Exempting axillary staging surgery in breast cancer using multimodal ultrasound imaging and radiomics of sentinel lymph nodes - PubMed
5 hours ago
- #radiomics
- #ultrasound-imaging
- #breast-cancer
- Study aims to exempt axillary staging surgery in breast cancer using multimodal ultrasound imaging and radiomics of sentinel lymph nodes (SLNs).
- A deep dual-modal fusion network (DDFN) model was developed to preoperatively predict SLN metastasis by integrating features from contrast-enhanced ultrasound (CEUS) and grayscale ultrasound (GSUS) images.
- The DDFN model demonstrated superior performance compared to single-modality models, with high negative predictive value (NPV), specificity, and area under the ROC curve (AUC).
- Results showed NPVs exceeding 0.9 in all test cohorts, indicating robust performance in distinguishing metastatic and non-metastatic SLNs.
- The study suggests that the DDFN model can preoperatively assess SLNs, potentially exempting patients without metastasis from unnecessary axillary staging surgery.
- The study was conducted across multiple medical centers in China and funded by the Sichuan Science and Technology Department.