Principal component analysis, classifier complexity, and robustness of sonographic breast lesion classification

K. Drukker; N. P. Gruszauskas; M. L. Giger

doi:10.1117/12.811341

3 March 2009 Principal component analysis, classifier complexity, and robustness of sonographic breast lesion classification

K. Drukker, N. P. Gruszauskas, M. L. Giger

Author Affiliations +

Proceedings Volume 7260, Medical Imaging 2009: Computer-Aided Diagnosis; 72602B (2009) https://doi.org/10.1117/12.811341
Event: SPIE Medical Imaging, 2009, Lake Buena Vista (Orlando Area), Florida, United States

Abstract

We investigated three classifiers for the task of distinguishing between benign and malignant breast lesions. Classification performance was measured in terms of area under the ROC curve (AUC value). We compared linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and a Bayesian neural net (BNN) with 5 hidden units. For each lesion, 46 image features were extracted and principal component analysis (PCA) of these features was used as classifier input. For each classifier, the optimal number of principal components was determined by performing PCA within each step of a leave-one-case-out protocol for the training dataset (1125 lesions, 14% cancer prevalence) and determining which number of components maximized the AUC value. Subsequently, each classifier was trained on the training dataset and applied 'cold turkey' to an independent test set from a different population (341 lesions, 30% cancer prevalence). The optimal number of principal components for LDA was 24, accounting for 97% of the variance in the image features. For QDA and BNN, these numbers were 5 (70%) and 15 (93%), respectively. The LDA, QDA and BNN obtained AUC values of 0.88, 0.85, and 0.91, respectively, in the leave-one-case-out analysis. In the independent test - with AUCs of 0.88, 0.76, and 0.82 - only LDA achieved performance identical to that for the training set (lower bound of 95% non-inferiority interval -.0067), while the others performed significantly worse (p-values << 0.05). While the more complex BNN classifier outperformed the others in leave-one-case-out of a large dataset, LDA was the robust best-performer in an independent test.

Citation Download Citation

K. Drukker, N. P. Gruszauskas, and M. L. Giger "Principal component analysis, classifier complexity, and robustness of sonographic breast lesion classification", Proc. SPIE 7260, Medical Imaging 2009: Computer-Aided Diagnosis, 72602B (3 March 2009); https://doi.org/10.1117/12.811341

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available