Improving Breast Cancer Prognosis with Cell Density Analysis
Author Information
Author(s): Liu Pu, Zhang Xueli, Wang Wenwen, Zhu Yunping, Xie Yongfang, Tai Yanhong, Ma Jie
Primary Institution: Chongqing University of Posts and Telecommunications
Hypothesis
The study investigates the relationship between cell densities in the tumor microenvironment and breast cancer prognosis.
Conclusion
The study found that cell density scores can effectively predict breast cancer patient outcomes.
Supporting Evidence
- The study created a unique dataset of over 70,000 breast cancer patches annotated with cell types.
- Deep learning models achieved over 99% accuracy in classifying different cell types.
- The risk assessment model based on TME cell density was validated with satisfactory predictive performance.
Takeaway
This study shows that counting different types of cells in breast cancer can help doctors understand how likely a patient is to do well.
Methodology
The study used Lasso-Cox regression and deep learning with a dataset of over 70,000 annotated patches to assess cell densities.
Limitations
The risk scores need validation in larger, prospective cohorts and the CNNs require fine-tuning on multicenter datasets.
Participant Demographics
The study included 362 breast cancer patients from the TCGA-BRCA cohort.
Statistical Information
P-Value
0.0018
Confidence Interval
1.130–5.653
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website