Skip to main content
. Author manuscript; available in PMC: 2021 Apr 1.
Published in final edited form as: IEEE Trans Med Imaging. 2019 Sep 25;39(4):1114–1126. doi: 10.1109/TMI.2019.2943841

Fig. 3.

Fig. 3.

The end-to-end network architecture of our proposed encoder-ST-ConvLSTM-decoder for tumor growth prediction. For 4D segmentation task, the input is replaced with the raw (e.g., ultrasound) image, the output is its mask, no “factor” branch for other clinical properties, and network model channels are set to 1-8-16-32-64-64-64-32-16-1.