Paper Title
Cooperative Approach Based on Imrpoved Geanerative Adversial Networks for Cerebral Tumor Detection

Abstract
One of the most critical problems in medical imaging is having high-quality data on healthy and sick patients. Also, gathering and creating a useful dataset is very time-consuming and is not always cost- effective. Machine learning methods are the newest methods in image processing, especially in medical image processing for classification, egmentation, and translation. GAN (Generative Adversarial Networks) is a class of machine learning frameworks that we consider a solution to image-to-image translation problems and segmentation for 3D visualization. One of GAN's applications is generating more realistic data for training and validation to improve the performance of the algorithm and evaluation. We propose a high-quality image-to-image translation framework based on Cycle-GAN in a paired and unpaired model of translation from T1 (or T2) to T2(or T1) weighted MRI (Magnetic Resonance Imaging) of brain images. Forevaluation, we used a dataset that consisted of T1 and T2 images acquired using the 3D structural MRI modality. BTseg allows the visualization of medical scans of each patient in 3D, the instant detection of the presence of a tumor and its localization by displaying the corresponding mask. In order to take advantage of all results of the used 3D models (3D U-Net and 3D WGAN), a combination of models has been performed. This offers medical professionals several advantages particularly in terms of accuracy and detection speed. The concept of the proposed software according to the evaluation metrics IoU score and Dice similarity coefficient – the results were very satisfactory. Keywords - MRI, Brain tumors, BraTS21, Image segmentation, U-Net, GAN, WGAN, 3D, segmentation, model combination.