Clinical Report: Noninvasive Evaluation of Ki-67 Overexpression in Breast Cancer
Overview
This study demonstrates the effectiveness of integrating habitat analysis with ultrasound radiomics to predict Ki-67 expression in breast cancer non-invasively. The proposed Clinics_Habitat_Radiomics model significantly outperformed conventional methods, providing a promising tool for personalized oncology care.
Background
Breast cancer remains the most commonly diagnosed malignancy among women, and accurate assessment of the Ki-67 proliferation index is crucial for treatment planning. Traditional methods rely on invasive biopsies, which may not capture the tumor's heterogeneity. Non-invasive imaging techniques like ultrasound radiomics offer a potential solution to improve prognostic stratification.
Data Highlights
Model
AUC (Training)
AUC (Validation)
Sensitivity
Specificity
Clinics_Habitat_Radiomics
0.877
0.830
60.3%
91.7%
Key Findings
The Clinics_Habitat_Radiomics model achieved an AUC of 0.877 in the training cohort.
In the validation cohort, the model maintained an AUC of 0.830 with a sensitivity of 60.3% and specificity of 91.7%.
Calibration curves showed good agreement between predicted probabilities and observed outcomes.
Decision curve analysis indicated superior net clinical benefit compared to single-modality approaches.
The integration of habitat analysis enhances the precision of tumor biology assessment.
Clinical Implications
The Clinics_Habitat_Radiomics model provides a non-invasive method for predicting Ki-67 expression, which can aid in optimizing treatment strategies for breast cancer patients. This approach may reduce the need for invasive biopsies and improve patient stratification for targeted therapies.
Conclusion
The study highlights the potential of ultrasound-based habitat analysis in enhancing the assessment of Ki-67 expression in breast cancer, paving the way for improved personalized treatment approaches.
