Multimodal Ultrasound Model for Predicting Breast Cancer Axillary Nodal Burden

Renjie Lu developed a multimodal model integrating tumor radiomics and lymph node morphology for predicting axillary nodal metastasis burden in breast cancer. The dataset includes information from 583 patients with pathologically confirmed breast cancer, split into training and testing cohorts. The model was last updated on June 4, 2026.

Use Cases

• Predicting axillary lymph node metastasis (N0 vs. N+) based on tumor radiomics and lymph node classification.
• Distinguishing axillary nodal tumor burden (N1–2 vs. N≥3) using integrated radiomics scores and clinicopathological variables.
• Conducting subgroup analysis for model performance based on Ki-67 status mentioned in the results.

Strengths

• Model performance is quantitatively validated, with a combined model achieving an AUC of 0.90 for predicting ALN metastasis.
• The study includes a substantial cohort of 583 patients, providing a basis for model development.
• The hierarchical modeling strategy addresses two distinct clinical prediction tasks.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is a single 125.8 KB DOCX file, suggesting limited raw data scope.

Provenance

Source

Author Renjie Lu via figshare.

Collection Method

Retrospective study of patient data; radiomic features were extracted from ultrasound images.

Freshness

Last updated 2026-06-04 04:27:32; freshness should be verified.