Results 1 - 10
of
58
Is a single energy functional sufficient? adaptive energy functionals and automatic initialization
- In Proc. MICCAI, Part II, volume 4792 of LNCS
, 2007
"... Abstract. Energy functional minimization is an increasingly popular technique for image segmentation. However, it is far too commonly applied with hand-tuned parameters and initializations that have only been validated for a few images. Fixing these parameters over a set of images assumes the same p ..."
Abstract
-
Cited by 19 (4 self)
- Add to MetaCart
(Show Context)
Abstract. Energy functional minimization is an increasingly popular technique for image segmentation. However, it is far too commonly applied with hand-tuned parameters and initializations that have only been validated for a few images. Fixing these parameters over a set of images assumes the same parameters are ideal for each image. We highlight the effects of varying the parameters and initialization on segmentation accuracy and propose a framework for attaining improved results using image adaptive parameters and initializations. We provide an analytical definition of optimal weights for functional terms through an examination of segmentation in the context of image manifolds, where nearby images on the manifold require similar parameters and similar initializations. Our results validate that fixed parameters are insufficient in addressing the variability in real clinical data, that similar images require similar parameters, and demonstrate how these parameters correlate with the image manifold. We present significantly improved segmentations for synthetic images and a set of 470 clinical examples. 1
Embedding overlap priors in variational left ventricle tracking
- IEEE Transactions on Medical Imaging
, 2009
"... Abstract—We propose to embed overlap priors in variational tracking of the left ventricle (LV) in cardiac magnetic resonance (MR) sequences. The method consists of evolving two curves toward the LV endo- and epicardium boundaries. We derive the curve evolution equations by minimizing two functionals ..."
Abstract
-
Cited by 16 (5 self)
- Add to MetaCart
Abstract—We propose to embed overlap priors in variational tracking of the left ventricle (LV) in cardiac magnetic resonance (MR) sequences. The method consists of evolving two curves toward the LV endo- and epicardium boundaries. We derive the curve evolution equations by minimizing two functionals each containing an original overlap prior constraint. The latter mea-sures the conformity of the overlap between the nonparametric (kernel-based) intensity distributions within the three target re-gions—LV cavity, myocardium and background-to a prior learned from a given segmentation of the first frame. The Bhattacharyya coefficient is used as an overlap measure. Different from existing intensity-driven constraints, the proposed priors do not assume implicitly that the overlap between the intensity distributions within different regions has to be minimal. This prevents both the papillary muscles from being included erroneously in the myocardium and the curves from spilling into the background. Although neither geometric training nor preprocessing were used, quantitative evaluation of the similarities between automatic and independent manual segmentations showed that the proposed method yields a competitive score in comparison with existing methods. This allows more flexibility in clinical use because our solution is based only on the current intensity data, and consequently, the results are not bounded to the characteristics, variability, and mathematical description of a finite training set. We also demonstrate experimentally that the overlap measures are approximately constant over a cardiac sequence, which allows to learn the overlap priors from a single frame. Index Terms—Active contours, cardiac magnetic resonance images (cardiac MRI), left ventricle tracking, level sets, overlap priors, variational image segmentation. I.
Topology preserving STACS segmentation of protein subcellular location images
- in Proc. Intl. Symp. on Biomedical Imaging (ISBI), 2006
"... We present an algorithm for the segmentation of multicell fluorescence microscopy images. Such images abound and a segmentation algorithm robust to different experimental conditions as well as cell types is becoming a necessity. In cellular imaging, among the most often used segmentation algorithms ..."
Abstract
-
Cited by 12 (6 self)
- Add to MetaCart
(Show Context)
We present an algorithm for the segmentation of multicell fluorescence microscopy images. Such images abound and a segmentation algorithm robust to different experimental conditions as well as cell types is becoming a necessity. In cellular imaging, among the most often used segmentation algorithms is seeded watershed. One of its features is that it tends to oversegment, splitting the cells, as well as create segmented regions much larger than a true cell. This can be an advantage (the entire cell is within the region) as well as a disadvantage (a large amount of background noise is included). We present an algorithm which segments with tight contours by building upon an active contour algorithm—STACS, by Pluempitiwiriyawej et al. We adapt the algorithm to suit the needs of our data and use another technique, topology preservation by Han et al., to build our topology preserving STACS (TPSTACS). Our algorithm significantly outperforms the seeded watershed both visually as well as by standard measures of segmentation quality: recall/precision, area similarity and area overlap.
