Abstract—A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottomup) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented. Index Terms — Image segmentation, nearest neighbor region merging, noise reduction, watershed transform. I.

We describe a sequence of low-level operations to isolate and classify brain tissue within T1-weighted magnetic resonance images (MRI). Our method first removes nonbrain tissue using a combination of anisotropic diffusion filtering, edge detection, and mathematical morphology. We compensate for image nonuniformities due to magnetic field inhomogeneities by fitting a tricubic B-spline gain field to local estimates of the image nonuniformity spaced throughout the MRI volume. The local estimates are computed by fitting a partial volume tissue measurement model to histograms of neighborhoods about each estimate point. The measurement model uses mean tissue intensity and noise variance values computed from the global image and a multiplicative bias parameter that is estimated for each region during the histogram fit. Voxels in the intensity-normalized image are then classified into six tissue types using a maximum a posteriori classifier. This classifier combines the partial volume tissue measurement model with a Gibbs prior that models the spatial properties of the brain. We validate each stage of our algorithm on real and phantom data. Using data from the 20 normal MRI brain data sets of the Internet Brain Segmentation Repository, our method achieved average � indices of ��0.746 � 0.114 for gray matter (GM) and ��0.798 � 0.089 for white matter (WM) compared to expert labeled data. Our method achieved average � indices �� 0.893 � 0.041 for GM and ��0.928 � 0.039 for WM compared to the ground truth labeling on 12 volumes from the Montreal Neurological Institute’s BrainWeb phantom.

Advances in visualization technology and specialized graphic workstations allow clinicians to virtually interact with anatomical structures contained within sampled medical-image datasets. A hindrance to the effective use of this technology is the difficult problem of image segmentation. In this paper, we utilize a recently proposed oscillator network called the locally excitatory globally inhibitory oscillator network (LEGION) whose ability to achieve fast synchrony with local excitation and desynchrony with global inhibition makes it an effective computational framework for grouping similar features and segregating dissimilar ones in an image. We extract an algorithm from LEGION dynamics and propose an adaptive scheme for grouping. We show results of the algorithm to two-dimensional (2-D) and threedimensional (3-D) (volume) computerized topography (CT) and magnetic resonance imaging (MRI) medical-image datasets. In addition, we compare our algorithm with other algorithms for medical-...

This paper presents a new method to segment brain parenchyma and cerebrospinal #uid spaces automatically in routine axial spin echo multispectral MR images. The algorithm simultaneously incorporates information about anatomical boundaries #shape# and tissue signature #grey scale# using a priori knowledge. The head and brain are divided into 4 regions and 7 di#erent tissue types. Each tissue type c is modeled by a multivariate Gaussian distribution N## c ; # c #. Each region is associated with a #nite mixture density corresponding to its constituent tissue types. Initial estimates of tissue parameters f# c ; # c g c=1;:::;7 are obtained from k-means clustering of a single slice used for training. The #rst algorithmic step uses the EM-algorithm for adjusting the initial tissue parameter estimates to the MR data of new patients. The second step uses a recently developed model of dynamic contours to detect three simply closed, non-intersecting curves in the plane, constituting the arachno...

The finite mixture (FM) model is the most commonly used model for statistical segmentation of brain MR images because of its simple mathematical form and the piecewise constant nature of ideal brain MR images. However,

this paper, a surface recovery method is described that approximates a digital 3-D shape by a rational Gaussian (RAG) surface. The obtained surface, which is obtained from coarse to fine, enables efficient transmission, rendering, and editing of the shape

An algorithm for automatic and accurate segmentation of multi-dimensional images is presented in this paper. It improves the classical watershed transform whose results are inaccurate when applied on noisy or anisotropic data. This algorithm combines a watershed-like region growing with a very simple marker selection step. It is particularly well suited for accurate segmentation of complex objects, such as the brain in 3D Magnetic Resonance (MR) images of the head since it provides an accurate and fully 3D segmentation in a reasonable computation time. Comparative results of the segmentation obtained by this algorithm and by the classical watershed transform are shown in the case of 3D MR images. Applications of this technique to 3D visualisation and brain sulcii identification are also presented. () 1997 Elsevier Science B.V.

Accurate detection and localization of two-dimensional (2D) image features (or `keypoints ') is important for vision tasks such as structure from motion, stereo matching, and line labeling. 2D image features are ideal for these vision tasks because 2D image features are high in information and yet they occur sparsely in typical images. Several methods for the detection of 2D image features have already been developed. However, it is difficult to assess the performance of these methods because no one has produced an adequate definition of corners that encompasses all types of 2D luminance variations that make up 2D image features. The fact that there does not exist a consensus on the definition of 2D image features is not surprising given the confusion surrounding the definition of 1D image features. The general perception of 1D image features has been that they correspond to `edges' in an image and so are points where the intensity gradient in some direction is a local maximum. The S...

We present a semi-automatic technique for segmenting a large cryo-sliced human brain data set that contains 753 highresolution RGB color images. This human brain data set presents a number of unique challenges to segmentation and visualization due to its size (over 7 GB) as well as the fact that each image not only shows the current slice of the brain but also unsliced "deeper layers" of the brain. These challenges are not present in traditional MRI and CT data sets. We have found that segmenting this data set can be made easier by using the YIQ color model and morphology. We have used a hardware-assisted interactive volume renderer to evaluate our segmentation results.

According to the Brain Tumor Society, approximately 100,000 people in the United States will be diagnosed with a primary or metastatic brain tumor within the next 12 months [16]. One of the primary diagnostic and treatment evaluation tools for brain tumors has been magnetic resonance (MR) imaging. MR imaging has become a widelyused