Noninvasive, accurate and novel approaches to predict patients who will achieve pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) could assist treatment strategies. The aim of this study was to explore the application of machine learning (ML) based peritumoral ultrasound radiomics signature (PURS), compared with intratumoral radiomics (IURS) and clinicopathologic factors, for early prediction of pCR.

We analyzed 358 locally advanced breast cancer patients (250 in the training set and 108 in the test set), who accepted NAC and post NAC surgery at our institution. The clinical and pathological data were analyzed using the independent t test and the Chi-square test to determine the factors associated with pCR. The PURS and IURS of baseline breast tumors were extracted by using 3D-slicer and PyRadiomics software. Five ML classifiers including linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), logistic regression (LR), and adaptive boosting (AdaBoost) were applied to construct radiomics predictive models. The performance of PURS, IURS models and clinicopathologic predictors were assessed with respect to sensitivity, specificity, accuracy and the areas under the curve (AUCs).

Ninety-seven patients achieved pCR. The clinicopathologic predictors obtained an AUC of 0.759. Among PURS models, the RF classifier achieved better efficacy (AUC of 0.889) than LR (0.849), AdaBoost (0.823), SVM (0.746) and LDA (0.732). The RF classifier also obtained a maximum AUC of 0.931 than 0.920 (AdaBoost), 0.875 (LR), 0.825 (SVM), and 0.798 (LDA) in IURS models in the test set. The RF based PURS yielded higher predictive ability (AUC 0.889; 95% CI 0.814, 0.947) than clinicopathologic factors (AUC 0.759; 95% CI 0.657, 0.861; p < 0.05), but lower efficacy compared with IURS (AUC 0.931; 95% CI 0.865, 0.980; p < 0.05).

The peritumoral US radiomics, as a novel potential biomarker, can assist clinical therapy decisions.

The atypical category (AC) by the Yokohama system is an indeterminate group characterized by predominantly benign cytomorphology of the lesions, with some uncommon features that may be seen in malignancy in breast fine-needle aspiration. The risk of malignancy (ROM) varies from 13% to 25%. Its management depends on the clinical and radiological findings. Since most cases are benign, selecting cases for further management may benefit patients. This study aims to determine the clinicoradiological predictors for malignancy in AC breast cytology.

All AC breast fine-needle aspirations at Chiang Mai University Hospital from 2015 to 2019 were selected from an electronic database for cyto-histological correlation and ROM calculation. The clinicoradiological factors calculated by ROM were analyzed using multivariable logistic regression for malignant prediction and screening scores.

There were 218 aspirates from patients aged 15-77 years. The lesion size ranged from 0.2 to 9.2 cm. The ROM was 27.5%. The significant predictors were age ≥40 years (P = 0.03), lesion size ≥1 cm (P< 0.01), and suspicious calcification on imaging (P < 0.01). The ROM was numerically increased in Breast Imaging-Reporting and Data System 5. The screening score showed 88.3% sensitivity, 55.1% specificity, 42.7% positive predictive value, and 92.6% negative predictive value.

The AC diagnosis varies from benign to malignant. Age ≥40 years, a lesion size ≥1 cm, and suspicious calcification/Breast Imaging-Reporting and Data System 5 are useful predictors of malignancy. Selecting cases according to screening scores can reduce invasive procedures by up to 43.1%.

This study aimed to develop an interpretable machine learning model that accurately predicts Ki-67 expression in breast cancer (BC) patients using a combination of dynamic-contrast enhanced magnetic resonance imaging (DCE-MRI) radiomics and clinical-imaging features. A total of 195 BC patients, including 201 lesions, were enrolled retrospectively. These lesions were randomized into training and testing set (7:3). The correlation between clinical-imaging features and Ki-67 expression was analyzed via univariate analysis and binary logistic regression, leading to the development of a Clinical-imaging model. Radiomics features were extracted based on the early and delayed phases of DCE-MRI. These features were screened by Pearson correlation coefficient and recursive feature elimination (RFE). The logistic regression classifier was used to develop the Radiomics model. The clinical imaging and radiomics features were combined to form a Combined model. The Shapley Additive Explanation (SHAP) algorithm was employed to explain the optimal model, and the AUC was used to assess the model's performance. Ki-67 expression was markedly different from the internal enhancement pattern and necrosis among the imaging features. Compared to the Clinical-imaging model (AUC = 0.682), the AUCs of the Radiomics and the Combined models in the training set were 0.797 and 0.821, respectively. Clinical-imaging, Radiomics, and Combined models had AUCs of 0.666, 0.796, and 0.802 in the test set. Based on the IDI results, the combined model outperformed the Clinical-imaging and Radiomics models in the training set by 11.8% and 2.1%, respectively. They increased by 11% and 1.74% in the test set. SHAP analysis showed that ph2-original-shape-surface volume ratio was the most important feature of the model. Based on clinical-imaging features and DCE-MRI radiomics, the interpretable machine learning model can accurately predict the expression of Ki-67 in BC. Combining the SHAP algorithm with the model improves its interpretability, which may assist clinicians in formulating more accurate treatment strategies.

To investigate whether sonographic glandular tissue component (GTC) can optimize the management of breast imaging reporting and data system (BI-RADS) 4A breast masses.

We reviewed the patients with BI-RADS 4A breast masses confirmed by ultrasound and pathology reports from January to December 2020. Based on conventional breast ultrasound images, GTC was categorized into GTC-Low and GTC-High. The consistency of the GTC classification between two radiologists was evaluated using a kappa test. Propensity score matching (PSM) was applied to adjust for unbalanced characteristics between the two groups. Logistic regression was used to analyze the relationship between sonographic GTC and the likelihood of BI-RADS 4A masses being benign or malignant.

Of the 319 patients included finally in the study, the agreement between the two radiologists regarding the GTC classification was good (weighted kappa: 0.736/0.716). The malignancy rate in the GTC-High group (32.7%, 16/49) was significantly higher than that in the overall cohort (14.1%, 45/319; P=0.001). After PSM adjustment to balance relevant covariates between the GTC-High and GTC-Low groups, 45 GTC-High patients were matched with 45 GTC-Low patients. After matching, univariate and multivariate logistic regression analyses identified sonographic GTC as an independent variable associated with malignancy in BI-RADS 4A masses (P=0.012). After matching, the malignancy rate in the GTC-High group (35.6%,16/45) was significantly higher (P=0.014) than that in the GTC-Low group (13.3%, 6/45).

Sonographic GTC is an independent predictor of malignancy in BI-RADS 4A breast masses. Masses initially classified as BI-RADS 4A may warrant reclassification to BI-RADS 4B when identified as GTC-High.

Breast cancer is the leading cause of mortality from cancer in women worldwide. Ultrasound is commonly utilized to identify breast cancers but is dependent on operator experience. This study established a radiomics model aimed at enhancing diagnostic efficacy in distinguishing between benign and malignant breast lesions using ultrasound.

A total of 316 patients were retrospectively included in this study. Two types of feature groups were extracted from ultrasound images: traditional radiomics features and customized features derived from BI-RADS (Breast Imaging Reporting & Data System) classification criteria. The radiomics features were categorized into 3 groups: (A) BI-RADS features, (B) radiomics features, and (C) a combination of both feature groups. Subsequently, SVM (Support Vector Machine), RF (Random Forest) and LR (Logistic Regression) algorithms were utilized to model and analyze based on the 3 feature groups. Finally, the model's performance was evaluated, and the SHAP method was employed to investigate the interpretability of the model.

In Group C, the SVM model demonstrated the best performance on the testing set, achieving an AUC and accuracy of approximately 0.91. The SHAP results revealed that the entropy and variance had the most significant impact on the output of the model (SVM for Group C).

