This paper presents an automated knowledge-based vision system for mass detection and classification in X-Ray mammograms. The system developed herein is based on several processing steps, which aim first at identifying the various regions of the mammogram such as breast, markers, artifacts and background area and then to analyze the identified areas by applying a contrast improvement method for highlighting the pixels of the candidate masses. The detection of such candidate masses is then done by applying locally a 2D Haar Wavelet transform, whereas the mass classification (in benign and malignant ones) is performed by means of a support vector machine whose features are the spatial moments extracted from the identified masses. The system was tested on the public database MIAS achieving very promising results in terms both of accuracy and of sensitivity. © 2011 Springer-Verlag Berlin Heidelberg.

Adaptive local contrast enhancement combined with 2D discrete wavelet transform for mammographic mass detection and classification

GIORDANO, Daniela;SPAMPINATO, CONCETTO
2011-01-01

Abstract

This paper presents an automated knowledge-based vision system for mass detection and classification in X-Ray mammograms. The system developed herein is based on several processing steps, which aim first at identifying the various regions of the mammogram such as breast, markers, artifacts and background area and then to analyze the identified areas by applying a contrast improvement method for highlighting the pixels of the candidate masses. The detection of such candidate masses is then done by applying locally a 2D Haar Wavelet transform, whereas the mass classification (in benign and malignant ones) is performed by means of a support vector machine whose features are the spatial moments extracted from the identified masses. The system was tested on the public database MIAS achieving very promising results in terms both of accuracy and of sensitivity. © 2011 Springer-Verlag Berlin Heidelberg.
2011
978-364221983-2
Biomedical Image Processing; Support Vector Machines; Computer assisted diagnosis
File in questo prodotto:
File Dimensione Formato  
Adaptive local contrast.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 271.12 kB
Formato Adobe PDF
271.12 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/88950
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact