Table 4. Summary of generative self-supervised learning methods in medical imaging.

No.	Authors	Pretext task	Down-stream task
1	Ross et al. (2018)	Image Colorization	Surgical instruments segmentation
2	Chen et al. (2019)	Context restoration	Fetal image classification Abdominal multi-organ localization Brain tumour segmentation
3	Zhou et al. (2019)	Models Genesis	Lung nodule segmentation FPR for nodule detection FPR for pulmonary embolism Liver segmentation pulmonary diseases classification RoI, bulb, and background classification Brain tumor segmentation
4	Matzkin et al. (2020)	Skull reconstruction	Bone flap volume estimation
5	Hervella et al. (2020b)	Multi-modal reconstruction	Fovea localization Optic disc localization Vasculature segmentation Optic disc segmentation
6	Holmberg et al. (2020)	Cross modal retinal thickness prediction	Diabetic retinopathy grading
7	Prakash et al. (2020)	Image denoising	Nuclei images segmentation
8	Hu et al. (2020)	Context encoder	Quality score classification Thyroid nodule segmentation Liver and kidney segmentation
9	Tao et al. (2020)	Rubik cube++	Pancreas segmentation Brain tissue segmentation