UNASSIGNED: To explore the utility of gray-scale ultrasound (GSUS) and mammography (MG) for radiomic analysis in distinguishing between breast adenosis and invasive ductal carcinoma (IDC).
UNASSIGNED: Data from 147 female patients with pathologically confirmed breast lesions (breast adenosis: 61 patients; IDC: 86 patients) between January 2018 and December 2022 were retrospectively collected. A training cohort of 113 patients (breast adenosis: 50 patients; IDC: 63 patients) diagnosed from January 2018 to December 2021 and a time-independent test cohort of 34 patients (breast adenosis: 11 patients; IDC: 23 patients) diagnosed from January 2022 to December 2022 were included. Radiomic features of lesions were extracted from MG and GSUS images. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the most discriminant features, followed by logistic regression (LR) to construct clinical and radiomic models, as well as a combined model merging radiomic and clinical features. Model performance was assessed using receiver operating characteristic (ROC) analysis.
UNASSIGNED: In the training cohort, the area under the curve (AUC) for radiomic models based on MG features, GSUS features, and their combination were 0.974, 0.936, and 0.991, respectively. In the test cohort, the AUCs were 0.885, 0.876, and 0.949, respectively. The combined model, incorporating clinical and all radiomic features, and the MG plus GSUS radiomics model were found to exhibit significantly higher AUCs than the clinical model in both the training cohort and test cohort (p<0.05). No significant differences were observed between the combined model and the MG plus GSUS radiomics model in the training cohort and test cohort (p>0.05).
UNASSIGNED: The effectiveness of radiomic features derived from GSUS and MG in distinguishing between breast adenosis and IDC is demonstrated. Superior discriminatory efficacy is shown by the combined model, integrating both modalities.

UNASSIGNED: This study aimed to develop a deep learning radiomic model using multimodal imaging to differentiate benign and malignant breast tumours.
UNASSIGNED: Multimodality imaging data, including ultrasonography (US), mammography (MG), and magnetic resonance imaging (MRI), from 322 patients (112 with benign breast tumours and 210 with malignant breast tumours) with histopathologically confirmed breast tumours were retrospectively collected between December 2018 and May 2023. Based on multimodal imaging, the experiment was divided into three parts: traditional radiomics, deep learning radiomics, and feature fusion. We tested the performance of seven classifiers, namely, SVM, KNN, random forest, extra trees, XGBoost, LightGBM, and LR, on different feature models. Through feature fusion using ensemble and stacking strategies, we obtained the optimal classification model for benign and malignant breast tumours.
UNASSIGNED: In terms of traditional radiomics, the ensemble fusion strategy achieved the highest accuracy, AUC, and specificity, with values of 0.892, 0.942 [0.886-0.996], and 0.956 [0.873-1.000], respectively. The early fusion strategy with US, MG, and MRI achieved the highest sensitivity of 0.952 [0.887-1.000]. In terms of deep learning radiomics, the stacking fusion strategy achieved the highest accuracy, AUC, and sensitivity, with values of 0.937, 0.947 [0.887-1.000], and 1.000 [0.999-1.000], respectively. The early fusion strategies of US+MRI and US+MG achieved the highest specificity of 0.954 [0.867-1.000]. In terms of feature fusion, the ensemble and stacking approaches of the late fusion strategy achieved the highest accuracy of 0.968. In addition, stacking achieved the highest AUC and specificity, which were 0.997 [0.990-1.000] and 1.000 [0.999-1.000], respectively. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity of 1.000 [0.999-1.000] under the early fusion strategy.
UNASSIGNED: This study demonstrated the potential of integrating deep learning and radiomic features with multimodal images. As a single modality, MRI based on radiomic features achieved greater accuracy than US or MG. The US and MG models achieved higher accuracy with transfer learning than the single-mode or radiomic models. The traditional radiomic and depth features of US+MG + MR achieved the highest sensitivity under the early fusion strategy, showed higher diagnostic performance, and provided more valuable information for differentiation between benign and malignant breast tumours.

