Share Email Print
cover

Proceedings Paper

Sparse representation of multi parametric DCE-MRI features using K-SVD for classifying gene expression based breast cancer recurrence risk
Author(s): Majid Mahrooghy; Ahmed B. Ashraf; Dania Daye; Carolyn Mies; Mark Rosen; Michael Feldman; Despina Kontos
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We evaluate the prognostic value of sparse representation-based features by applying the K-SVD algorithm on multiparametric kinetic, textural, and morphologic features in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). K-SVD is an iterative dimensionality reduction method that optimally reduces the initial feature space by updating the dictionary columns jointly with the sparse representation coefficients. Therefore, by using K-SVD, we not only provide sparse representation of the features and condense the information in a few coefficients but also we reduce the dimensionality. The extracted K-SVD features are evaluated by a machine learning algorithm including a logistic regression classifier for the task of classifying high versus low breast cancer recurrence risk as determined by a validated gene expression assay. The features are evaluated using ROC curve analysis and leave one-out cross validation for different sparse representation and dimensionality reduction numbers. Optimal sparse representation is obtained when the number of dictionary elements is 4 (K=4) and maximum non-zero coefficients is 2 (L=2). We compare K-SVD with ANOVA based feature selection for the same prognostic features. The ROC results show that the AUC of the K-SVD based (K=4, L=2), the ANOVA based, and the original features (i.e., no dimensionality reduction) are 0.78, 0.71. and 0.68, respectively. From the results, it can be inferred that by using sparse representation of the originally extracted multi-parametric, high-dimensional data, we can condense the information on a few coefficients with the highest predictive value. In addition, the dimensionality reduction introduced by K-SVD can prevent models from over-fitting.

Paper Details

Date Published: 20 March 2014
PDF: 7 pages
Proc. SPIE 9035, Medical Imaging 2014: Computer-Aided Diagnosis, 90350X (20 March 2014); doi: 10.1117/12.2043719
Show Author Affiliations
Majid Mahrooghy, Univ. of Pennsylvania (United States)
Ahmed B. Ashraf, Univ. of Pennsylvania (United States)
Dania Daye, Univ. of Pennsylvania (United States)
Carolyn Mies, Univ. of Pennsylvania (United States)
Mark Rosen, Univ. of Pennsylvania (United States)
Michael Feldman, Univ. of Pennsylvania (United States)
Despina Kontos, Univ. of Pennsylvania (United States)


Published in SPIE Proceedings Vol. 9035:
Medical Imaging 2014: Computer-Aided Diagnosis
Stephen Aylward; Lubomir M. Hadjiiski, Editor(s)

© SPIE. Terms of Use
Back to Top