Effect of BI-RADS assessment in improving CAD of masses

  • Authors:

  • Antonio García-Manso;Carlos J. García-Orellana;Ramón Gallardo-Caballero;Horacio González-Velasco;Miguel Macías-Macías

  • Affiliations:

  • Pattern Classification and Image Analysis Group, University of Extremadura, Badajoz, Spain;Pattern Classification and Image Analysis Group, University of Extremadura, Badajoz, Spain;Pattern Classification and Image Analysis Group, University of Extremadura, Badajoz, Spain;Pattern Classification and Image Analysis Group, University of Extremadura, Badajoz, Spain;Pattern Classification and Image Analysis Group, University of Extremadura, Badajoz, Spain

  • Venue:
  • IWDM'10 Proceedings of the 10th international conference on Digital Mammography
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this work we study how the BI-RADS assessment could help to improve the performance of a CAD (Computer Aided Diagnosis) image-based system in the task of masses diagnosis Our system is based on the use of Independent Component Analysis (ICA) as feature extractor from mammographic images, and Neural Networks as a final classifier For our tests, the “Digital Database for Screening Mammography” (DDSM) has been used, particularly the subset BCRP_MASS1 The best results were obtained when we used the image data (with feature extraction by means of ICA) together with the BI-RADS assessment provided by DDSM database.