Efficient embedding network for 3D brain tumor segmentation

TL;DR

This paper introduces an efficient 3D brain tumor segmentation method that leverages a 2D EfficientNet within an asymmetric U-Net architecture, effectively addressing data scarcity in 3D medical imaging.

Contribution

It proposes a novel asymmetric U-Net that incorporates EfficientNet for improved 3D brain tumor segmentation performance.

Findings

Achieved promising results on BraTS 2020 dataset.

Effectively reduces 3D data to fit 2D EfficientNet.

Demonstrates competitive segmentation accuracy.

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 classiffication 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.