Highlights •Proposed an iterative residual-sharing scheme based dual-task learning framework for vessel segmentation and unenhanced CT prediction.•Presented a pseudo-labeling based self-supervised strategy for vessel segmentation using contrasting modalities (pre/post-contrast imaging), which avoids labor-intensive manual labeling of training sets.•Verified the feasibility of unenhanced CT prediction, which has the potential to eliminate the pre-contrast CT scan for radiation-dose reduction.•The vessel segmentation results obtained by the proposed dual-task method are superior compared to popular 3D vessel segmentation models and deep-learning segmentation methods.