Microcalcification enhancement and classification on mammograms using the wavelet transform

Actas de congresos

Fecha

2008-11-24

Registro en:

Proceedings of the International Joint Conference on Neural Networks, p. 3181-3186, 2008.

http://hdl.handle.net/11449/70639

10.1109/IJCNN.2008.4634248

WOS:000263827202008

2-s2.0-56349133254

2098623262892719

6542086226808067

0000-0003-1086-3312

0000-0002-0924-8024

Autor

Universidade Estadual Paulista (Unesp)

Universidade de São Paulo (USP)

Shu-Te University

Institución

Universidade Estadual Paulista (Brasil)

Resumen

This paper presents a method to enhance microcalcifications and classify their borders by applying the wavelet transform. Decomposing an image and removing its low frequency sub-band the microcalcifications are enhanced. Analyzing the effects of perturbations on high frequency subband it's possible to classify its borders as smooth, rugged or undefined. Results show a false positive reduction of 69.27% using a region growing algorithm. © 2008 IEEE.

Materias

Region growing algorithms

Sub bands

Neural networks

Mostrar el registro completo del ítem