SVM and neural networks comparison in mammographic CAD.

Autor: García-Orellana CJ; CAPI Research Group, Universidad de Extremadura, 06071 - Badajoz, (SPAIN). carlos@capi.unex.es, Gallardo-Caballero R, Macías-Macias M, González-Velasco H
Jazyk: angličtina
Zdroj: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference [Annu Int Conf IEEE Eng Med Biol Soc] 2007; Vol. 2007, pp. 3204-7.
DOI: 10.1109/IEMBS.2007.4353011
Abstrakt: The purpose of this work is to compare the performance of Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP) in the task of detection and diagnosis of microcalcification clusters in mammograms (MCCs). As data source, the "Digital Database for Screening Mammography" (DDSM) was used. The results show a similar performance for SVM and MLP, in both tasks, detection and diagnosis (slightly better for MLP in detection).
Databáze: MEDLINE