Results 1 - 10
of
14
Tuner: Principled parameter finding for image segmentation algorithms using visual response surface exploration
- IEEE Transactions on Visualization and Computer Graphics
, 2011
"... Abstract—In this paper we address the difficult problem of parameter-finding in image segmentation. We replace a tedious manual process that is often based on guess-work and luck by a principled approach that systematically explores the parameter space. Our core idea is the following two-stage techn ..."
Abstract
-
Cited by 22 (6 self)
- Add to MetaCart
(Show Context)
Abstract—In this paper we address the difficult problem of parameter-finding in image segmentation. We replace a tedious manual process that is often based on guess-work and luck by a principled approach that systematically explores the parameter space. Our core idea is the following two-stage technique: We start with a sparse sampling of the parameter space and apply a statistical model to estimate the response of the segmentation algorithm. The statistical model incorporates a model of uncertainty of the estimation which we use in conjunction with the actual estimate in (visually) guiding the user towards areas that need refinement by placing additional sample points. In the second stage the user navigates through the parameter space in order to determine areas where the response value (goodness of segmentation) is high. In our exploration we rely on existing ground-truth images in order to evaluate the ”goodness ” of an image segmentation technique. We evaluate its usefulness by demonstrating this technique on two image segmentation algorithms: a three parameter model to detect microtubules in electron tomograms and an eight parameter model to identify functional regions in dynamic Positron Emission Tomography scans. Index Terms—Parameter exploration, Image segmentation, Gaussian Process Model. 1
Exploration and Visualization of Segmentation Uncertainty Using Shape and Appearance Prior Information
"... Abstract—We develop an interactive analysis and visualization tool for probabilistic segmentation in medical imaging. The originality of our approach is that the data exploration is guided by shape and appearance knowledge learned from expert-segmented images of a training population. We introduce a ..."
Abstract
-
Cited by 12 (4 self)
- Add to MetaCart
(Show Context)
Abstract—We develop an interactive analysis and visualization tool for probabilistic segmentation in medical imaging. The originality of our approach is that the data exploration is guided by shape and appearance knowledge learned from expert-segmented images of a training population. We introduce a set of multidimensional transfer function widgets to analyze the multivariate probabilistic field data. These widgets furnish the user with contextual information about conformance or deviation from the population statistics. We demonstrate the user’s ability to identify suspicious regions (e.g. tumors) and to correct the misclassification results. We evaluate our system and demonstrate its usefulness in the context of static anatomical and time-varying functional imaging datasets. Index Terms—Uncertainty visualization, Medical imaging, Probabilistic segmentation. 1
Paraglide: Interactive Parameter Space Partitioning for Computer Simulations
, 2011
"... Abstract—In this paper we introduce paraglide, a visualization system designed for interactive exploration of parameter spaces of multi-variate simulation models. To get the right parameter configuration, model developers frequently have to go back and forth between setting parameters and qualitativ ..."
Abstract
-
Cited by 8 (4 self)
- Add to MetaCart
(Show Context)
Abstract—In this paper we introduce paraglide, a visualization system designed for interactive exploration of parameter spaces of multi-variate simulation models. To get the right parameter configuration, model developers frequently have to go back and forth between setting parameters and qualitatively judging the outcomes of their model. During this process, they build up a grounded understanding of the parameter effects in order to pick the right setting. Current state-of-the-art tools and practices, however, fail to provide a systematic way of exploring these parameter spaces, making informed decisions about parameter settings a tedious and workload-intensive task. Paraglide endeavors to overcome this shortcoming by assisting the sampling of the parameter space and the discovery of qualitatively different model outcomes. This results in a decomposition of the model parameter space into regions of distinct behaviour. We developed paraglide in close collaboration with experts from three different domains, who all were involved in developing new models for their domain. We first analyzed current practices of six domain experts and derived a set of design requirements, then engaged in a longitudinal user-centered design process, and finally conducted three in-depth case studies underlining the usefulness of our approach. F 1 LINKING FORMAL AND REAL SYSTEMS A T the heart of computational science is the simulation ofreal-world scenarios. As it becomes possible to mimic in-creasingly comprehensive effects, it remains crucial to ensure
Fast Random Walker with Priors using Precomputation for Interactive Medical Image Segmentation
"... Abstract. Updating segmentation results in real-time based on repeated user input is a reliable way to guarantee accuracy, paramount in medical imaging applications, while making efficient use of an expert’s time. The random walker algorithm with priors is a robust method able to find a globally opt ..."
