Year: 2025
Type: article
Abstract: Brain tumors are a critical health issue requiring accurate and early diagnosis for effective treatment. Magnetic Resonance Imaging (MRI) provides detailed brain images that can be leveraged by deep learning techniques for tumor detection. In this paper, We propose a Convolutional Neural Network (CNN)-based approach for classifying brain MRI images into tumor and non-tumor categories. The model is trained on a publicly available dataset, achieving a validation accuracy of up to 99% and a testing accuracy of 100%. We also present visual insights using performance plots, a confusion matrix, and a Receiver Operating Characteristic (ROC) curve. Our findings demonstrate the potential of CNNs in assisting radiologists with efficient brain tumor diagnosis.
Author: Deborah Jestin
Language: English
Subfield: Neurology
Field: Neuroscience
Domain: Life Sciences
Open Access status: hybrid
OpenAlex ID: W4409395171