An attempt at beating the 3D U-Net

08/06/2019
by   Fabian Isensee, et al.
0

The U-Net is arguably the most successful segmentation architecture in the medical domain. Here we apply a 3D U-Net to the 2019 Kidney and Kidney Tumor Segmentation Challenge and attempt to improve upon it by augmenting it with residual and pre-activation residual blocks. Cross-validation results on the training cases suggest only very minor, barely measurable improvements. Due to marginally higher dice scores, the residual 3D U-Net is chosen for test set prediction. With a Composite Dice score of 91.23 on the test set, our method outperformed all 105 competing teams and won the KiTS2019 challenge by a small margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/27/2020

OR-UNet: an Optimized Robust Residual U-Net for Instrument Segmentation in Endoscopic Images

Segmentation of endoscopic images is an essential processing step for co...
research
10/07/2021

Optimized U-Net for Brain Tumor Segmentation

We propose an optimized U-Net architecture for a brain segmentation tas...
research
09/27/2018

No New-Net

In this paper we demonstrate the effectiveness of a well trained U-Net i...
research
07/11/2021

DiCOVA-Net: Diagnosing COVID-19 using Acoustics based on Deep Residual Network for the DiCOVA Challenge 2021

In this paper, we propose a deep residual network-based method, namely t...
research
11/02/2020

nnU-Net for Brain Tumor Segmentation

We apply nnU-Net to the segmentation task of the BraTS 2020 challenge. T...
research
08/23/2022

Extending nnU-Net is all you need

Semantic segmentation is one of the most popular research areas in medic...
research
08/09/2019

Multi Scale Supervised 3D U-Net for Kidney and Tumor Segmentation

U-Net has achieved huge success in various medical image segmentation ch...

Please sign up or login with your details

Forgot password? Click here to reset