Brain Tumor Detection by using ResNet-50 and Image Processing Tools

• Published in: 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) pp. 480 - 483
• Main Authors: Rathore, Shivansh, Rana, Tanishka, Mittal, Utkarsh, Gupta, Tejasvi, Malik, Nahid, A S, Mohammed Shariff
• Format: Conference Proceeding
• Language: English
• Published: IEEE 12.05.2023
• Subjects: Artificial neural networks; Brain modeling; Brain Tumor; CNN; Computational modeling; Computer architecture; Deep Learning; Image processing; Magnetic resonance imaging; MRI; ResNet-50; Transfer learning
• DOI: 10.1109/ICACITE57410.2023.10183081

Tumor is an uncontrollable growth of brain and its surrounding tissues. The probably rate of survival of a person having a tumor depends on various factors such as location, kind, size of tumor and age of patient and overall health. Detection of brain tumors is key to improving patient outcomes and increasing the chances of treatment success. Magnetic resonance imaging (MRI) is a well-known used imaging technique to detect brain tumor. The study aims to compare ResNet-50's performance on publicly available datasets of brain MRI images to that of other deep neural networks. Images of normal brain tissue and brain tumours are included in the dataset. Using the dataset, the researchers trained and tested the networks, evaluating their performance in terms of F1-score, accuracy, precision and overall efficiency.