A robust model training strategy using hard negative mining in a weakly labeled dataset for lymphatic invasion in gastric cancer.

"data availability statement the dataset for developing the model used in this study is freely available at the following link: https://zenodo org/records/10020633 . data availability statement the dataset for developing the model used in this study is freely available at the following link: https://zenodo"

"the source code for developing the model used in this study is freely available at the following link: https://github com/jonghyunlee1993/li_classification_with_hard_negative_mining ."

"No conflicts of interest were declared."

"We would like to thank Editage (www.editage.co.kr) for English language editing. This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean Government (MSIT) (2023R1A2C2006223)."