Effect of BI-RADS Assessment in Improving CAD of Masses (2010) |
|
Título: | Effect of BI-RADS Assessment in Improving CAD of Masses |
---|
Autores: | Antonio García-Manso, Carlos J. García-Orellana, Ramón Gallardo-Caballero, Horacio González-Velasco and Miguel Macías-Macías
|
---|
Revista: | Lecture Notes in Computer Science |
---|
Vol./Pag.: | 6136, 614-621 |
---|
DOI:
| 10.1007/978-3-642-13666-5_83 | Ed./Año: | Springer Verlag, 2010 |
---|
Abstract: | In this work we study how the BI-RADS assessment could help to improve the performance of a CAD (Computer Aided Diagno- sis) 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 Mammog- raphy” (DDSM) has been used, particularly the subset BCRP MASS1. The best results were obtained when we used the image data (with fea- ture extraction by means of ICA) together with the BI-RADS assessment provided by DDSM database. Keywords: CAD, breast cancer, mammo- gram, independent component analysis, neural networks. |
---|
|