Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 42, Issue 11, Pages 3140-3154Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2023.3240757
Keywords
Retina; Image segmentation; Surface morphology; Feature extraction; Surface reconstruction; Decorrelation; Pathology; Retinal layer detection; choroidal neovascularization segmentation; graph attention U-Net
Ask authors/readers for more resources
In this paper, a novel approach called graph attention U-Net (GA-UNet) is proposed for retinal layer surface detection and CNV segmentation in OCT images. The method addresses the challenge of retinal layer deformation caused by CNV and achieves improved performance through the use of graph attention encoder and graph decorrelation module. The proposed approach also introduces a new loss function to preserve the correct topological order and boundary continuity of retinal layers. Experimental results demonstrate that the proposed model outperforms existing methods and achieves new state of the art on the datasets.
Choroidal neovascularization (CNV) is a typical symptom of age-related macular degeneration (AMD) and is one of the leading causes for blindness. Accurate segmentation of CNV and detection of retinal layers are critical for eye disease diagnosis and monitoring. In this paper, we propose a novel graph attention U-Net (GA-UNet) for retinal layer surface detection and CNV segmentation in optical coherence tomography (OCT) images. Due to retinal layer deformation caused by CNV, it is challenging for existing models to segment CNV and detect retinal layer surfaces with the correct topological order. We propose two novel modules to address the challenge. The first module is a graph attention encoder (GAE) in a U-Net model that automatically integrates topological and pathological knowledge of retinal layers into the U-Net structure to achieve effective feature embedding. The second module is a graph decorrelation module (GDM) that takes reconstructed features by the decoder of the U-Net as inputs, it then decorrelates and removes information unrelated to retinal layer for improved retinal layer surface detection. In addition, we propose a new loss function to maintain the correct topological order of retinal layers and the continuity of their boundaries. The proposed model learns graph attention maps automatically during training and performs retinal layer surface detection and CNV segmentation simultaneously with the attention maps during inference. We evaluated the proposed model on our private AMD dataset and another public dataset. Experiment results show that the proposed model outperformed the competing methods for retinal layer surface detection and CNV segmentation and achieved new state of the arts on the datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available