Inferring Disease Status by Non-parametric Probabilistic Embedding

@inproceedings{Batmanghelich2016InferringDS,
  title={Inferring Disease Status by Non-parametric Probabilistic Embedding},
  author={Nematollah Batmanghelich and Ardavan Saeedi and Ra{\'u}l San Jos{\'e} Est{\'e}par and Michael H. Cho and William M. Wells},
  booktitle={MCV/BAMBI@MICCAI},
  year={2016}
}
Computing similarity between all pairs of patients in a dataset enables us to group the subjects into disease subtypes and infer their disease status. However, robust and efficient computation of pairwise similarity is a challenging task for large-scale medical image datasets. We specifically target diseases where multiple subtypes of pathology present simultaneously, rendering the definition of the similarity a difficult task. To define pairwise patient similarity, we characterize each subject… 

References

SHOWING 1-10 OF 21 REFERENCES
Generative Method to Discover Genetically Driven Image Biomarkers
TLDR
A generative probabilistic approach to discovery of disease subtypes determined by the genetic variants based on a variant of the so-called topic models that uncover the latent structure in a collection of data is presented.
A Feature-Based Approach to Big Data Analysis of Medical Images
TLDR
The theoretical contribution is a density estimator based on a generative model that generalizes kernel density estimation and K-nearest neighbor (KNN) methods that can be used for on-the-fly queries, without requiring explicit parametric models or an off-line training phase.
GRAM: A framework for geodesic registration on anatomical manifolds
Texture-Based Analysis of COPD: A Data-Driven Approach
TLDR
This study presents a fully automatic, data-driven approach for texture-based quantitative analysis of chronic obstructive pulmonary disease (COPD) in pulmonary computed tomography (CT) images where the class labels are based on measured lung function instead of on manually annotated regions of interest (ROIs).
On the Manifold Structure of the Space of Brain Images
TLDR
This paper hypothesizes that the space spanned by a set of brain images can be captured by a low-dimensional manifold, i.e. a parametrization of the set of images, and combines this manifold learning with distance measures between images that capture shape, in order to learn the underlying structure of a database ofbrain images.
Longitudinal Alignment of Disease Progression in Fibrosing Interstitial Lung Disease
TLDR
A method for temporally aligning imaging data from multiple patients driven by disease appearance is proposed, which aligns follow- up series of different patients in time, and creates a cross-sectional spatio-temporal disease pattern distribution model.
Scalable Nearest Neighbor Algorithms for High Dimensional Data
  • Marius Muja, D. Lowe
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2014
TLDR
It is shown that the optimal nearest neighbor algorithm and its parameters depend on the data set characteristics and an automated configuration procedure for finding the best algorithm to search a particular data set is described.
Over-Segmentation of 3D Medical Image Volumes based on Monogenic Cues
TLDR
A novel approach to compute 3D supervoxels for radiological image datasets that yields a highly regular, robust, homogeneous and edge-preserving over-segmentation of the image / volume while being the fastest approach.
Distinct quantitative computed tomography emphysema patterns are associated with physiology and function in smokers.
TLDR
Local histogram-based measures of distinct CT low-attenuation patterns are more predictive of measures of lung function, dyspnea, quality of life, and health care use than standard quantitative measures of emphysema from computed tomography.
Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates
TLDR
This paper presents a method to build rotation-invariant HOG descriptors using Fourier analysis in polar/spherical coordinates, which are closely related to the irreducible representation of the 2D/3D rotation groups.
...
...