Welcome to the pathology AI platform (PAIP). PAIP is an educational service platform for AI researchers.
PAIP provides high-quality pathologic slide images of six tumor types as well as region-of-interest annotations developed by pathology experts.
This project is funded by the Ministry of Health and Welfare, Republic of Korea (2018 ~ 2023).
Data is provided by Seoul National University Hospital (SNUH), Seoul National University Bundang Hospital (SNUBH), and SMG-SNU Boramae Medical Center (BRMH).
Please acknowledge PAIP 2019 in your publications as follows:
“Deidentified pathology images and annotations used in this research were provided by Seoul National University Hospital by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number: HI18C0316)”
PAIP data set is available under a Creative Commons Attribution-Non Commercial 4.0 International License (CC BY-NC 4.0) Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- Non Commercial — You may not use the material for commercial purposes.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
The PAIP uploads two types of pathology whole slide images(WSIs, SVS files); liver hepatocellular carcinoma and colorectal adenocarcinoma cases.
- liver hepatocellular carcinoma cases
- colorectal adenocarcinoma cases
The whole slide images include the corresponding annotations (XML files). However, please note that the annotation levels of two types of cancer are not the same due to the characteristics as follows.
- Liver cancer cases have 2 annotation levels, only for the tumor area and the other for the normal area.
- Colorectal cancer cases have 1 annotation level representing only the tumor area.
01 liver 02 biliary 03 prostate 04 kidney 05 colon 06 pancreas
00 none 01 Lymphatic Invasion 02 Vascular Invasion 03 Perineural Invasion
01 adenocarcinoma 02 ductal adenocarcinoma 03 hepatocellular carcinoma 04 renal cell carcinoma
01 HE (hematoxylin eosin) 02 IHC (immunohistochemistry)