Breast cancer (BC) significantly contributes to cancer-related mortality in women, underscoring the criticality of early detection for optimal patient outcomes. Mammography is a key tool for identifying and diagnosing breast abnormalities; however, accurately distinguishing malignant mass lesions remains challenging. To address this issue, we propose a novel deep learning approach for BC screening utilizing mammography images. Our proposed model comprises three distinct stages: data collection from established benchmark sources, image segmentation employing an Atrous Convolution-based Attentive and Adaptive Trans-Res-UNet (ACA-ATRUNet) architecture, and BC identification via an Atrous Convolution-based Attentive and Adaptive Multi-scale DenseNet (ACA-AMDN) model. The hyperparameters within the ACA-ATRUNet and ACA-AMDN models are optimized using the Modified Mussel Length-based Eurasian Oystercatcher Optimization (MML-EOO) algorithm. The performance is evaluated using a variety of metrics, and a comparative analysis against conventional methods is presented. Our experimental results reveal that the proposed BC detection framework attains superior precision rates in early disease detection, demonstrating its potential to enhance mammography-based screening methodologies.

To explore the diagnostic efficacy of tomosynthesis spot compression (TSC) compared with conventional spot compression (CSC) for ambiguous findings on full-field digital mammography (FFDM). In this retrospective study, 122 patients (including 108 patients with dense breasts) with ambiguous FFDM findings were imaged with both CSC and TSC. Two radiologists independently reviewed the images and evaluated lesions using the Breast Imaging Reporting and Data System. Pathology or at least a 1-year follow-up imaging was used as the reference standard. Diagnostic efficacies of CSC and TSC were compared, including area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). The mean glandular dose was recorded and compared for TSC and CSC. Of the 122 patients, 63 had benign lesions and 59 had malignant lesions. For Reader 1, the following diagnostic efficacies of TSC were significantly higher than those of CSC: AUC (0.988 vs. 0.906, P = 0.001), accuracy (93.4% vs. 77.8%, P = 0.001), specificity (87.3% vs. 63.5%, P = 0.002), PPV (88.1% vs. 70.5%, P = 0.010), and NPV (100% vs. 90.9%, P = 0.029). For Reader 2, TSC showed higher AUC (0.949 vs. 0.909, P = 0.011) and accuracy (83.6% vs. 71.3%, P = 0.022) than CSC. The mean glandular dose of TSC was higher than that of CSC (1.85 ± 0.53 vs. 1.47 ± 0.58 mGy, P < 0.001) but remained within the safety limit. TSC provides better diagnostic efficacy with a slightly higher but tolerable radiation dose than CSC. Therefore, TSC may be a candidate modality for patients with ambiguous findings on FFDM.

BACKGROUND: Higher mammographic density (MD), a radiological measure of the proportion of fibroglandular tissue in the breast, and lower terminal duct lobular unit (TDLU) involution, a histological measure of the amount of epithelial tissue in the breast, are independent breast cancer risk factors. Previous studies among predominantly white women have associated reduced TDLU involution with higher MD.
METHODS: In this cohort of 611 invasive breast cancer patients (ages 23-91 years [58.4% ≥ 50 years]) from China, where breast cancer incidence rates are lower and the prevalence of dense breasts is higher compared with Western countries, we examined the associations between TDLU involution assessed in tumor-adjacent normal breast tissue and quantitative MD assessed in the contralateral breast obtained from the VolparaDensity software. Associations were estimated using generalized linear models with MD measures as the outcome variables (log-transformed), TDLU measures as explanatory variables (categorized into quartiles or tertiles), and adjusted for age, body mass index, parity, age at menarche and breast cancer subtype.
RESULTS: We found that, among all women, percent dense volume (PDV) was positively associated with TDLU count (highest tertile vs. zero: Expbeta = 1.28, 95% confidence interval [CI] 1.08-1.51, ptrend =  < .0001), TDLU span (highest vs. lowest tertile: Expbeta = 1.23, 95% CI 1.11-1.37, ptrend =  < .0001) and acini count/TDLU (highest vs. lowest tertile: Expbeta = 1.22, 95% CI 1.09-1.37, ptrend = 0.0005), while non-dense volume (NDV) was inversely associated with these measures. Similar trend was observed for absolute dense volume (ADV) after the adjustment of total breast volume, although the associations for ADV were in general weaker than those for PDV. The MD-TDLU associations were generally more pronounced among breast cancer patients ≥ 50 years and those with luminal A tumors compared with patients < 50 years and with luminal B tumors.
CONCLUSIONS: Our findings based on quantitative MD and TDLU involution measures among Chinese breast cancer patients are largely consistent with those reported in Western populations and may provide additional insights into the complexity of the relationship, which varies by age, and possibly breast cancer subtype.

