Recent Advanced Deep Learning Architectures for Retinal Fluid Segmentation on Optical Coherence Tomography Images

Abstract

With non-invasive and high-resolution properties, optical coherence tomography (OCT) has been widely used as a retinal imaging modality for the effective diagnosis of ophthalmic diseases. The retinal fluid is often segmented by medical experts as a pivotal biomarker to assist in the clinical diagnosis of age-related macular diseases, diabetic macular edema, and retinal vein occlusion. In recent years, the advanced machine learning methods, such as deep learning paradigms, have attracted more and more attention from academia in the retinal fluid segmentation applications. The automatic retinal fluid segmentation based on deep learning can improve the semantic segmentation accuracy and efficiency of macular change analysis, which has potential clinical implications for ophthalmic pathology detection. This article summarizes several different deep learning paradigms reported in the up-to-date literature for the retinal fluid segmentation in OCT images. The deep learning architectures include the backbone of convolutional neural network (CNN), fully convolutional network (FCN), U-shape network (U-Net), and the other hybrid computational methods. The article also provides a survey on the prevailing OCT image datasets used in recent retinal segmentation investigations. The future perspectives and some potential retinal segmentation directions are discussed in the concluding context.

Automatic Extraction of Muscle Parameters with Attention UNet in Ultrasonography

“…The Attention UNet, an improved variant of the well-established UNet [ 24 ], has been incorporated to delineate the superficial and deep aponeuroses. The original version of UNet has shown outstanding performance in biomedical problems [ 25 , 26 ], mostly due to its ability to learn from a small amount of data. The Attention UNet variant is also boosted with attention gates to highlight better salient features passed through the skip connections.…”

Multimodal deep transfer learning to predict retinal vein occlusion macular edema recurrence after anti-VEGF therapy

“…CNNs directly process images, automatically extracting features and conducting classification [ 9 ]. Their ability to extract features from OCTA images provides a promising solution for predicting disease progression and determining treatment effects [ 10 ]. Feng et al used a CNN-based transfer learning to automatically predict the effectiveness of anti-VEGF therapy using OCT images before treatment, with a prediction area under the receiver operating characteristic (ROC) curve (AUC) exceeding 0.8 [ 11 ].…”

Retinal layer and fluid segmentation in optical coherence tomography images using a hierarchical framework

“…In recent years, several novel deep learning architectures have also been proposed uniquely for fluid segmentation 16 – 18 This may be a consequence of the RETOUCH challenge, 19 which was organized in 2017 to promote research in fluid detection and segmentation in OCT volumes. In this challenge, all participating teams proposed deep learning-based methods, and most of them were variants of fully convolutional networks.…”