TY - JOUR
T1 - A deep learning system for fully automated retinal vessel measurement in high throughput image analysis
AU - Shi, Danli
AU - Lin, Zhihong
AU - Wang, Wei
AU - Tan, Zachary
AU - Shang, Xianwen
AU - Zhang, Xueli
AU - Meng, Wei
AU - Ge, Zongyuan
AU - He, Mingguang
N1 - Funding Information:
This work was supported by Fundamental Research Funds of the State Key Laboratory of Ophthalmology, National Natural Science Foundation of China (82171075), Science and Technology Program of Guangzhou, China (202002020049), and Project of Special Research on Cardiovascular Diseases (2020XXG007). MH receives support from the University of Melbourne Research Accelerator Program and the CERA Foundation. The Center for Eye Research Australia receives Operational Infrastructure Support from the Victorian State Government. The sponsor or funding organization had no role in the design or conduct of this research. The sponsor or funding organization had no role in the design, conduct, analysis, or reporting of this study. The funding sources did not participate in the design and conduct of the study, collection, management, analysis interpretation of the data, preparation, review, or approval of the manuscript, and decision to submit the manuscript for publication.
Publisher Copyright:
Copyright © 2022 Shi, Lin, Wang, Tan, Shang, Zhang, Meng, Ge and He.
PY - 2022/3/22
Y1 - 2022/3/22
N2 - Motivation: Retinal microvasculature is a unique window for predicting and monitoring major cardiovascular diseases, but high throughput tools based on deep learning for in-detail retinal vessel analysis are lacking. As such, we aim to develop and validate an artificial intelligence system (Retina-based Microvascular Health Assessment System, RMHAS) for fully automated vessel segmentation and quantification of the retinal microvasculature. Results: RMHAS achieved good segmentation accuracy across datasets with diverse eye conditions and image resolutions, having AUCs of 0.91, 0.88, 0.95, 0.93, 0.97, 0.95, 0.94 for artery segmentation and 0.92, 0.90, 0.96, 0.95, 0.97, 0.95, 0.96 for vein segmentation on the AV-WIDE, AVRDB, HRF, IOSTAR, LES-AV, RITE, and our internal datasets. Agreement and repeatability analysis supported the robustness of the algorithm. For vessel analysis in quantity, less than 2 s were needed to complete all required analysis.
AB - Motivation: Retinal microvasculature is a unique window for predicting and monitoring major cardiovascular diseases, but high throughput tools based on deep learning for in-detail retinal vessel analysis are lacking. As such, we aim to develop and validate an artificial intelligence system (Retina-based Microvascular Health Assessment System, RMHAS) for fully automated vessel segmentation and quantification of the retinal microvasculature. Results: RMHAS achieved good segmentation accuracy across datasets with diverse eye conditions and image resolutions, having AUCs of 0.91, 0.88, 0.95, 0.93, 0.97, 0.95, 0.94 for artery segmentation and 0.92, 0.90, 0.96, 0.95, 0.97, 0.95, 0.96 for vein segmentation on the AV-WIDE, AVRDB, HRF, IOSTAR, LES-AV, RITE, and our internal datasets. Agreement and repeatability analysis supported the robustness of the algorithm. For vessel analysis in quantity, less than 2 s were needed to complete all required analysis.
KW - artificial intelligence
KW - automated analysis
KW - cardiovascular disease
KW - epidemiology
KW - hierarchical vessel morphology
UR - http://www.scopus.com/inward/record.url?scp=85138498788&partnerID=8YFLogxK
U2 - 10.3389/fcvm.2022.823436
DO - 10.3389/fcvm.2022.823436
M3 - Article
C2 - 35391847
AN - SCOPUS:85138498788
SN - 2297-055X
VL - 9
JO - Frontiers in Cardiovascular Medicine
JF - Frontiers in Cardiovascular Medicine
M1 - 823436
ER -
