eprintid: 10049640 rev_number: 42 eprint_status: archive userid: 608 dir: disk0/10/04/96/40 datestamp: 2018-11-28 13:56:07 lastmod: 2021-09-25 23:30:32 status_changed: 2018-11-29 11:11:25 type: article metadata_visibility: show creators_name: Davidson, B creators_name: Kalitzeos, A creators_name: Carroll, J creators_name: Dubra, A creators_name: Ourselin, S creators_name: Michaelides, M creators_name: Bergeles, C title: Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning ispublished: pub subjects: MOOR divisions: UCL divisions: B02 divisions: C07 divisions: D08 divisions: B04 divisions: C05 divisions: F42 divisions: C06 divisions: F60 note: Copyright © The Author(s) 2018. This article is licensed under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/). abstract: We present a robust deep learning framework for the automatic localisation of cone photoreceptor cells in Adaptive Optics Scanning Light Ophthalmoscope (AOSLO) split-detection images. Monitoring cone photoreceptors with AOSLO imaging grants an excellent view into retinal structure and health, provides new perspectives into well known pathologies, and allows clinicians to monitor the effectiveness of experimental treatments. The MultiDimensional Recurrent Neural Network (MDRNN) approach developed in this paper is the first method capable of reliably and automatically identifying cones in both healthy retinas and retinas afflicted with Stargardt disease. Therefore, it represents a leap forward in the computational image processing of AOSLO images, and can provide clinical support in on-going longitudinal studies of disease progression and therapy. We validate our method using images from healthy subjects and subjects with the inherited retinal pathology Stargardt disease, which significantly alters image quality and cone density. We conduct a thorough comparison of our method with current state-of-the-art methods, and demonstrate that the proposed approach is both more accurate and appreciably faster in localizing cones. As further validation to the method’s robustness, we demonstrate it can be successfully applied to images of retinas with pathologies not present in the training data: achromatopsia, and retinitis pigmentosa. date: 2018-05-21 date_type: published publisher: NATURE PUBLISHING GROUP official_url: https://doi.org/10.1038/s41598-018-26350-3 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1558385 doi: 10.1038/s41598-018-26350-3 lyricists_name: Bergeles, Christos lyricists_name: Davidson, Benjamin lyricists_name: Kalitzeos, Angelos lyricists_name: Michaelides, Michel lyricists_id: CBERG35 lyricists_id: BDAVI35 lyricists_id: AKALI23 lyricists_id: MMICH14 actors_name: Bracey, Alan actors_id: ABBRA90 actors_role: owner full_text_status: public publication: Scientific Reports volume: 8 article_number: 7911 pages: 13 issn: 2045-2322 citation: Davidson, B; Kalitzeos, A; Carroll, J; Dubra, A; Ourselin, S; Michaelides, M; Bergeles, C; (2018) Automatic Cone Photoreceptor Localisation in Healthy and Stargardt Afflicted Retinas Using Deep Learning. Scientific Reports , 8 , Article 7911. 10.1038/s41598-018-26350-3 <https://doi.org/10.1038/s41598-018-26350-3>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10049640/1/s41598-018-26350-3.pdf