PROJECT 12
OCT in advanced glaucoma: analysis of retinal tissue properties using deep learning
Why?
Glaucoma is a neurodegenerative disease of the optic nerve and the most common cause of irreversible blindness. With optical coherence tomography (OCT), changes in relevant tissues can be assessed reliably in early but not in advanced disease. Assessment of advanced disease is pivotal for, for example, making treatment decisions and for evaluating treatment effects. The aim of the project is to analyze current OCT images differently and to extend the dynamic range of OCT to advanced glaucoma.
How?
We will go beyond the current analysis approaches by (1) applying hypothesis-free analysis techniques (deep learning) to the OCT images and (2) adding focus on retinal circulation with OCT angiography. This should result in novel analysis methods for OCT and in guidelines for OCT-based progression detection in advanced glaucoma.
What can you expect?
You will gain extensive experience and expert insight into, among others, clinical ophthalmic assessment including perimetry and OCT, glaucoma care, and basic and complex data analysis, including big data analysis of medical images. You will be part of a vibrant, interdisciplinary research team and you will benefit from the wide academic exchange in national and international scientific networks.
Where?
The candidate will be located (1) in the Department of Ophthalmology of the UMCG of the University of Groningen, The Netherlands (PI: Jansonius) in close collaboration with the UMCG Data Science Center in Health (DASH; van Ooijen) and (2) the Section for Clinical and Experimental Sensory Physiology of the Department of Ophthalmology of the Otto-von-Guericke University of Magdeburg (OVGU), Germany (PI: Hoffmann). Both UMCG and OVGU have a strong focus on glaucoma and the investigation of structure and function in eye diseases.
Who are we looking for?
We are looking for a highly motivated candidate with a strong interest in the visual system, physics, mathematics, computer science, and programming.
References
- Heikka T, Cense B, Jansonius NM. Retinal layer thicknesses retrieved with different segmentation algorithms from optical coherence tomography scans acquired under different signal-to-noise ratio conditions. Biomedical optics express. 2020;11(12):7079-95. https://doi.org/10.1364/BOE.399949
- Pappelis K, Jansonius NM. Quantification and repeatability of vessel density and flux as assessed by optical coherence tomography angiography. Translational vision science & technology. 2019;8(3):3. https://doi.org/10.1167/tvst.8.3.3
- Huang H, Zhu L, Zhu W, Lin T, Los LI, Yao C, Chen X, Chen H. Algorithm for detection and quantification of hyperreflective dots on optical coherence tomography in diabetic macular edema. Frontiers in Medicine. 2021 Aug 18:1327. https://doi.org/10.3389/fmed.2021.688986
- Al-Nosairy KO, Prabhakaran GT, Pappelis K, Thieme H, Hoffmann MB. Combined multi-modal assessment of glaucomatous damage with electroretinography and optical coherence tomography/angiography. Translational vision science & technology. 2020 Nov 2;9(12):7. https://doi.org/10.1167/tvst.9.12.7
- Wong D, Chua J, Lin E, Tan B, Yao X, Chong R, Sng C, Lau A, Husain R, Aung T, Schmetterer L. Focal structure–function relationships in primary open-angle glaucoma using OCT and OCT-A measurements. Investigative ophthalmology & visual science. 2020;61(14):33. https://doi.org/10.1167/iovs.61.14.33