Pre-CT160K dataset's preprocess steps

Luffy03 / Large-Scale-Medical

[CVPR 2024 Extension] 160K volumes (42M slices) datasets, new segmentation datasets, 31M-1.2B pre-trained models, various pre-training recipes, 50+ downstream tasks implementation

Apache License 2.0

101 stars 7 forks source link

Pre-CT160K dataset's preprocess steps #23

Closed yuxuanou623 closed 1 week ago

yuxuanou623 commented 2 weeks ago

Hi, could you please provide the proprocess details of the pretrain dataset? In the paper, you mentioned that the size, spacing and intensity of all the images are the same. Could you provide the specific process steps regarding unifying the size, spacing and intensity?

Luffy03 commented 2 weeks ago

Dear yuxuan, the size, spacing, and intensity of all the images are not the same. The pre-processing codes are in https://github.com/Luffy03/Large-Scale-Medical/tree/main/Self-supervised/utils.