Deep Learning based retinal layer segmentation in optical coherence tomography scans of patients with inherited retinal diseases
Authors:
- Franziska EckardtFEFranziska Eckardt
- Nastassya HorlavaNastassya Horlava
- Johannes SchiefelbeinJSJohannes Schiefelbein
- Ben AsaniBABen Asani
- Stylianos MichalakisStylianos Michalakis
- Claudia PriglingerCPClaudia Priglinger
- Daniel KeeserDKDaniel Keeser
- Nikolaos KoutsoulerisNKNikolaos Koutsouleris
- Siegfried G. PriglingerSPSiegfried G. Priglinger
- Fabian J TheisFTFabian J Theis
Preprint
Abstract
Background: On optical coherence tomography (OCT) scans of patients with inherited retinal diseases (IRDs), the outer nuclear layer (ONL) thickness measurement has been well established as a surrogate marker for photoreceptor preservation. Current automatic segmentation tools fail in OCT segmentation in IRDs, and manual segmentation is time consuming. Methods and Material: Patients with IRD and the availability of an OCT scan were screened for the present study. Additionally, OCT scans of patients without retinal disease were included, to provide training data for the artificial intelligence (AI). We trained a U-net based model on healthy patients and applied a domain adaption technique to IRD patients’ scans. Results: We established an AI-based image segmentation algorithm that reliably segments the ONL in OCT scans of IRD patients. In a test dataset, the dice-score of the algorithm was 98.7% . Furthermore, we generated thickness maps of the full retinal thickness and the ONL layer for each patient. Conclusion: Accurate segmentation of anatomical layers on OCT scans plays a crucial role for predictive models linking retinal structure to visual function. The here-presented OCT image segmentation algorithm could provide the basis for further studies on IRDs.Keywords
This publication has 23 references indexed in Scilit:
- Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus PhotographsOphthalmology, 2018
- Deep learning for the segmentation of preserved photoreceptors on en face optical coherence tomography in two inherited retinal diseasesBiomedical Optics Express, 2018
- Efficacy and safety of voretigene neparvovec (AAV2-hRPE65v2) in patients with RPE65 -mediated inherited retinal dystrophy: a randomised, controlled, open-label, phase 3 trialThe Lancet, 2017
- Deep Learning Is Effective for Classifying Normal versus Age-Related Macular Degeneration OCT ImagesOphthalmology Retina, 2017
- Retinal Imaging and Image AnalysisIEEE Reviews in Biomedical Engineering, 2010
- Defining the Residual Vision in Leber Congenital Amaurosis Caused byRPE65MutationsInvestigative Ophthalmology & Visual Science, 2009
- Automated 3-D Intraretinal Layer Segmentation of Macular Spectral-Domain Optical Coherence Tomography ImagesIEEE Transactions on Medical Imaging, 2009
- Retinal Laminar Architecture in Human Retinitis Pigmentosa Caused byRhodopsinGene MutationsInvestigative Ophthalmology & Visual Science, 2008
- RETINAL THICKNESS AND VISUAL THRESHOLDS MEASURED IN PATIENTS WITH RETINITIS PIGMENTOSARetina, 2007
- Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic ApproachIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005