The SVM model constructed using BI-RADS features combined with radiomics feature demonstrated high diagnostic accuracy in distinguishing between benign and malignant breast lesions. This model may assist radiologists in differentiating malignant from benign breast lesions.

To explore the image features and the diagnostic value of contrast-enhanced ultrasound (CEUS) for ductal carcinoma in situ (DCIS) of the breast. A total of 96 female patients with a solitary and histologically proven DCIS were analyzed retrospectively, and 100 female cases of invasive ductal carcinoma (IDC) lesions were used as the control group. The Breast Imaging Reporting and Data System (BI-RADS) category of breast lesions was assessed according to conventional ultrasound features. The DCIS lesions were classified into mass type and non-mass type. The CEUS characteristics of these breast lesions were retrospectively analyzed qualitatively and quantitatively. The final gold standard was biopsy or surgery with histo-pathological examination. Comparing the ultrasound images of DCIS with that of IDC, there were significant differences in echo pattern, calcification morphology, and calcification distribution (p < .05 for all). There was a significant difference between DCIS and IDC in enhancement intensity, perfusion defects, peripheral high enhancement, intratumoral vessels, and arrival time (AT) (p < .05 for all). In the logistic multivariate regression analysis, two indicators linked with DCIS were recognized: perfusion defects (p = .002) and peripheral high enhancement (p < .001). In forecasting DCIS, the logistic regression equation resulted in an AUC of 0.689, a specificity of 0.720, and a sensitivity of 0.563. CEUS showed differences in enhancement characteristics between DCIS and IDC, with perfusion defects and peripheral high enhancement being associated with DCIS.

To compare the performance of ultrafast MRI with standard MRI in classifying histological factors and subtypes of invasive breast cancer among radiologists with varying experience.

From October 2021 to November 2022, this prospective study enrolled 225 participants with 233 breast cancers before treatment (NCT06104189 at clinicaltrials.gov). Tumor segmentation on MRI was performed independently by two readers (R1, dedicated breast radiologist; R2, radiology resident). We extracted 1618 radiomic features and four kinetic features from ultrafast and standard images, respectively. Logistic regression algorithms were adopted for prediction modeling, following feature selection by the least absolute shrinkage and selection operator. The performance of predicting histological factors and subtypes was evaluated using the area under the receiver-operating characteristic curve (AUC). Performance differences between MRI methods and radiologists were assessed using the DeLong test.

Ultrafast MRI outperformed standard MRI in predicting HER2 status (AUCs [95% CI] of ultrafast MRI vs standard MRI; 0.87 [0.83-0.91] vs 0.77 [0.64-0.90] for R1 and 0.88 [0.83-0.91] vs 0.77 [0.69-0.84] for R2) (all P < 0.05). Both ultrafast MRI and standard MRI showed comparable performance in predicting hormone receptors. Ultrafast MRI exhibited superior performance to standard MRI in classifying subtypes. The classification of the luminal subtype for both readers, the HER2-overexpressed subtype for R2, and the triple-negative subtype for R1 was significantly better with ultrafast MRI (P < 0.05).

Ultrafast MRI-based radiomics holds promise as a noninvasive imaging biomarker for classifying hormone receptors, HER2 status, and molecular subtypes compared to standard MRI, regardless of radiologist experience.

Sentinel lymph node biopsy (SLNB) of the axilla is standard in breast cancer (BC) management; however, its role in prophylactic/contralateral prophylactic mastectomy (CPM) is still questioned. To avoid future consequences on surgical morbidity and socioeconomic aspects in low and middle-income countries (LMICs), we intend to determine the prevalence of occult breast cancer (OBC) among CPM cases.

To determine the prevalence of OBC in patients undergoing prophylactic mastectomy (PM).

This is a retrospective cohort study.

This retrospective cohort study is conducted at a tertiary-care hospital from January 2017 to December 2022. All individuals with the positive genetic test for high-risk breast cancer (HRBC) genes who underwent PMs/CPM at our centre were included. We analysed data using SPSS version 23.0.

Twenty-six mutation-positive females underwent PM/CPM (16.1%). Two (7.69%) of 26 had later post-PM recurrence. Only 8 (30.76%) patients had SLNB and all were negative. No OBC was seen in PM/CPM specimens, whereas 3 (11.5%) had atypical ductal hyperplasia (ADH). Two of the ADH had BI-RADS-1, whereas 1 was BI-RADS-4 (33.3%) on the preoperative assessment. Results also showed that with an increase in the tumour grade of the diseased breast, the BI-RADS score of the asymptomatic breast was subsequently increased (P = .029).

Our study shows negative OBCs in PM/CPM cases with persistently negative SLNB results; however, ADH is identified in 11.5% of specimens. Our results suggest that SLNB can be safely omitted in patients undergoing CPM, but, preoperatively, patient and disease factors should be considered.

To investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions.

A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n = 655; test cohort: n = 281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation.

A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models.

The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.

IntroductionTumor-infiltrating lymphocytes (TILs) are key indicators of immune response and prognosis in breast cancer (BC). Accurate prediction of TIL levels is essential for guiding personalized treatment strategies. This study aimed to develop and evaluate machine learning models using ultrasound-derived radiomics and clinical features to predict TIL levels in BC.MethodsThis retrospective study included 256 BC patients between January 2019 and August 2023, who were randomly divided into training (n = 179) and test (n = 77) cohorts. Radiomics features were extracted from the intratumor and peritumor regions in ultrasound images. Feature selection was performed using the "Boruta" package in R to iteratively remove non-significant features. Extra Trees Classifier was used to construct radiomics and clinical models. A combined radiomics-clinical (R-C) model was also developed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and decision curve analysis (DCA) to assess clinical utility. A nomogram was created based on the best-performing model.ResultsA total of 1712 radiomics features were extracted from the intratumor and peritumor regions. The Boruta method selected five key features (four from the peritumor and one from the intratumor) for model construction. Clinical features, including immunohistochemistry, tumor size, shape, and echo characteristics, showed significant differences between high (≥10%) and low (<10%) TIL groups. Both the R-C and radiomics models outperformed the clinical model in the test cohort (area under the curve values of 0.869/0.838 vs 0.627, P < .05). Calibration curves and Brier scores demonstrated superior accuracy and calibration for the R-C and radiomics models. DCA revealed the highest net benefit of the R-C model at intermediate threshold probabilities.ConclusionUltrasound-derived radiomics effectively predicts TIL levels in BC, providing valuable insights for personalized treatment and surveillance strategies.

This study aims to explore the accuracy of Convolutional Neural Network (CNN) models in predicting malignancy in Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging (DCE-BMRI).

A total of 273 benign lesions (benign group) and 274 malignant lesions (malignant group) were collected and randomly divided into a training set (246 benign and 245 malignant lesions) and a testing set (28 benign and 28 malignant lesions) in a 9:1 ratio. An additional 53 lesions from 53 patients were designated as the validation set. Five models-VGG16, VGG19, DenseNet201, ResNet50, and MobileNetV2-were evaluated. Model performance was assessed using accuracy (Ac) in the training and testing sets, and precision (Pr), recall (Rc), F1 score (F1), and area under the receiver operating characteristic curve (AUC) in the validation set.

