A nomogram based on conventional and contrast-enhanced ultrasound radiomics for the noninvasively prediction of...

Area of Science:

• Medical Imaging
• Oncology
• Radiology

Background:

• Breast cancer patients often require axillary lymph node metastasis (ALNM) assessment.
• Noninvasive prediction of ALNM is crucial for treatment planning.
• Conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) are imaging modalities used in breast cancer diagnosis.

Purpose of the Study:

• To investigate the utility of radiomics features from CUS and CEUS for predicting ALNM in breast cancer.
• To develop and validate a nomogram for noninvasive ALNM prediction.

Main Methods:

• 111 breast cancer patients were enrolled, with data split into training (78) and validation (33) sets.
• Radiomics features were extracted from CUS and CEUS images using PyRadiomics.
• Feature selection (MRMR, LASSO) and nomogram development using logistic regression were performed.

Main Results:

• A nomogram combining CUS findings, CUS radiomics score, and CEUS radiomics score showed high predictive performance.
• The nomogram achieved an AUC of 0.845 in the training set and 0.901 in the validation set.
• Calibration curves and decision curve analysis confirmed the nomogram's clinical utility and consistency.

Conclusions:

• The developed nomogram is a valuable tool for noninvasive prediction of axillary lymph node metastasis in breast cancer.
• Radiomics analysis of CUS and CEUS images significantly enhances the prediction of ALNM.
• This approach can aid in preoperative assessment and treatment decision-making for breast cancer patients.