The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm

Peitong Li; Qiuju Deng; Huiqi Li

doi:10.1109/ICIVC50857.2020.9177446

The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm

Peitong Li
, Qiuju Deng
, Huiqi Li

School of Information and Electronics

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

5 Citations (Scopus)

Abstract

Retinal vessel is the only vessel structure in human circulatory system that can be directly observed by non-invasive methods. According to clinical findings, the reduction of arteriovenous width ratio (AVR) acts as an indicator to predict the risk of many systemic diseases. Therefore, it's essential to develop an automatic classification method for arteries and veins to calculate AVR. A method that combines the deep segmentation network and tracking algorithm is proposed in this paper to classify arteries and veins in retinal images. This automatic processing has three steps: (1) retinal images are preprocessed with a haze-removal technique (2) a U-net segmentation network is utilized to classify pixels into background, artery or vein (3) a tracking algorithm is applied for vessel-wise classifications. The proposed method is tested on a clinical dataset and the results present an accuracy of 93.57% for vessel-wise classifications.

Original language	English
Title of host publication	2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	182-187
Number of pages	6
ISBN (Electronic)	9781728166612
DOIs	https://doi.org/10.1109/ICIVC50857.2020.9177446
Publication status	Published - Jul 2020
Event	5th IEEE International Conference on Image, Vision and Computing, ICIVC 2020 - Beijing, China Duration: 10 Jul 2020 → 12 Jul 2020

Publication series

Name	2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020

Conference

Conference	5th IEEE International Conference on Image, Vision and Computing, ICIVC 2020
Country/Territory	China
City	Beijing
Period	10/07/20 → 12/07/20

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

U-net
artery and vein classification
vessel tracking

Access to Document

10.1109/ICIVC50857.2020.9177446

Cite this

Li, P., Deng, Q., & Li, H. (2020). The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm. In 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020 (pp. 182-187). Article 9177446 (2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIVC50857.2020.9177446

@inproceedings{1e8bef10c2e741fd86ff9e11985cc66e,

title = "The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm",

abstract = "Retinal vessel is the only vessel structure in human circulatory system that can be directly observed by non-invasive methods. According to clinical findings, the reduction of arteriovenous width ratio (AVR) acts as an indicator to predict the risk of many systemic diseases. Therefore, it's essential to develop an automatic classification method for arteries and veins to calculate AVR. A method that combines the deep segmentation network and tracking algorithm is proposed in this paper to classify arteries and veins in retinal images. This automatic processing has three steps: (1) retinal images are preprocessed with a haze-removal technique (2) a U-net segmentation network is utilized to classify pixels into background, artery or vein (3) a tracking algorithm is applied for vessel-wise classifications. The proposed method is tested on a clinical dataset and the results present an accuracy of 93.57\% for vessel-wise classifications.",

keywords = "U-net, artery and vein classification, vessel tracking",

author = "Peitong Li and Qiuju Deng and Huiqi Li",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 5th IEEE International Conference on Image, Vision and Computing, ICIVC 2020 ; Conference date: 10-07-2020 Through 12-07-2020",

year = "2020",

month = jul,

doi = "10.1109/ICIVC50857.2020.9177446",

language = "English",

series = "2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "182--187",

booktitle = "2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020",

address = "United States",

}

Li, P, Deng, Q & Li, H 2020, The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm. in 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020., 9177446, 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 182-187, 5th IEEE International Conference on Image, Vision and Computing, ICIVC 2020, Beijing, China, 10/07/20. https://doi.org/10.1109/ICIVC50857.2020.9177446

The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm. / Li, Peitong; Deng, Qiuju; Li, Huiqi.
2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 182-187 9177446 (2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020).

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

TY - GEN

T1 - The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm

AU - Li, Peitong

AU - Deng, Qiuju

AU - Li, Huiqi

PY - 2020/7

Y1 - 2020/7

N2 - Retinal vessel is the only vessel structure in human circulatory system that can be directly observed by non-invasive methods. According to clinical findings, the reduction of arteriovenous width ratio (AVR) acts as an indicator to predict the risk of many systemic diseases. Therefore, it's essential to develop an automatic classification method for arteries and veins to calculate AVR. A method that combines the deep segmentation network and tracking algorithm is proposed in this paper to classify arteries and veins in retinal images. This automatic processing has three steps: (1) retinal images are preprocessed with a haze-removal technique (2) a U-net segmentation network is utilized to classify pixels into background, artery or vein (3) a tracking algorithm is applied for vessel-wise classifications. The proposed method is tested on a clinical dataset and the results present an accuracy of 93.57% for vessel-wise classifications.

AB - Retinal vessel is the only vessel structure in human circulatory system that can be directly observed by non-invasive methods. According to clinical findings, the reduction of arteriovenous width ratio (AVR) acts as an indicator to predict the risk of many systemic diseases. Therefore, it's essential to develop an automatic classification method for arteries and veins to calculate AVR. A method that combines the deep segmentation network and tracking algorithm is proposed in this paper to classify arteries and veins in retinal images. This automatic processing has three steps: (1) retinal images are preprocessed with a haze-removal technique (2) a U-net segmentation network is utilized to classify pixels into background, artery or vein (3) a tracking algorithm is applied for vessel-wise classifications. The proposed method is tested on a clinical dataset and the results present an accuracy of 93.57% for vessel-wise classifications.

KW - U-net

KW - artery and vein classification

KW - vessel tracking

UR - https://www.scopus.com/pages/publications/85092147655

U2 - 10.1109/ICIVC50857.2020.9177446

DO - 10.1109/ICIVC50857.2020.9177446

M3 - Conference contribution

AN - SCOPUS:85092147655

T3 - 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020

SP - 182

EP - 187

BT - 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE International Conference on Image, Vision and Computing, ICIVC 2020

Y2 - 10 July 2020 through 12 July 2020

ER -

Li P, Deng Q, Li H. The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm. In 2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 182-187. 9177446. (2020 IEEE 5th International Conference on Image, Vision and Computing, ICIVC 2020). doi: 10.1109/ICIVC50857.2020.9177446

The Arteriovenous Classification in Retinal Images by U-net and Tracking Algorithm

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this