3D MRI brain tumor segmentation using autoencoder regularization

TL;DR

This paper presents a 3D MRI brain tumor segmentation method using an encoder-decoder network with autoencoder regularization, achieving top performance in the BraTS 2018 challenge.

Contribution

It introduces a novel autoencoder regularization technique within a segmentation network to improve accuracy with limited training data.

Findings

Won 1st place in BraTS 2018 challenge

Effective regularization improves segmentation accuracy

Applicable to limited dataset scenarios

Abstract

Automated segmentation of brain tumors from 3D magnetic resonance images (MRIs) is necessary for the diagnosis, monitoring, and treatment planning of the disease. Manual delineation practices require anatomical knowledge, are expensive, time consuming and can be inaccurate due to human error. Here, we describe a semantic segmentation network for tumor subregion segmentation from 3D MRIs based on encoder-decoder architecture. Due to a limited training dataset size, a variational auto-encoder branch is added to reconstruct the input image itself in order to regularize the shared decoder and impose additional constraints on its layers. The current approach won 1st place in the BraTS 2018 challenge.