Modified Convolutional Neural Networks for Efficient and Precise Brain Tumor Diagnosis in Clinical Application Use

Brain tumor is the growth of abnormal brain cells, some of which have the potential to develop into cancer. For medical professionals, it is quite difficult to diagnose brain tumors early. They assess the Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) scans for finding the brain tumor. Searching through the vast number of MRI images by hand to find a brain tumor is now extremely time consuming and inaccurate. Using basic imaging techniques to identify aberrant brain areas is challenging. This work uses image processing techniques to automatically detect and classify brain tumors. There are four primary steps in the methodology: The first step is image preprocessing, in which the Gaussian filter is used to enhance and filter the images. Second, the Global Thresholding approach for image segmentation. Third, the features of the image are extracted using the Local Binary Pattern (LBP). Fourth, the classification of brain cancers is done using the Modified Convolutional Neural Network (CNN).This classifier is implemented using the python software. The findings show that it offers greater accuracy and the results are then contrasted with those of earlier classification methods. This classification algorithm is executed with greater performances and detect the brain tumor in MRI images with more favorable results.