J Peter Campbell1, Esra Ataer-Cansizoglu2, Veronica Bolon-Canedo3, Alican Bozkurt2, Deniz Erdogmus2, Jayashree Kalpathy-Cramer4, Samir N Patel5, James D Reynolds6, Jason Horowitz7, Kelly Hutcheson8, Michael Shapiro9, Michael X Repka10, Phillip Ferrone11, Kimberly Drenser12, Maria Ana Martinez-Castellanos13, Susan Ostmo1, Karyn Jonas14, R V Paul Chan14, Michael F Chiang15. 1. Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland. 2. Cognitive Systems Laboratory, Northeastern University, Boston, Massachusetts. 3. Department of Computer Science, Universidade da Coruña, A Coruña, Spain. 4. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown. 5. Department of Ophthalmology, Weill Cornell Medical College, New York, New York. 6. Department of Ophthalmology, Ross Eye Institute, State University of New York at Buffalo. 7. Department of Ophthalmology, Columbia University, New York, New York. 8. Department of Ophthalmology, Sidra Medical and Research Center, Doha, Qatar. 9. Retina Consultants, Chicago, Illinois. 10. Wilmer Institute, Johns Hopkins University School of Medicine, Baltimore, Maryland. 11. Long Island Vitreoretinal Consultants, Great Neck, New York. 12. Associated Retinal Consultants, Oakland University, Royal Oak, Michigan. 13. Asociacion para Evitar la Ceguera en Mexico, Mexico City, Mexico. 14. Department of Ophthalmology and Visual Sciences, Illinois Eye and Ear Infirmary, University of Illinois at Chicago. 15. Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland15Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland.
Abstract
IMPORTANCE: Published definitions of plus disease in retinopathy of prematurity (ROP) reference arterial tortuosity and venous dilation within the posterior pole based on a standard published photograph. One possible explanation for limited interexpert reliability for a diagnosis of plus disease is that experts deviate from the published definitions. OBJECTIVE: To identify vascular features used by experts for diagnosis of plus disease through quantitative image analysis. DESIGN, SETTING, AND PARTICIPANTS: A computer-based image analysis system (Imaging and Informatics in ROP [i-ROP]) was developed using a set of 77 digital fundus images, and the system was designed to classify images compared with a reference standard diagnosis (RSD). System performance was analyzed as a function of the field of view (circular crops with a radius of 1-6 disc diameters) and vessel subtype (arteries only, veins only, or all vessels). Routine ROP screening was conducted from June 29, 2011, to October 14, 2014, in neonatal intensive care units at 8 academic institutions, with a subset of 73 images independently classified by 11 ROP experts for validation. The RSD was compared with the majority diagnosis of experts. MAIN OUTCOMES AND MEASURES: The primary outcome measure was the percentage of accuracy of the i-ROP system classification of plus disease, with the RSD as a function of the field of view and vessel type. Secondary outcome measures included the accuracy of the 11 experts compared with the RSD. RESULTS: Accuracy of plus disease diagnosis by the i-ROP computer-based system was highest (95%; 95% CI, 94%-95%) when it incorporated vascular tortuosity from both arteries and veins and with the widest field of view (6-disc diameter radius). Accuracy was 90% or less when using only arterial tortuosity and 85% or less using a 2- to 3-disc diameter view similar to the standard published photograph. Diagnostic accuracy of the i-ROP system (95%) was comparable to that of 11 expert physicians (mean 87%, range 79%-99%). CONCLUSIONS AND RELEVANCE: Experts in ROP appear to consider findings from beyond the posterior retina when diagnosing plus disease and consider tortuosity of both arteries and veins, in contrast with published definitions. It is feasible for a computer-based image analysis system to perform comparably with ROP experts, using manually segmented images.
IMPORTANCE: Published definitions of plus disease in retinopathy of prematurity (ROP) reference arterial tortuosity and venous dilation within the posterior pole based on a standard published photograph. One possible explanation for limited interexpert reliability for a diagnosis of plus disease is that experts deviate from the published definitions. OBJECTIVE: To identify vascular features used by experts for diagnosis of plus disease through quantitative image analysis. DESIGN, SETTING, AND PARTICIPANTS: A computer-based image analysis system (Imaging and Informatics in ROP [i-ROP]) was developed using a set of 77 digital fundus images, and the system was designed to classify images compared with a reference standard diagnosis (RSD). System performance was analyzed as a function of the field of view (circular crops with a radius of 1-6 disc diameters) and vessel subtype (arteries only, veins only, or all vessels). Routine ROP screening was conducted from June 29, 2011, to October 14, 2014, in neonatal intensive care units at 8 academic institutions, with a subset of 73 images independently classified by 11 ROP experts for validation. The RSD was compared with the majority diagnosis of experts. MAIN OUTCOMES AND MEASURES: The primary outcome measure was the percentage of accuracy of the i-ROP system classification of plus disease, with the RSD as a function of the field of view and vessel type. Secondary outcome measures included the accuracy of the 11 experts compared with the RSD. RESULTS:Accuracy of plus disease diagnosis by the i-ROP computer-based system was highest (95%; 95% CI, 94%-95%) when it incorporated vascular tortuosity from both arteries and veins and with the widest field of view (6-disc diameter radius). Accuracy was 90% or less when using only arterial tortuosity and 85% or less using a 2- to 3-disc diameter view similar to the standard published photograph. Diagnostic accuracy of the i-ROP system (95%) was comparable to that of 11 expert physicians (mean 87%, range 79%-99%). CONCLUSIONS AND RELEVANCE: Experts in ROP appear to consider findings from beyond the posterior retina when diagnosing plus disease and consider tortuosity of both arteries and veins, in contrast with published definitions. It is feasible for a computer-based image analysis system to perform comparably with ROP experts, using manually segmented images.
