A future of automated image contouring with machine learning in radiation therapy
Price Jackson1,2, Tomas Kron1,2, Nicholas Hardcastle2,3
1Department of Oncology, Sir Peter MacCallum, University of Melbourne, Melbourne, Victoria, Australia.
Journal of Medical Radiation Sciences
|December 20, 2019
Abstract:
Automated image contouring is showing improvements in efficiency for a number of clinical tasks in radiotherapy. While atlas segmentation has proven moderately beneficial, the next generation of algorithms based on convolutional neural networks is already pointing to improvements in precision and efficiency. This work provides a broad overview of the benefits of machine learning when applied to these tasks.
