Cross-Correlation of Confocal Images for Excised Breast Tissues of Total Mastectomy

OBJECT

The purpose of this study is to develop an image artifact removal method for radar-based microwave breast imaging and demonstrates the detectability on excised breast tissues of total mastectomy.

METHODS

A cross-correlation method was proposed and measurements were conducted. A hand-held radar-based breast cancer detector was utilized to measure a breast at different orientations. Images were generated by multiplying the confocal image data from two scans after cross-correlation. The optimum reconstruction permittivity values were extracted by the local maxima of the confocal image intensity as a function of reconstruction permittivity.

RESULTS

With the proposed cross-correlation method, the contrast of the imaging result was enhanced and the clutters were removed. The proposed method was applied to 50 cases of excised breast tissues and the detection sensitivity of 72% was achieved. With the limited number of samples, the dependency of detection sensitivity on the breast size, breast density, and tumor size were examined.

CONCLUSION AND SIGNIFICANCE

The detection sensitivity was strongly influenced by the breast density. The sensitivity was high for fatty breasts, whereas the sensitivity was low for heterogeneously dense breasts. In addition, it was observed that the sensitivity was high for extremely dense breast. This is the first detailed report on the excised breast tissues.

Clinical Significance of Background Parenchymal Enhancement in Breast Cancer Risk Stratification

BACKGROUND

Background parenchymal enhancement (BPE) is an established breast cancer risk factor. However, the relationship between BPE levels and breast cancer risk stratification remains unclear.

PURPOSE

To evaluate the clinical relationship between BPE levels and breast cancer risk with covariate adjustments for age, ethnicity, and hormonal status.

STUDY TYPE

Retrospective.

POPULATION

954 screening breast MRI datasets representing 721 women divided into four cohorts: women with pathogenic germline breast cancer (BRCA) mutations (Group 1, N = 211), women with non-BRCA germline mutations (Group 2, N = 60), women without high-risk germline mutations but with a lifetime breast cancer risk of ≥20% using the Tyrer-Cuzick model (Group 3, N = 362), and women with <20% lifetime risk (Group 4, N = 88).

FIELD STRENGTH/SEQUENCE

3 T/axial non-fat-saturated T1, short tau inversion recovery, fat-saturated pre-contrast, and post-contrast T1-weighted images.

ASSESSMENT

Data on age, body mass index, ethnicity, menopausal status, genetic predisposition, and hormonal therapy use were collected. BPE levels were evaluated by two breast fellowship-trained radiologists independently in accordance with BI-RADS, with a third breast fellowship-trained radiologist resolving any discordance.

STATISTICAL TESTS

Propensity score matching (PSM) was utilized to adjust covariates, including age, ethnicity, menopausal status, hormonal treatments, and prior bilateral oophorectomy. The Mann-Whitney U test, chi-squared test, and univariate and multiple logistic regression analysis were performed, with an odds ratio (OR) and corresponding 95% confidence interval. Weighted Kappa statistic was used to assess inter-reader variation. A P value <0.05 indicated a significant result.

RESULTS

In the assessment of BPE, there was substantial agreement between the two interpreting radiologists (κ = 0.74). Patient demographics were not significantly different between patient groups after PSM. The BPE of Group 1 was significantly lower than that of Group 4 and Group 3 among premenopausal women. In estimating the BPE level, the OR of gene mutations was 0.35.

DATA CONCLUSION

Adjusting for potential confounders, the BPE level of premenopausal women with BRCA mutations was significantly lower than that of non-high-risk women.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 3.

Assessing breast arterial calcification in mammograms and its implications for atherosclerotic cardiovascular disease risk

PURPOSE

Breast arterial calcifications (BAC) are incidentally observed on mammograms, yet their implications remain unclear. We investigated lifestyle, reproductive, and cardiovascular determinants of BAC in women undergoing mammography screening. Further, we investigated the relationship between BAC, coronary arterial calcifications (CAC) and estimated 10-year atherosclerotic cardiovascular (ASCVD) risk.