Active mask segmentation of fluorescence microscope images
- IEEE Trans. Imag. Proc
, 2009
"... Abstract—We propose a new active mask algorithm for the seg-mentation 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 of-fered by multiscale methods, and (d) statist ..."
Abstract
-
Cited by 11 (3 self)
- Add to MetaCart
(Show Context)
Abstract—We propose a new active mask algorithm for the seg-mentation 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 of-fered 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 multidimen-sional 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 al-gorithm widely used in fluorescence microscopy, seeded watershed, both qualitatively, as well as quantitatively. Index Terms—Active contours, active masks, cellular automata, fluorescence microscope, multiresolution, multiscale, segmenta-tion. I.
Semiautomated segmentation of myocardial contours for fast strain analysis in cine displacement-encoded MRI
- IEEE Trans. Med. Imag
, 2008
"... Abstract—The purposes of this study were to develop a semiauto-mated cardiac contour segmentation method for use with cine dis-placement-encoded MRI and evaluate its accuracy against manual segmentation. This segmentation model was designed with two dis-tinct phases: preparation and evolution. Durin ..."
Abstract
-
Cited by 10 (0 self)
- Add to MetaCart
(Show Context)
Abstract—The purposes of this study were to develop a semiauto-mated cardiac contour segmentation method for use with cine dis-placement-encoded MRI and evaluate its accuracy against manual segmentation. This segmentation model was designed with two dis-tinct phases: preparation and evolution. During the model prepa-ration phase, after manual image cropping and then image inten-sity standardization, the myocardium is separated from the back-ground based on the difference in their intensity distributions, and the endo- and epi-cardial contours are initialized automatically as zeros of an underlying level set function. During the model evolu-tion phase, the model deformation is driven by the minimization of an energy function consisting of five terms: model intensity, edge attraction, shape prior, contours interaction, and contour smooth-ness. The energy function is minimized iteratively by adaptively weighting the five terms in the energy function using an annealing algorithm. The validation experiments were performed on a pool of cine data sets of five volunteers. The difference between the semiau-tomated segmentation and manual segmentation was sufficiently small as to be considered clinically irrelevant. This relatively ac-curate semiautomated segmentation method can be used to signif-icantly increase the throughput of strain analysis of cine displace-ment-encoded MR images for clinical applications. Index Terms—Energy minimization, magnetic resonance imaging (MRI), segmentation, strain. I.
Content-based image sequence representation
- in Video Processing
, 2004
"... Abstract. In this chapter we overview methods that represent video sequences in terms of their content. These methods differ from those developed for MPEG/H.26X coding standards in that sequences are described in terms of extended images instead of collections of frames. We describe how these extend ..."
Abstract
-
Cited by 10 (8 self)
- Add to MetaCart
(Show Context)
Abstract. In this chapter we overview methods that represent video sequences in terms of their content. These methods differ from those developed for MPEG/H.26X coding standards in that sequences are described in terms of extended images instead of collections of frames. We describe how these extended images, e.g., mosaics, are generated by the basically same principle: the incremental composition of visual photometric, geometric, and multi-view information into one or more extended images. Different outputs, e.g., from single 2-D mosaics to full 3-D mosaics, are obtained depending on the quality and quantity of photometric, geometric, and multi-view information. In particular, we detail a framework well suited to the representation of scenes with independently moving objects. We address the two following important cases: i) the moving objects can be represented by 2-D silhouettes (generative video approach) ; or ii) the camera motion is such that the moving object must be described by their 3-D shape (recovered through rank 1 surface-based factorization). A basic pre-processing step in content-based image sequence representation is to extract and track the relevant background and foreground objects. This is achieved by 2-D shape segmentation for which there is a wealth of methods and approaches. The chapter includes a brief description of active contour methods for image segmentation. 1
Left ventricle segmentation via graph cut distribution matching
, 2009
"... Abstract. We present a discrete kernel density matching energy for segmenting the left ventricle cavity in cardiac magnetic resonance sequences. The energy and its graph cut optimization based on an original first-order approximation of the Bhattacharyya measure have not been proposed previously, an ..."