The accuracy of VGG19 on the test set (0.96) is higher than that of VGG16 (0.91), DenseNet201 (0.91), ResNet50 (0.67), and MobileNetV2 (0.88). For the validation set, VGG19 achieved higher performance metrics (Pr 0.75, Rc 0.76, F1 0.73, AUC 0.76) compared to the other models, specifically VGG16 (Pr 0.73, Rc 0.75, F1 0.70, AUC 0.73), DenseNet201 (Pr 0.71, Rc 0.74, F1 0.69, AUC 0.71), ResNet50 (Pr 0.65, Rc 0.68, F1 0.60, AUC 0.65), and MobileNetV2 (Pr 0.73, Rc 0.75, F1 0.71, AUC 0.73). S4 model achieved higher performance metrics (Pr 0.89, Rc 0.88, F1 0.87, AUC 0.89) compared to the other four fine-tuned models, specifically S1 (Pr 0.75, Rc 0.76, F1 0.74, AUC 0.75), S2 (Pr 0.77, Rc 0.79, F1 0.75, AUC 0.77), S3 (Pr 0.76, Rc 0.76, F1 0.73, AUC 0.75), and S5 (Pr 0.77, Rc 0.79, F1 0.75, AUC 0.77). Additionally, S4 model showed the lowest loss value in the testing set. Notably, the AUC of S4 for BI-RADS 3 was 0.90 and for BI-RADS 4 was 0.86, both significantly higher than the 0.65 AUC for BI-RADS 5.

The S4 model we propose has demonstrated superior performance in predicting the likelihood of malignancy in DCE-BMRI, making it a promising candidate for clinical application in patients with breast diseases. However, further validation is essential, highlighting the need for additional data to confirm its efficacy.

The prognosis of ductal carcinoma in situ with microinvasion (DCISM) is more similar to that of small invasive ductal carcinoma (IDC) than to pure ductal carcinoma in situ (DCIS). It is particularly important to accurately distinguish between DCISM and DCIS. The present study aims to compare the clinical and imaging characteristics of contrast-enhanced mammography (CEM) and magnetic resonance imaging (MRI) between DCISM and pure DCIS, and to identify predictive factors of microinvasive carcinoma, which may contribute to a comprehensive understanding of DCISM in clinical diagnosis and support surveillance strategies, such as surgery, radiation, and other treatment decisions.

Forty-seven female patients diagnosed with DCIS were included in the study from May 2019 to August 2023. Patients were further divided into two groups based on pathological diagnosis: DCIS and DCISM. Clinical and imaging characteristics of these two groups were analyzed statistically. The independent clinical risk factors were selected using multivariate logistic regression and used to establish the logistic model [Logit(P)]. The diagnostic performance of independent predictors was assessed and compared using receiver operating characteristic (ROC) analysis and DeLong's test.

In CEM, the maximum cross-sectional area (CSAmax), the percentage signal difference between the enhancing lesion and background in the craniocaudal and mediolateral oblique projection (%RSCC, and %RSMLO) were found to be significantly higher for DCISM compared to DCIS (p = 0.001; p < 0.001; p = 0.008). Additionally, there were noticeable statistical differences in the patterns of enhancement morphological distribution (EMD) and internal enhancement pattern (IEP) between DCIS and DCISM (p = 0.047; p = 0.008). In MRI, only CSAmax (p = 0.012) and IEP (p = 0.020) showed significant statistical differences. The multivariate regression analysis suggested that CSAmax (in CEM or MR) and %RSCC were independent predictors of DCISM (all p < 0.05). The area under the curve (AUC) of CSAmax (CEM), %RSCC (CEM), Logit(P) (CEM), and CSAmax (MR) were 0.764, 0.795, 0.842, and 0.739, respectively. There were no significant differences in DeLong's test for these values (all p > 0.10). DCISM was significantly associated with high nuclear grade, comedo type, high axillary lymph node (ALN) metastasis, and high Ki-67 positivity compared to DCIS (all p < 0.05).

The tumor size (CSAmax), enhancement index (%RS), and internal enhancement pattern (IEP) were highly indicative of DCISM. DCISM tends to express more aggressive pathological features, such as high nuclear grade, comedo-type necrosis, ALN metastasis, and Ki-67 overexpression. As with MRI, CEM has the capability to help predict when DCISM is accompanying DCIS.

To explore machine learning (ML)-based breast tumor peritumoral (P) and intratumoral ultrasound radiomics signatures (IURS) for predicting axillary response to neoadjuvant chemotherapy (NAC) in patients with breast cancer (BC) with node-positive. A total of 435 patients were divided into hormone receptor (HR)+/human epidermal growth factor receptor (HER)2-, HER2+, and triple-negative (TN) subtypes. ML classifiers including random forest (RF), support vector machine (SVM), and linear discriminant analysis (LDA) were applied to construct PURS, IURS, and the combined P-IURS radiomics models. SVM of the TN subtype obtained the most favorable performance with an AUC of 0.917 (95%CI: 0.859, 0.960) in PURS models, RF of the HER2+ subtype yielded the highest efficacy in IURS models [AUC = 0.935 (95%CI: 0.843, 0.976)]. The RF-based combined P-IURS model of the HER2+ subtype improved the efficacy to a maximum AUC of 0.952 (95%CI: 0.868, 0.994). ML-based US radiomics can be a promising biomarker to predict axillary response.

Radiomics offers a noninvasive avenue for predicting clinicopathological factors. However, thorough investigations into a robust breast cancer outcome-predicting model and its biological significance remain limited. This study develops a robust radiomic model for prognosis prediction, and further excavates its biological foundation and transferring prediction performance. We retrospectively collected preoperative dynamic contrast-enhanced MRI data from three distinct breast cancer patient cohorts. In FUSCC cohort (n = 466), Lasso was used to select features correlated with patient prognosis and multivariate Cox regression was utilized to integrate these features and build the radiomic risk model, while multiomic analysis was conducted to investigate the model's biological implications. DUKE cohort (n = 619) and I-SPY1 cohort (n = 128) were used to test the performance of the radiomic signature in outcome prediction. A thirteen-feature radiomic signature was identified in the FUSCC cohort training set and validated in the FUSCC cohort testing set, DUKE cohort and I-SPY1 cohort for predicting relapse-free survival (RFS) and overall survival (OS) (RFS: p = 0.013, p = 0.024 and p = 0.035; OS: p = 0.036, p = 0.005 and p = 0.027 in the three cohorts). Multiomic analysis uncovered metabolic dysregulation underlying the radiomic signature (ATP metabolic process: NES = 1.84, p-adjust = 0.02; cholesterol biosynthesis: NES = 1.79, p-adjust = 0.01). Regarding the therapeutic implications, the radiomic signature exhibited value when combining clinical factors for predicting the pathological complete response to neoadjuvant chemotherapy (DUKE cohort, AUC = 0.72; I-SPY1 cohort, AUC = 0.73). In conclusion, our study identified a breast cancer outcome-predicting radiomic signature in a multicenter radio-multiomic study, along with its correlations with multiomic features in prognostic risk assessment, laying the groundwork for future prospective clinical trials in personalized risk stratification and precision therapy.

To explore and validate the clinical value of ultrasound (US) viscosity imaging in differentiating breast lesions by combining with BI-RADS, and then comparing the diagnostic performances with BI-RADS alone.

This multicenter, prospective study enrolled participants with breast lesions from June 2021 to November 2022. A development cohort (DC) and validation cohort (VC) were established. Using histological results as reference standard, the viscosity-related parameter with the highest area under the receiver operating curve (AUC) was selected as the optimal one. Then the original BI-RADS would upgrade or not based on the value of this parameter. Finally, the results were validated in the VC and total cohorts. In the DC, VC and total cohorts, all breast lesions were divided into the large lesion, small lesion and overall groups respectively.

A total of 639 participants (mean age, 46 years ± 14) with 639 breast lesions (372 benign and 267 malignant lesions) were finally enrolled in this study including 392 participants in the DC and 247 in the VC. In the DC, the optimal viscosity-related parameter in differentiating breast lesions was calculated to be A'-S2-Vmax, with the AUC of 0.88 (95% CI: 0.84, 0.91). Using > 9.97 Pa.s as the cutoff value, the BI-RADS was then modified. The AUC of modified BI-RADS significantly increased from 0.85 (95% CI: 0.81, 0.88) to 0.91 (95% CI: 0.87, 0.93), 0.85 (95% CI: 0.80, 0.89) to 0.90 (95% CI: 0.85, 0.93) and 0.85 (95% CI: 0.82, 0.87) to 0.90 (95% CI: 0.88, 0.92) in the DC, VC and total cohorts respectively (P < .05 for all).

The quantitative viscous parameters evaluated by US viscosity imaging contribute to breast cancer diagnosis when combined with BI-RADS.

Previous studies have used different imaging sequences and different enhanced phases for breast lesion calsification in radiomics. The optimal sequence and contrast enhanced phase is unclear.

To identify the optimal magnetic resonance imaging (MRI) radiomics model for lesion clarification, and to simulate its incremental value for multiparametric MRI (mpMRI)-guided biopsy.

Retrospective.

329 female patients (138 malignant, 191 benign), divided into a training set (first site, n = 192) and an independent test set (second site, n = 137).

3.0-T, fast spoiled gradient-echo and fast spin-echo T1-weighted imaging (T1WI), fast spin-echo T2-weighted imaging (T2WI), echo-planar diffusion-weighted imaging (DWI), and fast spoiled gradient-echo contrast-enhanced MRI (CE-MRI).

Two breast radiologists with 3 and 10 years' experience developed radiomics model on CE-MRI, CE-MRI + DWI, CE-MRI + DWI + T2WI, CE-MRI + DWI + T2WI + T1WI at each individual phase (P) and for multiple combinations of phases. The optimal radiomics model (Rad-score) was identified as having the highest area under the receiver operating characteristic curve (AUC) in the test set. Specificity was compared between a traditional mpMRI model and an integrated model (mpMRI + Rad-score) at sensitivity >98%.

Wilcoxon paired-samples signed rank test, Delong test, McNemar test. Significance level was 0.05 and Bonferroni method was used for multiple comparisons (P = 0.007, 0.05/7).

For radiomics models, CE-MRI/P3 + DWI + T2WI achieved the highest performance in the test set (AUC = 0.888, 95% confidence interval: 0.833-0.944). The integrated model had significantly higher specificity (55.3%) than the mpMRI model (31.6%) in the test set with a sensitivity of 98.4%.

The CE-MRI/P3 + DWI + T2WI model is the optimized choice for breast lesion classification in radiomics, and has potential to reduce benign biopsies (100%-specificity) from 68.4% to 44.7% while retaining sensitivity >98%.

3 TECHNICAL EFFICACY: Stage 2.

Accurately identifying patients with axillary pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer patients remains challenging.

To compare the feasibility of shear wave elastography (SWE) performed on breast tumors and axillary lymph nodes (LNs) in predicting the axillary status after NAC.

This prospective study included a total of 319 breast cancer patients with biopsy-proven positive node who received NAC followed by axillary lymph node dissection from 2019 to 2022. The correlations between shear wave velocity (SWV) and pathologic characteristics were analyzed separately for both breast tumors and LNs after NAC. We compared the performance of SWV between breast tumors and LNs in predicting the axillary status after NAC. Additionally, we evaluated the performance of the most significantly correlated pathologic characteristic in breast tumors and LNs to investigate the pathologic evidence supporting the use of breast or axilla SWE.

Axillary pCR was achieved in 51.41% of patients with node-positive breast cancer. In breast tumors, there is a stronger correlation between SWV and collagen volume fraction (CVF) (r = 0.52, p < 0.001) compared to tumor cell density (TCD) (r = 0.37, p < 0.001). In axillary LNs, SWV was weakly correlated with CVF (r = 0.31, p = 0.177) and TCD (r = 0.29, p = 0.213). No significant correlation was found between SWV and necrosis proportion in breast tumors or axillary LNs. The predictive performances of both SWV and CVF for axillary pCR were found to be superior in breast tumors (AUC = 0.87 and 0.85, respectively) compared to axillary LNs (AUC = 0.70 and 0.74, respectively).

SWE has the ability to characterize the extracellular matrix, and serves as a promising modality for evaluating axillary LNs after NAC. Notably, breast SWE outperform axilla SWE in determining the axillary status in breast cancer patients after NAC.

The study aims to evaluate the diagnostic efficacy of contrast-enhanced ultrasound (CEUS) and shear-wave elastography (SWE) in detecting small malignant breast nodules in an effort to inform further refinements of the Breast Imaging Reporting and Data System (BI-RADS) classification system.

This study retrospectively analyzed patients with breast nodules who underwent conventional ultrasound, CEUS, and SWE at Gongli Hospital from November 2015 to December 2019. The inclusion criteria were nodules ≤ 2 cm in diameter with pathological outcomes determined by biopsy, no prior treatments, and solid or predominantly solid nodules. The exclusion criteria included pregnancy or lactation and low-quality images. Imaging features were detailed and classified per BI-RADS. Diagnostic accuracy was assessed using receiver operating characteristic curves.

The study included 302 patients with 305 breast nodules, 113 of which were malignant. The diagnostic accuracy was significantly improved by combining the BI-RADS classification with CEUS and SWE. The combined approach yielded a sensitivity of 88.5%, specificity of 87.0%, positive predictive value of 80.0%, negative predictive value of 92.8%, and accuracy of 87.5% with an area under the curve of 0.877. Notably, 55.8% of BI-RADS 4A nodules were downgraded to BI-RADS 3 and confirmed as benign after pathological examination, suggesting the potential to avoid unnecessary biopsies.

The integrated use of the BI-RADS classification, CEUS, and SWE enhances the accuracy of differentiating benign and malignant small breast nodule, potentially reducing the need for unnecessary biopsies.

Based on the ultrasonic characteristics of the breast mass and axillary lymph nodes as well as the clinicopathological information, a model was developed for predicting axillary lymph node metastasis in cT1 breast cancer, and relevant features associated with axillary lymph node metastasis were identified.

Our retrospective study included 808 patients with cT1 invasive breast cancer treated at the Second Affiliated Hospital and the Cancer Hospital Affiliated with Harbin Medical University from February 2012 to August 2021 (250 cases in the positive axillary lymph node group and 558 cases in the negative axillary lymph node group). We allocated 564 cases to the training set and 244 cases to the verification set. R software was used to compare clinicopathological data and ultrasonic features between the two groups. Based on the results of multivariate logistic regression analysis, a nomogram prediction model was developed and verified for axillary lymph node metastasis of cT1 breast cancer.

Univariate and multivariate logistic regression analysis indicated that palpable lymph nodes ( P  = 0.003), tumor location ( P  = 0.010), marginal contour ( P  < 0.001), microcalcification ( P  = 0.010), surrounding tissue invasion ( P  = 0.046), ultrasonic detection of lymph nodes ( P  = 0.001), cortical thickness ( P  < 0.001) and E-cadherin ( P  < 0.001) are independently associated with axillary lymph node metastasis. Using these features, a nomogram was developed for axillary lymph node metastasis. The training set had an area under the curve of 0.869, while the validation set had an area under the curve of 0.820. Based on the calibration curve, the model predicted axillary lymph node metastases were in good agreement with reality ( P  > 0.05). Nomogram's net benefit was good based on decision curve analysis.

The nomogram developed in this study has a high negative predictive value for axillary lymph node metastasis in invasive cT1 breast c ancer. Patients with no axillary lymph node metastases can be accurately screened using this nomogram, potentially allowing this group of patients to avoid invasive surgery.

