A spatiotemporal convolution recurrent neural network for pixel-level peripapillary atrophy prediction using sequential fundus images

Mengxuan Li, Weihang Zhang, He Zhao, Yubin Xu, Jie Xu, Huiqi Li

Abstract: Highlights•A novel method for pixel-level peripapillary atrophy prediction is proposed.•A temporal memory module is proposed to fully utilize historical information.•A spatiotemporal prediction module is constructed.•It can handle the challenge of missing input data.