Differential interference contrast (DIC) image of unstained living HepG2 human liver cancer cells

Introduction

This dataset is associated with our submission to Computers in Biology and Medicine, titled "Accurate Detection and Instance Segmentation of Unstained Living Adherent Cells in Differential Interference Contrast Images". The submission number for this manuscript is CIBM-D-23-09623R1.

Authors: Fei Pan, Yutong Wu, Kangning Cui, Shuxun Chen, Yanfang Li, Yaofang Liu, Adnan Shakoor, Han Zhao, Beijia Lu, Shaohua Zhi, Raymond Hon-Fu Chan, Dong Sun

Dataset Description

Our dataset comprises 520 differential interference contrast (DIC) images of 12,198 unstained HepG2 human liver cancer cells, each with a corresponding fluorescence image stained with calcein acetoxymethyl (AM), ensuring high-quality ground-truth annotations. Unique in addressing the multi-state nature of adherent cells commonly seen in wet labs, it includes both healthy and unhealthy cells in a single image, providing a valuable resource for studying multi-state cell detection and instance segmentation.Citation

We kindly request that researchers who use this dataset cite both our paper and this dataset. This will help acknowledge the work and facilitate further advancements in the field.

Please cite as follows:

Paper:Pan, F., Wu, Y., Cui, K., Chen, S., Li, Y., Liu, Y., Shakoor, A., Zhao, H., Lu, B., Zhi, S., Chan, R. H.-F., & Sun, D. "Accurate detection and instance segmentation of unstained living adherent cells in differential interference contrast images,” Computers in Biology and Medicine, vol. 182, p. 109151, Nov. 2024, doi: 10/g5p9d8.

Dataset:Pan, F., Chen, S., Li, Y., Shakoor, A., Zhao, H., & Sun, D. (2024). Differential interference contrast (DIC) image of unstained living HepG2 human liver cancer cells. Zenodo. 

Thank you for your interest and support in our work. We look forward to seeing the innovative research that this dataset will enable.