Shawn Andrews

Fast random walker with priors using precomputation for interactive medical image segmentation

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 experts 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 Dices similarity coefficient of 0.975, yet our method runs in 1/25th of the time.

Structural Network Analysis of Brain Development in Young Preterm Neonates

Preterm infants develop differently than those born at term and are at higher risk of brain pathology. Thus, an understanding of their development is of particular importance. Diffusion tensor imaging (DTI) of preterm infants offers a window into brain development at a very early age, an age at which that development is not yet fully understood. Recent works have used DTI to analyze structural connectome of the brain scans using network analysis. These studies have shown that, even from infancy, the brain exhibits small-world properties. Here we examine a cohort of 47 normal preterm neonates (i.e., without brain injury and with normal neurodevelopment at 18 months of age) scanned between 27 and 45 weeks post-menstrual age to further the understanding of how the structural connectome develops. We use full-brain tractography to find white matter tracts between the 90 cortical and sub-cortical regions defined in the University of North Carolina Chapel Hill neonatal atlas. We then analyze the resulting connectomes and explore the differences between weighting edges by tract count versus fractional anisotropy. We observe that the brain networks in preterm infants, much like infants born at term, show high efficiency and clustering measures across a range of network scales. Further, the development of many individual region-pair connections, particularly in the frontal and occipital lobes, is significantly correlated with age. Finally, we observe that the preterm infant connectome remains highly efficient yet becomes more clustered across this age range, leading to a significant increase in its small-world structure.

Convex multi-region probabilistic segmentation with shape prior in the isometric log-ratio transformation space

Image segmentation is often performed via the minimization of an energy function over a domain of possible segmentations. The effectiveness and applicability of such methods depends greatly on the properties of the energy function and its domain, and on what information can be encoded by it. Here we propose an energy function that achieves several important goals. Specifically, our energy function is convex and incorporates shape prior information while simultaneously generating a probabilistic segmentation for multiple regions. Our energy function represents multi-region probabilistic segmentations as elements of a vector space using the isometric log-ratio (ILR) transformation. To our knowledge, these four goals (convex, with shape priors, multi-region, and probabilistic) do not exist together in any other method, and this is the first time ILR is used in an image segmentation method. We provide examples demonstrating the usefulness of these features.

Probabilistic multi-shape segmentation of knee extensor and flexor muscles

Patients with chronic obstructive pulmonary disease (COPD) often exhibit skeletal muscle weakness in lower limbs. Analysis of the shapes and sizes of these muscles can lead to more effective therapy. Unfortunately, segmenting these muscles from one another is a challenging task due to a lack of image information in many areas. We present a fully automatic segmentation method that overcomes the inherent difficulties of this problem to accurately segment the different muscles. Our method enforces a multi-region shape prior on the segmentation to ensure feasibility and provides an energy minimizing probabilistic segmentation that indicates areas of uncertainty. Our experiments on 3D MRI datasets yield an average Dice similarity coefficient of 0.92 +/- 0.03 with the ground truth.

The Generalized Log-Ratio Transformation: Learning Shape and Adjacency Priors for Simultaneous Thigh Muscle Segmentation

We present a novel probabilistic shape representation that implicitly includes prior anatomical volume and adjacency information, termed the generalized log-ratio (GLR) representation. We demonstrate the usefulness of this representation in the task of thigh muscle segmentation. Analysis of the shapes and sizes of thigh muscles can lead to a better understanding of the effects of chronic obstructive pulmonary disease (COPD), which often results in skeletal muscle weakness in lower limbs. However, segmenting these muscles from one another is difficult due to a lack of distinctive features and inter-muscular boundaries that are difficult to detect. We overcome these difficulties by building a shape model in the space of GLR representations. We remove pose variability from the model by employing a presegmentation-based alignment scheme. We also design a rotationally invariant random forest boundary detector that learns common appearances of the interface between muscles from training data. We combine the shape model and the boundary detector into a fully automatic globally optimal segmentation technique. Our segmentation technique produces a probabilistic segmentation that can be used to generate uncertainty information, which can be used to aid subsequent analysis. Our experiments on challenging 3D magnetic resonance imaging data sets show that the use of the GLR representation improves the segmentation accuracy, and yields an average Dice similarity coefficient of 0.808 ±0.074, comparable to other state-of-the-art thigh segmentation techniques.

