MEDICAL IMAGE ANALYSIS FOR DISEASE PREDICTION

ABSTRACT

This study aims to design and develop a Brain Magnetic Resonance Imaging (MRI) diagnosis application specifically focused on brain tumor classification. Brain tumors pose significant challenges in terms of accurate and timely diagnosis, which directly impacts treatment planning and patient outcomes. The objective is to create a computer-based system that can automate the classification of brain tumors based on MRI images, providing healthcare professionals with a reliable tool for decision-making.The study focuses on leveraging advanced deep learning techniques to achieve accurate and efficient brain tumor classification. The application involves preprocessing MRI images to extract relevant features, followed by the transfer learning models such as Vgg16, DenseNet201 and EfficientNetV2M. These models will be trained on a large dataset of MRI scans to learn patterns and features associated with different types of brain tumors.The performance of the developed application will be evaluated using standard evaluation metrics such as accuracy, sensitivity, specificity, and area under the curve (AUC). These metrics will provide insights into the effectiveness and reliability of the classification system, aiding in the assessment of its diagnostic capabilities. The successful design and development of this Brain MRI diagnosis application have the potential to significantly improve the accuracy and efficiency of brain tumor classification. It can assist healthcare professionals in making informed decisions, leading to better treatment strategies and improved patient outcomes. The application may also serve as a valuable tool in research and clinical settings, contributing to advancements in the field of medical imaging and brain tumor diagnosis.