TISS-net: Brain tumor image synthesis and segmentation using cascaded dual-task networks and error-prediction consistency.

•To deal with missing modalities for brain tumor segmentation, we propose a novel framework TISS-Net that obtains the synthesized target modality and segmentation of brain tumors end-to-end.•We propose a novel dual-task-regularized generator that simultaneously obtains a synthesized target modality and a coarse segmentation, which is further regularized by a tumor-aware synthesis loss with perceptibility regularization.•A dual-task segmentor to predict a refined segmentation and error in the coarse segmentation simultaneously, where a consistency between these two predictions is introduced for regularization.•Experiments on two public brain tumor datasets showed that our method outperformed state-of-the-art image synthesis-based segmentation methods.