Statistical Inference for Imaging and Disease Core Publications

Venkataraman A, Kubicki M, Golland P. From Connectivity Models to Region Labels: Identifying Foci of a Neurological Disorder. IEEE Trans Med Imaging. 2013;32 (11) :2078-98.Abstract

We propose a novel approach to identify the foci of a neurological disorder based on anatomical and functional connectivity information. Specifically, we formulate a generative model that characterizes the network of abnormal functional connectivity emanating from the affected foci. This allows us to aggregate pairwise connectivity changes into a region-based representation of the disease. We employ the variational expectation-maximization algorithm to fit the model and subsequently identify both the afflicted regions and the differences in connectivity induced by the disorder. We demonstrate our method on a population study of schizophrenia.

Shackleford JA, Shusharina N, Verberg J, Warmerdam G, Winey B, Neuner M, Steininger P, Arbisser A, Golland P. Plastimatch 1.6 - Current Capabilities and Future Directions. Int Conf Med Image Comput Comput Assist Interv. Workshop on Image-Guidance and Multimodal Dose Planning in Radiation Therapy. 2012;15 (WS).Abstract
Open-source software provides an economic benefit by reducing duplicated development effort, and advances science knowledge by fostering a culture of reproducible experimentation. This paper describes recent advances in the Plastimatch open software suite, which implements a broad set of useful tools for research and practice in radiotherapy and medical imaging. The focus of this paper is to highlight recent advancements, including 2D-3D registration, GPU-accelerated mutual information, analytic regularization of B-spline registration, automatic 3D feature detection and feature matching, and radiotherapy plan evaluation tools.
Shackleford MICCAI WS 2012
Pohl KM, Fisher J, Kikinis R, Grimson EWL, Wells WM. Shape Based Segmentation of Anatomical Structures in Magnetic Resonance Images. Comput Vis Biomed Image Appl. 2005;3765 :489-98.Abstract
Standard image based segmentation approaches perform poorly when there is little or no contrast along boundaries of different regions. In such cases, segmentation is largely performed manually using prior knowledge of the shape and relative location of the underlying structures combined with partially discernible boundaries. We present an automated approach guided by covariant shape deformations of neighboring structures, which is an additional source of prior information. Captured by a shape atlas, these deformations are transformed into a statistical model using the logistic function. Structure boundaries, anatomical labels, and image inhomogeneities are estimated simultaneously within an Expectation-Maximization formulation of the maximum a posteriori probability estimation problem. We demonstrate the approach on 20 brain magnetic resonance images showing superior performance, particularly in cases where purely image based methods fail.