中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
GLIM-Net: Chronic Glaucoma Forecast Transformer for Irregularly Sampled Sequential Fundus Images

文献类型：期刊论文

作者Hu, Xiaoyan4; Zhang, Ling-Xiao4; Gao, Lin4,5; Dai, Weiwei2; Han, Xiaoguang1; Lai, Yu-Kun3; Chen, Yiqiang4,5
刊名IEEE TRANSACTIONS ON MEDICAL IMAGING
出版日期2023-06-01
卷号42期号:6页码:1875-1884
ISSN号0278-0062
关键词Transformers Feature extraction Predictive models Image segmentation Deep learning Biomedical imaging Task analysis Glaucoma forecast transformer attention mechanism fundus image
DOI10.1109/TMI.2023.3243692
英文摘要Chronic Glaucoma is an eye disease with progressive optic nerve damage. It is the second leading cause of blindness after cataract and the first leading cause of irreversible blindness. Glaucoma forecast can predict future eye state of a patient by analyzing the historical fundus images, which is helpful for early detection and intervention of potential patients and avoiding the outcome of blindness. In this paper, we propose a GLaucoma forecast transformer based on Irregularly saMpled fundus images named GLIM-Net to predict the probability of developing glaucoma in the future. The main challenge is that the existing fundus images are often sampled at irregular times, making it difficult to accurately capture the subtle progression of glaucoma over time. We therefore introduce two novel modules, namely time positional encoding and time-sensitive MSA (multi-head self-attention) modules, to address this challenge. Unlike many existing works that focus on prediction for an unspecified future time, we also propose an extended model which is further capable of prediction conditioned on a specific future time. The experimental results on the benchmark dataset SIGF show that the accuracy of our method outperforms the state-of-the-art models. In addition, the ablation experiments also confirm the effectiveness of the two modules we propose, which can provide a good reference for the optimization of Transformer models.
资助项目Science and Technology Service Network Initiative of the Chinese Academy of Sciences[KFJ-STS-QYZD-2021-11-001] ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Science and Technology Innovation Program of Hunan Province[2021GK4015] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
WOS研究方向Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:001002656700024
源URL[http://119.78.100.204/handle/2XEOYT63/21247]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Gao, Lin; Chen, Yiqiang
作者单位1.Chinese Univ Hong Kong, Sch Sci & Engn SSE, Shenzhen 518172, Peoples R China
2.Changsha Aier Eye Hosp, Changsha 410000, Hunan, Peoples R China
3.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales
4.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Hu, Xiaoyan,Zhang, Ling-Xiao,Gao, Lin,et al. GLIM-Net: Chronic Glaucoma Forecast Transformer for Irregularly Sampled Sequential Fundus Images[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,42(6):1875-1884.
APA Hu, Xiaoyan.,Zhang, Ling-Xiao.,Gao, Lin.,Dai, Weiwei.,Han, Xiaoguang.,...&Chen, Yiqiang.(2023).GLIM-Net: Chronic Glaucoma Forecast Transformer for Irregularly Sampled Sequential Fundus Images.IEEE TRANSACTIONS ON MEDICAL IMAGING,42(6),1875-1884.
MLA Hu, Xiaoyan,et al."GLIM-Net: Chronic Glaucoma Forecast Transformer for Irregularly Sampled Sequential Fundus Images".IEEE TRANSACTIONS ON MEDICAL IMAGING 42.6(2023):1875-1884.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。