Improving Probabilistic Image Registration via Reinforcement Learning and Uncertainty Evaluation

One framework for probabilistic image registration involves assigning probability distributions over spatial transformations (e.g. distributions over displacement vectors at each voxel). In this paper, we propose an uncertainty measure for these distributions that examines the actual spatial displacements, thus departing from the classical Shannon entropy-based measures, which examine only the probabilities of these distributions. We show that by incorporating the proposed uncertainty measure, along with features extracted from the input images and intermediate displacement fields, we are able to more accurately predict the pointwise registration errors of an intermediate solution as estimated for a previously unseen input image pair. We utilize the predicted errors to identify regions in the image that are trustworthy and through which we refine the tentative registration solution. Results show that our proposed framework, which incorporates uncertainty estimation and registration error prediction, can improve accuracy of 3D image registrations by about 25%.

Bounded Labeling Function for Global Segmentation of Multi-part Objects with Geometric Constraints

The inclusion of shape and appearance priors have proven useful for obtaining more accurate and plausible segmentations, especially for complex objects with multiple parts. In this paper, we augment the popular Mum ford-Shah model to incorporate two important geometrical constraints, termed containment and detachment, between different regions with a specified minimum distance between their boundaries. Our method is able to handle multiple instances of multi-part objects defined by these geometrical constraints using a single labeling function while maintaining global optimality. We demonstrate the utility and advantages of these two constraints and show that the proposed convex continuous method is superior to other state-of-the-art methods, including its discrete counterpart, in terms of memory usage, and metrication errors.

Topology Preservation and Anatomical Feasibility in Random Walker Image Registration

The random walker image registration (RWIR) method is a powerful tool for aligning medical images that also provides useful uncertainty information. However, it is difficult to ensure topology preservation in RWIR, which is an important property in medical image registration as it is often necessary for the anatomical feasibility of an alignment. In this paper, we introduce a technique for determining spatially adaptive regularization weights for RWIR that ensure an anatomically feasible transformation. This technique only increases the run time of the RWIR algorithm by about 10%, and avoids over-smoothing by only increasing regularization in specific image regions. Our results show that our technique ensures topology preservation and improves registration accuracy.

The isometric log-ratio transform for probabilistic multi-label anatomical shape representation.

Sources of uncertainty in the boundaries of structures in medical images have motivated the use of probabilistic labels in segmentation applications. An important component in many medical image segmentation tasks is the use of a shape model, often generated by applying statistical techniques to training data. Standard statistical techniques (e.g., principal component analysis) often assume data lies in an unconstrained vector space, but probabilistic labels are constrained to the unit simplex. If these statistical techniques are used directly on probabilistic labels, relative uncertainty information can be sacrificed. A standard method for facilitating analysis of probabilistic labels is to map them to a vector space using the LogOdds transform. However, the LogOdds transform is asymmetric in one of the labels, which skews results in some applications. The isometric log-ratio (ILR) transform is a symmetrized version of the LogOdds transform, and is so named as it is an isometry between the Aitchison geometry, the inherent geometry of the simplex, and standard Euclidean geometry. We explore how to interpret the Aitchison geometry when applied to probabilistic labels in medical image segmentation applications. We demonstrate the differences when applying the LogOdds transform or the ILR transform to probabilistic labels prior to statistical analysis. Specifically, we show that statistical analysis of ILR transformed data better captures the variability of anatomical shapes in cases where multiple different foreground regions share boundaries (as opposed to foreground-background boundaries).

Fast random walker image registration using precomputation

In this paper, we introduce an extension to the random walker image registration method designed to increase the speed at which a registration is performed. Our method involves precomputing data from one of the images being registered while anticipating the acquisition of the second image, and then using this precomputed data to approximate the final transformation once the second image becomes available. The precomputation scheme incorporates a parameter controlling the trade-off between registration speed and accuracy that can be tuned when the registration is being performed. Our results show that with precomputation, random walker image registration runs 3 to 10 times faster on volumetric images with only 3% to 20% loss in registration accuracy.