Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

Mohammad Hesam Hesamian; Wenjing Jia; Xiangjian He; Paul Kennedy

doi:10.1007/s10278-019-00227-x

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

Mohammad Hesam Hesamian, Wenjing Jia, Xiangjian He, Paul Kennedy

Research output: Journal Publication › Article › peer-review

1418 Citations (Scopus)

Abstract

Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

Original language	English
Pages (from-to)	582-596
Number of pages	15
Journal	Journal of Digital Imaging
Volume	32
Issue number	4
DOIs	https://doi.org/10.1007/s10278-019-00227-x
Publication status	Published - 15 Aug 2019
Externally published	Yes

Keywords

CNN
Deep learning
Medical image segmentation
Organ segmentation

ASJC Scopus subject areas

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

Access to Document

10.1007/s10278-019-00227-x

Cite this

@article{b6030d628640444aa159c7778a8ab66f,

title = "Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges",

abstract = "Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.",

keywords = "CNN, Deep learning, Medical image segmentation, Organ segmentation",

author = "Hesamian, \{Mohammad Hesam\} and Wenjing Jia and Xiangjian He and Paul Kennedy",

note = "Publisher Copyright: {\textcopyright} 2019, The Author(s).",

year = "2019",

month = aug,

day = "15",

doi = "10.1007/s10278-019-00227-x",

language = "English",

volume = "32",

pages = "582--596",

journal = "Journal of Digital Imaging",

issn = "0897-1889",

publisher = "Springer Nature",

number = "4",

}

TY - JOUR

T1 - Deep Learning Techniques for Medical Image Segmentation

T2 - Achievements and Challenges

AU - Hesamian, Mohammad Hesam

AU - Jia, Wenjing

AU - He, Xiangjian

AU - Kennedy, Paul

PY - 2019/8/15

Y1 - 2019/8/15

N2 - Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

AB - Deep learning-based image segmentation is by now firmly established as a robust tool in image segmentation. It has been widely used to separate homogeneous areas as the first and critical component of diagnosis and treatment pipeline. In this article, we present a critical appraisal of popular methods that have employed deep-learning techniques for medical image segmentation. Moreover, we summarize the most common challenges incurred and suggest possible solutions.

KW - CNN

KW - Deep learning

KW - Medical image segmentation

KW - Organ segmentation

UR - https://www.scopus.com/pages/publications/85066806685

U2 - 10.1007/s10278-019-00227-x

DO - 10.1007/s10278-019-00227-x

M3 - Article

C2 - 31144149

AN - SCOPUS:85066806685

SN - 0897-1889

VL - 32

SP - 582

EP - 596

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

IS - 4

ER -

Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this