Li H, Ye J, Liu H, et al. - A retrospective study was conducted to explore the model from populations with different breast densities and showed the model's performance on malignancy prediction. Researchers included a total of 608 mammograms from Northern Jiangsu People's Hospital in Yangzhou City. For different types of breast, the Yizhun AI model applied in our work has good diagnostic efficiency, even for the extremely dense breast. It has a guiding role in the clinical diagnosis of breast cancer. The finding suggsted that the performance of Yizhun AI on mass/distortion/asymmetry is affected by breast density significantly in comparison with that on amorphous calcification.