DocumentCode
1734698
Title
Early detection of masses in digitized mammograms using texture features and neuro-fuzzy model
Author
Youssry, Noha ; Abou-Chadi, Fatma E Z ; El-Sayad, Alaa M.
Author_Institution
Dept. of Electron. & Commun. Eng., Mansoura Univ., Egypt
fYear
2003
Lastpage
42378
Abstract
A neuro-fuzzy model for fast detection of candidate circumscribed masses in digitized mammograms is presented. The breast tissue is scanned using variable window size, for each sub-image co-occurrence matrices in different orientations (θ=0°, 45°, 90° and 135°) are calculated and texture features are estimated for each co-occurrence matrix, then the features are used to train neuro-fuzzy models. The classification results reach 100% for abnormal cases and 80% for normal ones.
Keywords
cancer; feature extraction; fuzzy neural nets; image enhancement; image texture; mammography; matrix algebra; medical image processing; tumours; breast tissue; digitized mammograms; fast mass detection; neuro-fuzzy model; subimage cooccurrence matrices; texture analysis; variable window size; Breast cancer; Breast tissue; Cancer detection; Feature extraction; Histograms; Image edge detection; Image segmentation; Lesions; Mammography; Neoplasms;
fLanguage
English
Publisher
ieee
Conference_Titel
Radio Science Conference, 2003. NRSC 2003. Proceedings of the Twentieth National
Print_ISBN
977-5031-75-3
Type
conf
DOI
10.1109/NRSC.2003.1217380
Filename
1217380
Link To Document