A RECENT study has highlighted the effectiveness of a new bimodal model that integrates contrast-enhanced ultrasound (CEUS) images to predict axillary lymph node (ALN) metastasis in patients with early-stage breast cancer. The model, which employs a light-gradient boosting machine, aims to identify key imaging features associated with lymph node metastasis. By analysing 788 CEUS images from patients who underwent breast surgery between 2013 and 2021, the research team sought to improve diagnostic accuracy.
The results showed that the model outperformed traditional radiologist diagnoses. With an impressive accuracy of 93%, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.93, compared to the radiologists’ 85% accuracy. The model’s success stems from its ability to extract important imaging features such as heterogeneous enhancement, diffuse cortical thickening, and eccentric cortical thickening, all of which were identified as significant indicators of metastasis.
These findings suggest that the integration of CEUS images with advanced machine learning techniques holds promise for enhancing the early detection of ALN metastasis in breast cancer patients. With its high diagnostic performance, this model could become a valuable tool in clinical settings, helping clinicians make more informed decisions and improve patient outcomes.
Helena Bradbury, EMJ
Reference
Oshino T et al. Artificial intelligence can extract important features for diagnosing axillary lymph node metastasis in early breast cancer using contrast-enhanced ultrasonography. Sci Rep. 2025;15(1):5648.