METHODS

In this cross-sectional study, we obtained reproductive history and CVD risk factors from 215 women aged 18 or older who underwent mammography and cardiac computed tomographic angiography (CCTA) within a 2-year period between 2007 and 2017 at hospital. BAC was categorized as binary (present/absent) and semi-quantitatively (mild, moderate, severe). CAC was determined using the Agatston method and recorded as binary (present/absent). Adjusted odds ratios (ORs) and 95 % confidence intervals (CIs) were calculated, accounting for age as a confounding factor. ASCVD risk over a 10-year period was calculated using the Pooled Cohort Risk Equations.

RESULTS

Older age, systolic and diastolic blood pressures, higher parity, and younger age at first birth (≤28 years) were significantly associated with greater odds of BAC. Women with both BAC and CAC had the highest estimated 10-year risk of ASCVD (13.30 %). Those with only BAC (8.80 %), only CAC (5.80 %), and no BAC or CAC (4.40 %) had lower estimated 10-year risks of ASCVD. No association was detected between presence of BAC and CAC.

CONCLUSIONS

These findings support the hypothesis that BAC on a screening mammogram may help to identify women at potentially increased risk of future cardiovascular disease without additional cost and radiation exposure.

Adding quantitative T1rho-weighted imaging to conventional MRI improves specificity and sensitivity for differentiating malignant from benign breast lesions

OBJECTIVES

To investigate the feasibility of T1rho-weighted imaging in differentiating malignant from benign breast lesions and to explore the additional value of T1rho to conventional MRI.

MATERIALS AND METHODS

We prospectively enrolled consecutive women with breast lesions who underwent preoperative T1rho-weighted imaging, diffusion-weighted imaging, and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) between November 2021 and July 2023. The T1rho, apparent diffusion coefficient (ADC), and semi-quantitative parameters from DCE-MRI were obtained and compared between benign and malignant groups. The diagnostic performance was analyzed and compared using receiver operating characteristic (ROC) curves and the Delong Test.

RESULTS

This study included 113 patients (74 malignant and 39 benign lesions). The mean T1rho value in the benign group (92.61 ± 22.10 ms) was significantly higher than that in the malignant group (72.18 ± 16.37 ms) (P < 0.001). The ADC value and time to peak (TTP) value in the malignant group (1.13 ± 0.45 and 269.06 ± 106.01, respectively) were lower than those in the benign group (1.57 ± 0.45 and 388.30 ± 81.13, respectively) (all P < 0.001). T1rho combined with ADC and TTP showed good diagnostic performance with an area under the curve (AUC) of 0.896, a sensitivity of 81.0%, and a specificity of 87.1%. The specificity and sensitivity of the combination of T1rho, ADC, and TTP were significantly higher than those of the combination of ADC and TTP (87.1% vs. 84.6%, P < 0.005; 81.0% vs. 77.0%, P < 0.001).

CONCLUSION

T1rho-weighted imaging was a feasible MRI sequence for differentiating malignant from benign breast lesions. The combination of T1rho, ADC and TTP could achieve a favorable diagnostic performance with improved specificity and sensitivity, T1rho could serve as a supplementary approach to conventional MRI.

Discriminative Factors of Malignancy of Ipsilateral Nonmass Enhancement in Women With Newly Diagnosed Breast Cancer on Initial Staging Breast MRI

BACKGROUND

Nonmass enhancement (NME) on breast MRI impacts surgical planning.

PURPOSE

To evaluate positive predictive values (PPVs) and identify malignancy discriminators of NME ipsilateral to breast cancer on initial staging MRI.

STUDY TYPE

Retrospective.

SUBJECTS

Eighty-six women (median age, 48 years; range, 26-75 years) with 101 NME lesions (BI-RADS 4 and 5) ipsilateral to known cancers and confirmed histopathology.