Authors: Michael F Chiang; Lu Wang; Mihai Busuioc; Yunling E Du; Patrick Chan; Steven A Kane; Thomas C Lee; David J Weissgold; Audina M Berrocal; Osode Coki; John T Flynn; Justin Starren Journal: Arch Ophthalmol Date: 2007-11
Authors: Michael F Chiang; Michael V Boland; Allen Brewer; K David Epley; Mark B Horton; Michele C Lim; Colin A McCannel; Sayjal J Patel; David E Silverstone; Linda Wedemeyer; Flora Lum Journal: Ophthalmology Date: 2011-06-16 Impact factor: 12.079
Authors: James D Reynolds; Velma Dobson; Graham E Quinn; Alistair R Fielder; Earl A Palmer; Richard A Saunders; Robert J Hardy; Dale L Phelps; John D Baker; Michael T Trese; David Schaffer; Betty Tung Journal: Arch Ophthalmol Date: 2002-11
Authors: Michelle T Cabrera; Sharon F Freedman; Mary Elizabeth Hartnett; Sandra S Stinnett; Bei Bei Chen; David K Wallace Journal: Ophthalmic Surg Lasers Imaging Retina Date: 2014 Nov-Dec Impact factor: 1.300
Authors: R V Paul Chan; Steven L Williams; Yoshihiro Yonekawa; David J Weissgold; Thomas C Lee; Michael F Chiang Journal: Retina Date: 2010-06 Impact factor: 4.256
Authors: Graham E Quinn; Gui-shuang Ying; Ebenezer Daniel; P Lloyd Hildebrand; Anna Ells; Agnieshka Baumritter; Alex R Kemper; Eleanor B Schron; Kelly Wade Journal: JAMA Ophthalmol Date: 2014-10 Impact factor: 7.389
Authors: Esra Ataer-Cansizoglu; Veronica Bolon-Canedo; J Peter Campbell; Alican Bozkurt; Deniz Erdogmus; Jayashree Kalpathy-Cramer; Samir Patel; Karyn Jonas; R V Paul Chan; Susan Ostmo; Michael F Chiang Journal: Transl Vis Sci Technol Date: 2015-11-30 Impact factor: 3.283
Authors: Chace Moleta; J Peter Campbell; Jayashree Kalpathy-Cramer; R V Paul Chan; Susan Ostmo; Karyn Jonas; Michael F Chiang Journal: Am J Ophthalmol Date: 2017-01-11 Impact factor: 5.258
Authors: Hilal Biten; Travis K Redd; Chace Moleta; J Peter Campbell; Susan Ostmo; Karyn Jonas; R V Paul Chan; Michael F Chiang Journal: JAMA Ophthalmol Date: 2018-05-01 Impact factor: 7.389
Authors: Dana Darwish; Ru-Ik Chee; Samir N Patel; Karyn Jonas; Susan Ostmo; J Peter Campbell; Michael F Chiang; R V Paul Chan Journal: Asia Pac J Ophthalmol (Phila) Date: 2018-05-29
Authors: Layla Ghergherehchi; Sang Jin Kim; J Peter Campbell; Susan Ostmo; R V Paul Chan; Michael F Chiang Journal: Asia Pac J Ophthalmol (Phila) Date: 2018-05-24
Authors: Rene Y Choi; James M Brown; Jayashree Kalpathy-Cramer; R V Paul Chan; Susan Ostmo; Michael F Chiang; J Peter Campbell Journal: Ophthalmol Retina Date: 2020-05-04
Authors: Jayashree Kalpathy-Cramer; J Peter Campbell; Deniz Erdogmus; Peng Tian; Dharanish Kedarisetti; Chace Moleta; James D Reynolds; Kelly Hutcheson; Michael J Shapiro; Michael X Repka; Philip Ferrone; Kimberly Drenser; Jason Horowitz; Kemal Sonmez; Ryan Swan; Susan Ostmo; Karyn E Jonas; R V Paul Chan; Michael F Chiang Journal: Ophthalmology Date: 2016-08-24 Impact factor: 12.079