Paper Contents
Abstract
AbstractBrain tumor detection is a critical problem in medical imaging since prompt and accurate diagnosis can significantly affect patient outcomes. Convolutional neural networks (CNNs), a deep learning-based method, are used in this article to automaticallyuse magnetic resonance imaging (MRI) scans to identify and categorize brain cancers. The Brain Tumor Segmentation Challenge dataset, which consists of multi-modal MRI scans that offer detailed information about tumor characteristics, is used to train the model. To increase the caliber and variety of the provided data, pre-processing methods including data augmentation, scaling, and standardization are applied.Convolutional layers for hierarchical feature extraction, max pooling layers for dimensionality reduction, and fully linked layers for final classification make up the CNN architecture. The model is evaluated using metrics like F1-score, sensitivity, specificity, and accuracy. After demonstrating significant improvements in processing speed and detection accuracy when compared to traditional manual and semi-automatic segmentation techniques, CNN is positioned as a promising method for brain tumor identification in clinical settings
Copyright
Copyright © 2024 Rohit Laxman Fasale. This is an open access article distributed under the Creative Commons Attribution License.