FIELD STRENGTH/SEQUENCE

1.5 T and 3.0 T dynamic contrast-enhanced fat-suppressed T1-weighted fast spoiled gradient-echo.

ASSESSMENT

Three radiologists blinded to pathology independently reviewed MRI features (distribution, internal enhancement pattern, and enhancement kinetics) of NME, locations relative to index cancers (contiguous, non-contiguous, and different quadrants), associated mammographic calcifications, lymphovascular invasion (LVI), axillary node metastasis, and radiology-pathology correlations. Clinical factors, NME features, and cancer characteristics were analyzed for associations with NME malignancy.

STATISTICAL TESTS

Fisher's exact, Chi-square, Wilcoxon rank sum tests, and mixed-effect multivariable logistic regression were used. Significance threshold was set at P < 0.05.

RESULTS

Overall NME malignancy rate was 48.5% (49/101). Contiguous NME had a significantly higher malignancy rate (86.7%) than non-contiguous NME (25.0%) and NME in different quadrants (10.7%), but no significant difference was observed by distance from cancer for non-contiguous NME, P = 0.68. All calcified NME lesions contiguous to the calcified index cancer were malignant. NME was significantly more likely malignant when index cancers were masses compared to NME (52.9% vs. 21.4%), had mammographic calcifications (63.2% vs. 39.7%), LVI (81.8% vs. 44.4%), and axillary node metastasis (70.8% vs. 41.6%). NME features with highest PPVs were segmental distribution (85.7%), clumped enhancement (66.7%), and nonpersistent kinetics (77.1%). On multivariable analysis, contiguous NME, segmental distribution, and nonpersistent kinetics were associated with malignancy.

DATA CONCLUSION

Malignancy discriminators of ipsilateral NME on staging MRI included contiguous location to index cancers, segmental distribution, and nonpersistent kinetics.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Comparison of continuous-time random walk and fractional order calculus models in characterizing breast lesions using histogram analysis

OBJECTIVE

To compare the diagnostic performance of different mathematical models for DWI and explore whether parameters reflecting spatial and temporal heterogeneity can demonstrate better diagnostic accuracy than the diffusion coefficient parameter in distinguishing benign and malignant breast lesions, using whole-tumor histogram analysis.

METHODS

This retrospective study was approved by the institutional ethics committee and included 104 malignant and 42 benign cases. All patients underwent breast magnetic resonance imaging (MRI) with a 3.0 T MR scanner using the simultaneous multi-slice (SMS) readout-segment ed echo-planar imaging (rs-EPI). Histogram metrics of Mono- apparent diffusion coefficient (ADC), CTRW, and FROC-derived parameters were compared between benign and malignant breast lesions, and the diagnostic performance of each diffusion parameter was evaluated. Statistical analysis was performed using Mann-Whitney U test and receiver operating characteristic (ROC) curve.

RESULTS

The DFROC-median exhibited the highest AUC for distinguishing benign and malignant breast lesions (AUC = 0.965). The temporal heterogeneity parameter αCTRW-median generated a statistically higher AUC compared to the spatial heterogeneity parameter βCTRW-median (AUC = 0.850 and 0.741, respectively; p = 0.047). Finally, the combination of median values of CTRW parameters displayed a slightly higher AUC than that of FROC parameters, with no significant difference however (AUC = 0.971 and 0.965, respectively; p = 0.172).

CONCLUSIONS

The diffusion coefficient parameter exhibited superior diagnostic performance in distinguishing breast lesions when compared to the temporal and spatial heterogeneity parameters.

Towards precision medicine in breast imaging: A novel open mammography database with tailor-made 3D image retrieval for AI and teaching

This project addresses the global challenge of breast cancer, particularly in low-resource settings, by creating a pioneering mammography database. Breast cancer, identified by the World Health Organization as a leading cause of cancer death among women, often faces diagnostic and treatment resource constraints in low- and middle-income countries. To enhance early diagnosis and address educational setbacks, the project focuses on leveraging artificial intelligence (AI) technologies through a comprehensive database. Developed in collaboration with Ambra Health, a cloud-based medical image management software, the database comprises 941 mammography images from 100 anonymized cases, with 62 % including 3D images. Accessible through http://mamografia.unifesp.br, the platform facilitates a simple registration process and an advanced search system based on 169 clinical and imaging variables. The website, customizable to the user's native language, ensures data security through an automatic anonymization system. By providing high-resolution, 3D digital images and supplementary clinical information, the platform aims to promote education and research in breast cancer diagnosis, representing a significant advancement in resource-constrained healthcare environments.

