A Deep Ensemble Learning-Based CNN Architecture for Multiclass Retinal Fluid Segmentation in OCT Images

Retinal Fluids (fluid collections) develop because of the accumulation of fluid in the retina, which may be caused by several retinal disorders, and can lead to loss of vision. Optical coherence tomography (OCT) provides non-invasive cross-sectional images of the retina and enables the visualization of different retinal abnormalities. The identification and segmentation of retinal cysts from OCT scans is gaining immense attention since the manual analysis of OCT data is time consuming and requires an experienced ophthalmologist. Identification and categorization of the retinal cysts aids in establishing the pathophysiology of various retinal diseases, such as macular edema, diabetic macular edema, and age-related macular degeneration. Hence, an automatic algorithm for the segmentation and detection of retinal cysts would be of great value to the ophthalmologists. In this study, we have proposed a convolutional neural network-based deep ensemble architecture that can segment the three different types of retinal cysts from the retinal OCT images. The quantitative and qualitative performance of the model was evaluated using the publicly available RETOUCH challenge dataset. The proposed model outperformed the state-of-the-art methods, with an overall improvement of 1.8%.

Automated summary

Retinal fluids develop due to fluid accumulation in the retina, which can be caused by various retinal disorders and lead to vision loss. Optical coherence tomography (OCT) allows for non-invasive imaging of the retina and visualization of retinal abnormalities. Identifying and segmenting retinal cysts from OCT scans is important for understanding retinal diseases and an automatic algorithm would be valuable to ophthalmologists. In this study, a convolutional neural network-based deep ensemble architecture was proposed and evaluated using a publicly available dataset, outperforming state-of-the-art methods with a 1.8% overall improvement.