Automatic detection of abnormal tissue in mammography

Author

Christoyianni, I. ; Dermatas, E. ; Kokkinakis, G.

Author_Institution

Dept. of Electr. & Comput. Eng., Patras Univ., Greece

Volume

2

fYear

2001

Firstpage

877

Abstract

A novel method for accurate detection of regions of interest (ROIs) that contain circumscribed lesions in mammograms is presented. The mammograms are segmented using a statistical threshold and a number of candidate regions are extracted. Then a set of qualification criteria is employed to filter these regions retaining the most suspicious for which a radial-basis function neural network makes the final decision marking them as ROIs that contain abnormal tissue. The proposed method detects the exact location of the circumscribed lesions with an accuracy of 90.9%, and a very low number of false positive regions per image (2.1 ROIs per image) in the MIAS database

Keywords

biological tissues; cancer; feature extraction; image classification; image segmentation; mammography; medical image processing; radial basis function networks; MIAS database; X-ray mammography; automatic abnormal tissue detection; breast cancer; circumscribed lesions; image region extraction; mammographic image segmentation; neural network classifier; qualification criteria; radial-basis function neural network; regions of interest detection; segmented image post-processing; statistical threshold; Breast cancer; Diseases; Filters; Image databases; Image segmentation; Lesions; Mammography; Neural networks; Qualifications; X-ray imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2001. Proceedings. 2001 International Conference on

Conference_Location

Thessaloniki

Print_ISBN

0-7803-6725-1

Type

conf

DOI

10.1109/ICIP.2001.958634

Filename

958634