Meeting Banner
Abstract #1094

Estimating Model and Data Dependant Uncertainty for Synthetic-CTs obtained using Generative Adversarial Networks

Matt Hemsley1,2, Brige Chugh3, Mark Ruschin3, Young Lee3, Chia-Lin Tseng4, Greg Stanisz1,2, and Angus Lau1,2

1Medical Biophysics, University of Toronto, Toronto, ON, Canada, 2Physical Sciences Platform, Sunnybrook Research Institute, Toronto, ON, Canada, 3Medical Physics, Sunnybrook Health Sciences Centre, Toronto, ON, Canada, 4Radiation Oncology, Sunnybrook Health Sciences Centre, Toronto, ON, Canada

The feasibility of using a neural network model to place uncertainty estimates on synthetic-CTs created with a generative adversarial network was investigated. Dropout-based variational inference was employed to account for the uncertainty on the trained model. The standard GAN loss function was also combined with an additional log-likelihood term, designed such that the network learns which regions of input data lead to highly variable output. On a dataset of n=105 brain patients, our results demonstrate that the predicted uncertainty can be interpreted as an upper bound on the true error with a confidence of approximately 95%.

This abstract and the presentation materials are available to members only; a login is required.

Join Here