Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer - Summary - MDSpire
Advertisement
Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer
To develop and validate an interpretable mpMRI-based habitat radiomics model for preoperative prediction of axillary lymph node metastasis (ALNM) in triple-negative breast cancer (TNBC), highlighting its potential clinical significance.
Key Findings:
Combined model achieved the highest AUC of 0.81 in the test set.
Habitat radiomics model outperformed conventional radiomics and clinical models.
ALN length identified as the most important predictor in SHAP analysis.
Interpretation:
The habitat radiomics model enhances predictive accuracy for ALNM in TNBC by effectively characterizing intratumoral heterogeneity, providing a non-invasive assessment tool that may improve clinical decision-making.
Limitations:
Retrospective design may introduce selection bias, potentially affecting the validity of results.
Single-center study limits generalizability of findings.
Conclusion:
The habitat radiomics model significantly improves preoperative ALNM prediction in TNBC, emphasizing the importance of intratumoral heterogeneity in non-invasive nodal risk stratification.
