Two-stage deep neural network for diagnosing fungal keratitis via in vivo confocal microscopy images

doi:10.1038/s41598-024-68768-y

	Two-stage deep neural network for diagnosing fungal keratitis via in vivo confocal microscopy images
	Li, Chun-Peng 1,2; Dai, Weiwei 3; Xiao, Yun-Peng 1; Qi, Mengying 4; Zhang, Ling-Xiao 1; Gao, Lin 1,2; Zhang, Fang-Lue 7; Lai, Yu-Kun 8; Liu, Chang 9; Lu, Jing 10; Chen, Fen 4; Chen, Dan 4; Shi, Shuai 9; Li, Shaowei 9; Zeng, Qingyan 4,5,6,11; Chen, Yiqiang 1,2
	2024-08-08
发表期刊	SCIENTIFIC REPORTS
ISSN	2045-2322
卷号	14 期号:1 页码:11
摘要	Timely and effective diagnosis of fungal keratitis (FK) is necessary for suitable treatment and avoiding irreversible vision loss for patients. In vivo confocal microscopy (IVCM) has been widely adopted to guide the FK diagnosis. We present a deep learning framework for diagnosing fungal keratitis using IVCM images to assist ophthalmologists. Inspired by the real diagnostic process, our method employs a two-stage deep architecture for diagnostic predictions based on both image-level and sequence-level information. To the best of our knowledge, we collected the largest dataset with 96,632 IVCM images in total with expert labeling to train and evaluate our method. The specificity and sensitivity of our method in diagnosing FK on the unseen test set achieved 96.65% and 97.57%, comparable or better than experienced ophthalmologists. The network can provide image-level, sequence-level and patient-level diagnostic suggestions to physicians. The results show great promise for assisting ophthalmologists in FK diagnosis.
关键词	Fungal keratitis Image classification Neural network Transformer
DOI	10.1038/s41598-024-68768-y
收录类别	SCI
语种	英语
资助项目	Science and Technology Service Network Initiative of the Chinese Academy of Sciences[SZYK202204] ; Aier-ICT Joint Laboratory for Digital Ophthalmology
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:001294094100046
出版者	NATURE PORTFOLIO
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39620
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zeng, Qingyan; Chen, Yiqiang
作者单位	1.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Changsha Aier Eye Hosp, Changsha, Hunan, Peoples R China 4.Wuhan Aier Hankou Eye Hosp, Wuhan, Peoples R China 5.Wuhan Univ, Aier Eye Hosp, Wuhan, Peoples R China 6.Hubei Univ Sci & Technol, Xianning, Peoples R China 7.Victoria Univ Wellington, Wellington, New Zealand 8.Cardiff Univ, Cardiff, Wales 9.Beijing Aier Intech Eye Hosp, Beijing, Peoples R China 10.Chengdu Aier East Eye Hosp, Chengdu, Peoples R China 11.Jinan Univ, Aier Eye Hosp, Guangzhou, Peoples R China
推荐引用方式 GB/T 7714	Li, Chun-Peng,Dai, Weiwei,Xiao, Yun-Peng,et al. Two-stage deep neural network for diagnosing fungal keratitis via in vivo confocal microscopy images[J]. SCIENTIFIC REPORTS,2024,14(1):11.
APA	Li, Chun-Peng.,Dai, Weiwei.,Xiao, Yun-Peng.,Qi, Mengying.,Zhang, Ling-Xiao.,...&Chen, Yiqiang.(2024).Two-stage deep neural network for diagnosing fungal keratitis via in vivo confocal microscopy images.SCIENTIFIC REPORTS,14(1),11.
MLA	Li, Chun-Peng,et al."Two-stage deep neural network for diagnosing fungal keratitis via in vivo confocal microscopy images".SCIENTIFIC REPORTS 14.1(2024):11.