BACKGROUND: The estrogen receptor (ER) serves as a pivotal indicator for assessing endocrine therapy efficacy and breast cancer prognosis. Invasive biopsy is a conventional approach for appraising ER expression levels, but it bears disadvantages due to tumor heterogeneity. To address the issue, a deep learning model leveraging mammography images was developed in this study for accurate evaluation of ER status in patients with breast cancer.
OBJECTIVE: To predict the ER status in breast cancer patients with a newly developed deep learning model leveraging mammography images.
METHODS: Datasets comprising preoperative mammography images, ER expression levels, and clinical data spanning from October 2016 to October 2021 were retrospectively collected from 358 patients diagnosed with invasive ductal carcinoma. Following collection, these datasets were divided into a training dataset (n = 257) and a testing dataset (n = 101). Subsequently, a deep learning prediction model, referred to as IP-SE-DResNet model, was developed utilizing two deep residual networks along with the Squeeze-and-Excitation attention mechanism. This model was tailored to forecast the ER status in breast cancer patients utilizing mammography images from both craniocaudal view and mediolateral oblique view. Performance measurements including prediction accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curves (AUCs) were employed to assess the effectiveness of the model.
RESULTS: In the training dataset, the AUCs for the IP-SE-DResNet model utilizing mammography images from the craniocaudal view, mediolateral oblique view, and the combined images from both views, were 0.849 (95% CIs: 0.809-0.868), 0.858 (95% CIs: 0.813-0.872), and 0.895 (95% CIs: 0.866-0.913), respectively. Correspondingly, the AUCs for these three image categories in the testing dataset were 0.835 (95% CIs: 0.790-0.887), 0.746 (95% CIs: 0.793-0.889), and 0.886 (95% CIs: 0.809-0.934), respectively. A comprehensive comparison between performance measurements underscored a substantial enhancement achieved by the proposed IP-SE-DResNet model in contrast to a traditional radiomics model employing the naive Bayesian classifier. For the latter, the AUCs stood at only 0.614 (95% CIs: 0.594-0.638) in the training dataset and 0.613 (95% CIs: 0.587-0.654) in the testing dataset, both utilizing a combination of mammography images from the craniocaudal and mediolateral oblique views.
CONCLUSIONS: The proposed IP-SE-DResNet model presents a potent and non-invasive approach for predicting ER status in breast cancer patients, potentially enhancing the efficiency and diagnostic precision of radiologists.

This study aimed to assess the utility of second-look ultrasonography (US) in differentiating breast imaging reporting and data system (BI-RADS) 4 calcifications initially detected on mammography (MG). BI-RADS 4 calcifications have a wide range of positive predictive values. We hypothesized that second-look US would help distinguish BI-RADS 4 calcifications without clinical manifestations and other abnormalities on MG. This study included 1622 pure BI-RADS 4 calcifications in 1510 women (112 patients with bilateral calcifications). The cases were randomly divided into training (85%) and testing (15%) datasets. Two nomograms were developed to differentiate BI-RADS 4 calcifications in the training dataset: the MG-US nomogram, based on multifactorial logistic regression and incorporated clinical information, MG, and second-look US characteristics, and the MG nomogram, based on clinical information and mammographic characteristics. Calibration of the MG-US nomogram was performed using calibration curves. The discriminative ability and clinical utility of both nomograms were compared using the area under the receiver operating characteristic curve (AUC) and the decision analysis curve (DCA) in the test dataset. The clinical information and imaging characteristics were comparable between the training and test datasets. The bias-corrected calibration curves of the MG-US nomogram closely approximate the ideal line for both datasets. In the test dataset, the MG-US nomogram exhibited a higher AUC than the MG nomogram (0.899 vs 0.852, P = .01). DCA demonstrated the superiority of the MG-US nomogram over the MG nomogram. Second-look US features, including ultrasonic calcifications, lesions, and moderate or marked color flow, were valuable for distinguishing BI-RADS 4 calcifications without clinical manifestations and other abnormalities on MG.

