Ross JC, Diaz AA, Okajima Y, Wassermann D, Washko GR, Dy J, San Jose Estépar R.
Airway labeling using a Hidden Markov Tree Model. In: Biomedical Imaging (ISBI), 2014 IEEE 11th International Symposium onBiomedical Imaging (ISBI), 2014 IEEE 11th International Symposium on. 2014 p. 554-558.
AbstractWe present a novel airway labeling algorithm based on a Hidden Markov Tree Model (HMTM). We obtain a collection of discrete points along the segmented airway tree using particles sampling [1] and establish topology using Kruskal's minimum spanning tree algorithm. Following this, our HMTM algorithm probabilistically assigns labels to each point. While alternative methods label airway branches out to the segmental level, we describe a general method and demonstrate its performance out to the subsubsegmental level (two generations further than previously published approaches). We present results on a collection of 25 computed tomography (CT) datasets taken from a Chronic Obstructive Pulmonary Disease (COPD) study.
Wasserman D, Ross JC, Washko GR, Wells WM, San Jose Estépar R.
Deformable Registration of Feature-Endowed Point Sets Based on Tensor Fields. In: Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference onComputer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. 2014 p. 2729-2735.
AbstractThe main contribution of this work is a framework to register anatomical structures characterized as a point set where each point has an associated symmetric matrix. These matrices can represent problem-dependent characteristics of the registered structure. For example, in airways, matrices can represent the orientation and thickness of the structure. Our framework relies on a dense tensor field representation which we implement sparsely as a kernel mixture of tensor fields. We equip the space of tensor fields with a norm that serves as a similarity measure. To calculate the optimal transformation between two structures we minimize this measure using an analytical gradient for the similarity measure and the deformation field, which we restrict to be a diffeomorphism. We illustrate the value of our tensor field model by comparing our results with scalar and vector field based models. Finally, we evaluate our registration algorithm on synthetic data sets and validate our approach on manually annotated airway trees.
Kurugol S, Washko GR, San Jose Estépar R.
Ranking and classification of monotonic emphysema patterns with a multi-class hierarchical approach. In: Biomedical Imaging (ISBI), 2014 IEEE 11th International Symposium onBiomedical Imaging (ISBI), 2014 IEEE 11th International Symposium on. 2014 p. 1031-1034.
AbstractEmphysema has distinct and well-defined visually apparent CT patterns called centrilobular and panlobular emphysema. Existing studies concentrated on the classification of these patterns but they have not looked at the complete evolution of this disease as the destruction of lung parenchyma progresses from normal lung tissue to mild, moderate, and severe disease with complete effacement of the lung architecture. In this paper, we discretize this continuous process into five classes of increasing disease severity and construct a training set of 1161 CT patches. We exploit three solutions to this monotonic multi-class classification problem: a global rankSVM for ranking, hierarchical SVM for classification and a combination of these two, which we call a hierarchical rankSVM. Results showed that both hierarchical approaches were computationally efficient. The classification accuracies were slightly better for hierarchical SVM. However, in addition to classification, ranking approaches also provided a ranking of patterns, which can be utilized as a continuous disease progression score. In terms of the classification accuracy and ratio of pair-wise constraints satisfied, hierarchical rankSVM outperformed the global rankSVM.
Ross JC, Castaldi PJ, Cho MH, Dy JG.
Dual Beta Process Priors for Latent Cluster Discovery in Chronic Obstructive Pulmonary Disease [Internet]. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA: ACM; 2014 p. 155–162.
Publisher's VersionAbstract
Chronic obstructive pulmonary disease (COPD) is a lung disease characterized by airflow limitation usually associated with an inflammatory response to noxious particles, such as cigarette smoke. COPD is currently the third leading cause of death in the United States and is the only leading cause of death that is increasing in prevalence. It also represents an enormous financial burden to society, costing tens of billions of dollars annually in the U.S. It is widely accepted by the medical community that COPD is a heterogeneous disease, with substantial evidence indicating that genetic variation contributes to varying levels of disease susceptibility. This heterogeneity makes it difficult to predict health decline and develop targeted treatments for better patient care. Although researchers have made several attempts to discover disease subtypes, results have been inconclusive, in part because standard clustering methods have not properly dealt with disease manifestations that may worsen with increased exposure. In this paper we introduce a transformative way of looking at the COPD subtyping task. Specifically, we model the relationship between risk factors (such as age and smoke exposure) and manifestations of disease severity using Gaussian Processes, which allow us to represent so-called "disease trajectories". We also posit that individuals can be associated with multiple disease types (latent clusters), which we assume are influenced by genetics. Furthermore, we predict that only subsets of the numerous disease-related quantitative features are useful for describing each latent subtype. We model these associations using two separate beta process priors, and we describe a variational inference approach to discover the most probable latent cluster assignments. Results are validated with associations to genetic markers.