Abstract:
3D médical image Processing with deep learning greatly suffers from a
lack of data. Thus, studies carried out in this field are limited compared
to 2D image analysis related works, where very large datasets exist. As a
result, powerful and efficient 2D convolutional neural networks have been
developed and trained. In this work, we investigate the way to transfer the
performance of a two-dimensional classification network for the purpose
of three-dimensional semantic segmentation of brain tumors. We propose
an asymmetric U-Net network by integrating the EfficientNet model as
part of the encoding branch. As the input data is in 3D, the first layers
of the encoder are devoted to the reduction of the third dimension in
order to fit the input of the EfficientNet network. Experimental results
on validation data from the BraTS 2020 challenge demonstrate that the
proposed method achieve promising performance.
