Jessica E Scholey1, Abhejit Rajagopal2, Elena Grace Vasquez3, Atchar Sudhyadhom4, and Peder Eric Zufall Larson2
1Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, United States, 2Department of Radiology, University of California, San Francisco, San Francisco, CA, United States, 3Department of Physics, University of California, Berkeley, Berkeley, CA, United States, 4Department of Radiation Oncology, Harvard Medical School, Boston, MA, United States
1Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, United States, 2Department of Radiology, University of California, San Francisco, San Francisco, CA, United States, 3Department of Physics, University of California, Berkeley, Berkeley, CA, United States, 4Department of Radiation Oncology, Harvard Medical School, Boston, MA, United States
A 3D deep convolutional neural network was used to synthetize CTs (acquired at MV energies) from MRIs for more mapping of accurate electron density (versus those acquired at kV energies) for radiotherapy treatment planning
Figure 2: Transverse images for four representative test datasets with their corresponding a) MRI, b) MVCT, c) sMVCT, and d) HU difference (sMVCT-MVCT) maps.
Figure 3: Transverse images of a) dose distribution calculated on the sMVCT, b) the identical plan calculated on the actual MVCT, c) the difference in dose distributions, and d) the dose volume histograms for the target and several organs-at-risk. In panel (d), DVHs are shown as dotted and solid lines for the sMVCT plan and MVCT plan, respectively.
