Development and evaluation of a virtual microscopy application for automated assessment of Ki-67 expression in breast cancer
2011

Automated Assessment of Ki-67 in Breast Cancer Using Virtual Microscopy

Sample size: 1334 publication Evidence: high

Author Information

Author(s): Konsti Juho, Lundin Mikael, Joensuu Heikki, Lehtimäki Tiina, Sihto Harri, Holli Kaija, Turpeenniemi-Hujanen Taina, Kataja Vesa, Sailas Liisa, Isola Jorma, Lundin Johan

Primary Institution: FIMM - Institute for Molecular Medicine Finland, University of Helsinki

Hypothesis

The study aims to develop a virtual microscopy method for assessing Ki-67 expression and evaluate its prognostic value in breast cancer patients.

Conclusion

Automated assessment of Ki-67 extent of staining is a significant and independent predictor of outcome in breast cancer.

Supporting Evidence

  • The automated assessment of Ki-67 extent of staining was significantly associated with clinicopathological characteristics.
  • Patients with moderate and high Ki-67 staining had hazard ratios of 1.77 and 2.34 for distant recurrence.
  • The study analyzed 1648 TMA spot images in less than two hours.
  • Visual and automated assessments showed a percentage agreement of 87%.

Takeaway

This study created a computer program to help doctors measure a protein called Ki-67 in breast cancer samples, which can help predict how well patients will do.

Methodology

The study used a virtual microscopy platform and an image processing tool to analyze Ki-67 staining in breast cancer tissue microarrays.

Potential Biases

Human interpretation variability may lead to discrepancies between visual and automated assessments.

Limitations

The algorithm may include stromal components in the assessment, which can affect staining distribution.

Participant Demographics

Patients diagnosed with breast cancer in Finland during 1991 and 1992, covering half of the population.

Statistical Information

P-Value

p<0.0001

Confidence Interval

95% CI 1.31-2.37 for moderate Ki-67; 95% CI 1.76-3.10 for high Ki-67

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1472-6890-11-3

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication