Automated segmentation of choroidal neovascularization on optical coherence tomography angiography images of neovascular age-related macular degeneration patients based on deep learning

Optical coherence tomography angiography (OCTA) has been a frequently used diagnostic method in neovascular age-related macular degeneration (nAMD) because it is non-invasive and provides a comprehensive view of the characteristic lesion, choroidal neovascularization (CNV). In order to study its characteristics, an automated method is needed to identify and quantify CNV. Here, we have developed a deep learning model that can automatically segment CNV regions from OCTA images. Specifically, we use the ResNeSt block as our basic backbone, which learns better feature representations through group convolution and split-attention mechanisms. In addition, considering the varying sizes of CNVs, we developed a spatial pyramid pooling module, which uses different receptive fields to enable the model to extract contextual information at different scales to better segment CNVs of different sizes, thus further improving the segmentation performance of the model. Experimental results on a clinical OCTA dataset containing 116 OCTA images show that the CNV segmentation model has an AUC of 0.9476 (95% CI 0.9473-0.9479), with specificity and sensitivity of 0.9950 (95% CI 0.9945-0.9955) and 0.7271 (95% CI 0.7265-0.7277), respectively. In summary, the model has satisfactory performance in extracting CNV regions from the background of OCTA images of nAMD patients.

Automated summary

Optical coherence tomography angiography (OCTA) is a non-invasive diagnostic method commonly used in neovascular age-related macular degeneration (nAMD) to provide a comprehensive view of choroidal neovascularization (CNV). In this study, a deep learning model was developed for automatic segmentation of CNV regions from OCTA images. The model demonstrated satisfactory performance in accurately extracting CNV regions from OCTA images of nAMD patients.