Skip to Main content Skip to Navigation
Conference papers

Efficient embedding network for 3D brain tumor segmentation

Abstract : 3D medical image processing with deep learning greatly suffers from a lack of data. Thus, studies carried out in this field are limited compared to works related to 2D natural image analysis, where very large datasets exist. As a result, powerful and efficient 2D convolutional neural networks have been developed and trained. In this paper, we investigate a 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 incorporating 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 and test data from the BraTS 2020 challenge demonstrate that the proposed method achieve promising performance.
Complete list of metadata
Contributor : Pierre-Henri Conze Connect in order to contact the contributor
Submitted on : Wednesday, March 10, 2021 - 11:03:00 PM
Last modification on : Monday, April 4, 2022 - 9:28:21 AM

Links full text



Hicham Messaoudi, Ahror Belaid, Mohamed Lamine Allaoui, Ahcene Zetout, Mohand Said Allili, et al.. Efficient embedding network for 3D brain tumor segmentation. BrainLes 2020: International MICCAI Brain Lesion Workshop, Oct 2020, Lima, Peru. pp.252-262, ⟨10.1007/978-3-030-72084-1_23⟩. ⟨hal-03165781⟩



Record views