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

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. 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). Retrospective. 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. A 3.0 T MR scanner, DCE-MRI sequence. 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.). 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. 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). 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. 3 TECHNICAL EFFICACY: Stage 2.

Gao J ，Zhong X ，Li W ，Li Q ，Shao H ，Wang Z ，Dai Y ，Ma H ，Shi Y ，Zhang H ，Duan S ，Zhang K ，Yang P ，Zhao F ，Zhang H ，Xie H ，Mao N ... -  《-》

Multitask Deep Learning-Based Whole-Process System for Automatic Diagnosis of Breast Lesions and Axillary Lymph Node Metastasis Discrimination from Dynamic Contrast-Enhanced-MRI: A Multicenter Study.

Accurate diagnosis of breast lesions and discrimination of axillary lymph node (ALN) metastases largely depend on radiologist experience. To develop a deep learning-based whole-process system (DLWPS) for segmentation and diagnosis of breast lesions and discrimination of ALN metastasis. Retrospective. 1760 breast patients, who were divided into training and validation sets (1110 patients), internal (476 patients), and external (174 patients) test sets. 3.0T/dynamic contrast-enhanced (DCE)-MRI sequence. DLWPS was developed using segmentation and classification models. The DLWPS-based segmentation model was developed by the U-Net framework, which combined the attention module and the edge feature extraction module. The average score of the output scores of three networks was used as the result of the DLWPS-based classification model. Moreover, the radiologists' diagnosis without and with the DLWPS-assistance was explored. To reveal the underlying biological basis of DLWPS, genetic analysis was performed based on RNA-sequencing data. Dice similarity coefficient (DI), area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and kappa value. The segmentation model reached a DI of 0.828 and 0.813 in the internal and external test sets, respectively. Within the breast lesions diagnosis, the DLWPS achieved AUCs of 0.973 in internal test set and 0.936 in external test set. For ALN metastasis discrimination, the DLWPS achieved AUCs of 0.927 in internal test set and 0.917 in external test set. The agreement of radiologists improved with the DLWPS-assistance from 0.547 to 0.794, and from 0.848 to 0.892 in breast lesions diagnosis and ALN metastasis discrimination, respectively. Additionally, 10 breast cancers with ALN metastasis were associated with pathways of aerobic electron transport chain and cytoplasmic translation. The performance of DLWPS indicates that it can promote radiologists in the judgment of breast lesions and ALN metastasis and nonmetastasis. 4 TECHNICAL EFFICACY STAGE: 3.

Zhou H ，Hua Z ，Gao J ，Lin F ，Chen Y ，Zhang S ，Zheng T ，Wang Z ，Shao H ，Li W ，Liu F ，Li Q ，Chen J ，Wang X ，Zhao F ，Qu N ，Xie H ，Ma H ，Zhang H ，Mao N ... -  《-》

Multi-modality radiomics model predicts axillary lymph node metastasis of breast cancer using MRI and mammography.

We aimed to develop a multi-modality model to predict axillary lymph node (ALN) metastasis by combining clinical predictors with radiomic features from magnetic resonance imaging (MRI) and mammography (MMG) in breast cancer. This model might potentially eliminate unnecessary axillary surgery in cases without ALN metastasis, thereby minimizing surgery-related complications. We retrospectively enrolled 485 breast cancer patients from two hospitals and extracted radiomics features from tumor and lymph node regions on MRI and MMG images. After feature selection, three random forest models were built using the retained features, respectively. Significant clinical factors were integrated with these radiomics models to construct a multi-modality model. The multi-modality model was compared to radiologists' diagnoses on axillary ultrasound and MRI. It was also used to assist radiologists in making a secondary diagnosis on MRI. The multi-modality model showed superior performance with AUCs of 0.964 in the training cohort, 0.916 in the internal validation cohort, and 0.892 in the external validation cohort. It surpassed single-modality models and radiologists' ALN diagnosis on MRI and axillary ultrasound in all validation cohorts. Additionally, the multi-modality model improved radiologists' MRI-based ALN diagnostic ability, increasing the average accuracy from 70.70 to 78.16% for radiologist A and from 75.42 to 81.38% for radiologist B. The multi-modality model can predict ALN metastasis of breast cancer accurately. Moreover, the artificial intelligence (AI) model also assisted the radiologists to improve their diagnostic ability on MRI. The multi-modality model based on both MRI and mammography images allows preoperative prediction of axillary lymph node metastasis in breast cancer patients. With the assistance of the model, the diagnostic efficacy of radiologists can be further improved. • We developed a novel multi-modality model that combines MRI and mammography radiomics with clinical factors to accurately predict axillary lymph node (ALN) metastasis, which has not been previously reported. • Our multi-modality model outperformed both the radiologists' ALN diagnosis based on MRI and axillary ultrasound, as well as single-modality radiomics models based on MRI or mammography. • The multi-modality model can serve as a potential decision support tool to improve the radiologists' ALN diagnosis on MRI.

Wang Q ，Lin Y ，Ding C ，Guan W ，Zhang X ，Jia J ，Zhou W ，Liu Z ，Bai G ... -  《-》

Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics.

