Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Mushaik Malik; Benjamin  Chong; Justin  Fernandez; Vickie Shim; Nikola Kasabov; Alan Wang

doi:10.3390/bioengineering11010086

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Mushaik Malik
, Benjamin Chong
, Justin Fernandez
, Vickie Shim
, Nikola Kasabov
, Alan Wang

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

22 Citations (Scopus)

112 Downloads (Pure)

Abstract

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are
available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the
development of more robust and effective stroke lesion segmentation models.

Original language	English
Article number	86
Pages (from-to)	1-19
Number of pages	19
Journal	Bioengineering
Volume	11
Issue number	1
Early online date	17 Jan 2024
DOIs	https://doi.org/10.3390/bioengineering11010086
Publication status	Published (in print/issue) - 31 Jan 2024

Bibliographical note

Publisher Copyright:
© 2024 by the authors.

Funding

This work was funded by the Health Research Council of New Zealand’s project 21/144, the MBIE Catalyst: Strategic Fund NZ-Singapore Data Science Research Programme UOAX2001, the Marsden Fund Project 22-UOA-120, and the Royal Society Catalyst: Seeding General Project 23-UOA-055-CSG.

Funders	Funder number
23-UOA-055-CSG
21/144
UOAX2001
Marsden Fund	22-UOA-120

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

stroke
deep learning
lesion segmentation
network
survey

Access to Document

10.3390/bioengineering11010086Licence: CC BY

Malik et al bioengineering-11-00086-v2Final published version, 321 KBLicence: CC BY

Cite this

@article{97948f8be0e8490a9b0baf834b1515eb,

title = "Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review",

abstract = "Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.",

keywords = "stroke, deep learning, lesion segmentation, network, survey",

author = "Mushaik Malik and Benjamin Chong and Justin Fernandez and Vickie Shim and Nikola Kasabov and Alan Wang",

note = "Publisher Copyright: {\textcopyright} 2024 by the authors.",

year = "2024",

month = jan,

day = "31",

doi = "10.3390/bioengineering11010086",

language = "English",

volume = "11",

pages = "1--19",

journal = "Bioengineering",

issn = "2306-5354",

publisher = "MDPI",

number = "1",

}

TY - JOUR

T1 - Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

AU - Malik, Mushaik

AU - Chong, Benjamin

AU - Fernandez, Justin

AU - Shim, Vickie

AU - Kasabov, Nikola

AU - Wang, Alan

PY - 2024/1/31

Y1 - 2024/1/31

N2 - Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

AB - Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

KW - stroke

KW - deep learning

KW - lesion segmentation

KW - network

KW - survey

UR - https://www.scopus.com/pages/publications/85183188238

U2 - 10.3390/bioengineering11010086

DO - 10.3390/bioengineering11010086

M3 - Article

C2 - 38247963

SN - 2306-5354

VL - 11

SP - 1

EP - 19

JO - Bioengineering

JF - Bioengineering

IS - 1

M1 - 86

ER -

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review

Abstract

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this