Literature DB >> 34373610

Deep learning-enabled ultra-widefield retinal vessel segmentation with an automated quality-optimized angiographic phase selection tool.

Duriye Damla Sevgi1, Sunil K Srivastava1, Charles Wykoff2, Adrienne W Scott3, Jenna Hach1, Margaret O'Connell1, Jon Whitney1, Amit Vasanji4, Jamie L Reese1, Justis P Ehlers5.   

Abstract

OBJECTIVES: To demonstrate the feasibility of a deep learning-based vascular segmentation tool for UWFA and evaluate its ability to automatically identify quality-optimized phase-specific images.
METHODS: Cumulative retinal vessel areas (RVA) were extracted from all available UWFA frames. Cubic splines were fitted for serial vascular assessment throughout the angiographic phases of eyes with diabetic retinopathy (DR), sickle cell retinopathy (SCR), or normal retinal vasculature. The image with maximum RVA was selected as the optimum early phase. A late phase frame was selected at a minimum of 4 min that most closely mirrored the RVA from the selected early image. Trained image analysts evaluated the selected pairs.
RESULTS: A total of 13,980 UWFA sequences from 462 sessions were used to evaluate the performance and 1578 UWFA sequences from 66 sessions were used to create cubic splines. Maximum RVA was detected at a mean of 41 ± 15, 47 ± 27, 38 ± 8 s for DR, SCR, and normals respectively. In 85.2% of the sessions, appropriate images for both phases were successfully identified. The individual success rate was 90.7% for early and 94.6% for late frames.
CONCLUSIONS: Retinal vascular characteristics are highly phased and field-of-view sensitive. Vascular parameters extracted by deep learning algorithms can be used for quality assessment of angiographic images and quality optimized phase selection. Clinical applications of a deep learning-based vascular segmentation and phase selection system might significantly improve the speed, consistency, and objectivity of UWFA evaluation.
© 2021. The Author(s), under exclusive licence to The Royal College of Ophthalmologists.

Entities:  

Mesh:

Year:  2021        PMID: 34373610      PMCID: PMC9391395          DOI: 10.1038/s41433-021-01661-4

Source DB:  PubMed          Journal:  Eye (Lond)        ISSN: 0950-222X            Impact factor:   4.456


  14 in total

Review 1.  Retinal microvascular network alterations: potential biomarkers of cerebrovascular and neural diseases.

Authors:  Delia Cabrera DeBuc; Gabor Mark Somfai; Akos Koller
Journal:  Am J Physiol Heart Circ Physiol       Date:  2016-12-06       Impact factor: 4.733

2.  Precise Measurement of Retinal Vascular Bed Area and Density on Ultra-wide Fluorescein Angiography in Normal Subjects.

Authors:  Wenying Fan; Akihito Uji; Enrico Borrelli; Michael Singer; Min Sagong; Jano van Hemert; Srinivas R Sadda
Journal:  Am J Ophthalmol       Date:  2018-02-08       Impact factor: 5.258

3.  Segmenting Retinal Blood Vessels With Deep Neural Networks.

Authors:  Pawel Liskowski; Krzysztof Krawiec
Journal:  IEEE Trans Med Imaging       Date:  2016-03-24       Impact factor: 10.048

4.  Ultra-wide-field fluorescein angiography of the ocular fundus.

Authors:  Ayyakkannu Manivannan; Jarka Plskova; Alison Farrow; Sandra Mckay; Peter F Sharp; John V Forrester
Journal:  Am J Ophthalmol       Date:  2005-09       Impact factor: 5.258

5.  Repeatability of automated leakage quantification and microaneurysm identification utilising an analysis platform for ultra-widefield fluorescein angiography.

Authors:  Alice Jiang; Sunil Srivastava; Natalia Figueiredo; Amy Babiuch; Ming Hu; Jamie Reese; Justis P Ehlers
Journal:  Br J Ophthalmol       Date:  2019-07-18       Impact factor: 4.638

6.  Automated quantitative characterisation of retinal vascular leakage and microaneurysms in ultra-widefield fluorescein angiography.

Authors:  Justis P Ehlers; Kevin Wang; Amit Vasanji; Ming Hu; Sunil K Srivastava
Journal:  Br J Ophthalmol       Date:  2017-04-21       Impact factor: 4.638

7.  Precise montaging and metric quantification of retinal surface area from ultra-widefield fundus photography and fluorescein angiography.

Authors:  Daniel E Croft; Jano van Hemert; Charles C Wykoff; David Clifton; Michael Verhoek; Alan Fleming; David M Brown
Journal:  Ophthalmic Surg Lasers Imaging Retina       Date:  2014 Jul-Aug       Impact factor: 1.300

8.  Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning.

Authors:  Ryan Poplin; Avinash V Varadarajan; Katy Blumer; Yun Liu; Michael V McConnell; Greg S Corrado; Lily Peng; Dale R Webster
Journal:  Nat Biomed Eng       Date:  2018-02-19       Impact factor: 25.671

Review 9.  Retinal imaging as a source of biomarkers for diagnosis, characterization and prognosis of chronic illness or long-term conditions.

Authors:  T J MacGillivray; E Trucco; J R Cameron; B Dhillon; J G Houston; E J R van Beek
Journal:  Br J Radiol       Date:  2014-06-17       Impact factor: 3.039

Review 10.  Ultra-wide-field imaging in diabetic retinopathy; an overview.

Authors:  Khalil Ghasemi Falavarjani; Kang Wang; Joobin Khadamy; Srinivas R Sadda
Journal:  J Curr Ophthalmol       Date:  2016-04-30
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.