Prediction of the axillary lymph-node metastatic burden of breast cancer by ¹⁸F-FDG PET/CT-based radiomics

Area of Science:

• Oncology
• Radiology
• Medical Imaging

Background:

• Axillary lymph-node metastatic burden significantly impacts breast cancer treatment and prognosis.
• Accurate prediction of nodal burden is crucial for personalized patient management.

Purpose of the Study:

• To evaluate the efficacy of 18F-fluorodeoxyglucose (18F-FDG) PET/CT-based radiomics combined with ultrasound and clinical pathological features for predicting axillary lymph-node metastatic burden in breast cancer.
• To develop and validate a multi-parameter predictive model.

Main Methods:

• Retrospective analysis of 124 early-stage breast cancer patients who underwent 18F-FDG PET/CT.
• Extraction of radiomic features from PET images.
• Development of a multi-parameter predictive model integrating ultrasound, PET/CT findings, clinical pathological features, and radiomics.

Main Results:

• High nodal burden groups showed significantly higher ultrasound and PET lymph-node positivity rates.
• PET-based radiomics score (RS) was a significant independent predictor of high lymph-node burden.
• The multi-parameter (MultiP) model achieved a superior area under the curve (AUC) of 0.895 compared to individual modalities (US_LNM: 0.703, PET_LNM: 0.814, RS: 0.773).
• Decision curve analysis confirmed the superior net benefit of the MultiP model.

Conclusions:

• A multi-parameter model incorporating PET-based radiomics, ultrasound, and clinical data effectively predicts axillary lymph-node metastatic burden in breast cancer.
• This integrated approach offers improved accuracy and clinical utility for treatment planning.