Mark Christopher1, Michael D Abràmoff2, Li Tang3, Mae O Gordon4, Michael A Kass5, Donald L Budenz6, John H Fingert7, Todd E Scheetz8. 1. Stephen A. Wynn Institute for Vision Research, University of Iowa, Iowa City, Iowa, United States 2Department of Biomedical Engineering, University of Iowa, Iowa City, Iowa, United States. 2. Stephen A. Wynn Institute for Vision Research, University of Iowa, Iowa City, Iowa, United States 2Department of Biomedical Engineering, University of Iowa, Iowa City, Iowa, United States 3Department of Electrical and Computer Engineering, University of I. 3. Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, Iowa, United States. 4. Division of Biostatistics, Washington University, St. Louis, Missouri, United States 7Department of Ophthalmology and Visual Sciences, Washington University, St. Louis, Missouri, United States. 5. Department of Ophthalmology and Visual Sciences, Washington University, St. Louis, Missouri, United States. 6. Department of Ophthalmology, University of North Carolina, Chapel Hill, North Carolina, United States. 7. Stephen A. Wynn Institute for Vision Research, University of Iowa, Iowa City, Iowa, United States 4Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, Iowa, United States. 8. Stephen A. Wynn Institute for Vision Research, University of Iowa, Iowa City, Iowa, United States 2Department of Biomedical Engineering, University of Iowa, Iowa City, Iowa, United States 4Department of Ophthalmology and Visual Sciences, University of Iow.
Abstract
PURPOSE: To identify objective, quantitative optic nerve head (ONH) structural features and model the contributions of glaucoma. METHODS: Baseline stereoscopic optic disc images of 1635 glaucoma-free participants at risk for developing primary open-angle glaucoma (POAG) were collected as part of the Ocular Hypertension Treatment Study. A stereo correspondence algorithm designed for fundus images was applied to extract the three-dimensional (3D) information about the ONH. Principal component analysis was used to identify ONH 3D structural features and the contributions of demographic features, clinical variables, and disease were modeled using linear regression and linear component analysis. The computationally identified features were evaluated based on associations with glaucoma and ability to predict which participants would develop POAG. RESULTS: The computationally identified features were significantly associated with future POAG, POAG-related demographics (age, ethnicity), and clinical measurements (horizontal and vertical cup-to-disc ratio, central corneal thickness, and refraction). Models predicting future POAG development using the OHTS baseline data and STEP features achieved an AUC of 0.722 in cross-validation testing. This was a significant improvement over using only demographics (age, sex, and ethnicity), which had an AUC of 0.599. CONCLUSIONS: Methods for identifying objective, quantitative measurements of 3D ONH structure were developed using a large dataset. The identified features were significantly associated with POAG and POAG-related variables. Further, these features increased predictive model accuracy in predicting future POAG. The results indicate that the computationally identified features might be useful in POAG early screening programs or as endophenotypes to investigate POAG genetics.
PURPOSE: To identify objective, quantitative optic nerve head (ONH) structural features and model the contributions of glaucoma. METHODS: Baseline stereoscopic optic disc images of 1635 glaucoma-free participants at risk for developing primary open-angle glaucoma (POAG) were collected as part of the Ocular Hypertension Treatment Study. A stereo correspondence algorithm designed for fundus images was applied to extract the three-dimensional (3D) information about the ONH. Principal component analysis was used to identify ONH 3D structural features and the contributions of demographic features, clinical variables, and disease were modeled using linear regression and linear component analysis. The computationally identified features were evaluated based on associations with glaucoma and ability to predict which participants would develop POAG. RESULTS: The computationally identified features were significantly associated with future POAG, POAG-related demographics (age, ethnicity), and clinical measurements (horizontal and vertical cup-to-disc ratio, central corneal thickness, and refraction). Models predicting future POAG development using the OHTS baseline data and STEP features achieved an AUC of 0.722 in cross-validation testing. This was a significant improvement over using only demographics (age, sex, and ethnicity), which had an AUC of 0.599. CONCLUSIONS: Methods for identifying objective, quantitative measurements of 3D ONH structure were developed using a large dataset. The identified features were significantly associated with POAG and POAG-related variables. Further, these features increased predictive model accuracy in predicting future POAG. The results indicate that the computationally identified features might be useful in POAG early screening programs or as endophenotypes to investigate POAG genetics.
