DR-Unet104 for Multimodal MRI brain tumor segmentation

TL;DR

This paper introduces DR-Unet104, a deep residual 2D U-Net architecture with 104 layers, enhanced with residual blocks and dropout, achieving state-of-the-art brain tumor segmentation results in the BraTS 2020 Challenge.

Contribution

The paper presents a novel 2D residual U-Net with 104 layers, incorporating residual blocks and dropout, outperforming existing models in brain tumor segmentation tasks.

Findings

Achieved a mean dice score of 0.8862 for whole tumor on validation data.

Outperformed DeepLabV3+ in the BraTS 2020 Challenge.

Produced competitive segmentation results using only 2D convolutions.

Abstract

In this paper we propose a 2D deep residual Unet with 104 convolutional layers (DR-Unet104) for lesion segmentation in brain MRIs. We make multiple additions to the Unet architecture, including adding the 'bottleneck' residual block to the Unet encoder and adding dropout after each convolution block stack. We verified the effect of introducing the regularisation of dropout with small rate (e.g. 0.2) on the architecture, and found a dropout of 0.2 improved the overall performance compared to no dropout, or a dropout of 0.5. We evaluated the proposed architecture as part of the Multimodal Brain Tumor Segmentation (BraTS) 2020 Challenge and compared our method to DeepLabV3+ with a ResNet-V2-152 backbone. We found that the DR-Unet104 achieved a mean dice score coefficient of 0.8862, 0.6756 and 0.6721 for validation data, whole tumor, enhancing tumor and tumor core respectively, an overall improvement on 0.8770, 0.65242 and 0.68134 achieved by DeepLabV3+. Our method produced a final mean DSC of 0.8673, 0.7514 and 0.7983 on whole tumor, enhancing tumor and tumor core on the challenge's testing data. We produced a competitive lesion segmentation architecture, despite only 2D convolutions, having the added benefit that it can be used on lower power computers than a 3D architecture. The source code and trained model for this work is openly available at https://github.com/jordan-colman/DR-Unet104.