Detecting cell types and densities in the tumor microenvironment improves prognostic risk assessment for breast cancer
2024

Improving Breast Cancer Prognosis with Cell Density Analysis

Sample size: 362 publication 10 minutes Evidence: high

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)

10.17305/bb.2024.10974

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication