Farnaz Hoseini - Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran
Asadollah Shahbahrami - Department of Computer Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran
Anaram Yaghoobi Notash - Department of Computer Engineering, Rasht Branch, Islamic Azad University, Rasht, Iran
Peyman Bayat - Department of Computer Engineering, Collage of Engineering, Rasht Branch, Islamic Azad University, rasht, Iran

According to world health organization, breast cancer is one of the most deadlycancers occurred in women. Therefore accurate diagnosis and prediction isimportant to decrease the high death rate. The aim of this paper is twofold. First,improving breast cancer detection accuracy using Modified Fuzzy Logic (MFL) thenimproving the performance of MFL algorithm using GPU platform. Theexperimental results show that the accuracy of the breast cancer detection usingMFL is higher than other techniques. In addition, by exploiting loop-levelparallelism and pipeline parallel communication pattern in MFL algorithm, itsperformance is improved up to 19.17 xfor different image sizes.

Edge Detection Algorithms, Fuzzy Logic, Breast Cancer, GPU, MATLAB, Parallel Computing