Table 6. Summary of multiple-tasks/multi-tasking self-supervised learning methods in medical imaging.

No.	Authors	Pretext task	Down-stream task
1	Tajbakhsh et al. (2019)	Colorization rotation prediction 3D patch reconstruction	Lung lobe segmentation FPR for nodule detection skin lesions segmentation diabetic retinopathy grading
2	Jiao et al. (2020)	Temporal order correction transformation prediction	Standard plane detection saliency prediction
3	Li, Chen & Zheng (2020)	ColorMe	Cervix type classification skin lesion segmentation
4	Taleb et al. (2020)	CPC Jigsaw puzzle Exemplar CNN Rotation Prediction Relative position prediction	Brain tumors segmentation pancreas tumor segmentation
5	Luo et al. (2020)	Self-supervised fuzzy clustering	Color fundus classification diabetic retinopathy classification
6	Haghighi et al. (2020)	Semantic Genesis	Lung nodule segmentation FPR for nodule detection liver segmentation chest diseases classification brain tumor segmentation pneumothorax segmentation
7	Zhang et al. (2020)	Scale-aware restoration	Brain tumor segmentation pancreas segmentation
8	Dong, Kampffmeyer & Voiculescu (2021)	Multi-task self-supervised learning	Whole heart segmentation
9	Koohbanani et al. (2021)	Self-path	histopathology image classification
10	Zhang et al. (2021)	SimCLR Jigsaw puzzle	Binary OCT classification multi-class OCT classification
11	Li et al. (2021)	Rotation prediction multi-view instance discriminate	PM classification AMD classification
12	Lu, Li & Ye (2021)	Fiber streamlines density map prediction Registration imitation	White matter tract segmentation