Watershed Algorithm based DAPP features for Brain Tumor Segmentation and Classification

Abstract

Brain tumor detection is a tedious task in the field of medical imaging. Detection or identification of brain tumor involves segmentation of brain image, extraction of brain features and classification of abnormality in the MRI brain image. This paper proposes the state of art tumor detection techniques using the Watershed Dynamic Angle Projection - Convolution Neural Network (WDAPP-CNN). The watershed algorithm accurately segments the tumor region. The dynamic angle projection pattern extracts the textured features of the brain and the convolutional neural network classifies the tumor and non-tumor regions of the MRI brain image. The abnormality of the brain image is detected and testing is achieved through the BRATS dataset in an efficient way.

Ähnliche Arbeiten