RPS‐Net: An effective retinal image projection segmentation network for retinal vessels and foveal avascular zone based on OCTA data

Abstract

Background Optical coherence tomography angiography (OCTA) is an advanced imaging technology that can present the three‐dimensional (3D) structure of retinal vessels (RVs). Quantitative analysis of retinal vessel density and foveal avascular zone (FAZ) area is of great significance in clinical diagnosis, and the automatic semantic segmentation at the pixel level helps quantitative analysis. The existing segmentation methods cannot effectively use the volume data and projection map data of the OCTA image at the same time and lack the trade‐off between global perception and local details, which lead to problems such as discontinuity of segmentation results and deviation of morphological estimation. Purpose In order to better assist physicians in clinical diagnosis and treatment, the segmentation accuracy of RVs and FAZ needs to be further improved. In this work, we propose an effective retinal image projection segmentation network (RPS‐Net) to achieve accurate RVs and FAZ segmentation. Experiments show that this network exhibits good performance and outperforms other existing methods. Methods Our method considers three aspects. First, we use two parallel projection paths to learn global perceptual features and local supplementary details. Second, we use the dual‐way projection learning module to reduce the depth of the 3D data and learn image spatial features. Finally, we merged the two‐dimensional features learned from the volume data with the two‐dimensional projection data, and used a U‐shaped network to further learn and generate the final result. Results We validated our model on the OCTA‐500, which is a large multi‐modal, multi‐task retinal dataset. The experimental results showed that our method achieved state‐of‐the‐art performance; the mean Dice coefficients for RVs are 89.89 ± 2.60 (%) and 91.40 ± 9.18 (%) on the two subsets, while the Dice coefficients for FAZ are 91.55 ± 2.05 (%) and 97.80 ± 2.75 (%), respectively. Conclusions Our method can make full use of the information of 3D data and 2D data to generate segmented images with higher continuity and accuracy. Code is available at https://github.com/hchuanZ/MFFN/tree/master.

OVS‐Net: An effective feature extraction network for optical coherence tomography angiography vessel segmentation

“…To demonstrate the effectiveness of the OVS‐Net, we performed experiments on the OCTA‐SS 12 and the OCTA‐500, 18 and compared our OVS‐Net with several most advanced methods (including DeepLabv3+, 21 U‐Net, 3 R2U‐Net, 4 AttU‐Net, 5 CE‐Net, 6 CS‐Net, 14 Octave U‐Net, 20 FARGO, 10 IMN, 9 IPN V2+, 18 and RPS‐Net 11 ).…”

“…Peng et al 10 realized retinal vessel segmentation in OCTA images through the designed joint network FARGO. Li et al 11 proposed a network that simultaneously takes 2D and 3D data as input to segment retinal vessels. Giarratano et al 12 published an public OCTA dataset with corresponding manual labels and extensively testing different thresholding and machine learning based methods on this dataset.…”

Disentangled Representation Learning for OCTA Vessel Segmentation With Limited Training Data

“…Pissas et al [ 30 ] proposed an iterative approach for 8 × 8 mm SVP scans. Li et al [ 23 ], [ 24 ] and [ 31 ] proposed to directly output 2D vessel maps and FAZ segmentations from 3D OCTA images. Hu et al [ 32 ] investigated segmenting 3D vessels from the 3D OCTA volumes; Yu et al [ 33 ] proposed a method for segmenting vessels from 2D OCTA images and estimated the depth information for the segmented vessels to facilitate 3D vessel analysis.…”

“…The performance of vessel segmentation was evaluated on two publicly available datasets, OCTA-500 [ 24 ] and ROSE [ 25 ], both with manual delineation of vessels, and a proprietary dataset, XJU [ 18 ]. All training and evaluations were carried out on OCTA scans representing the superficial vascular plexus (SVP).…”

“…Quantitative studies of en face OCTA images usually require segmentation of the retinal vessels and capillaries. Different methods for segmenting OCTA images have been explored in recent years [ 16 ]–[ 24 ]. In particular, supervised trained deep learning methods have drawn a lot of attention, because of their success in many related applications.…”