Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks

Freerk G Venhuizen; Bram van Ginneken; Bart Liefers; Mark J J P van Grinsven; Sascha Fauser; Carel Hoyng; Thomas Theelen; Clara I Sánchez

doi:10.1364/BOE.8.003292

Robust total retina thickness segmentation in optical coherence tomography images using convolutional neural networks

Biomed Opt Express. 2017 Jun 16;8(7):3292-3316. doi: 10.1364/BOE.8.003292. eCollection 2017 Jul 1.

Authors

Freerk G Venhuizen^{1

2}, Bram van Ginneken¹, Bart Liefers^{1

2}, Mark J J P van Grinsven^{1

2}, Sascha Fauser^{3

4}, Carel Hoyng², Thomas Theelen^{1

2}, Clara I Sánchez^{1

2}

Affiliations

¹ Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.
² Department of Ophthalmology, Radboud University Medical Center, Nijmegen, the Netherlands.
³ Roche Pharma Research and Early Development, F. Hoffmann-La Roche Ltd, Basel, Switzerland.
⁴ Cologne University Eye Clinic, Cologne, Germany.

Abstract

We developed a fully automated system using a convolutional neural network (CNN) for total retina segmentation in optical coherence tomography (OCT) that is robust to the presence of severe retinal pathology. A generalized U-net network architecture was introduced to include the large context needed to account for large retinal changes. The proposed algorithm outperformed qualitative and quantitatively two available algorithms. The algorithm accurately estimated macular thickness with an error of 14.0 ± 22.1 µm, substantially lower than the error obtained using the other algorithms (42.9 ± 116.0 µm and 27.1 ± 69.3 µm, respectively). These results highlighted the proposed algorithm's capability of modeling the wide variability in retinal appearance and obtained a robust and reliable retina segmentation even in severe pathological cases.

Keywords: (100.2960) Image analysis; (100.4996) Pattern recognition, neural networks; (110.4500) Optical coherence tomography; (170.1610) Clinical applications; (170.4470) Ophthalmology.