone. The top-down approach uses object representation learned from examples to detect an object in a given input image and provide an approximation to its figure-ground segmentation. The bottom-up approach uses image-based criteria to define coherent groups of pixels that are likely to belong together to either the figure or the background part. The combination provides a final segmentation that draws on the relative merits of both approaches: The result is as close as possible to the top-down approximation, but is also constrained by the bottom-up process to be consistent with significant image discontinuities. We construct a global cost function that represents these top-down and bottom-up requirements. We then show how the global minimum of this function can be efficiently found by applying the sum-product algorithm. This algorithm also provides a confidence map that can be used to identify image regions where additional top-down or bottom-up information may further improve the segmentation. Our experiments show that the results derived from the algorithm are superior to results given by a pure top-down or pure bottom-up approach. The scheme has broad applicability, enabling the combined use of a range of existing bottom-up and top-down segmentations.

Abstract: Market segmentation is an accepted tool in strategic marketing. It helps to understand and serve the needs of homogeneous consumer subpopulations. Two approaches are recognized: a priori and data-driven (a posteriori, post hoc) segmentation. In tourism, there is a long history of a priori segmentation studies in industry and academia. These lead to the identification of tourist groups derived from dividing the population according to prior knowledge (“commonsense segmentation”). However, due to the wide use of this approach, there is not much room for competitive advantage to be gained by using a priori segmentation. This article (1) reviews segmentation studies in tourism, (2) proposes a systematics of segmentation approaches, and (3) illustrates the managerial usefulness of novel approaches emerging from this systematics. The main aim is to offer academics and practitioners a menu of exploratory techniques that can be used to increase market understanding.

Abstract: We consider data clustering problems where partial grouping is known a priori. We formulate such biased grouping problems as a constrained optimization problem, where structural properties of the data define the goodness of a grouping and partial grouping cues define the feasibility of a grouping. We enforce grouping smoothness and fairness on labeled data points so that sparse partial grouping information can be effectively propagated to the unlabeled data. Considering the normalized cuts criterion in particular, our formulation leads to a constrained eigenvalue problem. By generalizing the Rayleigh-Ritz theorem to projected matrices, we find the global optimum in the relaxed continuous domain by eigendecomposition, from which a near-global optimum to the discrete labeling problem can be obtained effectively. We apply our method to real image segmentation problems, where partial grouping priors can often be derived based on a crude spatial attentional map that binds places with common salient features or focuses on expected object locations. We demonstrate not only that it is possible to integrate both image structures and priors in a single grouping process, but also that objects can be segregated from the background without specific object knowledge.

Abstract: The pulse coupled neural network (PCNN) is a new neural network that was developed and formed in the 1990's. The key point of a PCNN is the modulated coupling mechanism, while coupled results produce internal activity. The output of the PCNN is a binary image sequence, which can be considered the result of threshold segmentation. In this paper, the matrix made by the internal activity is regarded as a breadth of image, which then can be conjoined with the technique of traditional threshold segmentation. The application of the minimum cross-entropy criterion in the technique of image segmentation makes the discrepancy of information content between segmented image and image after segmentation to be minimal. A kind of novel of image segmentation algorithm based on automatic cycle iterations is put forward, after the traditional PCNN threshold segmentation mechanism is improved in combination with the minimum cross-entropy criterion. Theory analysis and experimental results all show that the best segmentation output can be drawn using this new algorithm.

Abstract: We formulate and apply spectral clustering to 3D mesh segmentation for the first time and report our preliminary findings Given a set of mesh faces, an affinity matrix which encodes the likelihood of each pair of faces belonging to the same group is first constructed Spectral methods then use selected eigenvectors of the affinity matrix or its closely related graph Laplacian to obtain data representations that can be more easily clustered We develop an algorithm that favors segmentation along concave regions, which is inspired by human perception Our algorithm is theoretically sound, efficient, simple to implement, andean achieve high-quality segmentation results on 3D meshes

Abstract: A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling, and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using maximum likelihood estimation and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24 percent is observed in 17 out of 21 test sequences. In all but one case, the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation.

Abstract: It is well known in the pattern recognition community that the accuracy of classifications obtained by combining decisions made by independent classifiers can be substantially higher than the accuracy of the individual classifiers. We have previously shown this to be true for atlas-based segmentation of biomedical images. The conventional method for combining individual classifiers weights each classifier equally (vote or sum rule fusion). In this paper, we propose two methods that estimate the performances of the individual classifiers and combine the individual classifiers by weighting them according to their estimated performance. The two methods are multiclass extensions of an expectation-maximization (EM) algorithm for ground truth estimation of binary classification based on decisions of multiple experts (Warfield et al., 2004). The first method performs parameter estimation independently for each class with a subsequent integration step. The second method considers all classes simultaneously. We demonstrate the efficacy of these performance-based fusion methods by applying them to atlas-based segmentations of three-dimensional confocal microscopy images of bee brains. In atlas-based image segmentation, multiple classifiers arise naturally by applying different registration methods to the same atlas, or the same registration method to different atlases, or both. We perform a validation study designed to quantify the success of classifier combination methods in atlas-based segmentation. By applying random deformations, a given ground truth atlas is transformed into multiple segmentations that could result from imperfect registrations of an image to multiple atlas images. In a second evaluation study, multiple actual atlas-based segmentations are combined and their accuracies computed by comparing them to a manual segmentation. We demonstrate in both evaluation studies that segmentations produced by combining multiple individual registration-based segmentations are more accurate for the two classifier fusion methods we propose, which weight the individual classifiers according to their EM-based performance estimates, than for simple sum rule fusion, which weights each classifier equally.