Abstract
-
Cited by 10 (3 self)
- Add to MetaCart
(Show Context)
Abstract. We present a discrete kernel density matching energy for segmenting the left ventricle cavity in cardiac magnetic resonance sequences. The energy and its graph cut optimization based on an original first-order approximation of the Bhattacharyya measure have not been proposed previously, and yield competi-tive results in nearly real-time. The algorithm seeks a region within each frame by optimization of two priors, one geometric (distance-based) and the other pho-tometric, each measuring a distribution similarity between the region and a model learned from the first frame. Based on global rather than pixelwise information, the proposed algorithm does not require complex training and optimization with respect to geometric transformations. Unlike related active contour methods, it does not compute iterative updates of computationally expensive kernel densities. Furthermore, the proposed first-order analysis can be used for other intractable energies and, therefore, can lead to segmentation algorithms which share the flex-ibility of active contours and computational advantages of graph cuts. Quantita-tive evaluations over 2280 images acquired from 20 subjects demonstrated that the results correlate well with independent manual segmentations by an expert. 1
Adaptive Regularization for Image Segmentation using Local Image Curvature Cues
"... Abstract. Image segmentation techniques typically require proper weighting of competing data fidelity and regularization terms. Conventionally, the associated parameters are set through tedious trial and error procedures and kept constant over the image. However, spatially varying structural charact ..."
Abstract
-
Cited by 7 (5 self)
- Add to MetaCart
(Show Context)
Abstract. Image segmentation techniques typically require proper weighting of competing data fidelity and regularization terms. Conventionally, the associated parameters are set through tedious trial and error procedures and kept constant over the image. However, spatially varying structural characteristics, such as object curvature, combined with varying noise and imaging artifacts, significantly complicate the selection process of segmentation parameters. In this work, we propose a novel approach for automating the parameter selection by employing a robust structural cue to prevent excessive regularization of trusted (i.e. low noise) high curvature image regions. Our approach autonomously adapts local regularization weights by combining local measures of image curvature and edge evidence that are gated by a signal reliability measure. We demonstrate the utility and favorable performance of our approach within two major segmentation frameworks, graph cuts and active contours, and present quantitative and qualitative results on a variety of natural and medical images. 1
Active mask segmentation for the cell-volume computation and Golgi-body segmentation of HeLa cell images
- in Proc. IEEE Int. Symp. Biomed. Imaging
, 2008
"... We present a novel active mask framework for the segmenta-tion of fluorescence microscope images of cells, and in par-ticular, for the segmentation of the Golgi body as well as cell-volume computation. We demonstrate that the algorithm is able to efficiently segment a stack of images and successfull ..."
Abstract
-
Cited by 6 (2 self)
- Add to MetaCart
(Show Context)
We present a novel active mask framework for the segmenta-tion of fluorescence microscope images of cells, and in par-ticular, for the segmentation of the Golgi body as well as cell-volume computation. We demonstrate that the algorithm is able to efficiently segment a stack of images and successfully assign multiple pieces of the Golgi body in a 2D image to the cell to which they belong. Further, we demonstrate that our algorithm is more accurate than manual segmentation of these images. Index Terms — active contours, active mask, segmenta-tion 1.
Segmentation of Intra-Retinal Layers from Optical Coherence Tomography Images using an Active Contour Approach
, 2010
"... Optical Coherence Tomography (OCT) is a noninvasive, depth-resolved imaging modality that has become a prominent ophthalmic diagnostic technique. We present a semiautomated segmentation algorithm to detect intra-retinal layers in OCT images acquired from rodent models of retinal degeneration. We ada ..."
Abstract
-
Cited by 6 (1 self)
- Add to MetaCart
Optical Coherence Tomography (OCT) is a noninvasive, depth-resolved imaging modality that has become a prominent ophthalmic diagnostic technique. We present a semiautomated segmentation algorithm to detect intra-retinal layers in OCT images acquired from rodent models of retinal degeneration. We adapt Chan–Vese’s energy-minimizing active contours without edges for the OCT images, which suffer from low contrast and are highly corrupted by noise. A multi-phase framework with a circular shape prior is adopted in order to model the boundaries of retinal layers and estimate the shape parameters using least squares. We use a contextual scheme to balance the weight of different terms in the energy functional. The results from various synthetic experiments and segmentation results on OCT images of rats are presented, demonstrating the strength of our method to detect the desired retinal layers with sufficient accuracy even in the presence of intensity inhomogeneity resulting from blood vessels. Our algorithm achieved an average Dice similarity coefficient of 0.84 over all segmented retinal layers, and of 0.94 for the combined nerve fiber layer, ganglion cell layer, and inner plexiform layer which are the critical layers for glaucomatous degeneration.
