S2S-ARSNet: Sequence-to-Sequence automatic renal segmentation network

•A Sequence-to-Sequence Automatic Renal Segmentation Network (S2S-ARSNet) is proposed for diuretic renography.•Through embedding the ConvLSTM into the Unet structure, inter-slice sequence information and intra-slice spatial information can be automatically learned. The spatial and temporal information is enriched and the segmentation results are further optimized.•A pre-trained Unet was used to generate an auxiliary mask at the intermediate moment to supervise each frame, which eliminated the interference of displacement caused by patients in clinical diagnosis.•Compared with the existing methods, the proposed method achieves a better result with a DSC of 0.9470 and an IOU of 0.9004.