Abnormal Cell Segmentation Using Convolutional Neural Network

Abstract : This project describes about the segmentation of abnormal cells. The purpose of image segmentation is to partition an image into meaningful regions with respect to a particular application. Automatic segmentation can be possible by  using  Convolutional  Neural Network. The CNN is built over convolutional layers with small 3*3 kernels to allow deeper architectures.CNN segmentation provides better delineation of the abnormal cell. Advantage of CNN is to provide intensity normalization. Convolutional layers have fewer weights to train than dense FC layers, making CNN easier to train and less prone to over fitting. The  proposed system is to implement CNN for the diagnosis of  lung tumor with complex patterns.