Paper Title
Detection of Retinoblastoma and its Response to Treatment

Abstract
Retinoblastoma is the most common primary ocular malignancy(Eye cancer) of children. It gets developed in the eyes of children born due to mutation in the RB1 gene. Retinoblastoma is also called leukocoria which develops from the immature cells of a retina. The proposed idea is to develop a web-based application to detect eye cancer and its response to the treatment. Deep learning algorithms like Convolution Neural Network(CNN) can be used for classifying eye images to detect the presence or absence of Retinoblastoma. The proposed system applies pre-processing techniques such as smoothening and resizing to the fundus images of the eye for better results. Image processing techniques such as Histogram equalization, Morphological Operations, Unsharp Masking, Image Intensity Adjustment, and Segmentation are used for tumor extraction. After extraction, the tumor regression is calculated by comparing the area of consecutive stages of the tumor. Thus the proposed system serves as a helping aid to health professionals to track the response of their treatment to such patients. Keywords - Convolution Neural Network, Histogram Equalization, Morphological Operations, Regression, Segmentation, Unsharp Masking