Robust parametric modeling approach based on domain knowledge for computer aided detection of vertebrae column metastases in MRI

Authors:
A. K. Jerebko;G. P. Schmidt;X. Zhou;J. Bi;V. Anand;J. Liu;S. Schoenberg;I. Schmuecking;B. Kiefer;A. Krishnan
Affiliations:
Siemens Medical Solutions, Inc., Malvern, PA;Department of Clinical Radiology, University of Munich, Munich, Germany;Siemens Medical Solutions, Inc., Malvern, PA;Siemens Medical Solutions, Inc., Malvern, PA;Siemens Medical Solutions, Inc., Malvern, PA;Siemens Medical Solutions, Inc., Malvern, PA;Department of Clinical Radiology, University of Munich, Munich, Germany;Siemens Medical Solutions, Inc., Malvern, PA;Siemens AG Medical Solutions, Erlangen, Germany;Siemens Medical Solutions, Inc., Malvern, PA
Venue:
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Year:
2007

Citing 4
Cited 0

Applied multivariate statistical analysis

Applied multivariate statistical analysis
Bagging predictors

Machine Learning
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Tensor scale: A local morphometric parameter with applications to computer vision and image processing

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study evaluates a robust parametric modeling approach for computer-aided detection (CAD) of vertebrae column metastases in whole-body MRI. Our method involves constructing a model based on geometric primitives from purely anatomical knowledge of organ shapes and rough variability limits. The basic intensity range of primary 'simple' objects in our models is derived from expert knowledge of image formation and appearance for certain tissue types. We formulated the classification problem as a multiple instance learning problem for which a novel algorithm is designed based on Fisher's linear discriminant analysis. Evaluation of metastases detection algorithm is done on a separate test set as well as on the training set via leave-one-patient-out approach.