Abstract

Despite advances in artificial intelligence (AI), its application in medical imaging has been burdened and limited by expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures retinal blood flow, to train an AI algorithm to generate flow maps from standard optical coherence tomography (OCT) images, exceeding the ability and bypassing the need for expert labeling. Deep learning was able to infer flow from single structural OCT images with similar fidelity to OCTA and significantly better than expert clinicians (P < 0.00001). Our model allows generating flow maps from large volumes of previously collected OCT data in existing clinical trials and clinical practice. This finding demonstrates a novel application of AI to medical imaging, whereby subtle regularities between different modalities are used to image the same body part and AI is used to generate detailed inferences of tissue function from structure imaging.

Details

Title
Generating retinal flow maps from structural optical coherence tomography with artificial intelligence
Author
Lee, Cecilia S 1 ; Tyring, Ariel J 1 ; Wu, Yue 1 ; Xiao, Sa 1 ; Rokem, Ariel S 2 ; DeRuyter, Nicolaas P 1 ; Zhang Qinqin 3 ; Tufail Adnan 4 ; Wang, Ruikang K 5 ; Lee, Aaron Y 6 

 University of Washington, Department of Ophthalmology, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657) 
 University of Washington, eScience Institute, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657) 
 University of Washington, Department of Bioengineering, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657) 
 Moorfields Eye Hospital NHS Foundation Trust, London, UK (GRID:grid.436474.6) (ISNI:0000 0000 9168 0080) 
 University of Washington, Department of Ophthalmology, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657); University of Washington, Department of Bioengineering, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657) 
 University of Washington, Department of Ophthalmology, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657); University of Washington, eScience Institute, Seattle, USA (GRID:grid.34477.33) (ISNI:0000000122986657) 
Publication year
2019
Publication date
Dec 2019
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2203734392
Copyright
© The Author(s) 2019. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.