Abstract:
Brain tumours are regarded as a fatal condition that impacts the lives of so many people worldwide. The kind, location, and size of a brain tumour all affect how it will ...Show MoreMetadata
Abstract:
Brain tumours are regarded as a fatal condition that impacts the lives of so many people worldwide. The kind, location, and size of a brain tumour all affect how it will be treated. Hence, an automated diagnosis is needed for early detection. Convolutional neural networks (CNNs) have become increasingly desired in recent times for tasks like these. In this work, we have performed a multi-class classification of Brain tumour into different types of tumours over MRI scans. For these several convolutional neural networks are used and a comparative analysis is made for better detection. These networks include AlexNet, GoogleNet, VGG-19, Customized model, and an ensemble of ML models. This comparative analysis is made over certain parameters such as optimization, learning Rate, count of epochs, and Loss. The models gave promising results. The models were evaluated over different parameters such as accuracy, F1-Score, Recall, and Precision.
Published in: 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES)
Date of Conference: 28-30 April 2023
Date Added to IEEE Xplore: 21 July 2023
ISBN Information: