Deep-learning visualization enhancement method for optical coherence tomography angiography in dermatology

Optical coherence tomography angiography (OCTA) in dermatology usually suffers from low image quality due to the highly scattering property of the skin, the complexity of cutaneous vasculature, and limited acquisition time. Deep-learning methods have achieved great success in many applications. However, the deep learning approach to improve dermatological OCTA images has not been investigated due to the requirement of high-performance OCTA systems and difficulty of obtaining high-quality images as ground truth. This study aims to generate proper datasets and develop a robust deep learning method to enhance the skin OCTA images. A swept-source skin OCTA system was employed to create low-quality and high-quality OCTA images with different scanning protocols. We propose a model named vascular visualization enhancement generative adversarial network and adopt an optimized data augmentation strategy and perceptual content loss function to achieve better image enhancement effect with small amount of training data. We demonstrate the superiority of the proposed method in skin OCTA image enhancement by quantitative and qualitative comparisons.

Automated summary

This study aims to improve the quality of dermatological optical coherence tomography angiography (OCTA) images by developing a robust deep learning method and creating proper datasets. A swept-source skin OCTA system was used to generate low-quality and high-quality images. The proposed vascular visualization enhancement generative adversarial network model, along with an optimized data augmentation strategy and perceptual content loss function, achieved better image enhancement effect with limited training data. The superiority of the proposed method in skin OCTA image enhancement was demonstrated through quantitative and qualitative comparisons.