Rubik's Cube+: A self-supervised feature learning framework for 3D medical image analysis.

•We propose a pretext task, namely Rubik's cube+, consisting of three sub-tasks, i.e., cube ordering, cube orientation and masking identification.•Experiments on the two target tasks, i.e., cerebral hemorrhage classification and brain tumor segmentation, are conducted to demonstrate the effectiveness of our Rubik’s cube+.•Comprehensive discussions on the limitation and potential applications of our study are included.