Attention‐based Deep Learning for the Preoperative Differentiation of Axillary Lymph Node Metastasis in Breast Cancer on DCE‐MRI

Abstract

Background Previous studies have explored the potential on radiomics features of primary breast cancer tumor to identify axillary lymph node (ALN) metastasis. However, the value of deep learning (DL) to identify ALN metastasis remains unclear. Purpose To investigate the potential of the proposed attention‐based DL model for the preoperative differentiation of ALN metastasis in breast cancer on dynamic contrast‐enhanced MRI (DCE‐MRI). Study Type Retrospective. Population A total of 941 breast cancer patients who underwent DCE‐MRI before surgery were included in the training (742 patients), internal test (83 patients), and external test (116 patients) cohorts. Field Strength/Sequence A 3.0 T MR scanner, DCE‐MRI sequence. Assessment A DL model containing a 3D deep residual network (ResNet) architecture and a convolutional block attention module, named RCNet, was proposed for ALN metastasis identification. Three RCNet models were established based on the tumor, ALN, and combined tumor‐ALN regions on the images. The performance of these models was compared with ResNet models, radiomics models, the Memorial Sloan‐Kettering Cancer Center (MSKCC) model, and three radiologists (W.L., H.S., and F. L.). Statistical Tests Dice similarity coefficient for breast tumor and ALN segmentation. Accuracy, sensitivity, specificity, intercorrelation and intracorrelation coefficients, area under the curve (AUC), and Delong test for ALN classification. Results The optimal RCNet model, that is, RCNet−tumor+ALN, achieved an AUC of 0.907, an accuracy of 0.831, a sensitivity of 0.824, and a specificity of 0.837 in the internal test cohort, as well as an AUC of 0.852, an accuracy of 0.828, a sensitivity of 0.792, and a specificity of 0.853 in the external test cohort. Additionally, with the assistance of RCNet−tumor+ALN, the radiologists' performance was improved (external test cohort, P < 0.05). Data Conclusion DCE‐MRI‐based RCNet model could provide a noninvasive auxiliary tool to identify ALN metastasis preoperatively in breast cancer, which may assist radiologists in conducting more accurate evaluation of ALN status. Evidence Level 3 Technical Efficacy Stage 2

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions

“…When this was not possible, we selected the MRI acquisition with the highest peak of the enhanced phase (the first one of the second sequence when the highest peak was not reached at first). This method is consistent with the recent literature [ 30 , 31 ].…”

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

“…An interesting study by Gao et al investigated the potential of a new attention-based DL model [ 30 ]. The model combined Transfer learning (ResNet50) with a convolutional block attention module (named RCNet).…”

“…The model combined Transfer learning (ResNet50) with a convolutional block attention module (named RCNet). The dataset consisted of 941 breast cancer patients who underwent DCE-MRI before surgery (742 training set, 83 internal test set, 116 external test set) [ 30 ]. The model achieved an AUC of 0.852 (0.779–0.925) when evaluated on the external test set ( Table 1 ).…”

“…The model achieved an AUC of 0.852 (0.779–0.925) when evaluated on the external test set ( Table 1 ). Notably, the authors also showed how the model improves radiologist performance in a statistically significant manner [ 30 ].…”

Editorial for “Attention‐based Deep Learning for the Preoperative Differentiation of Axillary Lymph Node Metastasis in Breast Cancer on DCE‐MRI”

“…8 Thus, the use of various radiomic features of the primary tumor is extracted and analyzed by the use of the DCE-MRI by several machine learning methods. 9 Sikandar Shaikh, DMRD, DNB, MNAMS, EDiR, FICR Department of Radiology, Shadan Institute of Medical Sciences, Hyderabad, India E-mail: idrsikandar@gmail.com…”