Breast cancer is the most common female cancer globally. The method of choice for screening and diagnosing breast cancer is mammography, which is not widely available in Ghana as compared to ultrasonography. This study aimed to evaluate the sonographic features of solid breast lesions using the new sonographic Breast Imaging- Reporting and Data System (BI-RADS-US) lexicon for malignancy with histopathology as the gold standard.

This was a prospective quantitative study that sonographically scanned female patients with breast masses and consecutively selected cases recommended for core biopsy from May 2018 to May 2021. Sixty (60) solid breast masses were described using the sonographic BI-RADS lexicon features. Lesion description and biopsy results from histopathology were compared and analyzed using Pearson's Chi-square test. Odds ratios, sensitivity, specificity, and predictive values were also calculated. Statistical significance level was set at p ≤ 0.05.

Irregular shape (p < 0.0001), spiculated mass margins (p < 0.0001), and not parallel mass orientation (p= 0.0007) were more commonly associated with malignant masses. The sensitivity of breast ultrasound for malignancy was 93.9 % and the specificity was 55.6 % with an overall accuracy rate of 76.6 %. The negative predictive value was 88.7 % and the positive predictive value was 72.1 %. Descriptors like irregular shape, non-parallel orientation, angular and spiculated margins, echogenic halo, and markedly hypoechoic internal content, demonstrated higher odds ratios for malignancy.

This study adds valuable insights to the diagnosis of breast cancer using the sonographic BI-RADS lexicon features. The results demonstrate that specific sonographic descriptors can effectively differentiate between benign and malignant breast masses.

To investigate the value of contrast-enhanced microflow imaging (CEUS-MFI) in distinguishing benign and malignant breast masses.

A total of 116 breast masses classified as Breast Imaging Reporting and Data System (BI-RADS) category 3-5 by ultrasound (US) were included. Both contrast-enhanced ultrasound (CEUS) and CEUS-MFI were performed before excision or biopsy, with features and diagnostic efficiency analyzed. The US and CEUS BI-RADS 4A masses were also re-assessed by CEUS-MFI.

The features of CEUS-MFI including both interior and peripheral enlarged, twisted vessels (both P < 0.05), penetrating vessels (P = 0.007), and radial/spiculated vessels (P < 0.001) were more frequently detected in malignant masses, while peripheral annular vessels were mostly observed in benign masses (P < 0.001). Interestingly, a significant difference in the orientation of penetrating vessels between benign and malignant masses was found (P < 0.001), with parallel orientation mostly displayed in benign masses, while vertical or multiple-direction orientation mostly displayed in malignant masses. The microvascular architecture of breast masses was categorized into five patterns: avascular, line-like, tree-like, root hair-like, and crab claw-like pattern. Benign masses mainly displayed tree-like pattern (77.1% vs 10.9%, P < 0.05); malignant masses mainly displayed root hair-like (34.8% vs 5.7%, P < 0.05) and crab claw-like patterns (50.0% vs 1.4%, P < 0.05). The diagnostic efficiency of CEUS-MFI was higher relative to CEUS and US. In addition, CEUS-MFI decreased the biopsy rates of US and CEUS BI-RADS 4A masses without missing malignancies.

CEUS-MFI could be a valuable and promising technique in diagnosis of breast masses, and could provide more diagnostic information for radiologists.

Ductal carcinoma in situ (DCIS) is often reclassified as invasive cancer in the final pathology report of the surgical specimen. It is of significant clinical relevance to acknowledge the possibility of underestimating invasive disease when utilizing preoperative biopsies for a DCIS diagnosis. In cases where such histologic upgrades occur, it is imperative to consider them in the preoperative planning process, including the potential inclusion of sentinel lymph node biopsy due to the risk of axillary lymph node metastasis.

To assess the capability of breast multiparametric magnetic resonance imaging (MP-MRI) in differentiating between pure DCIS and microinvasive carcinoma (MIC).

Between January 2018 and November 2022, this retrospective study enrolled patients with biopsy-proven DCIS who had undergone preoperative breast MP-MRI. We assessed various MP-MRI features, including size, morphology, margins, internal enhancement pattern, extent of disease, presence of peritumoral edema, time-intensity curve value, diffusion restriction, and ADC value. Subsequently, a logistic regression analysis was conducted to explore the association of these features with the pathological outcome.

Of 129 patients with biopsy-proven DCIS, 36 had foci of micro-infiltration on surgical specimens and eight were diagnosed with invasive ductal carcinoma (IDC). The presence of micro-infiltration foci was significantly associated with several MP-MRI features, including tumor size (P <0.001), clustered ring enhancement (P <0.001), segmental distribution (P <0.001), diffusion restriction (P = 0.005), and ADC values <1.3 × 10-3 mm2/s (P = 0.004).

Breast MP-MRI has the potential to predict the presence of micro-infiltration foci in biopsy-proven DCIS and may serve as a valuable tool for guiding therapeutic planning.

This study intended to investigate the feasibility and effectiveness of using clinical magnetic resonance imaging (MRI) radiomics features to predict lymphovascular invasion (LVI) status in breast cancer (BC) patients.

A total of 182 BC patients were retrospectively collected and randomly divided into a training set (n = 127) and a validation set (n = 55) in a 7:3 ratio. Based on pathological examination results, the training set was further divided into LVI group (n = 60) and non-LVI group (n = 67), and the validation set was divided into LVI group (n = 24) and non-LVI group (n = 31). General data and MRI examination indicators were compared. Multivariate logistic regression was utilized to analyze MRI radiomics features and clinically relevant indicators that were significant in the baseline information of patients in training set, independent risk factors were identified, and a logistic regression model was built. The accuracy of logistic model was validated using ROC curves in training and validation sets.

Age, pathohistological classification, tumor length, tumor width, presence or absence of Magnetic Resonance Spectroscopy (MRS) cho peak, presence or absence of spicule sign, peritumoral enhancement, and peritumoral edema were statistically significant (P < 0.05) between the two groups. Multivariate logistic regression analysis presented that spicule and peritumoral edema were independent risk factors for LVI in BC patients (P < 0.05). The ROC curve illustrated that AUC of the logistic regression model in the training set was 0.807 (95%CI: 0.730-0.885) and that in the validation set was 0.837 (95%CI: 0.731-0.944).

Radiomics features of spicule sign and peritumoral edema were independent risk factors for LVI in BC patients. A logistic regression model based on these factors, along with age, could accurately predict LVI occurrence in BC patients, providing data support for diagnosis and modeling of LVI in BC patients.

Breast conservation surgery (BCS) with adjuvant radiotherapy has become a gold standard in the treatment of early-stage breast cancer, significantly reducing the risk of tumor recurrence. However, this treatment is associated with adverse effects, including the rare but aggressive radiation-induced angiosarcoma (RIAS). Despite its rarity and nonspecific initial presentation, RIAS presents a challenging diagnosis, emphasizing the importance of imaging techniques for early detection and accurate diagnosis.

We present a case of a 48-year-old post-menopausal woman who developed skin ecchymosis on the right breast seven years after receiving BCS and adjuvant radiotherapy for breast cancer. Initial mammography and ultrasound were inconclusive, showing post-treatment changes but failing to identify the underlying angiosarcoma. Contrast-enhanced breast magnetic resonance imaging (MRI) revealed diffuse skin thickening and nodularity with distinctive enhancement kinetics, leading to the diagnosis of RIAS. This case highlights the crucial role of MRI in diagnosing and determining the extent of RIAS, facilitating timely and appropriate surgical intervention.

Breast MRI is crucial for detecting RIAS, especially when mammography and ultrasound are inconclusive.

In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions' decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types.