Quantitative characterization of breast lesions and normal fibroglandular tissue using compartmentalized diffusion-weighted model: comparison of intravoxel incoherent motion and restriction spectrum imaging

BACKGROUND

To compare the compartmentalized diffusion-weighted models, intravoxel incoherent motion (IVIM) and restriction spectrum imaging (RSI), in characterizing breast lesions and normal fibroglandular tissue.

METHODS

This prospective study enrolled 152 patients with 157 histopathologically verified breast lesions (41 benign and 116 malignant). All patients underwent a full-protocol preoperative breast MRI, including a multi-b-value DWI sequence. The diffusion parameters derived from the mono-exponential model (ADC), IVIM model (Dt, Dp, f), and RSI model (C1, C2, C3, C1C2, F1, F2, F3, F1F2) were quantitatively measured and then compared among malignant lesions, benign lesions and normal fibroglandular tissues using Kruskal-Wallis test. The Mann-Whitney U-test was used for the pairwise comparisons. Diagnostic models were built by logistic regression analysis. The ROC analysis was performed using five-fold cross-validation and the mean AUC values were calculated and compared to evaluate the discriminative ability of each parameter or model.

RESULTS

Almost all quantitative diffusion parameters showed significant differences in distinguishing malignant breast lesions from both benign lesions (other than C2) and normal fibroglandular tissue (all parameters) (all P < 0.0167). In terms of the comparisons of benign lesions and normal fibroglandular tissues, the parameters derived from IVIM (Dp, f) and RSI (C1, C2, C1C2, F1, F2, F3) showed significant differences (all P < 0.005). When using individual parameters, RSI-derived parameters-F1, C1C2, and C2 values yielded the highest AUCs for the comparisons of malignant vs. benign, malignant vs. normal tissue and benign vs. normal tissue (AUCs = 0.871, 0.982, and 0.863, respectively). Furthermore, the combined diagnostic model (IVIM + RSI) exhibited the highest diagnostic efficacy for the pairwise discriminations (AUCs = 0.893, 0.991, and 0.928, respectively).

CONCLUSIONS

Quantitative parameters derived from the three-compartment RSI model have great promise as imaging indicators for the differential diagnosis of breast lesions compared with the bi-exponential IVIM model. Additionally, the combined model of IVIM and RSI achieves superior diagnostic performance in characterizing breast lesions.

Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection

BACKGROUND

Artificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women.

METHODS

We retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI's performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A-D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories.

RESULTS

Mean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7-77.3] vs. 67.1% [95% CI, 58.8-74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9-93.2] vs. 77.6% [95% CI, 61.7-77.9]), PPV (1.5% [95% CI, 1.2-1.9] vs. 0.5% [95% CI, 0.4-0.6]), recall rate (7.1% [95% CI, 6.9-7.2] vs. 22.5% [95% CI, 22.2-22.7]), and AUC values (0.8 [95% CI, 0.76-0.84] vs. 0.74 [95% CI, 0.7-0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category.

CONCLUSIONS

AI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

Investigating the detection of breast cancer with deep transfer learning using ResNet18 and ResNet34

A lot of underdeveloped nations particularly in Africa struggle with cancer-related, deadly diseases. Particularly in women, the incidence of breast cancer is rising daily because of ignorance and delayed diagnosis. Only by correctly identifying and diagnosing cancer in its very early stages of development can be effectively treated. The classification of cancer can be accelerated and automated with the aid of computer-aided diagnosis and medical image analysis techniques. This research provides the use of transfer learning from a Residual Network 18 (ResNet18) and Residual Network 34 (ResNet34) architectures to detect breast cancer. The study examined how breast cancer can be identified in breast mammography pictures using transfer learning from ResNet18 and ResNet34, and developed a demo app for radiologists using the trained models with the best validation accuracy. 1, 200 datasets of breast x-ray mammography images from the National Radiological Society's (NRS) archives were employed in the study. The dataset was categorised as implant cancer negative, implant cancer positive, cancer negative and cancer positive in order to increase the consistency of x-ray mammography images classification and produce better features. For the multi-class classification of the images, the study gave an average accuracy for binary classification of benign or malignant cancer cases of 86.7% validation accuracy for ResNet34 and 92% validation accuracy for ResNet18. A prototype web application showcasing ResNet18 performance has been created. The acquired results show how transfer learning can improve the accuracy of breast cancer detection, providing invaluable assistance to medical professionals, particularly in an African scenario.

