Brain MRI Images Generating Method Based on Cyclegan

Abstract

Generating tumor images on a brain MRI image at random locations can help medical researchers and medical students in predicting possible tumor possibilities. In this study, we propose to apply CycleGan to create MRI images with brain tumors from MRI images without brain tumors, thereby increasing the number of MRI images with brain tumors. With the initial data set of 660 images without brain tumors, the CycleGan model has created a new data set of 660 images with brain tumors, aiming to increase the number of brain MRI images for future studies. The received results will be evaluated and compared to others studied based on FID score.