Results 1  10
of
42
Hybrid Image Segmentation Using Watersheds and Fast Region Merging
 IEEE transactions on Image Processing
, 1998
"... Abstract—A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and regionbased techniques through the morphological algorithm of watersheds. An edgepreserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate est ..."
Abstract

Cited by 104 (1 self)
 Add to MetaCart
(Show Context)
Abstract—A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and regionbased techniques through the morphological algorithm of watersheds. An edgepreserving 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 socalled nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, onepixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with twodimensional/threedimensional (2D/3D) magnetic resonance images are presented. Index Terms — Image segmentation, nearest neighbor region merging, noise reduction, watershed transform. I.
Magnetic resonance image tissue classification using a partial volume model
 NEUROIMAGE
, 2001
"... We describe a sequence of lowlevel operations to isolate and classify brain tissue within T1weighted 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 imag ..."
Abstract

Cited by 104 (5 self)
 Add to MetaCart
We describe a sequence of lowlevel operations to isolate and classify brain tissue within T1weighted 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 Bspline 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 intensitynormalized 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.
Segmentation of Medical Images Using LEGION
 IEEE Trans. Med. Imag
, 1999
"... Advances in visualization technology and specialized graphic workstations allow clinicians to virtually interact with anatomical structures contained within sampled medicalimage datasets. A hindrance to the effective use of this technology is the difficult problem of image segmentation. In this pap ..."
Abstract

Cited by 20 (6 self)
 Add to MetaCart
(Show Context)
Advances in visualization technology and specialized graphic workstations allow clinicians to virtually interact with anatomical structures contained within sampled medicalimage 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 twodimensional (2D) and threedimensional (3D) (volume) computerized topography (CT) and magnetic resonance imaging (MRI) medicalimage datasets. In addition, we compare our algorithm with other algorithms for medical...
Segmentation of Brain Parenchyma and Cerebrospinal Fluid in Multispectral Magnetic Resonance Images
 IEEE Transactions on Medical Imaging
, 1995
"... 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 kno ..."
Abstract

Cited by 16 (1 self)
 Add to MetaCart
(Show Context)
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 kmeans clustering of a single slice used for training. The #rst algorithmic step uses the EMalgorithm 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, nonintersecting curves in the plane, constituting the arachno...
Hidden Markov Random Field Model and Segmentation of Brain MR Images
 IEEE TRANSACTIONS ON MEDICAL IMAGING
, 2001
"... 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, ..."
Abstract

Cited by 10 (0 self)
 Add to MetaCart
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,
Segmentation of magnetic resonance images using fuzzy algorithms for learning vector quantization
 IEEE Transactions on Medical Imaging
, 1999
"... Abstract—This paper evaluates a segmentation technique for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ). These algorithms perform vector quantization by updating all prototypes of a competitive network through an unsupervised learning ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
(Show Context)
Abstract—This paper evaluates a segmentation technique for magnetic resonance (MR) images of the brain based on fuzzy algorithms for learning vector quantization (FALVQ). These algorithms perform vector quantization by updating all prototypes of a competitive network through an unsupervised learning process. Segmentation of MR images is formulated as an unsupervised vector quantization process, where the local values of different relaxation parameters form the feature vectors which are represented by a relatively small set of prototypes. The experiments evaluate a variety of FALVQ algorithms in terms of their ability to identify different tissues and discriminate between normal tissues and abnormalities. Index Terms—Fuzzy algorithms for learning vector quantization, learning vector quantization, magnetic resonance imaging, segmentation. I.
Approximating Digital 3D Shapes by Rational Gaussian Surfaces
 IEEE Trans. Visualization and Computer Graphics
, 2003
"... this paper, a surface recovery method is described that approximates a digital 3D 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 ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
(Show Context)
this paper, a surface recovery method is described that approximates a digital 3D 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
A QueueBased Region Growing Algorithm for Accurate Segmentation of MultiDimensional Digital Images
, 1997
"... An algorithm for automatic and accurate segmentation of multidimensional 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 watershedlike region growing with a very simpl ..."
Abstract

Cited by 7 (2 self)
 Add to MetaCart
An algorithm for automatic and accurate segmentation of multidimensional 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 watershedlike 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.
The Detection Of 2D Image Features Using Local Energy
, 1996
"... Accurate detection and localization of twodimensional (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 ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
Accurate detection and localization of twodimensional (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...
Segmentation and 3D visualization of highresolution human brain cryosections
, 2002
"... We present a semiautomatic technique for segmenting a large cryosliced 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 eac ..."
Abstract

Cited by 6 (4 self)
 Add to MetaCart
We present a semiautomatic technique for segmenting a large cryosliced 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 hardwareassisted interactive volume renderer to evaluate our segmentation results.