SEGMENTATION OF PELVIS TO DETECT THE OVARIAN CANCER USING NEURAL NETWORK by Beant Kaur
Abstract
The tumor is a standard term for a large set of diseases that can affect any portion of the body. One defining feature of cancer is the rapid creation of abnormal cells that grow beyond their usual boundaries, and which can then invade adjoining parts of the body and spread to other organs, the latter process is referred to as metastasizing. Metastases are a key cause of death after cancer. Ovarian cancer is the fifth most common cancer affecting women today. In fact, ovarian cancer is responsible for more deaths than any other type of female reproductive cancer. Ovarian cancer is a cancer that begins in the ovaries. The ovaries are female generative organs situated in the pelvis, approximately the size of an almond. The ovaries produce eggs (ova) for reproduction. The eggs travel through the Fallopian tubes into the uterus where the fertilized egg implants and develops into a fetus. The proposed system provides various view angles of image that used to detect the problems and calculate high accuracy rate. The proposed algorithm is used to feature extraction technique using SIFT algorithm. Any object there are many features, interesting points on the object, that can be extracted to provide a description of the object. This description can then be used when attempting to locate the object in an image containing many other objects. In genetic algorithm used to optimize the extracted feature with the help of the fitness function. In fitness function depends upon three parameters i.e, each feature, total features and classification error rate. The detection of the ovarian cancer and stages found using a convolution neural network. The accuracy is achieved with CNN classifier is 98.8% and with SVM is 85.01%. The performance parameters used are Sensitivity, Specificity and accuracy.
