Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens

doi:10.21037/atm-20-4706

	Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens
	Xin, Chen 1; Bian, Gui-Bin2 ; Zhang, Haojie 3; Liu, Weipeng 3; Dong, Zhe 4
发表期刊	ANNALS OF TRANSLATIONAL MEDICINE
ISSN	2305-5839
	2020-07-01
卷号	8 期号:14 页码:11
通讯作者	Dong, Zhe(dongzhe0@126.com)
摘要	Background: Cataract surgery has been recently developed from sight rehabilitating surgery to accurate refractive surgery. The precise concentration of intraocular lens (IOL) is crucial for postoperative high visual quanlity. The three-dimentional (3D) images of ocular anterior segment captured by optial coherence tomography (OCT) make it possible to evaluate the IOL position in 3D space, which provide insights into factors relavant to the visual quanlity and better design of new functional IOL. The deep learning algorithm potentially quantify the IOL position in an objective and efficient way. Methods: The region-based fully convolutional network (R-FCN) was used to recogonize and delineate the IOL configuration in 3D OCT images. Scleral spur was identified automatically. Then the tilt angle of the IOL relative to the scleral spur plane along with its decentration with respect to the pupil were calculated. Repeatability and reliability of the method was evaluated by the intraclass correlation coefficient. Results: After improvement, the R-FCN network recognition efficiency of IOL configuration reached 0.910. The ICC of reliability and repeatability of the method is 0.867 and 0.901. The average tilt angle of the IOL relative to scleral spur is located in 1.65 +/- 1.00 degrees. The offsets dx and dy occurring in the early X and Y directions of the IOL are 0.29 +/- 0.22 and 0.33 +/- 0.24 mm, respectively. The IOL offset distance is 0.44 +/- 0.33 mm. Conclusions: We proposed a practical method to quantify the IOL postion in 3D space based on OCT images and assisted by an algorithm.
关键词	Intraocular lens optical coherence tomography deep learning position
DOI	10.21037/atm-20-4706
关键词[WOS]	DECENTRATION ; TILT
收录类别	SCI
语种	英语
资助项目	Beijing Municipal Administration of Hospitals' Youth Programme[QML20180202] ; National Natural Science Foundation of China[U1713220]
项目资助者	Beijing Municipal Administration of Hospitals' Youth Programme ; National Natural Science Foundation of China
WOS研究方向	Oncology ; Research & Experimental Medicine
WOS类目	Oncology ; Medicine, Research & Experimental
WOS记录号	WOS:000554494600002
出版者	AME PUBL CO
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40373
专题	复杂系统认知与决策实验室_先进机器人
通讯作者	Dong, Zhe
作者单位	1.Capital Med Univ, Beijing Tongren Hosp, Beijing Inst Ophthalmol, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 3.Hebei Univ Technol, Coll Artificial Intelligence & Data Sci, Tianjin, Peoples R China 4.Capital Med Univ, Beijing Tongren Hosp, Beijing Key Lab Ophthalmol & Visual Sci, Beijing Tongren Eye Ctr, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Xin, Chen,Bian, Gui-Bin,Zhang, Haojie,et al. Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens[J]. ANNALS OF TRANSLATIONAL MEDICINE,2020,8(14):11.
APA	Xin, Chen,Bian, Gui-Bin,Zhang, Haojie,Liu, Weipeng,&Dong, Zhe.(2020).Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens.ANNALS OF TRANSLATIONAL MEDICINE,8(14),11.
MLA	Xin, Chen,et al."Optical coherence tomography-based deep learning algorithm for quantification of the location of the intraocular lens".ANNALS OF TRANSLATIONAL MEDICINE 8.14(2020):11.