Detecting Collagen by Machine Learning Improved Photoacoustic Spectral Analysis for Breast Cancer Diagnostics: Feasibility Studies With Murine Models
2024

Detecting Collagen for Breast Cancer Diagnosis Using Machine Learning

Sample size: 100 publication 10 minutes Evidence: moderate

Author Information

Author(s): Li Jiayan, Bai Lu, Chen Yingna, Cao Junmei, Zhu Jingtao, Zhi Wenxiang, Cheng Qian

Primary Institution: Institute of Acoustics, School of Physics Science and Engineering Tongji University

Hypothesis

Can photoacoustic spectral analysis improved by machine learning effectively detect collagen levels in breast cancer diagnostics?

Conclusion

The study demonstrates that machine learning-enhanced photoacoustic spectral analysis can improve the accuracy of breast cancer diagnostics by effectively detecting collagen levels.

Supporting Evidence

  • The study identified collagen as a significant biomarker for breast cancer diagnostics.
  • Machine learning improved the diagnostic accuracy of photoacoustic spectral analysis.
  • Collagen levels were found to be significantly different between normal and cancerous tissues.

Takeaway

This study shows that a special light technique can help doctors find out if someone has breast cancer by looking at collagen, a protein in the body.

Methodology

The study used photoacoustic spectral analysis combined with machine learning to analyze collagen levels in murine models of breast cancer.

Potential Biases

Potential biases may arise from the use of a single animal model and the limited number of histopathological samples.

Limitations

The study's findings may not fully translate to human subjects due to differences in tissue composition and the limited scope of murine models.

Participant Demographics

Murine models were used, specifically nude mice with implanted human breast cancer cells.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1002/jbio.202400371

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication