CU-Net: a U-Net architecture for efficient brain-tumor segmentation on BraTS 2019 dataset

TL;DR

This paper presents CU-Net, a U-Net based architecture that achieves high-accuracy brain tumor segmentation on the BraTS 2019 dataset, potentially improving clinical treatment planning.

Contribution

Introduces CU-Net, a novel U-Net architecture with improved segmentation accuracy for brain tumors on MRI scans.

Findings

Achieved a Dice score of 82.41% on BraTS 2019 dataset.

Outperformed two other state-of-the-art models.

Demonstrated robustness and effectiveness in delineating tumor boundaries.

Abstract

Accurately segmenting brain tumors from MRI scans is important for developing effective treatment plans and improving patient outcomes. This study introduces a new implementation of the Columbia-University-Net (CU-Net) architecture for brain tumor segmentation using the BraTS 2019 dataset. The CU-Net model has a symmetrical U-shaped structure and uses convolutional layers, max pooling, and upsampling operations to achieve high-resolution segmentation. Our CU-Net model achieved a Dice score of 82.41%, surpassing two other state-of-the-art models. This improvement in segmentation accuracy highlights the robustness and effectiveness of the model, which helps to accurately delineate tumor boundaries, which is crucial for surgical planning and radiation therapy, and ultimately has the potential to improve patient outcomes.