Akhond, Mosta jur RahmanAlam, Mohd TanjeemNawal, NafisaNishi, Nusrat JahanSahan, MD SamiulIslam, Mohammad Tanjil2022-02-062022-02-0620212021-09ID 17101223ID 17201075ID 17301070ID 17101504ID 15301110http://hdl.handle.net/10361/16116Cataloged from PDF version of thesis.Includes bibliographical references (pages 37-41).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.Identifying brain tumors precisely within the early stage is still a challenging problem for the medical sector consistent with recent research. In a previous research approved by Cancer. Net Editorial Board, it was observed that this year, approximately twenty four thousand ve hundred thirty adults will be detected with initial stage cancer tumors of the brain and spinal cord in the United States. So, a developed technology is required to identify this tumor in an early stage to increase the survival rate from this disease. To overcome this problem, many Deep Learning models like CNN (Convolutional Neural Network), LSTM(Long-Short Term Memory) were proposed to detect tumor areas in the primary stage through segmentation and classi cation in previous research. In our proposed paper, we will attempt to use combination of Res-Unet and Unet model to perform segmentation on brain MRI images. So, basically, our target will be to take brain MRI images as input data and after that, we will try to t the combination of Unet and Res-Unet model on the dataset to perform segmentation to compare the result with other proposed models to get better result.41 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Brain tumorDeep learningCNNLSTMSegmentationRes-UnetUnetData train-testComparisonResult analysisNeural networks (Computer science)Cognitive learning theory (Deep learning)Machine learningThesis