Aims/Background Breast leukaemia (BL) is a rare breast malignancy that is treated differently from other malignant conditions. However, it is easily confused with other conditions; therefore, how to accurately diagnose is crucial. We retrospectively analysed the imaging findings of 13 patients to provide a diagnostic reference. Methods From January 2015 to April 2023, 13 patients with BL confirmed by biopsy who underwent imaging in Peking University People\'s hospital were retrospectively analysed. The imaging findings obtained via ultrasound (US), mammography (MMG), magnetic resonance imaging (MRI), and positron emission tomography/computed tomography (PET/CT) were analysed, and the detection rates of these methods for diagnosing BL were compared. Results Twenty-nine lesions were detected in the 13 patients. These patients presented with palpable masses or breast swelling several months after treatment for leukaemia, mainly involving the bilateral breasts. Ultrasonography was performed for 13 patients, and all lesions were detected. Most of the identified masses were hypoechoic and had indistinct boundaries, irregular shapes, no enhancement of the posterior echo, and no abundant blood flow. MMG was performed for five patients, revealing breast masses, architectural distortion, and no abnormalities. MRI was performed for four patients, and all lesions were detected; most of the lesions were hypointense on T1-weighted imaging and hyperintense on T2-weighted imaging and diffusion-weighted imaging, with a decreased apparent diffusion coefficient and inhomogeneous enhancement. The enhancement curves were mostly inflow patterns. PET/CT was performed for four patients; two patients had hypermetabolism, and the other two had no obvious radioactive uptake. Conclusion Compared to MMG and PET/CT, US and MRI have higher detection rates. Furthermore, compared to MRI, US is inexpensive, convenient and efficient; therefore, it should be the first choice for diagnosing BL.

Computer-aided diagnosis systems play a crucial role in the diagnosis and early detection of breast cancer. However, most current methods focus primarily on the dual-view analysis of a single breast, thereby neglecting the potentially valuable information between bilateral mammograms. In this paper, we propose a Four-View Correlation and Contrastive Joint Learning Network (FV-Net) for the classification of bilateral mammogram images. Specifically, FV-Net focuses on extracting and matching features across the four views of bilateral mammograms while maximizing both their similarities and dissimilarities. Through the Cross-Mammogram Dual-Pathway Attention Module, feature matching between bilateral mammogram views is achieved, capturing the consistency and complementary features across mammograms and effectively reducing feature misalignment. In the reconstituted feature maps derived from bilateral mammograms, the Bilateral-Mammogram Contrastive Joint Learning module performs associative contrastive learning on positive and negative sample pairs within each local region. This aims to maximize the correlation between similar local features and enhance the differentiation between dissimilar features across the bilateral mammogram representations. Our experimental results on a test set comprising 20% of the combined Mini-DDSM and Vindr-mamo datasets, as well as on the INbreast dataset, show that our model exhibits superior performance in breast cancer classification compared to competing methods.

To explore the clinicopathological characteristics and prognostic significance of casting-type calcification (CC) in patients with breast cancer presenting with microcalcification on mammography. Data on patients with invasive breast cancer who had mammographic calcification was retrospectively analyzed. The chi-square test was utilized to assess the clinicopathological characteristics of two forms of CC-related breast cancer. The examination of prognostic variables was conducted using Kaplan-Meier and Cox regression analyses. A total of 427 eligible patients were included in this study. Chi-square analysis indicated that the presence of CC was associated with estrogen receptor (ER) negativity (P = 0.005), progesterone receptor (PR) negativity (P < 0.001), and epidermal growth factor receptor 2 (HER-2) positivity (P < 0.001); among these, the association was stronger with the CC-predominant type. After a median follow-up of 82 months, those with CC had a worse 5-year recurrence-free survival (RFS) (77.1% vs. 86.9%, p = 0.036; hazard ratio [HR], 1.86; 95% confidence interval [CI] 1.04-3.31) and overall survival (OS) (84.0% vs. 94.4%, p = 0.007; HR, 2.99; 95% CI 1.34-6.65) rates. In COX regression analysis, such differences were still observed in HER-2 positive subgroups (RFS: HR: 2.45, 95% CI 1-5.97, P = 0.049; OS: HR: 4.53, 95% CI 1.17-17.52, P = 0.029). In patients with invasive breast cancer exhibiting calcifications on mammography, the presence of CC, especially the CC-predominant type, is linked to a higher frequency of hormone receptor negativity and HER-2 positivity. The presence of CC is associated with an unfavorable 5-year RFS and OS rates.