Chris McIntosh

Vessel Crawlers: 3D Physically-based Deformable Organisms for Vasculature Segmentation and Analysis

We present a novel approach to the segmentation and analysis of vasculature from volumetric medical image data. Our method is an adoption and significant extension of deformable organisms, an artificial life framework for medical image analysis that complements classical deformable models with high-level, anatomically-driven control mechanisms. We extend deformable organisms to 3D, model their bodies as tubular spring-mass systems, and equip them with a new repertoire of sensory modules, behavioral routines, and decision making strategies. The result is a new breed of robust deformable organisms, vessel crawlers, that crawl along vasculature in 3D images, accurately segmenting vessel boundaries, detecting and exploring bifurcations, and providing sophisticated, clinically-relevant structural analysis. We validate our method through the segmentation and analysis of vascular structures in both noisy synthetic and real medical image data.

3D live-wire-based semi-automatic segmentation of medical images

Segmenting anatomical structures from medical images is usually one of the most important initial steps in many applications, including visualization, computer-aided diagnosis, and morphometric analysis. Manual 2D segmentation suffers from operator variability and is tedious and time-consuming. These disadvantages are accentuated in 3D applications and, the additional requirement of producing intuitive displays to integrate 3D information for the user, makes manual segmentation even less approachable in 3D. Robust, automatic medical image segmentation in 2D to 3D remains an open problem caused particularly by sensitivity to low-level parameters of segmentation algorithms. Semi-automatic techniques present possible balanced solution where automation focuses on low-level computing-intensive tasks that can be hidden from the user, while manual inter- vention captures high-level expert knowledge nontrivial to capture algorithmically. In this paper we present a 3D extension to the 2D semi-automatic live-wire technique. Live-wire based contours generated semi-automatically on a selected set of slices are used as seed points on new unseen slices in different orientations. The seed points are calculated from intersections of user-based live-wire techniques with new slices. Our algorithm includes a step for ordering the live-wire seed points in the new slices, which is essential for subsequent multi-stage optimal path calculation. We present results of automatically detecting contours in new slices in 3D volumes from a variety of medical images.

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.

Is a single energy functional sufficient? adaptive energy functionals and automatic initialization

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.

Medial-Based Deformable Models in Nonconvex Shape-Spaces for Medical Image Segmentation

We explore the application of genetic algorithms (GA) to deformable models through the proposition of a novel method for medical image segmentation that combines GA with nonconvex, localized, medial-based shape statistics. We replace the more typical gradient descent optimizer used in deformable models with GA, and the convex, implicit, global shape statistics with nonconvex, explicit, localized ones. Specifically, we propose GA to reduce typical deformable model weaknesses pertaining to model initialization, pose estimation and local minima, through the simultaneous evolution of a large number of models. Furthermore, we constrain the evolution, and thus reduce the size of the search-space, by using statistically-based deformable models whose deformations are intuitive (stretch, bulge, bend) and are driven in terms of localized principal modes of variation, instead of modes of variation across the entire shape that often fail to capture localized shape changes. Although GA are not guaranteed to achieve the global optima, our method compares favorably to the prevalent optimization techniques, convex/nonconvex gradient-based optimizers and to globally optimal graph-theoretic combinatorial optimization techniques, when applied to the task of corpus callosum segmentation in 50 mid-sagittal brain magnetic resonance images.

Perception-Based Visualization of Manifold-Valued Medical Images Using Distance-Preserving Dimensionality Reduction

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 multidimensional 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, second-order positive semi-definite DTs, whereas the dissimilarity between TACs is approximated via ISOMAP. We demonstrate our approach via artificial high-dimensional, 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.

Human Limb Delineation and Joint Position Recovery Using Localized Boundary Models

We outline the development of a self-initializing kinematic tracker that automatically discovers its part appearance models from a video sequence. Through its unique combination of an existing global joint estimation technique and a robust physical deformation based local search method, the tracker is demonstrated as a novel approach to recovering 2D human joint locations and limb outlines from video sequences. Appearance models are discovered and employed through a novel use of the deformable organisms framework which we have extended to the temporal domain. Quantitative and qualitative results for a set of five test videos are provided. The results demonstrate an overall improvement in tracking performance and that the method is relatively insensitive to initialization, an important consideration in gradient descent-style search algorithms.

Optimal Weights for Convex Functionals in Medical Image Segmentation

Energy functional minimization is a popular technique for medical image segmentation. The segmentation must be initialized, weights for competing terms of an energy functional must be tuned, and the functional minimized. There is a substantial amount of guesswork involved. We reduce this guesswork by analytically determining the optimal weights and minimizing a convex energy functional independent of the initialization. We demonstrate improved results over state of the art on a set of 470 clinical examples.

Globally optimal spinal cord segmentation using a minimal path in high dimensions

Spinal cord segmentation is an important step to empirically quantify spinal cord atrophy that can occur in neurological diseases such as multiple sclerosis (MS). In this work, we propose a novel method to find the globally optimal segmentation of the spinal cord using a high dimensional minimal path search. The spinal cord cross-sectional shapes are represented using principal component analysis (in the probability simplex) which captures most of spinal cords axial cross-sectional variation and partial volume effects. We propose modifications to the A* minimal path search algorithm that drastically reduce the required memory and run-time to make our high dimensional minimal path optimization computationally feasible. Finally, we validate our results over five vertebrae levels of both healthy and MS clinical MR volumes (20 volumes total) and show improvements on volume agreement with expert segmentations and less user interaction when compared to current state-of-the-art methods.

Voxel-based dose prediction with multi-patient atlas selection for automated radiotherapy treatment planning

Automating the radiotherapy treatment planning process is a technically challenging problem. The majority of automated approaches have focused on customizing and inferring dose volume objectives to be used in plan optimization. In this work we outline a multi-patient atlas-based dose prediction approach that learns to predict the dose-per-voxel for a novel patient directly from the computed tomography planning scan without the requirement of specifying any objectives. Our method learns to automatically select the most effective atlases for a novel patient, and then map the dose from those atlases onto the novel patient. We extend our previous work to include a conditional random field for the optimization of a joint distribution prior that matches the complementary goals of an accurately spatially distributed dose distribution while still adhering to the desired dose volume histograms. The resulting distribution can then be used for inverse-planning with a new spatial dose objective, or to create typical dose volume objectives for the canonical optimization pipeline. We investigated six treatment sites (633 patients for training and 113 patients for testing) and evaluated the mean absolute difference in all DVHs for the clinical and predicted dose distribution. The results on average are favorable in comparison to our previous approach (1.91 versus 2.57). Comparing our method with and without atlas-selection further validates that atlas-selection improved dose prediction on average in whole breast (0.64 versus 1.59), prostate (2.13 versus 4.07), and rectum (1.46 versus 3.29) while it is less important in breast cavity (0.79 versus 0.92) and lung (1.33 versus 1.27) for which there is high conformity and minimal dose shaping. In CNS brain, atlas-selection has the potential to be impactful (3.65 versus 5.09), but selecting the ideal atlas is the most challenging.