Develop and Validate a Nomogram Combining Contrast-Enhanced Spectral Mammography Deep Learning with Clinical-Pathological Features to Predict Neoadjuvant Chemotherapy Response in Patients with ER-Positive/HER2-Negative Breast Cancer

Rationale and objectives: To develop and validate a nomogram that combines contrast-enhanced spectral mammography (CESM) deep learning with clinical-pathological features to predict neoadjuvant chemotherapy (NAC) response (either low Miller Payne (MP-L) grades 1-2 or high MP (MP-H) grades 3-5) in patients with ER-positive/HER2-negative breast cancer.

Materials and methods: In this retrospective study, 265 breast cancer patients were randomly allocated into training and test sets (used for models training and testing, respectively) at a 4:1 ratio. Deep learning models, based on the pre-trained ResNet34 model and initially fine-tuned for identifying breast cancer, were trained using low-energy and subtracted CESM images. The predicted results served as deep learning features for the deep learning-based model. Clinical-pathological features, including age, progesterone receptor (PR) status, estrogen receptor (ER) status, Ki67 expression levels, and neutrophil-to-lymphocyte ratio, were used for the clinical model. All these features contributed to the nomogram. Feature selection was performed through univariate analysis. Logistic regression models were developed and chosen using a stepwise selection method. The deep learning-based and clinical models, along with the nomogram, were evaluated using precision-recall curves, receiver operating characteristic (ROC) curves, specificity, recall, accuracy, negative predictive value, positive predictive value (PPV), balanced accuracy, F1-score, and decision curve analysis (DCA).

Results: The nomogram demonstrated considerable predictive ability, with higher area under the ROC curve (0.95, P < 0.05), accuracy (0.94), specificity (0.98), PPV (0.89), and precision (0.89) compared to the deep learning-based and clinical models. In DCA, the nomogram showed substantial clinical value in assisting breast cancer treatment decisions, exhibiting a higher net benefit than the other models.

Conclusion: The nomogram, integrating CESM deep learning with clinical-pathological features, proved valuable for predicting NAC response in patients with ER-positive/HER2-negative breast cancer. Nomogram outperformed deep learning-based and clinical models.