Little is known about how the COVID-19 pandemic affected screening mammography rates and Breast Imaging Reporting and Data Systems (BI-RADS) categorizations within populations facing social and economic inequities. Our study seeks to compare trends in breast cancer screening and BI-RADS assessments in an academic safety-net patient population before and during the COVID-19 pandemic.

Our single-center retrospective study evaluated women ≥ 18 years old with no known breast cancer diagnosis who received breast cancer screening from March 2019-September 2020. The screening BI-RADS score, completion of recommended diagnostic imaging, and diagnostic BI-RADS scores were compared between the pre-COVID-19 era (from 1 March 2019 to 19 March 2020) and COVID-19 era (from 20 March 2020 to 30 September 2020).

Among the 11,798 patients identified, screened patients were younger (median age 57 versus 59 years, p < 0.001) and more likely covered by private insurance (35.9% versus 32.3%, p < 0.001) during the COVID-19 era compared with the pre-COVID-19 era. During the pandemic, there was an increase in screening mammograms categorized as BI-RADS 0 compared with the pre-COVID-19 era (20% versus 14.5%, p < 0.0001). There was no statistically significant difference in rates of completion of diagnostic imaging (81.6% versus 85.4%, p = 0.764) or assignment of suspicious BI-RADS scores (BI-RADS 4-5; 79.9% versus 80.8%, p = 0.762) between the two eras.

Although more patients were recommended to undergo diagnostic imaging during the pandemic, there were no significant differences in race, completion of diagnostic imaging, or proportions of mammograms categorized as suspicious between the two time periods. These findings likely reflect efforts to maintain equitable care among diverse racial groups served by our safety-net hospital.

Axillary lymph node (ALN) status is a key prognostic factor in patients with early-stage invasive breast cancer (IBC). The present study aimed to develop and validate a nomogram based on multimodal ultrasonographic (MMUS) features for early prediction of axillary lymph node metastasis (ALNM). A total of 342 patients with early-stage IBC (240 in the training cohort and 102 in the validation cohort) who underwent preoperative conventional ultrasound (US), strain elastography, shear wave elastography and contrast-enhanced US examination were included between August 2021 and March 2022. Pathological ALN status was used as the reference standard. The clinicopathological factors and MMUS features were analyzed with uni- and multivariate logistic regression to construct a clinicopathological and conventional US model and a MMUS-based nomogram. The MMUS nomogram was validated with respect to discrimination, calibration, reclassification and clinical usefulness. US features of tumor size, echogenicity, stiff rim sign, perfusion defect, radial vessel and US Breast Imaging Reporting and Data System category 5 were independent risk predictors for ALNM. MMUS nomogram based on these factors demonstrated an improved calibration and favorable performance [area under the receiver operator characteristic curve (AUC), 0.927 and 0.922 in the training and validation cohorts, respectively] compared with the clinicopathological model (AUC, 0.681 and 0.670, respectively), US-depicted ALN status (AUC, 0.710 and 0.716, respectively) and the conventional US model (AUC, 0.867 and 0.894, respectively). MMUS nomogram improved the reclassification ability of the conventional US model for ALNM prediction (net reclassification improvement, 0.296 and 0.288 in the training and validation cohorts, respectively; both P<0.001). Taken together, the findings of the present study suggested that the MMUS nomogram may be a promising, non-invasive and reliable approach for predicting ALNM.

The aim of the work described here was to assess the application of ultrasound (US) radiomics with machine learning (ML) classifiers to the prediction of axillary sentinel lymph node metastasis (SLNM) burden in early-stage invasive breast cancer (IBC).

In this study, 278 early-stage IBC patients with at least one SLNM (195 in the training set and 83 in the test set) were studied at our institution. Pathologic SLNM burden was used as the reference standard. The US radiomics features of breast tumors were extracted by using 3D-Slicer and PyRadiomics software. Four ML classifiers-linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF) and decision tree (DT)-were used to construct radiomics models for the prediction of SLNM burden. The combined clinicopathologic-radiomics models were also assessed with respect to sensitivity, specificity, accuracy and areas under the curve (AUCs).

Among the US radiomics models, the SVM classifier achieved better predictive performance with an AUC of 0.920 compared with RF (AUC = 0.874), LDA (AUC = 0.835) and DT (AUC = 0.800) in the test set. The clinicopathologic model had low efficacy, with AUCs of 0.678 and 0.710 in the training and test sets, respectively. The combined clinicopathologic (C) factors and SVM classifier (C + SVM) model improved the predictive ability with an AUC of 0.934, sensitivity of 86.7%, specificity of 89.9% and accuracy of 91.0% in the test set.

ML-based US radiomics analysis, as a novel and promising predictive tool, is conducive to a precise clinical treatment strategy.

To evaluate the value of non-contrast micro-flow imaging (MFI) and high-definition micro-flow imaging (HD-MFI) in differentiating malignant and benign breast lesions.

One hundred and thirty-three patients with 138 breast lesions (80 benign and 58 malignant lesions) were examined using colour Doppler flow imaging (CDFI), MFI, and HD-MFI before biopsy, with blood flow signals graded into four types (grade 0, 1, 2, and 3) and penetrating vessels evaluated. The micro-vascular patterns of MFI and HD-MFI were evaluated and classified into five patterns: avascular, line-like, tree-like, root hair-like, and crab claw-like pattern. The diagnostic efficiency of micro-vascular patterns was analysed. Moreover, ultrasound Breast Imaging Reporting and Data System (BI-RADS) 4A lesions were also re-assessed according to the micro-vascular patterns of MFI or HD-MFI.

The capability of detecting blood flow and penetrating vessels from high to low was HD-MFI, MFI, and CDFI, respectively (p<0.05). Rich blood flow signals, penetrating vessels, and root hair-like or crab claw-like pattern were more likely in malignant breast lesions, while few blood flow signals, tree-like pattern were mostly in benign lesions (p<0.05). The diagnostic efficiency of HD-MFI and MFI were higher than CDFI (p>0.05). MFI could reduce unnecessary biopsy of 52 US BI-RADS 4A lesions but with two malignancies missed, while 56 ultrasound BI-RADS 4A lesions could be downgraded by HD-MFI with none malignancies missed.

MFI and HD-MFI can detect more blood flow in breast lesions than CDFI, and could help distinguish benign and malignant breast lesions. HD-MFI could reduce the unnecessary biopsy of US BI-RADS 4A lesions without missed malignancy.

We aimed to evaluate the added value of inversion imaging in differentiating between benign and malignant breast masses when combined with the Breast Imaging Reporting and Data System (BI-RADS).

A total of 364 patients with 367 breast masses (151 benign and 216 malignant) who underwent conventional ultrasound and inversion imaging prior to breast surgery were included. A 5-point inversion score (IS) scale was proposed based on the masses' internal echogenicity and distribution characteristics in the inversion images. The combination of IS and BI-RADS was compared with BI-RADS alone to evaluate the value of inversion imaging for breast mass diagnosis. The diagnostic performance of the BI-RADS and its combination with IS for breast masses were analyzed using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

The IS for malignant breast masses (3.96 ± 0.77) was significantly higher than benign masses (2.58 ± 0.98) (P < 0.001). The sensitivity, specificity, accuracy, PPV, and NPV of BI-RADS were 86.1%, 81.5%, 84.2%, 86.9%, and 80.4%, respectively, and an AUC was 0.909. By compared with BI-RADS, 72 breast masses were downgraded from suspected malignancy to benign, and 6 masses were upgraded from benign to suspected malignancy. Thus, the specificity was increased from 81.5 to 84.8%, it allows 72 benign masses avoid biopsy.

The combination of inversion imaging with BI-RADS can effectively improve the diagnostic efficacy of breast masses, and inversion imaging could help benign masses avoid biopsy.

