Predicting of axillary lymph node metastasis in invasive breast cancer using multiparametric MRI dataset based on CNN model

Abstract

PurposeTo develop a multiparametric MRI model for predicting axillary lymph node metastasis in invasive breast cancer.MethodsClinical data and T2WI, DWI, and DCE-MRI images of 252 patients with invasive breast cancer were retrospectively analyzed and divided into the axillary lymph node metastasis (ALNM) group and non-ALNM group using biopsy results as a reference standard. The regions of interest (ROI) in T2WI, DWI, and DCE-MRI images were segmented using MATLAB software, and the ROI was unified into 224 × 224 sizes, followed by image normalization as input to T2WI, DWI, and DCE-MRI models, all of which were based on ResNet 50 networks. The idea of a weighted voting method in ensemble learning was employed, and then T2WI, DWI, and DCE-MRI models were used as the base models to construct a multiparametric MRI model. The entire dataset was randomly divided into training sets and testing sets (the training set 202 cases, including 78 ALNM, 124 non-ALNM; the testing set 50 cases, including 20 ALNM, 30 non-ALNM). Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of models were calculated. The receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to evaluate the diagnostic performance of each model for axillary lymph node metastasis, and the DeLong test was performed, P< 0.05 statistically significant.ResultsFor the assessment of axillary lymph node status in invasive breast cancer on the test set, multiparametric MRI models yielded an AUC of 0.913 (95% CI, 0.799-0.974); T2WI-based model yielded an AUC of 0.908 (95% CI, 0.792-0.971); DWI-based model achieved an AUC of 0.702 (95% CI, 0.556-0.823); and the AUC of the DCE-MRI-based model was 0.572 (95% CI, 0.424-0.711). The improvement in the diagnostic performance of the multiparametric MRI model compared with the DWI and DCE-MRI-based models were significant (P< 0.01 for both). However, the increase was not meaningful compared with the T2WI-based model (P = 0.917).ConclusionMultiparametric MRI image analysis based on an ensemble CNN model with deep learning is of practical application and extension for preoperative prediction of axillary lymph node metastasis in invasive breast cancer.

Deep Learning Prediction of Axillary Lymph Node Metastasis in Breast Cancer Patients Using Clinical Implication-Applied Preprocessed CT Images

“…The most common radiological methods used in radiomics for classifying ALNs are MRI and ultrasound. After the release of multiple promising results from MRI-based AI models (AUROC of 0.913-0.996) [19,20] and ultrasonography-based AI models (AUROC of 0.912-0.916) [21,22], the latest machine learning/deep learning approaches for predicting malignant LN incorporate a multi-modal analysis model that combines radiomics and clinicopathological features [23,24]. Together with other currently published studies, our findings and the image processing protocol used in our study can be applied to develop optimal multi-modal models that combine different radiomics to maximize diagnostic accuracy.…”

Application of Machine Learning Algorithm in Predicting Axillary Lymph Node Metastasis from Breast Cancer on Preoperative Chest CT

“…Various ML approaches have been proposed for classifying or detecting breast cancer metastasis in ALN [ 44 , 45 , 46 ]. Song et al [ 45 ] proposed a ML-based radiomics model for predicting ALN metastasis in invasive ductal breast cancer (IDC).…”

“…Their combined DLR model offers a non-invasive imaging biomarker which can predict the status of ALN for patients with early stage breast cancer. Zhang et al [ 46 ] developed a multiparametric MRI model combined with ensemble learning to predict ALN metastasis in invasive breast cancer. They fused axial T2WI, DWI, and DCE-MRI models and achieved an AUC of 0.913.…”

The Role of AI in Breast Cancer Lymph Node Classification: A Comprehensive Review

“…Another recent study, by Zhang et al, has also reported excellent results, with an AUC of 0.913 (95% CI: 0.799–0.974) ( Table 1 ) [ 29 ]. A total of 252 patients were randomly divided into a training (202) and test set (50), and Transfer learning (with pre-trained ResNet50) was used.…”

“…A total of 252 patients were randomly divided into a training (202) and test set (50), and Transfer learning (with pre-trained ResNet50) was used. Finally, T2WI, DWI, and DCE-MRI sequences were used, and their results were pooled to perform the final classification [ 29 ]. While 95% confidence intervals were reported, it was not specified whether CV or bootstrapping was performed.…”