Modeling correlated pairs of mammogram images

Mammography remains the primary screening strategy for breast cancer, which continues to be the most prevalent cancer diagnosis among women globally. Because screening mammograms capture both the left and right breast, there is a nonnegligible correlation between the pair of images. Previous studies have explored the concept of averaging between the pair of images after proper image registration; however, no comparison has been made in directly utilizing the paired images. In this paper, we extend the bivariate functional principal component analysis over triangulations to jointly characterize the pair of imaging data bounded in an irregular domain and then nest the extracted features within the survival model to predict the onset of breast cancer. The method is applied to our motivating data from the Joanne Knight Breast Health Cohort at Siteman Cancer Center. Our findings indicate that there was no statistically significant difference in model discrimination performance between averaging the pair of images and jointly modeling the two images. Although the breast cancer study did not reveal any significant difference, it is worth noting that the methods proposed here can be readily extended to other studies involving paired or multivariate imaging data.

Glandular doses and diagnostic reference levels (DRLs) for Saudi breast cancer screening programme (2012-2021)

The aim of this study was to report the diagnostic reference levels (DRLs) corresponding to different compressed breast thickness (CBT) ranges. To achieve this, mammographic examinations with 187,788 exposures were analysed. The mean average glandular (AGD) dose was calculated per view, examination, and center. Moreover, the DRL values corresponding to different CBT ranges were reported. The result of the mean AGD per view was found to be 1.36 mGy for craniocaudal (CC) and 1.54 mGy for Mediolateral oblique (MLO), while the mean AGD per examination for all women was 1.45 mGy. The DRL values corresponding to CBTs between 20 to 79 mm ranges were below 2 mGy. These results were from a population of mean age = 49 ± 8 years and mean CBT = 58 ± 8 mm, and was imaged with mean exposures of 29 ± 1 kVp and 74 ± 31 mAs, and a mean compression force of 135±37 N. In conclusion, good mammography practice has been shown, as DRL values are within the limits suggested by the international organizations.

Increased matrix stiffness enhances pro-tumorigenic traits in a physiologically relevant breast tissue- monocyte 3D model

High mammographic density, associated with increased tissue stiffness, is a strong risk factor for breast cancer per se. In postmenopausal women there is no differences in the occurrence of ductal carcinoma in situ (DCIS) depending on breast density. Preliminary data suggest that dense breast tissue is associated with a pro-inflammatory microenvironment including infiltrating monocytes. However, the underlying mechanism(s) remains largely unknown. A major roadblock to understanding this risk factor is the lack of relevant in vitro models. A biologically relevant 3D model with tunable stiffness was developed by cross-linking hyaluronic acid. Breast cancer cells were cultured with and without freshly isolated human monocytes. In a unique clinical setting, extracellular proteins were sampled using microdialysis in situ from women with various breast densities. We show that tissue stiffness resembling high mammographic density increases the attachment of monocytes to the cancer cells, increase the expression of adhesion molecules and epithelia-mesenchymal-transition proteins in estrogen receptor (ER) positive breast cancer. Increased tissue stiffness results in increased secretion of similar pro-tumorigenic proteins as those found in human dense breast tissue including inflammatory cytokines, proteases, and growth factors. ER negative breast cancer cells were mostly unaffected suggesting that diverse cancer cell phenotypes may respond differently to tissue stiffness. We introduce a biological relevant model with tunable stiffness that resembles the densities found in normal breast tissue in women. The model will be key for further mechanistic studies. Additionally, our data revealed several pro-tumorigenic pathways that may be exploited for prevention and therapy against breast cancer. STATEMENT OF SIGNIFICANCE: Women with mammographic high-density breasts have a 4-6-fold higher risk of breast cancer than low-density breasts. Biological mechanisms behind this increase are not fully understood and no preventive therapeutics are available. One major reason being a lack of suitable experimental models. Having such models available would greatly enhance the discovery of relevant targets for breast cancer prevention. We present a biologically relevant 3D-model for studies of human dense breasts, providing a platform for investigating both biophysical and biochemical properties that may affect cancer progression. This model will have a major scientific impact on studies for identification of novel targets for breast cancer prevention.

