Abstract: Brain tumours are dangerous and serious disorders affected by uncontrolled cell growth in the brain. Brain tumours are one of the most challenging diseases to cure among the different ailments encountered in medical study. Early classification of brain tumours from magnetic resonance imaging (MRI) plays an important role in the diagnosis of such diseases. There are many diagnostic imaging methods used to identify tumours in the brain. MRI is commonly used for such tasks because of its unmatched image quality. The traditional method of identifying tumours relies on physicians, which is time-consuming and prone to errors, putting the patient’s life in jeopardy. Identifying the classes of brain tumours is difficult due to the high anatomical and spatial diversity of the brain tumour’s surrounding region. An automated and precise diagnosis approach is required to treat this severe disease effectively. The relevance of artificial intelligence (AI) in the form of deep learning (DL) has revolutionized new methods of automated medical image diagnosis. As a result, good planning can protect a person's life that has a brain tumour. Using the 2D Convolutional Neural Network (CNN) technique, this project proposes Computer-Aided Diagnosis (CAD) a deep learning-based intelligent brain tumour detection framework for brain tumour type (glioma, meningioma, and pituitary) and stages (benign or malignant). CNN is used to classify tumours into pituitary, glioma, and meningioma. Then its classify the three grades of classified disease type, i.e., Grade-two, Grade-three, and Grade-four. The performance of the CNN models is evaluated using performance metrics such as accuracy, sensitivity, precision, specificity and F1-score. From the experimental results, our proposed CNN model based on the Xception architecture using ADAM optimizer is better than the other three proposed models. The Xception model achieved accuracy, sensitivity, precision specificity, and F1-score values of 99.67%, 99.68%, 99.68%, 99.66%, and 99.68% on the MRI-large dataset. The proposed method is superior to the existing literature, indicating that it can be used to quickly and accurately classify brain tumours.
|
DOI:
10.17148/IJARCCE.2024.134205
