Automated Segmentation of Retinal Fluid Volumes From Structural and Angiographic Optical Coherence Tomography Using Deep Learning

Abstract

We proposed a deep convolutional neural network (CNN), named Retinal Fluid Segmentation Network (ReF-Net), to segment retinal fluid in diabetic macular edema (DME) in optical coherence tomography (OCT) volumes. Methods: The 3-× 3-mm OCT scans were acquired on one eye by a 70-kHz OCT commercial AngioVue system (RTVue-XR; Optovue, Inc., Fremont, CA, USA) from 51 participants in a clinical diabetic retinopathy (DR) study (45 with retinal edema and six healthy controls, age 61.3 ± 10.1 (mean ± SD), 33% female, and all DR cases were diagnosed as severe NPDR or PDR). A CNN with U-Net-like architecture was constructed to detect and segment the retinal fluid. Cross-sectional OCT and angiography (OCTA) scans were used for training and testing ReF-Net. The effect of including OCTA data for retinal fluid segmentation was investigated in this study. Volumetric retinal fluid can be constructed using the output of ReF-Net. Area-under-receiver-operating-characteristiccurve, intersection-over-union (IoU), and F1-score were calculated to evaluate the performance of ReF-Net. Results: ReF-Net shows high accuracy (F1 = 0.864 ± 0.084) in retinal fluid segmentation. The performance can be further improved (F1 = 0.892 ± 0.038) by including information from both OCTA and structural OCT. ReF-Net also shows strong robustness to shadow artifacts. Volumetric retinal fluid can provide more comprehensive information than the two-dimensional (2D) area, whether cross-sectional or en face projections. Conclusions: A deep-learning-based method can accurately segment retinal fluid volumetrically on OCT/OCTA scans with strong robustness to shadow artifacts. OCTA data can improve retinal fluid segmentation. Volumetric representations of retinal fluid are superior to 2D projections. Translational Relevance: Using a deep learning method to segment retinal fluid volumetrically has the potential to improve the diagnostic accuracy of diabetic macular edema by OCT systems.

Automated Quantification of Pathological Fluids in Neovascular Age-Related Macular Degeneration, and Its Repeatability Using Deep Learning

“…The comparison with previously reported artificial intelligence methods—Unet, ReLayNet 18 and RefNet 21 is summarized in Table 4 . On our dataset, our method outperformed these reported methods for all types of fluids in terms of Dice scores.…”

“…To compare our approach to other state-of-the-art segmentation methods (Unet, ReLayNet, 18 and RefNet 21 ), we reimplemented them and trained and tested on our datasets. The utility of the proposed architecture improvements (dilated convolutions and squeeze-excite block), as well as the effect of layer information, was evaluated in an ablation study.…”

“…The comparison with previously reported artificial intelligence methods-Unet, ReLayNet 18 and RefNet 21 is summarized in Table 4. On our dataset, B-scans/OCT volumes with a small amount of fluid tend to have lower scores, because even small mistakes of a few pixels may have a big effect on the metric.…”

Directional analysis of intensity changes for determining the existence of cyst in optical coherence tomography images

“…For instance, in 29 the authors introduce subretinal pseudocysts as a manifestation of DME disease. Also, the fluid-filled regions are considered as the specific biomarkers for DME 30 . In 31 , it has been shown that elongated cystic regions can be observed in a large percent of AMD cases.…”

Machine learning in optical coherence tomography angiography

“…. [45][46][47][48] Recent development and the implementation of quantitative OCTA features for machine learning classification indicate that OCTA images contain the necessary information to identify different retinopathies and perform disease staging. In principle, the CNN can automatically perform the feature extraction and classification, thereby reducing the burden for manual feature engineering.…”