Optimizing feature selection across a multimodality database in computerized classification of breast lesions

Linear step-wise feature selection is performed for computerized analysis methods on a set of mammography features using a database of mammography cases, a set of ultrasound features using a database of ultrasound cases, and a set of mammography and sonography features using a multi-modality database of lesions with both mammograms and sonograms. The large mammography and sonography databases were randomly split 20 times into three subdatabases for feature selection, classifier training and independent validation. The average validation Az value over the 20 random splits for the mammography database was 0.82 ± 0.04 and for the sonography database was 0.85 ± 0.03. The average consistency feature selection Az value for the mammography and sonography databases were 0.87 ± 0.02 and 0.88 ± 0.02, respectively. For the mulit-modality database, the consistency feature selection Az value was 0.93. © 2002 SPIE · 1605-7422/02/$15.00.

Duke Scholars

Author Li Lan Molecular Genetics and Microbiology