Deep Learning for Brain MRI Segmentation

State of the Art and Future Directions

Zeynettin Akkus, Alfiia Galimzianova, Assaf Hoogi, Daniel L. Rubin, Bradley J Erickson

Research output: Contribution to journalArticle

106 Citations (Scopus)

Abstract

Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

Original languageEnglish (US)
Pages (from-to)1-11
Number of pages11
JournalJournal of Digital Imaging
DOIs
StateAccepted/In press - Jun 2 2017

Fingerprint

Magnetic resonance imaging
Brain
Learning
Aptitude
Learning algorithms
Learning systems
Deep learning
Direction compound
Chemical analysis

Keywords

  • Brain lesion segmentation
  • Convolutional neural network
  • Deep learning
  • Quantitative brain MRI

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Cite this

Deep Learning for Brain MRI Segmentation : State of the Art and Future Directions. / Akkus, Zeynettin; Galimzianova, Alfiia; Hoogi, Assaf; Rubin, Daniel L.; Erickson, Bradley J.

In: Journal of Digital Imaging, 02.06.2017, p. 1-11.

Research output: Contribution to journalArticle

Akkus, Zeynettin ; Galimzianova, Alfiia ; Hoogi, Assaf ; Rubin, Daniel L. ; Erickson, Bradley J. / Deep Learning for Brain MRI Segmentation : State of the Art and Future Directions. In: Journal of Digital Imaging. 2017 ; pp. 1-11.
@article{f661bcd3791f4ea2965f76503a3cf6c2,
title = "Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions",
abstract = "Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.",
keywords = "Brain lesion segmentation, Convolutional neural network, Deep learning, Quantitative brain MRI",
author = "Zeynettin Akkus and Alfiia Galimzianova and Assaf Hoogi and Rubin, {Daniel L.} and Erickson, {Bradley J}",
year = "2017",
month = "6",
day = "2",
doi = "10.1007/s10278-017-9983-4",
language = "English (US)",
pages = "1--11",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",

}

TY - JOUR

T1 - Deep Learning for Brain MRI Segmentation

T2 - State of the Art and Future Directions

AU - Akkus, Zeynettin

AU - Galimzianova, Alfiia

AU - Hoogi, Assaf

AU - Rubin, Daniel L.

AU - Erickson, Bradley J

PY - 2017/6/2

Y1 - 2017/6/2

N2 - Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

AB - Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

KW - Brain lesion segmentation

KW - Convolutional neural network

KW - Deep learning

KW - Quantitative brain MRI

UR - http://www.scopus.com/inward/record.url?scp=85020130546&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020130546&partnerID=8YFLogxK

U2 - 10.1007/s10278-017-9983-4

DO - 10.1007/s10278-017-9983-4

M3 - Article

SP - 1

EP - 11

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

ER -