Automatic brain tumour regions segmentation using modified U-Net

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

doi:10.5281/zenodo.4383337

Automatic brain tumour regions segmentation using modified U-Net

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

Electronic And Electrical Engineering

Research output: Contribution to journal › Article › peer-review

13 Downloads (Pure)

Abstract

Early diagnosis is an important key for brain tumour patients' survival. The segmentation of the tumour regions is done manually by the experts and it is time-consuming. In this work, we present a novel network architecture that automatically segments the whole tumour regions and intra-tumour structures (edema, enhancing tumour, necrotic and non-enhancing tumour). We evaluated the results using dice similarity coefficient and obtained promising results.

Original language	English
Pages (from-to)	45-48
Number of pages	4
Journal	Academic Journal for Thai Researchers in Europe
Volume	1
Issue number	1
DOIs	https://doi.org/10.5281/zenodo.4383337
Publication status	Published - 31 Dec 2020

Keywords

automatic segmentation
brain tumour
U-net

Access to Document

10.5281/zenodo.4383337Licence: CC BY-NC-SA 4.0

Kaewrak-etal-AJTRE-2020-Automatic-brain-tumour-regions-segmentation-using-modifiedFinal published version, 375 KBLicence: CC BY-NC-SA 4.0

Cite this

@article{0e38bb3af7474ab5be8331cfe4bc4dae,

title = "Automatic brain tumour regions segmentation using modified U-Net",

abstract = "Early diagnosis is an important key for brain tumour patients' survival. The segmentation of the tumour regions is done manually by the experts and it is time-consuming. In this work, we present a novel network architecture that automatically segments the whole tumour regions and intra-tumour structures (edema, enhancing tumour, necrotic and non-enhancing tumour). We evaluated the results using dice similarity coefficient and obtained promising results.",

keywords = "automatic segmentation, brain tumour, U-net",

author = "Keerati Kaewrak and John Soraghan and \{Di Caterina\}, Gaetano and Derek Grose",

year = "2020",

month = dec,

day = "31",

doi = "10.5281/zenodo.4383337",

language = "English",

volume = "1",

pages = "45--48",

journal = "Academic Journal for Thai Researchers in Europe",

issn = "2730-2784",

number = "1",

}

TY - JOUR

T1 - Automatic brain tumour regions segmentation using modified U-Net

AU - Kaewrak, Keerati

AU - Soraghan, John

AU - Di Caterina, Gaetano

AU - Grose, Derek

PY - 2020/12/31

Y1 - 2020/12/31

N2 - Early diagnosis is an important key for brain tumour patients' survival. The segmentation of the tumour regions is done manually by the experts and it is time-consuming. In this work, we present a novel network architecture that automatically segments the whole tumour regions and intra-tumour structures (edema, enhancing tumour, necrotic and non-enhancing tumour). We evaluated the results using dice similarity coefficient and obtained promising results.

AB - Early diagnosis is an important key for brain tumour patients' survival. The segmentation of the tumour regions is done manually by the experts and it is time-consuming. In this work, we present a novel network architecture that automatically segments the whole tumour regions and intra-tumour structures (edema, enhancing tumour, necrotic and non-enhancing tumour). We evaluated the results using dice similarity coefficient and obtained promising results.

KW - automatic segmentation

KW - brain tumour

KW - U-net

UR - https://www.ajtre.org/about/

U2 - 10.5281/zenodo.4383337

DO - 10.5281/zenodo.4383337

M3 - Article

SN - 2730-2784

VL - 1

SP - 45

EP - 48

JO - Academic Journal for Thai Researchers in Europe

JF - Academic Journal for Thai Researchers in Europe

IS - 1

ER -

Automatic brain tumour regions segmentation using modified U-Net

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this