Optimal Weights for Convex Functionals in Medical Image Segmentation

McIntosh, Chris; Hamarneh, Ghassan

doi:10.1007/978-3-642-10331-5_100

Cited by 9 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mcintosh and Hamarneh [26] optimized a non-convex energy function to find the optimal parameters. They later extended their technique using a constrained convex energy function to avoid sensitivity to the initial parameter settings [27]. The common goal in these algorithms is to learn the parameters so that the ground truth emerges as the optimal solution.…”

Section: Automatic Parameter Tuning In Image Segmentationmentioning

confidence: 99%

Tuner: Principled Parameter Finding for Image Segmentation Algorithms Using Visual Response Surface Exploration

Torsney-Weir

Saad

Möller

et al. 2011

IEEE Trans. Visual. Comput. Graphics

105

View full text Add to dashboard Cite

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. MOTIVATIONFor visual analysis image data often need to be segmented. Segmentation refers to the process of partitioning the image into multiple segments, i.e. sets of pixels or voxels, that form contiguous and semantically meaningful regions. If each of these regions is marked by a unique identifier, image segmentation simply means labelling of pixels or voxels. In biomedical imaging, where images are acquired using some kind of tomography or microscopy, segmented regions might correspond to anatomical structures in the case of nonfunctional imaging, and to regions with specific physiological activity in the case of functional imaging.In recent years a variety of semi-and fully automatic techniques have been developed to address the segmentation problem [32]. However, even the current state-of-the-art approaches fall short of providing a "silver bullet" for image segmentation. This has several reasons. One reason is that given some image, the segmentation problem is not well defined; in fact it depends on the application which regions are semantically meaningful. Another reason is that due to different image degradation factors such as low signal-to-noise ratio, imaging artifacts, partial volume effects and shape variability, different kinds of a priori knowledge need to be included. Additionally, the majority of the existing segmentation methods rely on and are sensitive to setting a number of parameters. For example, most of the algorithms contain weighting parameters between multiple competing image-driven or prior-driven cost terms in an attempt to mimic the cognitive capabilities of expert users (e.g. radiologists for medical images).A good parameter setting is usually found by a manual trial and error procedure. Th...

show abstract

Section: Automatic Parameter Tuning In Image Segmentationmentioning

confidence: 99%

Tuner: Principled Parameter Finding for Image Segmentation Algorithms Using Visual Response Surface Exploration

Torsney-Weir

Saad

Möller

et al. 2011

IEEE Trans. Visual. Comput. Graphics

105

View full text Add to dashboard Cite

show abstract

“…In order to improve the segmentation accuracy, possibilities for future work include: Exploring optimization-based segmentation techniques (instead of region growing) [25]; searching the hyper-parameters space using rigorous methods (instead of using the method proposed by Menchattini et al [25] for setting the region growing thresholds, or for setting the CLAHE method parameters), e.g. via harmony search [43] and evolutionary computing [44] or combinatorial/continuous optimization of hyper-parameters [39][40][41]; or setting hyper-parameter values based on image contents [42]. However, it remains to be seen whether such additional methodological complexity will lead to worthwhile improvements in accuracy.…”

Section: Discussionmentioning

confidence: 99%

Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views

Taghanaki

Liu²,

Miles³

et al. 2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972 ± 0.003 and 0.985 ± 0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5 mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972 ± 0.003 and 0.985 ± 0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5 mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.

show abstract

“…To minimize the number of unknowns to be optimized, the weighting factor is taken to be spatially invariant, i.e. λ (X) = λ , and is usually set empirically based on trial and error, training data, or contextual information [34,16,42]. Also, P(C i ) is further decomposed into multiple terms (i.e.…”

Section: Methodsmentioning

confidence: 99%

Exploration and Visualization of Segmentation Uncertainty using Shape and Appearance Prior Information

Saad¹,

Hamarneh

Möller

2010

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

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.

show abstract

Optimal Weights for Convex Functionals in Medical Image Segmentation

Cited by 9 publications

References 18 publications

Tuner: Principled Parameter Finding for Image Segmentation Algorithms Using Visual Response Surface Exploration

Tuner: Principled Parameter Finding for Image Segmentation Algorithms Using Visual Response Surface Exploration

Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views

Exploration and Visualization of Segmentation Uncertainty using Shape and Appearance Prior Information

Contact Info

Product

Resources

About