Matthias Gutfleisch1,2, Oliver Ester3, Sökmen Aydin3, Martin Quassowski3, Georg Spital4,5, Albrecht Lommatzsch4,5,6,7, Kai Rothaus4,5, Adam Michael Dubis8, Daniel Pauleikhoff4,5,6,7. 1. Department of Ophthalmology, St. Franziskus-Hospital, Hohenzollernring 74, 48145, Muenster, Germany. Matthias.Gutfleisch@augen-franziskus.de. 2. M3 Macula Monitor Muenster GmbH & Co KG, Muenster, Germany. Matthias.Gutfleisch@augen-franziskus.de. 3. Westphalia DataLab GmbH, Muenster, Germany. 4. Department of Ophthalmology, St. Franziskus-Hospital, Hohenzollernring 74, 48145, Muenster, Germany. 5. M3 Macula Monitor Muenster GmbH & Co KG, Muenster, Germany. 6. Department of Ophthalmology, University Duisburg-Essen, Essen, Germany. 7. Achim Wessing Institute of Ophthalmic Diagnostic, University Duisburg-Essen, Essen, Germany. 8. NIHR Biomedical Resource Centre, UCL Institute of Ophthalmology and Moorfields Eye Hospital NHS Trust, London, United Kingdom.
Abstract
PURPOSE: Anti-vascular endothelial growth factor (Anti-VEGF) therapy is currently seen as the standard for treatment of neovascular AMD (nAMD). However, while treatments are highly effective, decisions for initial treatment and retreatment are often challenging for non-retina specialists. The purpose of this study is to develop convolutional neural networks (CNN) that can differentiate treatment indicated presentations of nAMD for referral to treatment centre based solely on SD-OCT. This provides the basis for developing an applicable medical decision support system subsequently. METHODS: SD-OCT volumes of a consecutive real-life cohort of 1503 nAMD patients were analysed and two experiments were carried out. To differentiate between no treatment class vs. initial treatment nAMD class and stabilised nAMD vs. active nAMD, two novel CNNs, based on SD-OCT volume scans, were developed and tested for robustness and performance. In a step towards explainable artificial intelligence (AI), saliency maps of the SD-OCT volume scans of 24 initial indication decisions with a predicted probability of > 97.5% were analysed (score 0-2 in respect to staining intensity). An AI benchmark against retina specialists was performed. RESULTS: At the first experiment, the area under curve (AUC) of the receiver-operating characteristic (ROC) for the differentiation of patients for the initial analysis was 0.927 (standard deviation (SD): 0.018), for the second experiment (retreatment analysis) 0.865 (SD: 0.027). The results were robust to downsampling (¼ of the original resolution) and cross-validation (tenfold). In addition, there was a high correlation between the AI analysis and expert opinion in a sample of 102 cases for differentiation of patients needing treatment (κ = 0.824). On saliency maps, the relevant structures for individual initial indication decisions were the retina/vitreous interface, subretinal space, intraretinal cysts, subretinal pigment epithelium space, and the choroid. CONCLUSION: The developed AI algorithms can define and differentiate presentations of AMD, which should be referred for treatment or retreatment with anti-VEGF therapy. This may support non-retina specialists to interpret SD-OCT on expert opinion level. The individual decision of the algorithm can be supervised by saliency maps.
PURPOSE: Anti-vascular endothelial growth factor (Anti-VEGF) therapy is currently seen as the standard for treatment of neovascular AMD (nAMD). However, while treatments are highly effective, decisions for initial treatment and retreatment are often challenging for non-retina specialists. The purpose of this study is to develop convolutional neural networks (CNN) that can differentiate treatment indicated presentations of nAMD for referral to treatment centre based solely on SD-OCT. This provides the basis for developing an applicable medical decision support system subsequently. METHODS: SD-OCT volumes of a consecutive real-life cohort of 1503 nAMD patients were analysed and two experiments were carried out. To differentiate between no treatment class vs. initial treatment nAMD class and stabilised nAMD vs. active nAMD, two novel CNNs, based on SD-OCT volume scans, were developed and tested for robustness and performance. In a step towards explainable artificial intelligence (AI), saliency maps of the SD-OCT volume scans of 24 initial indication decisions with a predicted probability of > 97.5% were analysed (score 0-2 in respect to staining intensity). An AI benchmark against retina specialists was performed. RESULTS: At the first experiment, the area under curve (AUC) of the receiver-operating characteristic (ROC) for the differentiation of patients for the initial analysis was 0.927 (standard deviation (SD): 0.018), for the second experiment (retreatment analysis) 0.865 (SD: 0.027). The results were robust to downsampling (¼ of the original resolution) and cross-validation (tenfold). In addition, there was a high correlation between the AI analysis and expert opinion in a sample of 102 cases for differentiation of patients needing treatment (κ = 0.824). On saliency maps, the relevant structures for individual initial indication decisions were the retina/vitreous interface, subretinal space, intraretinal cysts, subretinal pigment epithelium space, and the choroid. CONCLUSION: The developed AI algorithms can define and differentiate presentations of AMD, which should be referred for treatment or retreatment with anti-VEGF therapy. This may support non-retina specialists to interpret SD-OCT on expert opinion level. The individual decision of the algorithm can be supervised by saliency maps.
Authors: Daniel B Russakoff; Ali Lamin; Jonathan D Oakley; Adam M Dubis; Sobha Sivaprasad Journal: Invest Ophthalmol Vis Sci Date: 2019-02-01 Impact factor: 4.799
Authors: David M Brown; Peter K Kaiser; Mark Michels; Gisele Soubrane; Jeffrey S Heier; Robert Y Kim; Judy P Sy; Susan Schneider Journal: N Engl J Med Date: 2006-10-05 Impact factor: 91.245
Authors: J Stasch-Bouws; S M Eller-Woywod; S Schmickler; J Inderfurth; P Hoffmann; C Ohlmeyer; B Kammering; D Pauleikhoff Journal: Ophthalmologe Date: 2020-04 Impact factor: 1.059
Authors: Philippe M Burlina; Neil Joshi; Michael Pekala; Katia D Pacheco; David E Freund; Neil M Bressler Journal: JAMA Ophthalmol Date: 2017-11-01 Impact factor: 7.389
Authors: Christian K Brinkmann; Petrus Chang; Tina Schick; Britta Heimes; Jessica Vögeler; Birgit Haegele; Bernd Kirchhof; Frank G Holz; Daniel Pauleikhoff; Focke Ziemssen; Sandra Liakopoulos; Georg Spital; Steffen Schmitz-Valckenberg Journal: Ophthalmologe Date: 2019-08 Impact factor: 1.059
Authors: Jeffrey De Fauw; Joseph R Ledsam; Bernardino Romera-Paredes; Stanislav Nikolov; Nenad Tomasev; Sam Blackwell; Harry Askham; Xavier Glorot; Brendan O'Donoghue; Daniel Visentin; George van den Driessche; Balaji Lakshminarayanan; Clemens Meyer; Faith Mackinder; Simon Bouton; Kareem Ayoub; Reena Chopra; Dominic King; Alan Karthikesalingam; Cían O Hughes; Rosalind Raine; Julian Hughes; Dawn A Sim; Catherine Egan; Adnan Tufail; Hugh Montgomery; Demis Hassabis; Geraint Rees; Trevor Back; Peng T Khaw; Mustafa Suleyman; Julien Cornebise; Pearse A Keane; Olaf Ronneberger Journal: Nat Med Date: 2018-08-13 Impact factor: 53.440