Lymphovascular invasion (LVI) status facilitates the selection of optimal therapeutic strategy for breast cancer patients, but in clinical practice LVI status is determined in pathological specimens after resection. To explore the use of dynamic contrast-enhanced (DCE)-magnetic resonance imaging (MRI)-based radiomics for preoperative prediction of LVI in invasive breast cancer. Prospective. Ninety training cohort patients (22 LVI-positive and 68 LVI-negative) and 59 validation cohort patients (22 LVI-positive and 37 LVI-negative) were enrolled. 1.5 T and 3.0 T, T1 -weighted DCE-MRI. Axillary lymph node (ALN) status for each patient was evaluated based on MR images (defined as MRI ALN status), and DCE semiquantitative parameters of lesions were calculated. Radiomic features were extracted from the first postcontrast DCE-MRI. A radiomics signature was constructed in the training cohort with 10-fold cross-validation. The independent risk factors for LVI were identified and prediction models for LVI were developed. Their prediction performances and clinical usefulness were evaluated in the validation cohort. Mann-Whitney U-test, chi-square test, kappa statistics, least absolute shrinkage and selection operator (LASSO) regression, logistic regression, receiver operating characteristic (ROC) analysis, DeLong test, and decision curve analysis (DCA). Two radiomic features were selected to construct the radiomics signature. MRI ALN status (odds ratio, 10.452; P < 0.001) and the radiomics signature (odds ratio, 2.895; P = 0.031) were identified as independent risk factors for LVI. The value of the area under the curve (AUC) for a model combining both (0.763) was higher than that for MRI ALN status alone (0.665; P = 0.029) and similar to that for the radiomics signature (0.752; P = 0.857). DCA showed that the combined model added more net benefit than either feature alone. The DCE-MRI-based radiomics signature in combination with MRI ALN status was effective in predicting the LVI status of patients with invasive breast cancer before surgery. 1 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:847-857.

Liu Z ，Feng B ，Li C ，Chen Y ，Chen Q ，Li X ，Guan J ，Chen X ，Cui E ，Li R ，Li Z ，Long W ... -  《-》

Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: A machine learning, multicenter study.

in current clinical practice, the standard evaluation for axillary lymph node (ALN) status in breast cancer has a low efficiency and is based on an invasive procedure that causes operative-associated complications in many patients. Therefore, we aimed to use machine learning techniques to develop an efficient preoperative magnetic resonance imaging (MRI) radiomics evaluation approach of ALN status and explore the association between radiomics and the tumor microenvironment in patients with early-stage invasive breast cancer. in this retrospective multicenter study, three independent cohorts of patients with breast cancer (n = 1,088) were used to develop and validate signatures predictive of ALN status. After applying the machine learning random forest algorithm to select the key preoperative MRI radiomic features, we used ALN and tumor radiomic features to develop the ALN-tumor radiomic signature for ALN status prediction by the support vector machine algorithm in 803 patients with breast cancer from Sun Yat-sen Memorial Hospital and Sun Yat-sen University Cancer Center (training cohort). By combining ALN and tumor radiomic features with corresponding clinicopathologic information, the multiomic signature was constructed in the training cohort. Next, the external validation cohort (n = 179) of patients from Shunde Hospital of Southern Medical University and Tungwah Hospital of Sun Yat-Sen University, and the prospective-retrospective validation cohort (n = 106) of patients treated with neoadjuvant chemotherapy in prospective phase 3 trials [NCT01503905], were included to evaluate the predictive value of the two signatures, and their predictive performance was assessed by the area under operating characteristic curve (AUC). This study was registered with ClinicalTrials.gov, number NCT04003558. the ALN-tumor radiomic signature for ALN status prediction comprising ALN and tumor radiomic features showed a high prediction quality with AUC of 0·88 in the training cohort, 0·87 in the external validation cohort, and 0·87 in the prospective-retrospective validation cohort. The multiomic signature incorporating tumor and lymph node MRI radiomics, clinical and pathologic characteristics, and molecular subtypes achieved better performance for ALN status prediction with AUCs of 0·90, 0·91, and 0·93 in the training cohort, the external validation cohort, and the prospective-retrospective validation cohort, respectively. Among patients who underwent neoadjuvant chemotherapy in the prospective-retrospective validation cohort, there were significant differences in the key radiomic features before and after neoadjuvant chemotherapy, especially in the gray-level dependence matrix features. Furthermore, there was an association between MRI radiomics and tumor microenvironment features including immune cells, long non-coding RNAs, and types of methylated sites. Interpretation this study presented a multiomic signature that could be preoperatively and conveniently used for identifying patients with ALN metastasis in early-stage invasive breast cancer. The multiomic signature exhibited powerful predictive ability and showed the prospect of extended application to tailor surgical management. Besides, significant changes in key radiomic features after neoadjuvant chemotherapy may be explained by changes in the tumor microenvironment, and the association between MRI radiomic features and tumor microenvironment features may reveal the potential biological underpinning of MRI radiomics. No funding.

Yu Y ，He Z ，Ouyang J ，Tan Y ，Chen Y ，Gu Y ，Mao L ，Ren W ，Wang J ，Lin L ，Wu Z ，Liu J ，Ou Q ，Hu Q ，Li A ，Chen K ，Li C ，Lu N ，Li X ，Su F ，Liu Q ，Xie C ，Yao H ... -  《EBioMedicine》