A Pyramid Spatial Attention Network For Fovea Localization

Zeheng Li; Shuai Lu; Huiqi Li; Hanruo Liu; Ningli Wang

doi:10.1109/CTISC54888.2022.9849760

A Pyramid Spatial Attention Network For Fovea Localization

Zeheng Li
, Shuai Lu
, Huiqi Li^*
, Hanruo Liu
, Ningli Wang^*

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology
Capital Medical University

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

1 Citation (Scopus)

Abstract

Fovea localization plays an important role in the treatment of Diabetic Retinopathy (DR). Fovea is located in the center of the macula and is the most sensitive part of the fundus structure. Accurate fovea localization is challenging in the cases that the lesions of diseases such as DR and Age-related Macular Degeneration (AMD) appear near the fovea. In this paper, we propose a deep regression network based on a pyramid spatial attention module (PAM) for fovea localization. Fovea localization is obtained from coarse to fine through a three-stage cascade network. The PAM attention module is embedded in the first stage to focus on the spatial relationship between optic disc and macula. A coarse candidate area can be got in the first stage. Then the surrounding structure information such as vessels and colors in the coarse candidate area will be learned in the second and third stages to obtain fine localization. The proposed framework is verified on GAMMA and IDRID public datasets, and experiments show that the robustness of localization is significantly improved by the pyramid scheme and spatial attention.

Original language	English
Title of host publication	CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications
Editors	Vassilis C. Gerogianni, Yong Yue, Fairouz Kamareddine
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665458726
DOIs	https://doi.org/10.1109/CTISC54888.2022.9849760
Publication status	Published - 2022
Event	4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022 - Suzhou, China Duration: 22 Apr 2022 → 24 Apr 2022

Publication series

Name	CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications

Conference

Conference	4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022
Country/Territory	China
City	Suzhou
Period	22/04/22 → 24/04/22

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

attention module
deep regression network
fovea localization
three-stage cascade framework

Access to Document

10.1109/CTISC54888.2022.9849760

Cite this

Li, Z., Lu, S., Li, H., Liu, H., & Wang, N. (2022). A Pyramid Spatial Attention Network For Fovea Localization. In V. C. Gerogianni, Y. Yue, & F. Kamareddine (Eds.), CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CTISC54888.2022.9849760

Li, Zeheng ; Lu, Shuai ; Li, Huiqi et al. / A Pyramid Spatial Attention Network For Fovea Localization. CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications. editor / Vassilis C. Gerogianni ; Yong Yue ; Fairouz Kamareddine. Institute of Electrical and Electronics Engineers Inc., 2022. (CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications).

@inproceedings{d4b6338b92ce4fd599e887d24f5f632b,

title = "A Pyramid Spatial Attention Network For Fovea Localization",

abstract = "Fovea localization plays an important role in the treatment of Diabetic Retinopathy (DR). Fovea is located in the center of the macula and is the most sensitive part of the fundus structure. Accurate fovea localization is challenging in the cases that the lesions of diseases such as DR and Age-related Macular Degeneration (AMD) appear near the fovea. In this paper, we propose a deep regression network based on a pyramid spatial attention module (PAM) for fovea localization. Fovea localization is obtained from coarse to fine through a three-stage cascade network. The PAM attention module is embedded in the first stage to focus on the spatial relationship between optic disc and macula. A coarse candidate area can be got in the first stage. Then the surrounding structure information such as vessels and colors in the coarse candidate area will be learned in the second and third stages to obtain fine localization. The proposed framework is verified on GAMMA and IDRID public datasets, and experiments show that the robustness of localization is significantly improved by the pyramid scheme and spatial attention.",

keywords = "attention module, deep regression network, fovea localization, three-stage cascade framework",

author = "Zeheng Li and Shuai Lu and Huiqi Li and Hanruo Liu and Ningli Wang",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022 ; Conference date: 22-04-2022 Through 24-04-2022",

