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.

BACKGROUND: Accurate diagnosis of breast lesions and discrimination of axillary lymph node (ALN) metastases largely depend on radiologist experience. PURPOSE: To develop a deep learning-based whole-process system (DLWPS) for segmentation and diagnosis of breast lesions and discrimination of ALN metastasis. STUDY TYPE: Retrospective. POPULATION: 1760 breast patients, who were divided into training and validation sets (1110 patients), internal (476 patients), and external (174 patients) test sets. FIELD STRENGTH/SEQUENCE: 3.0T/dynamic contrast-enhanced (DCE)-MRI sequence. ASSESSMENT: 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. STATISTICAL TESTS: Dice similarity coefficient (DI), area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and kappa value. RESULTS: 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. DATA CONCLUSION: The performance of DLWPS indicates that it can promote radiologists in the judgment of breast lesions and ALN metastasis and nonmetastasis. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 3.

Role of contrast-enhanced mammography in the preoperative detection of ductal carcinoma in situ of the breasts: a comparison with low-energy image and magnetic resonance imaging.

OBJECTIVES: To compare contrast-enhanced mammography (CEM) with low-energy image (LEI) alone and with magnetic resonance imaging (MRI) in the preoperative diagnosis of ductal carcinoma in situ (DCIS). METHODS: In this single-center retrospective study, we reviewed 98 pure DCIS lesions in 96 patients who underwent CEM and MRI within 2 weeks preoperatively. The diagnostic performances of each imaging modality, lesion morphology, and extent were evaluated. RESULTS: The sensitivity of CEM to DCIS was similar to that of MRI (92.9% vs. 93.9%, p = 0.77) and was significantly higher than that of LEI alone (76.5%, p = 0.002). The sensitivity of CEM to calcified DCIS (92.4%) was not significantly different from LEI alone (92.4%) and from MRI (93.9%, p = 1.00). However, CEM contributed to the simultaneous comparison of calcifications with enhancements. CEM had considerably higher sensitivity compared with LEI alone (93.8% vs. 43.8%, p < 0.001) and performed similarly to MRI (93.8%, p = 1.00) for noncalcified DCIS. All DCIS lesions were enhanced in MRI, whereas 94.9% (93/98) were enhanced in CEM. Non-mass enhancement was the most common presentation (CEM 63.4% and MRI 66.3%). The difference between the lesion size on each imaging modality and the histopathological size was smallest in MRI, followed by CEM, and largest in LEI. CONCLUSION: CEM was more sensitive than LEI alone and comparable to MRI in DCIS diagnosis. The enhanced morphology of DCIS in CEM was consistent with that in MRI. CEM was superior to LEI alone in size measurement of DCIS. CLINICAL RELEVANCE STATEMENT: This study investigated the value of CEM in the diagnosis and evaluation of DCIS, aiming to offer a reference for the selection of examination methods for DCIS and contribute to the early diagnosis and precise treatment of DCIS. KEY POINTS: • DCIS is an important indication for breast surgery. Early and accurate diagnosis is crucial for DCIS treatment and prognosis. • CEM overcomes the deficiency of mammography in noncalcified DCIS diagnosis, exhibiting similar sensitivity to MRI; and CEM contributes to the comparison of calcification and enhancement of calcified DCIS, thereby outperforming MRI. • CEM is superior to LEI alone and slightly inferior to MRI in the size evaluation of DCIS.

Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study.

Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography (CEM) images. Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system (MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion (AFF) algorithm that could intelligently incorporates multiple types of information from CEM images. The average free-response receiver operating characteristic score (AFROC-Score) was presented to validate system's detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve (AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases, comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists' performance. Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909 [95% confidence interval (95% CI): 0.822-0.996] and 0.912 (95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists' average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance. Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions, and greatly enhanced the overall performance of radiologists.

Intra- and peritumoral radiomics for predicting malignant BiRADS category 4 breast lesions on contrast-enhanced spectral mammography: a multicenter study.

OBJECTIVE: To construct and test a nomogram based on intra- and peritumoral radiomics and clinical factors for predicting malignant BiRADS 4 lesions on contrast-enhanced spectral mammography. METHODS: A total of 884 patients with BiRADS 4 lesions were enrolled from two centers. For each lesion, five ROIs were defined using the intratumoral region (ITR), peritumoral regions (PTRs) of 5 and 10 mm around the tumor, and ITR plus PTRs of 5 mm and 10 mm. Five radiomics signatures were established by LASSO after selecting features. A nomogram was built using selected signatures and clinical factors by multivariable logistic regression analysis. The performance of the nomogram was assessed with the AUC, decision curve analysis, and calibration curves, and also compared with the radiomics model, clinical model, and radiologists. RESULTS: The nomogram built by three radiomics signatures (constructed from ITR, 5 mm PTR, and ITR + 10 mm PTR) and two clinical factors (age and BiRADS category) showed powerful predictive ability in internal and external test sets with AUCs of 0.907 and 0.904, respectively. The calibration curves, decision curve analysis, showed favorable predictive performance of the nomogram. In addition, radiologists improved the diagnostic performance with the help of nomogram. CONCLUSION: The nomogram established via intratumoral and peritumoral radiomics features and clinical risk factors had the best performance in distinguishing benign and malignant BiRADS 4 lesions, which could help radiologists improve diagnostic capabilities. KEY POINTS: • Radiomics features from peritumoral regions in contrast-enhanced spectral mammography images may provide valuable information for the diagnosis of benign and malignant breast imaging reporting and data system category 4 breast lesions. • The nomogram incorporated intra- and peritumoral radiomics features and clinical variables have good application prospects in assisting clinical decision-makers.

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

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.

Improving CT detection sensitivity for nodal metastases in oesophageal cancer with combination of smaller size and lymph node axial ratio.

OBJECTIVES: To investigate the value of CT with inclusion of smaller lymph node (LN) sizes and axial ratio to improve the sensitivity in diagnosis of regional lymph node metastases in oesophageal squamous cell carcinoma (OSCC). METHODS: The contrast-enhanced multidetector row spiral CT (MDCT) multiplanar reconstruction images of 204 patients with OSCC were retrospectively analysed. The long-axis and short-axis diameters of the regional LNs were measured and axial ratios were calculated (short-axis/long-axis diameters). Nodes were considered round if the axial ratio exceeded the optimal LN axial ratio, which was determined by receiver operating characteristic analysis. RESULTS: A positive predictive value (PPV) exceeding 50% is needed. This was achieved only with LNs larger than 9 mm in short-axis diameter, but nodes of this size were rare (sensitivity 37.3%, specificity 96.4%, accuracy 85.8%). If those round nodes (axial ratio exceeding 0.66 ) between 7 mm and 9 mm in size were considered metastases as well, it might improve the sensitivity to 67.2% with a PPV of 63.9% (specificity 91.6%, accuracy 87.2%). CONCLUSION: Combination of a smaller size and axial ratio for LNs in MDCT as criteria improves the detection sensitivity for LN metastases in OSCC. KEY POINTS: • CT is widely used to assess metastatic lymph nodes. • CT has low sensitivity in detecting metastases using conventional criteria. • Diagnostic sensitivity of CT was improved by using lymph node axial ratio. • New diagnostic criteria provide greater diagnostic confidence with PPVs exceeding 50%. • New diagnostic criteria may help clinicians assess patients with oesophageal cancer.