A multimodal ultrasound-based model combining tumor radiomics and axillary lymph node morphologic classification for predicting axillary nodal burden in breast cancer - Summary - MDSpire
Advertisement
A multimodal ultrasound-based model combining tumor radiomics and axillary lymph node morphologic classification for predicting axillary nodal burden in breast cancer
To develop and validate a multimodal ultrasound-based model integrating tumor radiomics and axillary lymph node (ALN) morphologic classification for preoperative prediction of axillary nodal metastasis burden in breast cancer.
Key Findings:
The first-level radiomics model achieved an AUC of 0.79; the combined model improved this to 0.90.
The second-level radiomics model yielded an AUC of 0.74, increasing to 0.78 after integration.
Ki-67 was identified as an independent predictor.
The combined model performed well across Ki-67 subgroups, with superior performance in the low Ki-67 subgroup (AUC 0.82 vs. 0.68).
Interpretation:
The multimodal model enables accurate, noninvasive prediction of ALN metastasis and axillary nodal tumor burden.
Limitations:
Retrospective design may introduce bias.
Study limited to patients with pathologically confirmed breast cancer.
Conclusion:
The proposed model integrates tumor radiomics with lymph node morphology for improved preoperative assessment of axillary nodal involvement in breast cancer.