year = "2022",

doi = "10.1109/CTISC54888.2022.9849760",

language = "English",

series = "CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications",

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

editor = "Gerogianni, \{Vassilis C.\} and Yong Yue and Fairouz Kamareddine",

booktitle = "CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications",

address = "United States",

}

Li, Z, Lu, S, Li, H, Liu, H & Wang, N 2022, A Pyramid Spatial Attention Network For Fovea Localization. in VC Gerogianni, Y Yue & F Kamareddine (eds), CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications. CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications, Institute of Electrical and Electronics Engineers Inc., 4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022, Suzhou, China, 22/04/22. https://doi.org/10.1109/CTISC54888.2022.9849760

A Pyramid Spatial Attention Network For Fovea Localization. / Li, Zeheng; Lu, Shuai; Li, Huiqi et al.
CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications. ed. / Vassilis C. Gerogianni; Yong Yue; Fairouz Kamareddine. Institute of Electrical and Electronics Engineers Inc., 2022. (CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications).

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

TY - GEN

T1 - A Pyramid Spatial Attention Network For Fovea Localization

AU - Li, Zeheng

AU - Lu, Shuai

AU - Li, Huiqi

AU - Liu, Hanruo

AU - Wang, Ningli

PY - 2022

Y1 - 2022

N2 - Fovea localization plays an important role in the treatment of Diabetic Retinopathy (DR). Fovea is located in the center of the macula and is the most sensitive part of the fundus structure. Accurate fovea localization is challenging in the cases that the lesions of diseases such as DR and Age-related Macular Degeneration (AMD) appear near the fovea. In this paper, we propose a deep regression network based on a pyramid spatial attention module (PAM) for fovea localization. Fovea localization is obtained from coarse to fine through a three-stage cascade network. The PAM attention module is embedded in the first stage to focus on the spatial relationship between optic disc and macula. A coarse candidate area can be got in the first stage. Then the surrounding structure information such as vessels and colors in the coarse candidate area will be learned in the second and third stages to obtain fine localization. The proposed framework is verified on GAMMA and IDRID public datasets, and experiments show that the robustness of localization is significantly improved by the pyramid scheme and spatial attention.

AB - Fovea localization plays an important role in the treatment of Diabetic Retinopathy (DR). Fovea is located in the center of the macula and is the most sensitive part of the fundus structure. Accurate fovea localization is challenging in the cases that the lesions of diseases such as DR and Age-related Macular Degeneration (AMD) appear near the fovea. In this paper, we propose a deep regression network based on a pyramid spatial attention module (PAM) for fovea localization. Fovea localization is obtained from coarse to fine through a three-stage cascade network. The PAM attention module is embedded in the first stage to focus on the spatial relationship between optic disc and macula. A coarse candidate area can be got in the first stage. Then the surrounding structure information such as vessels and colors in the coarse candidate area will be learned in the second and third stages to obtain fine localization. The proposed framework is verified on GAMMA and IDRID public datasets, and experiments show that the robustness of localization is significantly improved by the pyramid scheme and spatial attention.

KW - attention module

KW - deep regression network

KW - fovea localization

KW - three-stage cascade framework

UR - https://www.scopus.com/pages/publications/85136954863

U2 - 10.1109/CTISC54888.2022.9849760

DO - 10.1109/CTISC54888.2022.9849760

M3 - Conference contribution

AN - SCOPUS:85136954863

T3 - CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications

BT - CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications

A2 - Gerogianni, Vassilis C.

A2 - Yue, Yong

A2 - Kamareddine, Fairouz

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022

Y2 - 22 April 2022 through 24 April 2022

ER -

Li Z, Lu S, Li H, Liu H, Wang N. A Pyramid Spatial Attention Network For Fovea Localization. In Gerogianni VC, Yue Y, Kamareddine F, editors, CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications. Institute of Electrical and Electronics Engineers Inc. 2022. (CTISC 2022 - 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications). doi: 10.1109/CTISC54888.2022.9849760

A Pyramid Spatial Attention Network For Fovea Localization

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this