As a remarkably specific characteristic of breast cancer observed on magnetic resonance imaging (MRI), the association between the NME type breast cancer and prognosis, including Ki-67, necessitates comprehensive exploration. To investigate the correlation between dynamic contrast-enhanced MRI (DCE-MRI) characteristics and apparent diffusion coefficient (ADC) values with Ki-67-positive expression in NME type breast cancer. A total of 63 NME type breast cancer patients were retrospectively reviewed. Malignancies were confirmed by surgical pathology. All patients underwent DCE and diffusion-weighted imaging (DWI) before surgery. DCE-MRI characteristics, including tumor distribution, internal enhancement pattern, axillary adenopathy, and time-intensity curve types were observed. ADC values and lesion sizes were also measured. The correlation between these features and Ki-67 expression were assessed using Chi-square test, Fisher's exact test, and Spearman rank analysis. The receiver operating characteristic curve and area under the curve (AUC) was used to evaluate the diagnostic performance of Ki-67-positive expression. Regional distribution, TIC type, and ipsilateral axillary lymph node enlargement were correlated with Ki-67-positive expression (χ2 = 0.397, 0.357, and 0.357, respectively; P < 0.01). ADC value and lesion size were positively correlated with Ki-67-positive expression (rs = 0.295, 0.392; P < 0.05). The optimal threshold values for lesion size and ADC value to assess Ki-67 expression were determined to be 5.05 (AUC = 0.759) cm and 0.403 × 10-3 s/mm2 (AUC = 0.695), respectively. The best diagnosis performance was the ADC combined with lesion size (AUC = 0.791). The ADC value, lesion size, regional distribution, and TIC type in NME type breast cancer were correlated with Ki-67-positive expression. These features will aid diagnosis and treatment of NME type breast cancer.

To demonstrate that positive predictive values (PPVs) for suspicious (category 4) magnetic resonance imaging (MRI) findings that have been stratified are equivalent to those stipulated in the American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) for mammography and ultrasound.

This retrospective analysis of electronic medical records generated between January 4, 2016 and December 29, 2021 provided 365 patients in which 419 suspicious (BI-RADS category 4) findings were subcategorized as BI-RADS 4A, 4B or 4C. Malignant and nonmalignant outcomes were determined by pathologic analyses, follow-up, or both. For each subcategory, the level 2 PPV (PPV2) was calculated and tested for equivalence/noninferiority against the established benchmarks.

Of the 419 findings evaluated, 168 (40.1%) were categorized as malignant and 251 (59.9%) were categorized as nonmalignant. The PPV2 for subcategory 4A was 14.2% (95% CI: 9.3-20.4%), whereas it was 41.2% (95% CI: 32.8-49.9%) for subcategory 4B and 77.2% (95% CI: 68.4-84.5%) for subcategory 4C. Multivariate analysis showed a significantly different cancer yield for each subcategory (p < 0.001).

We found that stratification of suspicious findings by MRI criteria is feasible, and malignancy probabilities for sub-categories 4B and 4C are equivalent to the values established for the other imaging methods in the BI-RADS. Nevertheless, low suspicion (4A) findings might show slightly higher malignancy rates.

Several breast reduction techniques have been introduced, and the reliability of these techniques has been demonstrated in clinical practice. However, it is still controversial how patients should be evaluated radiologically both preoperative and postoperative. This study aims to compare the radiological findings seen following reduction mammoplasty with two different techniques (inferior pedicle and superomedial pedicle), in connection with the surgical steps.

Medical records of 141 patients and a total of 278 breasts who underwent breast reduction with the diagnosis of macromastia were retrospectively analyzed. Demographic and operative data such as age, type of pedicle, preoperative and postoperative nipple-areola complex (NAC) position, and NAC transfer distance were recorded. Radiological evaluation was performed by two radiologists experienced in breast imaging by reinterpreting preoperative and postoperative mammography images.

The rate of postoperative structural distortion (p < 0.001), thickened areola (p = 0.011), and retroareolar fibrotic band (p < 0.001) were observed to be significantly higher in the superomedial group. The risk of fat necrosis increases as the NAC transfer distance increases and a value of >9.5 cm in the NAC transfer distance can be considered as the cutoff value in terms of fat necrosis development, especially in those using superomedial pedicle technique.

Surgical technique-specific benign radiological changes occur following reduction mammoplasty. However, these changes do not significantly affect the Breast imaging, reporting, and data system category. The localization of fat necrosis differs depending on the surgical technique, and the risk of fat necrosis increases as the NAC transfer distance increases, especially in those who have undergone superomedial pedicle breast reduction surgery.

We explored the role of maximum intensity projection (MIP) based on high frame rate contrast-enhanced ultrasound (H-CEUS) for the differentiation of breast tumors.

MIP imaging was performed in patients with breast tumors who underwent H-CEUS examinations. The microvasculature morphology of breast tumors was assessed. The receiver operating characteristic curve was plotted to evaluate the diagnostic performance of MIP.

Forty-three breast tumors were finally analyzed, consisting of 19 benign and 24 malignant tumors. For the ≤30-s and >30-s phases, dot-, line-, or branch-like patterns were significantly more common in benign tumors. A tree-like pattern was only present in the benign tumors. A crab claw-like pattern was significantly more common in the malignant tumors. Among the tumors with crab claw-like patterns, three cases of malignant tumors had multiple parallel small spiculated vessels. There were significant differences in the microvasculature morphology for the ≤30-s and >30-s phases between the benign and malignant tumors (all p < 0.001). The area under the curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the ≤30-s phase were all higher than those of the >30-s phase for the classification of breast tumors.

MIP based on H-CEUS can be used for the differentiation of breast tumors, and the ≤30-s phase had a better diagnostic value. Multiple parallel small spiculated vessels were a new finding, which could provide new insight for the subsequent study of breast tumors.

In patients with triple-negative breast cancer (TNBC)-the subtype with the poorest prognosis among breast cancers-it is crucial to assess the response to the currently widely employed neoadjuvant treatment (NAT) approaches. This study investigates the correlation between baseline conventional ultrasound (US) and shear-wave elastography (SWE) indicators and the pathological response of TNBC following NAT, with a specific focus on assessing predictive capability in the baseline state. This retrospective analysis was conducted by extracting baseline US features and SWE parameters, categorizing patients based on postoperative pathological grading. A univariate analysis was employed to determine the relationship between ultrasound indicators and pathological reactions. Additionally, we employed a receiver operating characteristic (ROC) curve analysis and multivariate logistic regression methods to evaluate the predictive potential of the baseline US indicators. This study comprised 106 TNBC patients, with 30 (28.30%) in a nonmajor histological response (NMHR) group and 76 (71.70%) in a major histological response (MHR) group. Following the univariate analysis, we found that T staging, dmax values, volumes, margin changes, skin alterations (i.e., thickening and invasion), retromammary space invasions, and supraclavicular lymph node abnormalities were significantly associated with pathological efficacy (p < 0.05). Combining clinical information with either US or SWE independently yielded baseline predictive abilities, with AUCs of 0.816 and 0.734, respectively. Notably, the combined model demonstrated an improved AUC of 0.827, with an accuracy of 76.41%, a sensitivity of 90.47%, a specificity of 55.81%, and statistical significance (p < 0.01). The baseline US and SWE indicators for TNBC exhibited a strong relationship with NAT response, offering predictive insights before treatment initiation, to a considerable extent.

