A Hybrid Approach to Brain Tumor Detection from MRI Images Using Computer Vision

2019 
Magnetic Resonance Imaging (MRI) is highly pre-scribed to the patients with symptoms of Brain Tumor for proper diagnosis. This is because of the reason that MRI uses magnetic fields to generate more detailed image of the brain than the other diagnosis methods like CT scan or EEG. Brain Tumor is a very serious medical condition characterized by proliferation of abnormal cells in the brain tissue. So, swift and correct analysis of the presence or absence of Brain Tumor from Brain MRI Images is necessary. The principal goal of the paper is the classification of MRI Images of the brain into tumorous and non-tumorous. A Convolution-SVM Hybrid Classifier is developed, which clocked a Test Accuracy of 98.04% and Recall of 0.98. Such an Intelligent Computerized System speeds up the investigation process, hence leading to arrive at the conclusion much faster than the involvement of doctors reviews.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    0
    References
    1
    Citations
    NaN
    KQI
    []
    Baidu
    map