Authors: Jac Charlesworth; Patricia L Kramer; Tom Dyer; Victor Diego; John R Samples; Jamie E Craig; David A Mackey; Alex W Hewitt; John Blangero; Mary K Wirtz Journal: Invest Ophthalmol Vis Sci Date: 2010-03-17 Impact factor: 4.799
Authors: Li Tang; Todd E Scheetz; David A Mackey; Alex W Hewitt; John H Fingert; Young H Kwon; Gwenole Quellec; Joseph M Reinhardt; Michael D Abràmoff Journal: Invest Ophthalmol Vis Sci Date: 2010-05-26 Impact factor: 4.799
Authors: Wishal D Ramdas; Leonieke M E van Koolwijk; Hans G Lemij; Francesca Pasutto; Angela J Cree; Gudmar Thorleifsson; Sarah F Janssen; Ten Brink Jacoline; Najaf Amin; Fernando Rivadeneira; Roger C W Wolfs; G Bragi Walters; Fridbert Jonasson; Nicole Weisschuh; Christian Y Mardin; Jane Gibson; Richard H C Zegers; Albert Hofman; Paulus T V M de Jong; André G Uitterlinden; Ben A Oostra; Unnur Thorsteinsdottir; Eugen Gramer; Ulrich C Welgen-Lüssen; James F Kirwan; Arthur A B Bergen; André Reis; Kari Stefansson; Andrew J Lotery; Johannes R Vingerling; Nomdo M Jansonius; Caroline C W Klaver; Cornelia M van Duijn Journal: Hum Mol Genet Date: 2011-03-22 Impact factor: 6.150
Authors: Chiea Chuen Khor; Wishal D Ramdas; Eranga N Vithana; Belinda K Cornes; Xueling Sim; Wan-Ting Tay; Seang-Mei Saw; Yingfeng Zheng; Raghavan Lavanya; Renyi Wu; Jie Jin Wang; Paul Mitchell; André G Uitterlinden; Fernando Rivadeneira; Yik-Ying Teo; Kee-Seng Chia; Mark Seielstad; Martin Hibberd; Johannes R Vingerling; Caroline C W Klaver; Nomdo M Jansonius; E-Shyong Tai; Tien-Yin Wong; Cornelia M van Duijn; Tin Aung Journal: Hum Mol Genet Date: 2011-02-09 Impact factor: 6.150
Authors: Paul G Sanfilippo; Andrea Cardini; Ian A Sigal; Jonathan B Ruddle; Brian E Chua; Alex W Hewitt; David A Mackey Journal: Exp Eye Res Date: 2010-06-22 Impact factor: 3.467
Authors: John H Fingert; Alan L Robin; Jennifer L Stone; Ben R Roos; Lea K Davis; Todd E Scheetz; Steve R Bennett; Thomas H Wassink; Young H Kwon; Wallace L M Alward; Robert F Mullins; Val C Sheffield; Edwin M Stone Journal: Hum Mol Genet Date: 2011-03-29 Impact factor: 6.150
Authors: Wishal D Ramdas; Leonieke M E van Koolwijk; M Kamran Ikram; Nomdo M Jansonius; Paulus T V M de Jong; Arthur A B Bergen; Aaron Isaacs; Najaf Amin; Yurii S Aulchenko; Roger C W Wolfs; Albert Hofman; Fernando Rivadeneira; Ben A Oostra; Andre G Uitterlinden; Pirro Hysi; Christopher J Hammond; Hans G Lemij; Johannes R Vingerling; Caroline C W Klaver; Cornelia M van Duijn Journal: PLoS Genet Date: 2010-06-10 Impact factor: 5.917
Authors: Nicholas G Strouthidis; Stuart K Gardiner; Christos Sinapis; Claude F Burgoyne; David F Garway-Heath Journal: Invest Ophthalmol Vis Sci Date: 2009-04-08 Impact factor: 4.799
Authors: Mark Christopher; Akram Belghith; Robert N Weinreb; Christopher Bowd; Michael H Goldbaum; Luke J Saunders; Felipe A Medeiros; Linda M Zangwill Journal: Invest Ophthalmol Vis Sci Date: 2018-06-01 Impact factor: 4.799