Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer - Scorecard - MDSpire
Advertisement
Multi-parametric MRI habitat radiomics with interpretable machine learning for early prediction of axillary lymph node metastasis in triple-negative breast cancer
Clinical Scorecard: Interpretable Machine Learning-Enhanced Multi-Parametric MRI Habitat Radiomics for Early Detection of Axillary Lymph Node Metastasis in Triple-Negative Breast Cancer
At a Glance
Category
Detail
Condition
Triple-Negative Breast Cancer (TNBC)
Key Mechanisms
Intratumoral heterogeneity (ITH) and habitat radiomics for predicting axillary lymph node metastasis (ALNM)
Target Population
Patients with pathologically confirmed TNBC
Care Setting
Preoperative assessment
Key Highlights
Habitat radiomics model outperformed conventional radiomics for ALNM prediction.
Combined model achieved the highest predictive performance with an AUC of 0.81.
SHAP analysis identified ALN length as the most important predictor.
Guideline-Based Recommendations
Diagnosis
Utilize mpMRI and habitat radiomics for non-invasive ALNM assessment.
Management
Consider integrating habitat radiomics into preoperative treatment planning.
Monitoring & Follow-up
Regularly evaluate model performance using ROC analysis and calibration curves.
Risks
Invasive procedures like sentinel lymph node biopsy (SLNB) and axillary lymph node dissection (ALND) carry morbidity.
Patient & Prescribing Data
125 patients with pathologically confirmed TNBC
Non-invasive prediction of ALNM can guide neoadjuvant therapy and surgical management.
Clinical Best Practices
Incorporate habitat radiomics in routine imaging assessments for TNBC.
Use SHAP for model interpretation to enhance clinical decision-making.
