Deep Learning Models for Retinal Blood Vessels Segmentation: A Review

Toufique Soomro, Ahmed J. Afifi , Lihong Zheng, Shafiullah Soomro, Junbin Gao, Olaf Hellwich, Manoranjan Paul

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper presents a comprehensive review of the principle and application of deep learning in retinal image analysis. Many eye diseases often lead to blindness in the absence of proper clinical diagnosis and medical treatment. For example, diabetic retinopathy (DR) is one such disease in which the retinal blood vessels of human eyes are damaged. The ophthalmologists diagnose DR based on their professional knowledge, that is labor intensive. With the advances in image processing and artificial intelligence, computer vision-based techniques have been applied rapidly and widely in the field of medical images analysis and are becoming a better way to advance ophthalmology in practice. Such approaches utilize accurate visual analysis to identify the abnormality of blood vessels with improved performance over manual procedures. More recently, machine learning, in particular, deep learning, has been successfully implemented in this area. In this paper, we focus on recent advances in deep learning methods for retinal image analysis. We review the related publications since 1982, which include more than 80 papers for retinal vessels detections in the research scope spanning from segmentation to classification. Although deep learning has been successfully implemented in other areas, we found only 17 papers so far focus on retinal blood vessel segmentation. This paper characterizes each deep learning based segmentation method as described in the literature. Analyzing along with the limitations and advantages of each method. In the end, we offer some recommendations for future improvement for retinal image analysis.
Original languageEnglish
Pages (from-to)71696-71717
Number of pages22
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 03 Jun 2019

Fingerprint

Blood vessels
Image analysis
Ophthalmology
Computer vision
Artificial intelligence
Learning systems
Image processing
Deep learning
Personnel

Cite this

Soomro, Toufique ; Afifi , Ahmed J. ; Zheng, Lihong ; Soomro, Shafiullah ; Gao, Junbin ; Hellwich, Olaf ; Paul, Manoranjan. / Deep Learning Models for Retinal Blood Vessels Segmentation : A Review. In: IEEE Access. 2019 ; Vol. 7. pp. 71696-71717.
@article{475656e7cdab41a99902348afa8b36b0,
title = "Deep Learning Models for Retinal Blood Vessels Segmentation: A Review",
abstract = "This paper presents a comprehensive review of the principle and application of deep learning in retinal image analysis. Many eye diseases often lead to blindness in the absence of proper clinical diagnosis and medical treatment. For example, diabetic retinopathy (DR) is one such disease in which the retinal blood vessels of human eyes are damaged. The ophthalmologists diagnose DR based on their professional knowledge, that is labor intensive. With the advances in image processing and artificial intelligence, computer vision-based techniques have been applied rapidly and widely in the field of medical images analysis and are becoming a better way to advance ophthalmology in practice. Such approaches utilize accurate visual analysis to identify the abnormality of blood vessels with improved performance over manual procedures. More recently, machine learning, in particular, deep learning, has been successfully implemented in this area. In this paper, we focus on recent advances in deep learning methods for retinal image analysis. We review the related publications since 1982, which include more than 80 papers for retinal vessels detections in the research scope spanning from segmentation to classification. Although deep learning has been successfully implemented in other areas, we found only 17 papers so far focus on retinal blood vessel segmentation. This paper characterizes each deep learning based segmentation method as described in the literature. Analyzing along with the limitations and advantages of each method. In the end, we offer some recommendations for future improvement for retinal image analysis.",
author = "Toufique Soomro and Afifi, {Ahmed J.} and Lihong Zheng and Shafiullah Soomro and Junbin Gao and Olaf Hellwich and Manoranjan Paul",
year = "2019",
month = "6",
day = "3",
doi = "10.1109/ACCESS.2019.2920616",
language = "English",
volume = "7",
pages = "71696--71717",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Deep Learning Models for Retinal Blood Vessels Segmentation : A Review. / Soomro, Toufique; Afifi , Ahmed J.; Zheng, Lihong; Soomro, Shafiullah; Gao, Junbin; Hellwich, Olaf; Paul, Manoranjan.

In: IEEE Access, Vol. 7, 03.06.2019, p. 71696-71717.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Deep Learning Models for Retinal Blood Vessels Segmentation

T2 - A Review

AU - Soomro, Toufique

AU - Afifi , Ahmed J.

AU - Zheng, Lihong

AU - Soomro, Shafiullah

AU - Gao, Junbin

AU - Hellwich, Olaf

AU - Paul, Manoranjan

PY - 2019/6/3

Y1 - 2019/6/3

N2 - This paper presents a comprehensive review of the principle and application of deep learning in retinal image analysis. Many eye diseases often lead to blindness in the absence of proper clinical diagnosis and medical treatment. For example, diabetic retinopathy (DR) is one such disease in which the retinal blood vessels of human eyes are damaged. The ophthalmologists diagnose DR based on their professional knowledge, that is labor intensive. With the advances in image processing and artificial intelligence, computer vision-based techniques have been applied rapidly and widely in the field of medical images analysis and are becoming a better way to advance ophthalmology in practice. Such approaches utilize accurate visual analysis to identify the abnormality of blood vessels with improved performance over manual procedures. More recently, machine learning, in particular, deep learning, has been successfully implemented in this area. In this paper, we focus on recent advances in deep learning methods for retinal image analysis. We review the related publications since 1982, which include more than 80 papers for retinal vessels detections in the research scope spanning from segmentation to classification. Although deep learning has been successfully implemented in other areas, we found only 17 papers so far focus on retinal blood vessel segmentation. This paper characterizes each deep learning based segmentation method as described in the literature. Analyzing along with the limitations and advantages of each method. In the end, we offer some recommendations for future improvement for retinal image analysis.

AB - This paper presents a comprehensive review of the principle and application of deep learning in retinal image analysis. Many eye diseases often lead to blindness in the absence of proper clinical diagnosis and medical treatment. For example, diabetic retinopathy (DR) is one such disease in which the retinal blood vessels of human eyes are damaged. The ophthalmologists diagnose DR based on their professional knowledge, that is labor intensive. With the advances in image processing and artificial intelligence, computer vision-based techniques have been applied rapidly and widely in the field of medical images analysis and are becoming a better way to advance ophthalmology in practice. Such approaches utilize accurate visual analysis to identify the abnormality of blood vessels with improved performance over manual procedures. More recently, machine learning, in particular, deep learning, has been successfully implemented in this area. In this paper, we focus on recent advances in deep learning methods for retinal image analysis. We review the related publications since 1982, which include more than 80 papers for retinal vessels detections in the research scope spanning from segmentation to classification. Although deep learning has been successfully implemented in other areas, we found only 17 papers so far focus on retinal blood vessel segmentation. This paper characterizes each deep learning based segmentation method as described in the literature. Analyzing along with the limitations and advantages of each method. In the end, we offer some recommendations for future improvement for retinal image analysis.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85067385233&origin=inward&txGid=6c8bd3d04b65acdddc023062c0196330

U2 - 10.1109/ACCESS.2019.2920616

DO - 10.1109/ACCESS.2019.2920616

M3 - Article

VL - 7

SP - 71696

EP - 71717

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -