Esra Ataer-Cansizoglu1, Veronica Bolon-Canedo2, J Peter Campbell3, Alican Bozkurt1, Deniz Erdogmus1, Jayashree Kalpathy-Cramer4, Samir Patel5, Karyn Jonas5, R V Paul Chan5, Susan Ostmo3, Michael F Chiang6. 1. Cognitive Systems Laboratory, Northeastern University, Boston, MA, USA. 2. Department of Computer Science, Universidade da Coruña, A Coruña, Spain. 3. Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland, OR, USA. 4. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, USA. 5. Department of Ophthalmology, Weill Cornell Medical College, New York, NY, USA. 6. Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University, Portland, OR, USA ; Departments of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, OR, USA.
Abstract
PURPOSE: We developed and evaluated the performance of a novel computer-based image analysis system for grading plus disease in retinopathy of prematurity (ROP), and identified the image features, shapes, and sizes that best correlate with expert diagnosis. METHODS: A dataset of 77 wide-angle retinal images from infants screened for ROP was collected. A reference standard diagnosis was determined for each image by combining image grading from 3 experts with the clinical diagnosis from ophthalmoscopic examination. Manually segmented images were cropped into a range of shapes and sizes, and a computer algorithm was developed to extract tortuosity and dilation features from arteries and veins. Each feature was fed into our system to identify the set of characteristics that yielded the highest-performing system compared to the reference standard, which we refer to as the "i-ROP" system. RESULTS: Among the tested crop shapes, sizes, and measured features, point-based measurements of arterial and venous tortuosity (combined), and a large circular cropped image (with radius 6 times the disc diameter), provided the highest diagnostic accuracy. The i-ROP system achieved 95% accuracy for classifying preplus and plus disease compared to the reference standard. This was comparable to the performance of the 3 individual experts (96%, 94%, 92%), and significantly higher than the mean performance of 31 nonexperts (81%). CONCLUSIONS: This comprehensive analysis of computer-based plus disease suggests that it may be feasible to develop a fully-automated system based on wide-angle retinal images that performs comparably to expert graders at three-level plus disease discrimination. TRANSLATIONAL RELEVANCE: Computer-based image analysis, using objective and quantitative retinal vascular features, has potential to complement clinical ROP diagnosis by ophthalmologists.
PURPOSE: We developed and evaluated the performance of a novel computer-based image analysis system for grading plus disease in retinopathy of prematurity (ROP), and identified the image features, shapes, and sizes that best correlate with expert diagnosis. METHODS: A dataset of 77 wide-angle retinal images from infants screened for ROP was collected. A reference standard diagnosis was determined for each image by combining image grading from 3 experts with the clinical diagnosis from ophthalmoscopic examination. Manually segmented images were cropped into a range of shapes and sizes, and a computer algorithm was developed to extract tortuosity and dilation features from arteries and veins. Each feature was fed into our system to identify the set of characteristics that yielded the highest-performing system compared to the reference standard, which we refer to as the "i-ROP" system. RESULTS: Among the tested crop shapes, sizes, and measured features, point-based measurements of arterial and venous tortuosity (combined), and a large circular cropped image (with radius 6 times the disc diameter), provided the highest diagnostic accuracy. The i-ROP system achieved 95% accuracy for classifying preplus and plus disease compared to the reference standard. This was comparable to the performance of the 3 individual experts (96%, 94%, 92%), and significantly higher than the mean performance of 31 nonexperts (81%). CONCLUSIONS: This comprehensive analysis of computer-based plus disease suggests that it may be feasible to develop a fully-automated system based on wide-angle retinal images that performs comparably to expert graders at three-level plus disease discrimination. TRANSLATIONAL RELEVANCE: Computer-based image analysis, using objective and quantitative retinal vascular features, has potential to complement clinical ROP diagnosis by ophthalmologists.
Entities:
Keywords:
computer-based image analysis; machine learning; retinopathy of prematurity
Authors: Don Julian De Silva; Ken D Cocker; Gordon Lau; Simon T Clay; Alistair R Fielder; Merrick J Moseley Journal: Invest Ophthalmol Vis Sci Date: 2006-11 Impact factor: 4.799
Authors: Clare M Wilson; Kenneth D Cocker; Merrick J Moseley; Carl Paterson; Simon T Clay; William E Schulenburg; Monte D Mills; Anna L Ells; Kim H Parker; Graham E Quinn; Alistair R Fielder; Jeffrey Ng Journal: Invest Ophthalmol Vis Sci Date: 2008-04-11 Impact factor: 4.799
Authors: Jane S Myung; Robison Vernon Paul Chan; Michael J Espiritu; Steven L Williams; David B Granet; Thomas C Lee; David J Weissgold; Michael F Chiang Journal: J AAPOS Date: 2011-12 Impact factor: 1.220
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: Esra Ataer-Cansizoglu; Jayashree Kalpathy-Cramer; Susan Ostmo; Karyn Jonas; R V Paul Chan; J Peter Campbell; Michael F Chiang; Deniz Erdogmus Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2016-08
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: 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: J Peter Campbell; Esra Ataer-Cansizoglu; Veronica Bolon-Canedo; Alican Bozkurt; Deniz Erdogmus; Jayashree Kalpathy-Cramer; Samir N Patel; James D Reynolds; Jason Horowitz; Kelly Hutcheson; Michael Shapiro; Michael X Repka; Phillip Ferrone; Kimberly Drenser; Maria Ana Martinez-Castellanos; Susan Ostmo; Karyn Jonas; R V Paul Chan; Michael F Chiang Journal: JAMA Ophthalmol Date: 2016-06-01 Impact factor: 7.389
Authors: Aaron S Coyner; Ryan Swan; James M Brown; Jayashree Kalpathy-Cramer; Sang Jin Kim; J Peter Campbell; Karyn E Jonas; Susan Ostmo; R V Paul Chan; Michael F Chiang Journal: AMIA Annu Symp Proc Date: 2018-12-05
Authors: Aaron S Coyner; Ryan Swan; J Peter Campbell; Susan Ostmo; James M Brown; Jayashree Kalpathy-Cramer; Sang Jin Kim; Karyn E Jonas; R V Paul Chan; Michael F Chiang Journal: Ophthalmol Retina Date: 2019-01-31
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