Brain tumor segmentation using 2d-unet convolutional neural network

Khushboo Munir; Fabrizio Frezza; Antonello Rizzi

doi:10.1007/978-981-15-6321-8_14

Brain tumor segmentation using 2d-unet convolutional neural network

Khushboo Munir^*, Fabrizio Frezza, Antonello Rizzi

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

19 Scopus citations

Abstract

Gliomas are considered as the most aggressive and commonly found type among brain tumors. This leads to the shortage of lives of oncological patients. These tumors are mostly by magnetic resonance imaging (MRI) from which the segmentation becomes a big problem because of the large structural and spatial variability. In this study, we propose a 2D-UNET model based on convolutional neural networks (CNN). The model is trained, validated and tested on BRATS 2019 dataset. The average dice coefficient achieved is 0.9694.

Original language	English
Title of host publication	Studies in Computational Intelligence
Publisher	Springer
Pages	239-248
Number of pages	10
DOIs	https://doi.org/10.1007/978-981-15-6321-8_14
State	Published - 2021
Externally published	Yes

Publication series

Name	Studies in Computational Intelligence
Volume	908
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Bibliographical note

Publisher Copyright:
© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

Keywords

Artificial intelligence
Brain tumor segmentation
Convolutional neural network
Deep UNET
Deep learning

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.1007/978-981-15-6321-8_14

Cite this

@inbook{fd477d9fdaad44d4abae03a0755e3647,

title = "Brain tumor segmentation using 2d-unet convolutional neural network",

abstract = "Gliomas are considered as the most aggressive and commonly found type among brain tumors. This leads to the shortage of lives of oncological patients. These tumors are mostly by magnetic resonance imaging (MRI) from which the segmentation becomes a big problem because of the large structural and spatial variability. In this study, we propose a 2D-UNET model based on convolutional neural networks (CNN). The model is trained, validated and tested on BRATS 2019 dataset. The average dice coefficient achieved is 0.9694.",

keywords = "Artificial intelligence, Brain tumor segmentation, Convolutional neural network, Deep UNET, Deep learning",

author = "Khushboo Munir and Fabrizio Frezza and Antonello Rizzi",

note = "Publisher Copyright: {\textcopyright} The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.",

year = "2021",

doi = "10.1007/978-981-15-6321-8\_14",

language = "English",

series = "Studies in Computational Intelligence",

publisher = "Springer",

pages = "239--248",

booktitle = "Studies in Computational Intelligence",

address = "Germany",

}

TY - CHAP

T1 - Brain tumor segmentation using 2d-unet convolutional neural network

AU - Munir, Khushboo

AU - Frezza, Fabrizio

AU - Rizzi, Antonello

N1 - Publisher Copyright: © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

PY - 2021

Y1 - 2021

N2 - Gliomas are considered as the most aggressive and commonly found type among brain tumors. This leads to the shortage of lives of oncological patients. These tumors are mostly by magnetic resonance imaging (MRI) from which the segmentation becomes a big problem because of the large structural and spatial variability. In this study, we propose a 2D-UNET model based on convolutional neural networks (CNN). The model is trained, validated and tested on BRATS 2019 dataset. The average dice coefficient achieved is 0.9694.

AB - Gliomas are considered as the most aggressive and commonly found type among brain tumors. This leads to the shortage of lives of oncological patients. These tumors are mostly by magnetic resonance imaging (MRI) from which the segmentation becomes a big problem because of the large structural and spatial variability. In this study, we propose a 2D-UNET model based on convolutional neural networks (CNN). The model is trained, validated and tested on BRATS 2019 dataset. The average dice coefficient achieved is 0.9694.

KW - Artificial intelligence

KW - Brain tumor segmentation

KW - Convolutional neural network

KW - Deep UNET

KW - Deep learning

UR - https://www.scopus.com/pages/publications/85090887639

U2 - 10.1007/978-981-15-6321-8_14

DO - 10.1007/978-981-15-6321-8_14

M3 - Chapter

AN - SCOPUS:85090887639

T3 - Studies in Computational Intelligence

SP - 239

EP - 248

BT - Studies in Computational Intelligence

PB - Springer

ER -

Brain tumor segmentation using 2d-unet convolutional neural network

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this