COMPUTER-AIDED DIAGNOSIS OF BREAST CANCER USING GAUSSIAN MIXTURE CYTOLOGICAL IMAGE SEGMENTATION 2

This paper presents an automatic computer system to breast cancer diagnosis. System was designed to distinguish benign from malignant tumors based on f ine needle biopsy microscope images. Studies conduc te focus on two different problems, the first concern the extra ction of morphometric and colorimetric parameters o f nuclei from cytological images and the other concentrate on bre ast cancer classification. In order to extract the nuclei features, segmentation procedure that integrates results of a daptive thresholding and Gaussian mixture clusterin g was implemented. Next, tumors were classified using fou r different classification methods: k-nearest neigh bors, naive Bayes, decision trees and classifiers ensemble. Dia gnostic accuracy obtained for conducted experiments varies according to different classification methods and f luctuates up to 98% for quasi optimal subset of fea tur s. All computational experiments were carried out using mi croscope images collected from 25 benign and 25 mal ignant lesions cases.