Gererating Twin VFs of Unlabeled and Unpaired VF through Generative Model

The accurate analysis and denoising of visual field (VF) measurements play a crucial role in the diagnosis and monitoring of glaucoma, a widespread optic disease leading to visual impairment. This study presents a novel approach that harnesses generative models, specifically the Variational Autoencoder (VAE) and conditional Generative Adversarial Network (cGAN), to address the challenges of denoising VFs posed by the scarcity of labeled and paired VF data. By generating twin VFs whose patterns are consistent with the input of generative models, the denoising network can be trained using these generated twin data under the framework of VF2VF. Thus the applicable range of VF2VF framework expands to encompass unlabeled and unpaired VF datasets. Experiments demonstrate that the denoising network, trained on cGAN-generated data, effectively enhances precision while maintaining accuracy. Furthermore, sensitivity analysis using independent validation datasets showcases the improved sensitivity of the transformed VF vectors to changes. Besides, this study delves into the influence of data volume on denoising performance and compares the performance of VAE and cGAN models. While the method requires extensive generative network training, it unveils promising avenues for advancing VF analysis and denoising by capitalizing on the power of generative models in the absence of labeled and paired data.