Brain Tumour Identification and Prognostication from Magnetic Resonance Images using CNN and Light weight Sequential model

Abstract

The most deadly and terrible disease is a brain tumour. Medical image newline processing plays a significant part in medical diagnosis as well as therapy. Imaging newline modalities such as Magnetic Resonance Imaging (MRI), Positron Emission Tomography newline (PET), and Computed Tomography (CT) are widely utilised in the detection of brain newline tumours. In the realm of clinical diagnosis and therapy, medical image processing is newline essential. However, the conventional techniques utilized to evaluate these images requires newline a significant investment of effort and time. Furthermore, patients may have a lower chance newline of surviving if brain tumour sub types are incorrectly identified, which could hinder their newline access to treatment that is required. On categorization problems, the emerging deep newline learning approach has shown encouraging results. This research aims to diagnose brain newline tumours through the utilization of artificial intelligence. newline The primary objective of the initial study is to detect brain tumours through newline the integration of deep learning and machine learning algorithms. To achieve this, 2D MRI newline brain tumour images are subjected to automatic classification using a Convolutional Neural newline Network (Alexnet). Additionally, the study investigates the impact of various optimization newline techniques on enhancing the performance newline