Abstract
-
Cited by 7 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Updating segmentation results in real-time based on repeated user input is a reliable way to guarantee accuracy, paramount in medical imaging applications, while making efficient use of an expert’s time. The random walker algorithm with priors is a robust method able to find a globally optimal probabilistic segmentation with an intuitive method for user input. However, like many other segmentation algorithms, it can be too slow for real-time user interaction. We propose a speedup to this popular algorithm based on offline precomputation, taking advantage of the time images are stored on servers prior to an analysis session. Our results demonstrate the benefits of our approach. For example, the segmentations found by the original random walker and by our new precomputation method for a given 3D image have a Dice’s similarity coefficient of 0.975, yet our method runs in 1/25 th of the time. 1
Segmentation-based regularization of dynamic SPECT reconstructions
- in IEEE Medical Imaging / Nuclear Science Conference, 2009
"... Abstract-Dynamic SPECT reconstruction using a single slow camera rotation is a highly underdetermined problem, which requires the use of regularization techniques to obtain useful results. The dSPECT algorithm We test this approach with a digital phantom simulating the kinetics of Tc99m-DTPA in th ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
Abstract-Dynamic SPECT reconstruction using a single slow camera rotation is a highly underdetermined problem, which requires the use of regularization techniques to obtain useful results. The dSPECT algorithm We test this approach with a digital phantom simulating the kinetics of Tc99m-DTPA in the renal system, including healthy and unhealthy behaviour. Summed TACs for each kidney and the bladder were calculated for the spatially regularized and nonregularized reconstructions, and compared to the true values. The TACs for the two kidneys were noticeably improved in every case, while TACs for the smaller bladder region were unchanged. Furthermore, in two cases where the segmentation was intentionally done incorrectly, the spatially regularized reconstructions were still as good as the non-regularized ones. In general, the segmentation-based regularization improves TAC quality within ROIs, as well as image contrast.
1 Perception-based Visualization of Manifold-Valued Medical Images using Distance-Preserving Dimensionality Reduction
"... Abstract—A method for visualizing manifold-valued medical image data is proposed. The method operates on images in which each pixel is assumed to be sampled from an underlying manifold. For example, each pixel may contain a high dimensional vector, such as the time activity curve (TAC) in a dynamic ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
Abstract—A method for visualizing manifold-valued medical image data is proposed. The method operates on images in which each pixel is assumed to be sampled from an underlying manifold. For example, each pixel may contain a high dimensional vector, such as the time activity curve (TAC) in a dynamic positron emission tomography (dPET) or a dynamic single photon emission computed tomography (dSPECT) image, or the positive semi-definite tensor in a diffusion tensor magnetic resonance image (DTMRI). A nonlinear mapping reduces the dimensionality of the pixel data to achieve two goals: distance preservation and embedding into a perceptual color space. We use multi-dimensional scaling distance-preserving mapping to render similar pixels (e.g. DT or TAC pixels) with perceptually similar colors. The 3D CIELAB perceptual color space is adopted as the range of the distance preserving mapping, with a final similarity transform mapping colors to a maximum gamut size. Similarity between pixels is either determined analytically as geodesics on the manifold of pixels or is approximated using manifold learning techniques. In particular, dissimilarity between DTMRI pixels is evaluated via a Log-Euclidean Riemannian metric respecting the manifold of the rank 3, 2 nd order positive semi-definite DTs, whereas the dissimilarity between TACs is approximated via ISOMAP. We demonstrate our approach via artificial highdimensional, manifold-valued data, as well as case studies of normal and pathological clinical brain and heart DTMRI, dPET, and dSPECT images. Our results demonstrate the effectiveness of our approach in capturing, in a perceptually meaningful way, important features in the data. Keywords: Manifold-valued data; high dimensional data; visualization; color; nonlinear dimensionality reduction; multidimensional scaling; distance-preserving mapping; diffusion tensor magnetic resonance imaging (DTMRI); dynamic positron emission tomography (dPET); dynamic single photon emission computed tomography (dSPECT). I.
N.: Barycentric label space
- In: MICCAI Workshop on Probabilistic Models for Medical Image Analysis
, 2009
"... Abstract. Multiple neighboring organs or structures captured in medical images are frequently represented by labeling the underlying image domain (e.g. labeling a brain image into white matter, gray matter, cerebrospinal fluid, etc). However, given the different sources of uncertainties in shape bou ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. Multiple neighboring organs or structures captured in medical images are frequently represented by labeling the underlying image domain (e.g. labeling a brain image into white matter, gray matter, cerebrospinal fluid, etc). However, given the different sources of uncertainties in shape boundaries (e.g. tissue heterogeneity, partial volume effect, fuzzy image processing and segmentation results), it is favorable to adopt a probabilistic labeling approach. In many medical image analysis tasks, it is necessary that shapes are properly manipulated, e.g. optimized (i.e. segmentation), de-noised, interpolated, or statistically analyzed (e.g. using principle component analysis). Formulating a representation that not only captures the uncertainty in shapes, but also facilitates algebraic manipulations, is therefore a desirable goal. In this work, we extend the label space multi-shape representation of Malcolm et al. [1] to the barycentric label space, which describes a proper invertible mapping between probability vectors and label space. Our method uses the probability vectors as barycentric coefficients describing arbitrary labels in label space and a non-singular matrix inversion to map points in label space to probability vectors. We demonstrate how the conversion errors are eliminated compared to the original label space approach, and demonstrate the effect of these errors in the context of smoothing, linear shape statistics, and uncertainty calculation, on artificial objects and brain image data. 1
