Can deep learning improve the automatic segmentation of deep foveal avascular zone in optical coherence tomography angiography?

• Published in: Biomedical signal processing and control Vol. 66; p. 102456
• Main Authors: Guo, Menglin, Zhao, Mei, Cheong, Allen MY, Corvi, Federico, Chen, Xin, Chen, Siping, Zhou, Yongjin, Lam, Andrew KC
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2021
• Subjects: Automatic segmentation; Deep foveal avascular zone; Deep learning; Optical coherence tomography angiography; Deep learning; Deep foveal avascular zone; Automatic segmentation; Optical coherence tomography angiography
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2021.102456

•The first study applied deep learning techniques to the segmentation of the deep foveal avascular zone (dFAZ).•The proposed method, based on an encoder-decoder network, outperformed 3 classic and 2 state-of-the-art networks.•Boundary alignment and supervision modules improved the accuracy of locating the dFAZ and provided segmentation with smooth boundaries.•This objective, repeatable, and reliable tool for dFAZ segmentation is expected to save clinician time and boost related investigations. Optical coherence tomography angiography (OCTA) is extensively used for visualizing retinal vasculature, including the foveal avascular zone (FAZ). Assessment of the FAZ is critical in the diagnosis and management of various retinal diseases. Accurately segmenting the FAZ in the deep retinal layer (dFAZ) is very challenging due to unclear capillary terminals. In this study, a customized encoder-decoder deep learning network was used for dFAZ segmentation. Six-fold cross-validation was performed on a total of 80 subjects (63 healthy subjects and 17 diabetic retinopathy subjects). The proposed method obtained an average Dice of 0.88 and an average Hausdorff distance of 17.79, suggesting the dFAZ was accurately segmented. The proposed method is expected to realize good clinical application value by providing an objective and faster and spatially-quantitative preparation of dFAZ-related investigations.