Paper Details
Intelligent Supervised Machine Learning-Deep Learning Driven Severity Evaluation and Classification of Brain Tumor using CNN-SVM
Authors
Bhagyalaxmi B S, Yashodha H R, Ashwini M S
Abstract
Brain tumours are among the tenth most common diseases causing the death worldwide, up to 80% and 90% of all primary cancers of the central nervous system. Because of increase in the tumour diseases globally, it becomes necessary to predict the brain tumours in the initial stages only. The survival rate depends on the early diagnosis and efficient treatment. The risk of death is significantly increased when brain tumours are not detected in a timely manner. However, radiologists face many difficulties due to the complex and varied nature of tumour cells, which makes manual processing of magnetic resonance imaging (MRI) scans difficult which is time-consuming. Deep Neural Network learning (DL) and Intelligent Machine Learning (ML) algorithms have become promising technologies in diagnosing medical images, allowing for the automated extraction of relevant patterns and features from MRI data reports to improve tumour diagnosis with fast and accuracy results. The intricacy and unpredictability of brain tumour characteristics can be addressed by these technologies, which could enhance the diagnosis process. Various Deep Neural Network and Intelligent Machine Learning Networks such as VGG19 net, Inception, U-net, RNN, Bi-LSTM, Hybrid model, CNN, Logistic Regression, RF, Decision tress, hybrid models, have been used to extract the expected features from MRI for the early prediction of the brain tumours. This article gives the severity analysis of brain tumours using the MRI imaging taken from the FigShare datasets and BRATs datasets. The CNN model gives the more accuracy compared to the SVM model with 93% and 86% respectively.
Keywords
Deep Learning, Machine Learning, SVM, CNN, Hybrid Model
Citation
Intelligent Supervised Machine Learning-Deep Learning Driven Severity Evaluation and Classification of Brain Tumor using CNN-SVM. Bhagyalaxmi B S, Yashodha H R, Ashwini M S. 2025. IJIRCT, Volume 11, Issue 1. Pages 1-10. https://www.ijirct.org/viewPaper.php?paperId=2501044