Modified U-Net for automatic brain tumor regions segmentation

Keerati Kaewrak, John Soraghan, Gaetano Di Caterina, Derek Grose

Research output: Contribution to conference › Paper

5 Downloads (Pure)

Abstract

Novel deep learning based network architectures are investigated for advanced brain tumor image classification and segmentation. Variations in brain tumor characteristics together with limited labelled datasets represent significant challenges in automatic brain tumor segmentation. In this paper, we present a novel architecture based on the U-Net that incorporates both global and local feature extraction paths to improve the segmentation accuracy. The results included in the paper show superior performance of the novel segmentation for five tumor regions on the large BRATs 2018 dataset over other approaches.
Original languageEnglish
Number of pages5
Publication statusPublished - 5 Sep 2019
Event27th European Signal Processing Conference - A Coruna, Spain
Duration: 2 Sep 2019 → 6 Sep 2019
http://eusipco2019.org/

Conference

Conference27th European Signal Processing Conference
Abbreviated titleEUSIPCO 2019
CountrySpain
CityA Coruna
Period2/09/19 → 6/09/19
Internet address

Fingerprint

Tumors
Brain
Image classification
Network architecture
Image segmentation
Feature extraction

Keywords

  • segmentation
  • u-net
  • tumor

Cite this

Kaewrak, K., Soraghan, J., Di Caterina, G., & Grose, D. (2019). Modified U-Net for automatic brain tumor regions segmentation. Paper presented at 27th European Signal Processing Conference, A Coruna, Spain.
Kaewrak, Keerati ; Soraghan, John ; Di Caterina, Gaetano ; Grose, Derek. / Modified U-Net for automatic brain tumor regions segmentation. Paper presented at 27th European Signal Processing Conference, A Coruna, Spain.5 p.
@conference{cb67f5c746ab463680545a59c6700125,
title = "Modified U-Net for automatic brain tumor regions segmentation",
abstract = "Novel deep learning based network architectures are investigated for advanced brain tumor image classification and segmentation. Variations in brain tumor characteristics together with limited labelled datasets represent significant challenges in automatic brain tumor segmentation. In this paper, we present a novel architecture based on the U-Net that incorporates both global and local feature extraction paths to improve the segmentation accuracy. The results included in the paper show superior performance of the novel segmentation for five tumor regions on the large BRATs 2018 dataset over other approaches.",
keywords = "segmentation, u-net, tumor",
author = "Keerati Kaewrak and John Soraghan and {Di Caterina}, Gaetano and Derek Grose",
year = "2019",
month = "9",
day = "5",
language = "English",
note = "27th European Signal Processing Conference, EUSIPCO 2019 ; Conference date: 02-09-2019 Through 06-09-2019",
url = "http://eusipco2019.org/",

}

Kaewrak, K, Soraghan, J, Di Caterina, G & Grose, D 2019, 'Modified U-Net for automatic brain tumor regions segmentation' Paper presented at 27th European Signal Processing Conference, A Coruna, Spain, 2/09/19 - 6/09/19, .

Modified U-Net for automatic brain tumor regions segmentation. / Kaewrak, Keerati; Soraghan, John; Di Caterina, Gaetano; Grose, Derek.

2019. Paper presented at 27th European Signal Processing Conference, A Coruna, Spain.

Research output: Contribution to conference › Paper

TY - CONF

T1 - Modified U-Net for automatic brain tumor regions segmentation

AU - Kaewrak, Keerati

AU - Soraghan, John

AU - Di Caterina, Gaetano

AU - Grose, Derek

PY - 2019/9/5

Y1 - 2019/9/5

N2 - Novel deep learning based network architectures are investigated for advanced brain tumor image classification and segmentation. Variations in brain tumor characteristics together with limited labelled datasets represent significant challenges in automatic brain tumor segmentation. In this paper, we present a novel architecture based on the U-Net that incorporates both global and local feature extraction paths to improve the segmentation accuracy. The results included in the paper show superior performance of the novel segmentation for five tumor regions on the large BRATs 2018 dataset over other approaches.

AB - Novel deep learning based network architectures are investigated for advanced brain tumor image classification and segmentation. Variations in brain tumor characteristics together with limited labelled datasets represent significant challenges in automatic brain tumor segmentation. In this paper, we present a novel architecture based on the U-Net that incorporates both global and local feature extraction paths to improve the segmentation accuracy. The results included in the paper show superior performance of the novel segmentation for five tumor regions on the large BRATs 2018 dataset over other approaches.

KW - segmentation

KW - u-net

KW - tumor

UR - http://eusipco2019.org/

M3 - Paper

ER -

Kaewrak K, Soraghan J, Di Caterina G, Grose D. Modified U-Net for automatic brain tumor regions segmentation. 2019. Paper presented at 27th European Signal Processing Conference, A Coruna, Spain.

Access to Document