Abstract: The vertebral column is derived from somites formed by segmentation of presomitic mesoderm, a fundamental process of vertebrate embryogenesis. Models on the mechanism controlling this process date back some three to four decades. Access to understanding the molecular control of somitogenesis has been gained only recently by the discovery of molecular oscillators (segmentation clock) and gradients of signaling molecules, as predicted by early models. The Notch signaling pathway is linked to the oscillator and plays a decisive role in inter- and intrasomitic boundary formation. An Fgf8 signaling gradient is involved in somite size control. And the (canonical) Wnt signaling pathway, driven by Wnt3a, appears to integrate clock and gradient in a global mechanism controlling the segmentation process. In this review, we discuss recent advances in understanding the molecular mechanism controlling somitogenesis.

Abstract: Image segmentation methods for μCT can influence the accuracy of bone morphometry calculations. A new automated segmentation method is introduced, and its performance is compared with standard segmentation methods. The new method can improve the results of in vivo μCT, where the need to keep radiation dose low limits scan quality. Introduction: An important topic for μCT analysis of bone samples is the segmentation of the original reconstructed grayscale data sets to separate bone from non-bone. Problems like noise, resolution limitations, and beam-hardening make this a nontrivial issue. Inappropriate segmentation methods will reduce the potential power of μCT and may introduce bias in the architectural measurements, in particular, when new in vivo μCT with its inherent limitations in scan quality is used. Here we introduce a new segmentation method using local thresholds and compare its performance to standard global segmentation methods. Material and Methods: The local threshold method was validated by comparing the result of the segmentation with histology. Furthermore, the effect of choosing this new method versus standard segmentation methods using global threshold values was investigated by studying the sensitivity of these methods to signal to noise ratio and resolution. Results: Using the new method on high-quality scans yielded accurate results and virtually no differences between histology and the segmented data sets could be observed. When prior knowledge about the volume fraction of the bone was available the global threshold also resulted in appropriate results. Degrading the scan quality had only minor effects on the performance of the new segmentation method. Although global segmentation methods were not sensitive to noise, it was not possible to segment both lower mineralized thin trabeculae and the higher mineralized cortex correctly with the same threshold value. Conclusion: At high resolutions, both the new local and conventional global segmentation methods gave near exact representations of the bone structure. When scanned samples are not homogenous (e.g., thick cortices and thin trabeculae) and when resolution is relatively low, the local segmentation method outperforms global methods. It maximizes the potential of in vivo μCT by giving good structural representation without the need to use longer scanning times that would increase absorption of harmful X-ray radiation by the living tissue.

Abstract: We describe a new approach for learning to perform class-based segmentation using only unsegmented training examples. As in previous methods, we first use training images to extract fragments that contain common object parts. We then show how these parts can be segmented into their figure and ground regions in an automatic learning process. This is in contrast with previous approaches, which required complete manual segmentation of the objects in the training examples. The figure-ground learning combines top-down and bottom-up processes and proceeds in two stages, an initial approximation followed by iterative refinement. The initial approximation produces figure-ground labeling of individual image fragments using the unsegmented training images. It is based on the fact that on average, points inside the object are covered by more fragments than points outside it. The initial labeling is then improved by an iterative refinement process, which converges in up to three steps. At each step, the figure-ground labeling of individual fragments produces a segmentation of complete objects in the training images, which in turn induce a refined figure-ground labeling of the individual fragments. In this manner, we obtain a scheme that starts from unsegmented training images, learns the figure-ground labeling of image fragments, and then uses this labeling to segment novel images. Our experiments demonstrate that the learned segmentation achieves the same level of accuracy as methods using manual segmentation of training images, producing an automatic and robust top-down segmentation.

Abstract: A novel method for the segmentation of multiple objects from three-dimensional (3-D) medical images using interobject constraints is presented. Our method is motivated by the observation that neighboring structures have consistent locations and shapes that provide configurations and context that aid in segmentation. We define a maximum a posteriori (MAP) estimation framework using the constraining information provided by neighboring objects to segment several objects simultaneously. We introduce a representation for the joint density function of the neighbor objects, and define joint probability distributions over the variations of the neighboring shape and position relationships of a set of training images. In order to estimate the MAP shapes of the objects, we formulate the model in terms of level set functions, and compute the associated Euler-Lagrange equations. The contours evolve both according to the neighbor prior information and the image gray level information. This method is useful in situations where there is limited interobject information as opposed to robust global atlases. In addition, we compare our level set representation of the object shape to the point distribution model. Results and validation from experiments on synthetic data and medical imagery in two-dimensional and 3-D are demonstrated.