获取途径

作者

MacCormick, Ian J. C Williams, Bryan M Zheng, Yalin Li, Kun Al-Bander, Baidaa Czanner, Silvester Cheeseman, Rob Willoughby, Colin E Brown, Emery N Spaeth, George L Czanner, Gabriela

作者单位

Biomedical Sciences Research Institute, Faculty of Life & Centre for Clinical Brain Sciences, University of Edinburgh, Chancellor's Building, Edinburgh, United Kingdom St Paul’s Eye Unit, Royal Liverpool University Hospitals NHS Trust, Liverpool, United Kingdom Medical Information Engineering Department, Taishan Medical School, TaiAn City, ShanDong Province, China School of Computing, Mathematics and Digital Technology, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester, Manchester, United Kingdom Vision Science, Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, United Kingdom Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States of America 10 Anesthesia, Critical Care and Pain Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States of America 11 Glaucoma Research Center, Wills Eye Hospital, Philadelphia, Pennsylvania, United States of America 12 Department of Applied Mathematics, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool, United Kingdom Department of Electrical Engineering and Electronics, University of Liverpool, Brownlow Hill, Liverpool, United Kingdom Department of Eye & Department of Ophthalmology, Royal Victoria Hospital, Belfast, Northern Ireland Health Sciences, Ulster University, Coleraine, Northern Ireland

刊名

PLoS ONE

年份

2019

卷号

Vol.14 No.1

页码

1-20

ISSN

1932-6203

关键词

Algorithms Anatomy Applied mathematics Artificial intelligence Biology and life sciences Classical mechanics Computer and information sciences Damage mechanics Deep learning Deformation Eye diseases Eyes Glaucoma Head Machine learning Machine learning algorithms Mathematics Medicine and health sciences Ocular anatomy Ocular system Ophthalmology Optic disc Optic nerve Physical sciences Physics Research and analysis methods Research Article Simulation and modeling

摘要

Background: Glaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment ...更多

Background: Glaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment are therefore needed to prevent sight loss. Methods: We developed a novel glaucoma detection algorithm that segments and analyses colour photographs to quantify optic nerve rim consistency around the whole disc at 15-degree intervals. This provides a profile of the cup/disc ratio, in contrast to the vertical cup/disc ratio in common use. We introduce a spatial probabilistic model, to account for the optic nerve shape, we then use this model to derive a disc deformation index and a decision rule for glaucoma. We tested our algorithm on two separate image datasets . Results: The spatial algorithm accurately distinguished glaucomatous and healthy discs on internal and external validation . It achieves this using a dataset 100-times smaller than that required for deep learning algorithms, is flexible to the type of cup and disc segmentation , utilises images with missing data, and is correlated with the disc size and the rim-to-disc at the narrowest rim . Discussion: The spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings.收起

文献类型

期刊