Radiation therapy is one of the most effective treatments used in the treatment of about half of all people with cancer. A critical goal in radiation therapy is to deliver optimal radiation doses to the perceived tumor while sparing the surrounding healthy tissues. Radiation oncologists often manually delineate normal and diseased structures on 3D-CT scans, a time consuming task. We present a segmentation algorithm using non-parametric snakes and principal curves that can be used in an automatic or semi-supervised fashion. It provides fast segmentation that is robust with respect to noisy edges and does not require the user to optimize a variety of parameters, unlike many segmentation algorithms. It allows multiple cues to be incorporated easily for the purposes of estimating the edge probability density. These cues, including texture, intensity and shape priors, can be used simultaneously to delineate tumors and normal anatomy, thereby increasing the robustness of the algorithm. The notion of principal curves is used to interpolate between data points in sparse areas. We compare the results using a non-parametric snake technique with a gold standard consisting of manually delineated structures for tumors as well as normal organs.