Intratumor heterogeneity (ITH) profoundly affects therapeutic responses and clinical outcomes. However, the widespread methods for assessing ITH based on genomic sequencing or pathological slides, which rely on limited tissue samples, may lead to inaccuracies due to potential sampling biases. Using a newly established multicenter breast cancer radio-multiomic dataset (n = 1474) encompassing radiomic features extracted from dynamic contrast-enhanced magnetic resonance images, we formulated a noninvasive radiomics methodology to effectively investigate ITH. Imaging ITH (IITH) was associated with genomic and pathological ITH, predicting poor prognosis independently in breast cancer. Through multiomic analysis, we identified activated oncogenic pathways and metabolic dysregulation in high-IITH tumors. Integrated metabolomic and transcriptomic analyses highlighted ferroptosis as a vulnerability and potential therapeutic target of high-IITH tumors. Collectively, this work emphasizes the superiority of radiomics in capturing ITH. Furthermore, we provide insights into the biological basis of IITH and propose therapeutic targets for breast cancers with elevated IITH.

Full-field optical coherence tomography combined with dynamic cell imaging (D-FFOCT) is a new, simple-to-use, nondestructive, quick technique that can provide sufficient spatial resolution to mimic histopathological analysis. The objective of this study was to evaluate diagnostic performance of D-FFOCT for one-stop rapid diagnosis breast clinic.

Dynamic full-field optical coherence tomography was applied to fresh, untreated breast and nodes biopsies. Four different readers (senior and junior radiologist, surgeon, and pathologist) analyzed the samples without knowing final histological diagnosis or American College of Radiology classification. The results were compared to conventional processing and staining (hematoxylin-eosin).

A total of 217 biopsies were performed on 152 patients. There were 144 breast biopsies and 61 lymph nodes with 101 infiltrative cancers (49.27%), 99 benign lesions (48.29%), 3 ductal in situ carcinoma (1.46%), and 2 atypias (0.98%). The diagnostic performance results were as follow: sensitivity: 77% [0.7;0.82], specificity: 64% [0.58;0.71], PPV: 74% [0.68;0.78], and NPV: 75% [0.72;0.78]. A large image atlas was created as well as a diagnosis algorithm from the readers' experience.

With 74% PPV and 75% NPV, D-FFOCT is not yet ready to be used in clinical practice to identify breast cancer. This is mainly explained by the lack of experience and knowledge of this new technic by the four lectors. By training with the diagnosis algorithm and the image atlas, radiologists could have better outcomes allowing quick detection of breast cancer and lymph node involvement. Deep learning could also be used, and further investigation will follow.

The primary objective is to optimize the population eligible for Mammotome Minimally Invasive Surgery (MIS) by refining selection criteria. This involves maximizing procedure benefits, minimizing malignancy risk, and reducing the rate of malignant outcomes.

A total of 1158 female patients who came to our hospital from November 2016 to August 2021 for the Mammotome MIS were analyzed retrospectively. Following χ2 tests to screen for risk variables, binary logistic regression analysis was used to determine the independent predictors of malignant lesions. In addition, the correlation between age and lesion diameter was investigated for BI-RADS ultrasound (US) category 4a lesions in order to better understand the relationship between these variables.

The malignancy rates of BI-RADS US category 3, category 4a and category 4b patients who underwent the Mammotome MIS were 0.6% (9/1562), 6.4% (37/578) and 8.3% (2/24) respectively. Malignant lesions were more common in patients over the age of 40, have visible blood supply, and BI-RADS category 4 of mammography. In BI-RADS US category 4a lesions, the diameter of malignant tumor was highly correlated with age, and this correlation was strengthened in patients over the age of 40 and with BI-RADS category 4 of mammography.

The results of this study demonstrate that the clinical data and imaging results, particularly age, blood supply, and mammography classification, offer valuable insights to optimize patients' surgical options and decrease the incidence of malignant outcomes.

This study aimed to develop a nomogram through the collection of quantitative ultrasound parameters to predict breast cancer. From March 2021 to September 2022, a total of 313 breast tumors were included with pathological results. Through collecting quantitative ultrasound parameters of breast tumors and multivariate regression analysis, a nomogram was developed. The diagnostic performances, calibration and clinical usefulness of the nomogram for predicting breast cancer were assessed. A total of 182 benign and 131 malignant breast tumors were included in this study. The nomogram indicated excellent predictive properties with an AUC of 0.934, sensitivity of 0.881, specificity of 0.848, PPV of 0.795 and NPV of 0.841. The calibration curve showed the predicted values are basically consistent with the actual observed values. The optimum cut-off for the nomogram was 0.310 for predicting cancer. The decision curve analysis results corroborated good clinical usefulness. The model including BI-RADS score, SWE and VI is potentially useful for predicting breast cancer.

To evaluate the ability of integrated radiomics nomogram based on ultrasound images to distinguish between breast fibroadenoma (FA) and pure mucinous carcinoma (P-MC).

One hundred seventy patients with FA or P-MC (120 in the training set and 50 in the test set) with definite pathological confirmation were retrospectively enrolled. Four hundred sixty-four radiomics features were extracted from conventional ultrasound (CUS) images, and radiomics score (Radscore) was constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Different models were developed by a support vector machine (SVM), and the diagnostic performance of the different models was assessed and validated. A comparison of the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) was performed to evaluate the incremental value of the different models.

Finally, 11 radiomics features were selected, and then Radscore was developed based on them, which was higher in P-MC in both cohorts. In the test group, the clinic + CUS + radiomics (Clin + CUS + Radscore) model achieved a significantly higher area under the curve (AUC) value (AUC = 0.86, 95% CI, 0.733-0.942) when compared with the clinic + radiomics (Clin + Radscore) (AUC = 0.76, 95% CI, 0.618-0.869, P > 0.05), clinic + CUS (Clin + CUS) (AUC = 0.76, 95% CI, 0.618-0.869, P< 0.05), Clin (AUC = 0.74, 95% CI, 0.600-0.854, P< 0.05), and Radscore (AUC = 0.64, 95% CI, 0.492-0.771, P< 0.05) models, respectively. The calibration curve and DCA also suggested excellent clinical value of the combined nomogram.

The combined Clin + CUS + Radscore model may help improve the differentiation of FA from P-MC.

In clinical practice, reducing unnecessary biopsies for mammographic BI-RADS 4 lesions is crucial. The objective of this study was to explore the potential value of deep transfer learning (DTL) based on the different fine-tuning strategies for Inception V3 to reduce the number of unnecessary biopsies that residents need to perform for mammographic BI-RADS 4 lesions.

A total of 1980 patients with breast lesions were included, including 1473 benign lesions (185 women with bilateral breast lesions), and 692 malignant lesions collected and confirmed by clinical pathology or biopsy. The breast mammography images were randomly divided into three subsets, a training set, testing set, and validation set 1, at a ratio of 8:1:1. We constructed a DTL model for the classification of breast lesions based on Inception V3 and attempted to improve its performance with 11 fine-tuning strategies. The mammography images from 362 patients with pathologically confirmed BI-RADS 4 breast lesions were employed as validation set 2. Two images from each lesion were tested, and trials were categorized as correct if the judgement (≥ 1 image) was correct. We used precision (Pr), recall rate (Rc), F1 score (F1), and the area under the receiver operating characteristic curve (AUROC) as the performance metrics of the DTL model with validation set 2.

The S5 model achieved the best fit for the data. The Pr, Rc, F1 and AUROC of S5 were 0.90, 0.90, 0.90, and 0.86, respectively, for Category 4. The proportions of lesions downgraded by S5 were 90.73%, 84.76%, and 80.19% for categories 4 A, 4B, and 4 C, respectively. The overall proportion of BI-RADS 4 lesions downgraded by S5 was 85.91%. There was no significant difference between the classification results of the S5 model and pathological diagnosis (P = 0.110).

The S5 model we proposed here can be used as an effective approach for reducing the number of unnecessary biopsies that residents need to conduct for mammographic BI-RADS 4 lesions and may have other important clinical uses.