Computer-Aided Diagnosis for Breast Ultrasound Using Computerized BI-RADS Features and Machine Learning Methods.

Journal: Ultrasound in medicine & biology
Published Date: Jan 21, 2016

Abstract

This work identifies effective computable features from the Breast Imaging Reporting and Data System (BI-RADS), to develop a computer-aided diagnosis (CAD) system for breast ultrasound. Computerized features corresponding to ultrasound BI-RADs categories were designed and tested using a database of 283 pathology-proven benign and malignant lesions. Features were selected based on classification performance using a "bottom-up" approach for different machine learning methods, including decision tree, artificial neural network, random forest and support vector machine. Using 10-fold cross-validation on the database of 283 cases, the highest area under the receiver operating characteristic (ROC) curve (AUC) was 0.84 from a support vector machine with 77.7% overall accuracy; the highest overall accuracy, 78.5%, was from a random forest with the AUC 0.83. Lesion margin and orientation were optimum features common to all of the different machine learning methods. These features can be used in CAD systems to help distinguish benign from worrisome lesions.

Authors

  • Juan Shan
    Department of Computer Science, Seidenberg School of Computer Science and Information Systems, Pace University, New York, New York, USA. Electronic address: jshan@pace.edu.
  • S Kaisar Alam
    Improlabs Pte Ltd, Valley Point, Singapore; Computational Biomedicine Imaging and Modeling Center (CBIM), Rutgers University, Piscataway, New Jersey, USA; Department of Electrical & Electronic Engineering, Islamic University of Technology, Gazipur, Bangladesh.
  • Brian Garra
    U.S. Food and Drug Administration, Silver Spring, Maryland, USA; Washington DC Veterans Affairs Medical Center, Washington, DC, USA.
  • Yingtao Zhang
    School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.
  • Tahira Ahmed
    Washington DC Veterans Affairs Medical Center, Washington, DC, USA.

Keywords

External Resources

Popular Topics
Recent Journals