Title | Structure-Oriented Transformer for retinal diseases grading from OCT images |
Author | |
Corresponding Author | Hu, Yan |
Publication Years | 2023-01
|
DOI | |
Source Title | |
ISSN | 0010-4825
|
EISSN | 1879-0534
|
Volume | 152 |
Abstract | Retinal diseases are the leading causes of vision temporary or permanent loss. Precise retinal disease grading is a prerequisite for early intervention or specific therapeutic schedules. Existing works based on Convolutional Neural Networks (CNN) focus on typical locality structures and cannot capture long-range dependencies. But retinal disease grading relies more on the relationship between the local lesion and the whole retina, which is consistent with the self-attention mechanism. Therefore, the paper proposes a novel Structure-Oriented Transformer (SoT) framework to further construct the relationship between lesions and retina on clinical datasets. To reduce the dependence on the amount of data, we design structure guidance as a model-oriented filter to emphasize the whole retina structure and guide relation construction. Then, we adopt the pre-trained vision transformer that efficiently models all feature patches’ relationships via transfer learning. Besides, to make the best of all output tokens, a Token vote classifier is proposed to obtain the final grading results. We conduct extensive experiments on one clinical neovascular Age-related Macular Degeneration (nAMD) dataset. The experiments demonstrate the effectiveness of SoT components and improve the ability of relation construction between lesion and retina, which outperforms the state-of-the-art methods for nAMD grading. Furthermore, we evaluate our SoT on one publicly available retinal diseases dataset, which proves our algorithm has classification superiority and good generality. © 2022 Elsevier Ltd |
Indexed By | |
Language | English
|
SUSTech Authorship | First
; Corresponding
|
Funding Project | This work was supported in part by The National Natural Science Foundation of China ( 8210072776 ), Guangdong Provincial Department of Education, China ( 2020ZDZX3043 ), Guangdong Basic and Applied Basic Research Foundation, China ( 2021A1515012195 ), Guangdong Provincial Key Laboratory, China ( 2020B121201001 ), and Shenzhen Natural Science Fund, China ( JCYJ20200109140820699 ), the Stable Support Plan Program, China ( 20200925174052004 ) and Shenzhen Stable Support Plan Program, China ( 20220815111736001 ).
|
WOS Accession No | WOS:000911582900001
|
Publisher | |
EI Accession Number | 20225213290089
|
EI Keywords | Classification (of information)
; Convolutional neural networks
; Grading
; Ophthalmology
|
ESI Classification Code | Medicine and Pharmacology:461.6
; Information Theory and Signal Processing:716.1
; Optical Devices and Systems:741.3
; Information Sources and Analysis:903.1
|
ESI Research Field | COMPUTER SCIENCE
|
Data Source | EV Compendex
|
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Journal Article |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/519641 |
Department | Research Institute of Trustworthy Autonomous Systems 工学院_计算机科学与工程系 |
Affiliation | 1.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Guangdong, Shenzhen; 51805, China 2.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Guangdong, Shenzhen; 51805, China 3.Ningbo Eye hospital, Zhenjiang, Ningbo; 315000, China 4.Osaka University Graduate School of Medicine, Osaka, Suita, Japan |
First Author Affilication | Research Institute of Trustworthy Autonomous Systems; Department of Computer Science and Engineering |
Corresponding Author Affilication | Research Institute of Trustworthy Autonomous Systems; Department of Computer Science and Engineering |
First Author's First Affilication | Research Institute of Trustworthy Autonomous Systems; Department of Computer Science and Engineering |
Recommended Citation GB/T 7714 |
Shen, Junyong,Hu, Yan,Zhang, Xiaoqing,et al. Structure-Oriented Transformer for retinal diseases grading from OCT images[J]. COMPUTERS IN BIOLOGY AND MEDICINE,2023,152.
|
APA |
Shen, Junyong,Hu, Yan,Zhang, Xiaoqing,Gong, Yan,Kawasaki, Ryo,&Liu, Jiang.(2023).Structure-Oriented Transformer for retinal diseases grading from OCT images.COMPUTERS IN BIOLOGY AND MEDICINE,152.
|
MLA |
Shen, Junyong,et al."Structure-Oriented Transformer for retinal diseases grading from OCT images".COMPUTERS IN BIOLOGY AND MEDICINE 152(2023).
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment