BRAIN TUMOR SEGMENTATION USING IMAGE PROCESSING IN MRI I

Abstract

Magnetic Resonance Imaging (MRI) may be widely used imaging technique to assess  these tumors, but the massive amount of knowledge produced by MRI prevents manual segmentation during a reasonable time, limiting the use of precise quantitative measurements in the clinical practices. The proposed system an automatic segmentation method based on Convolutional Neural Networks (CNN), exploring small 3 kernels. The use of small kernels designs a deeper architecture, besides having a positive effect against over ?tting. Data augmentation to be very effective for brain tumor segmentation in MRI images.