Editorial for "A Channel-Dimensional Feature-Reconstructed Deep Learning Model for Predicting Breast Cancer Molecular Subtypes on Overall b-Value Diffusion-Weighted MRI"

Level of Evidence

5

Technical Efficacy Stage

2

Validation of artificial intelligence contrast mammography in diagnosis of breast cancer: Relationship to histopathological results

INTRODUCTION

Contrast-enhanced mammography (CEM) is used for characterization of breast lesions with increased diagnostic accuracy compared to digital mammography (DM). Artificial intelligence (AI) approaches are emerging with accuracies equal to an average radiologist. However, most studies trained deep learning (DL) models on DM images and there is a paucity in literature for discovering the application of AI using CEM.

OBJECTIVES

To develop and test a DL model that classifies CEM images and produces corresponding highlights of lesions detected.

METHODS

Fully annotated 2006 images of 326 females available from the previously published Categorized Digital Database for Contrast Enhanced Mammography images (CDD-CESM) were used for training. We developed a DL multiview contrast mammography model (MVCM) for classification of CEM low energy and recombined images. An external test set of 288 images of 37 females not included in the training was used for validation. Correlation with histopathological results and follow-up was considered the standard reference. The study protocol was approved by the Institutional Review Board and patient informed consent was obtained.

RESULTS

Assessment was done on an external test set of 37 females (mean age, 51.31 years ± 11.07 [SD]) with AUC-ROC for AI performance 0.936; (95 % CI: 0.898, 0.973; p < 0.001) and the best cut off value for prediction of malignancy using AI score = 0.28. Findings were then correlated with histopathological results and follow up which revealed a sensitivity of 75 %, specificity 96.3 %, total accuracy of 90.1 %, positive predictive value (PPV) 87.1 %, and negative predictive value (NPV) 92 %, p-value (<0.001). Diagnostic indices of radiologists were sensitivity 88.9 %, specificity 92.6 %, total accuracy 91.7 %, PPV 80 %, and NPV 96.2 %, p-value (<0.001).

CONCLUSION

A deep learning multiview CEM model was developed and evaluated in a cohort of female participants and showed promising results in detecting breast cancer. This warrants further studies, external training, and validation.

A multi-task fusion model based on a residual-Multi-layer perceptron network for mammographic breast cancer screening

BACKGROUND AND OBJECTIVE

Deep learning approaches are being increasingly applied for medical computer-aided diagnosis (CAD). However, these methods generally target only specific image-processing tasks, such as lesion segmentation or benign state prediction. For the breast cancer screening task, single feature extraction models are generally used, which directly extract only those potential features from the input mammogram that are relevant to the target task. This can lead to the neglect of other important morphological features of the lesion as well as other auxiliary information from the internal breast tissue. To obtain more comprehensive and objective diagnostic results, in this study, we developed a multi-task fusion model that combines multiple specific tasks for CAD of mammograms.

METHODS

We first trained a set of separate, task-specific models, including a density classification model, a mass segmentation model, and a lesion benignity-malignancy classification model, and then developed a multi-task fusion model that incorporates all of the mammographic features from these different tasks to yield comprehensive and refined prediction results for breast cancer diagnosis.

