B S Gerendas1, S M Waldstein1, U Schmidt-Erfurth2. 1. Univ.-Klinik für Augenheilkunde und Optometrie, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich. 2. Univ.-Klinik für Augenheilkunde und Optometrie, Medizinische Universität Wien, Währinger Gürtel 18-20, 1090, Wien, Österreich. ursula.schmidt-erfurth@meduniwien.ac.at.
Abstract
BACKGROUND: Modern retinal imaging creates gigantic amounts of data (big data) of anatomic information. At the same time patient numbers and interventions are increasing exponentially. OBJECTIVE: Introduction of artificial intelligence (AI) for optimization of personalized therapy and diagnosis. MATERIAL AND METHODS: Deep learning was introduced for automated segmentation and recognition of risk factors and activity levels in retinal diseases. RESULTS: Automated algorithms enable the precise identification and quantification of retinal fluid in all compartments. Early detection of retinopathy in diabetes or glaucoma or risk determination for the development of age-related macular degeneration (AMD) are possible as well as an individual visual prognosis and evaluation of the need for retreatment in intravitreal injection therapy. CONCLUSION: Methods using AI constitute a breakthrough perspective for the introduction of individualized medicine and optimization of diagnosis and therapy, screening and prognosis.
BACKGROUND: Modern retinal imaging creates gigantic amounts of data (big data) of anatomic information. At the same time patient numbers and interventions are increasing exponentially. OBJECTIVE: Introduction of artificial intelligence (AI) for optimization of personalized therapy and diagnosis. MATERIAL AND METHODS: Deep learning was introduced for automated segmentation and recognition of risk factors and activity levels in retinal diseases. RESULTS: Automated algorithms enable the precise identification and quantification of retinal fluid in all compartments. Early detection of retinopathy in diabetes or glaucoma or risk determination for the development of age-related macular degeneration (AMD) are possible as well as an individual visual prognosis and evaluation of the need for retreatment in intravitreal injection therapy. CONCLUSION: Methods using AI constitute a breakthrough perspective for the introduction of individualized medicine and optimization of diagnosis and therapy, screening and prognosis.
Authors: Thomas Schlegl; Sebastian M Waldstein; Hrvoje Bogunovic; Franz Endstraßer; Amir Sadeghipour; Ana-Maria Philip; Dominika Podkowinski; Bianca S Gerendas; Georg Langs; Ursula Schmidt-Erfurth Journal: Ophthalmology Date: 2017-12-08 Impact factor: 12.079
Authors: Wolf-Dieter Vogl; Sebastian M Waldstein; Bianca S Gerendas; Ursula Schmidt-Erfurth; Georg Langs Journal: IEEE Trans Med Imaging Date: 2017-05-02 Impact factor: 10.048
Authors: Su Wang; Hongying Lilian Tang; Lutfiah Ismail Al Turk; Yin Hu; Saeid Sanei; George Michael Saleh; Tunde Peto Journal: IEEE Trans Biomed Eng Date: 2016-06-27 Impact factor: 4.538
Authors: Luis de Sisternes; Noah Simon; Robert Tibshirani; Theodore Leng; Daniel L Rubin Journal: Invest Ophthalmol Vis Sci Date: 2014-10-09 Impact factor: 4.799
Authors: Mark J J P van Grinsven; Yara T E Lechanteur; Johannes P H van de Ven; Bram van Ginneken; Carel B Hoyng; Thomas Theelen; Clara I Sánchez Journal: Invest Ophthalmol Vis Sci Date: 2013-04-30 Impact factor: 4.799
Authors: Ferdinand G Schlanitz; Bernhard Baumann; Michael Kundi; Stefan Sacu; Magdalena Baratsits; Ulrike Scheschy; Abtin Shahlaee; Tamara J Mittermüller; Alessio Montuoro; Philipp Roberts; Michael Pircher; Christoph K Hitzenberger; Ursula Schmidt-Erfurth Journal: Br J Ophthalmol Date: 2016-04-04 Impact factor: 4.638