1. Automatically Enhanced OCT Scans of the Retina: A proof of concept study
- Author
-
Carlos Ciller, Stefanos Apostolopoulos, Marion R. Munk, Shern Shiou Tan, Sandro De Zanet, Andreas Ebneter, José L. P. Ordóñez, Martin S. Zinkernagel, Raphael Sznitman, Sebastian Wolf, and Jazmín Salas
- Subjects
genetic structures ,Image quality ,Noise reduction ,lcsh:Medicine ,610 Medicine & health ,Drusen ,Proof of Concept Study ,01 natural sciences ,Retina ,Article ,010309 optics ,03 medical and health sciences ,0302 clinical medicine ,Software ,0103 physical sciences ,medicine ,Humans ,Fluorescein Angiography ,Optical techniques ,lcsh:Science ,Ground truth ,Multidisciplinary ,Artificial neural network ,business.industry ,lcsh:R ,Pattern recognition ,medicine.disease ,eye diseases ,Ophthalmoscopy ,medicine.anatomical_structure ,Proof of concept ,570 Life sciences ,biology ,lcsh:Q ,Neural Networks, Computer ,Medical imaging ,Artificial intelligence ,sense organs ,business ,Algorithms ,Tomography, Optical Coherence ,030217 neurology & neurosurgery - Abstract
In this work we evaluated a postprocessing, customized automatic retinal OCT B-scan enhancement software for noise reduction, contrast enhancement and improved depth quality applicable to Heidelberg Engineering Spectralis OCT devices. A trained deep neural network was used to process images from an OCT dataset with ground truth biomarker gradings. Performance was assessed by the evaluation of two expert graders who evaluated image quality for B-scan with a clear preference for enhanced over original images. Objective measures such as SNR and noise estimation showed a significant improvement in quality. Presence grading of seven biomarkers IRF, SRF, ERM, Drusen, RPD, GA and iRORA resulted in similar intergrader agreement. Intergrader agreement was also compared with improvement in IRF and RPD, and disagreement in high variance biomarkers such as GA and iRORA.
- Published
- 2020
- Full Text
- View/download PDF