TwoPath U-Net for automatic brain tumor segmentation from multimodal MRI data

Kaewrak, Keerati and Soraghan, John and Di Caterina, Gaetano and Grose, Derek; Crimi, Alessandro and Bakas, Spyridon, eds. (2021) TwoPath U-Net for automatic brain tumor segmentation from multimodal MRI data. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Springer International Publishing AG, Cham, 300–309. ISBN 9783030720872 (https://doi.org/10.1007/978-3-030-72087-2_26)

[thumbnail of Kaewrak-etal-Springer-2021-TwoPath-U-Net-for-automatic-brain-tumor-segmentation]
Preview
 Text. Filename: Kaewrak_etal_Springer_2021_TwoPath_U_Net_for_automatic_brain_tumor_segmentation.pdf
Accepted Author Manuscript
Download (370kB)| Preview

Abstract

A novel encoder-decoder deep learning network called TwoPath U-Net for multi-class automatic brain tumor segmentation task is presented. The network uses cascaded local and global feature extraction paths in the down-sampling path of the network which allows the network to learn different aspects of both the low-level feature and high-level features. The proposed network architecture using a full image and patches input technique was used on the BraTS2020 training dataset. We tested the network performance using the BraTS2019 validation dataset and obtained the mean dice score of 0.76, 0.64, and 0.58 and the Hausdorff distance 95% of 25.05, 32.83, and 37.57 for the whole tumor, tumor core and enhancing tumor regions.

CORE (COnnecting REpositories)