RESULTS

The experimental results showed that our proposed multi-task fusion model outperformed other related state-of-the-art models in both breast cancer screening tasks in the publicly available datasets CBIS-DDSM and INbreast, achieving a competitive screening performance with area-under-the-curve scores of 0.92 and 0.95, respectively.

CONCLUSIONS

Our model not only allows an overall assessment of lesion types in mammography but also provides intermediate results related to radiological features and potential cancer risk factors, indicating its potential to offer comprehensive workflow support to radiologists.

Contrast-Enhanced Mammography for Women with Palpable Breast Abnormalities

RATIONALE AND OBJECTIVES

To examine the role of contrast-enhanced mammography (CEM) in the work-up of palpable breast abnormalities.

MATERIALS AND METHODS

In this single-center combination prospective-retrospective study, women with palpable breast abnormalities underwent CEM evaluation prospectively, comprising the acquisition of low energy (LE) images and recombined images (RI) which depict enhancement, followed by targeted ultrasound (US). Two independent readers retrospectively reviewed the imaging and assigned BI-RADS assessment based on LE alone, LE plus US, RI with LE plus US (CEM plus US), and RI alone. Pathology results or 1-year follow-up imaging served as the reference standard.

RESULTS

237 women with 262 palpable abnormalities were included (mean age, 51 years). Of the 262 palpable abnormalities, 116/262 (44%) had no imaging correlate and 242/262 (92%) were benign. RI alone had better specificity compared to LE plus US (Reader 1, 94% versus 89% (p = 0.009); Reader 2, 93% versus 88% (p = 0.03)), better positive predictive value (Reader 1, 52% versus 42% (p = 0.04); Reader 2, 53% versus 42% (p = 0.04)), and better accuracy (Reader 1, 93% versus 89% (p = 0.05); Reader 2, 93% versus 90% (p = 0.06)). CEM plus US was not significantly different in performance metrics versus LE plus US.

CONCLUSION

RI had better specificity compared to LE in combination with US. There was no difference in performance between CEM plus US and LE plus US, likely reflecting the weight US carries in radiologist decision-making. However, the results indicate that the absence of enhancement on RI in the setting of palpable lesions may help avoid benign biopsies.

The Postoperative Breast: Imaging Findings and Diagnostic Pitfalls After Breast-Conserving Surgery and Oncoplastic Breast Surgery

Breast surgery is the cornerstone of treatment for early breast cancer. Historically, mastectomy and conventional breast-conserving surgery (BCS) were the main surgical techniques for treatment. Now, oncoplastic breast surgery (OBS), introduced in the 1990s, allows for a combination of BCS and reconstructive surgery to excise the cancer while preserving or enhancing the contour of the breast, leading to improved aesthetic results. Although imaging after conventional lumpectomy demonstrates typical postsurgical changes with known evolution patterns over time, OBS procedures show postsurgical changes/fat necrosis in locations other than the lumpectomy site. The purpose of this article is to familiarize radiologists with various types of surgical techniques for removal of breast cancer and to distinguish benign postoperative imaging findings from suspicious findings that warrant further work-up.

Locoregional staging of breast cancer: contrast-enhanced mammography versus breast magnetic resonance imaging

PURPOSE

Breast cancer diagnosis often involves assessing the locoregional spread of the disease through MRI, as multicentricity, multifocality and/or bilaterality are increasingly common. Contrast-enhanced mammography (CEM) is emerging as a potential alternative method. This study compares the performance of CEM and MRI in preoperative staging of women with confirmed breast carcinoma. Patients were also asked to fill in a satisfaction questionnaire to rate their comfort level with each investigation.

METHODS

From May 1st, 2021 to May 1st, 2022, we enrolled 70 women with confirmed breast carcinoma who were candidates for surgery. For pre-operative locoregional staging, all patients underwent CEM and MRI examination, which two radiologists evaluated blindly. We further investigated all suspicious locations for disease spread, identified by both CEM and MRI, with a second-look ultrasound (US) and eventual histological examination.

RESULTS

In our study cohort, MRI and CEM identified 114 and 102 areas of focal contrast enhancement, respectively. A true discrepancy between MRI and CEM occurred in 9 out of 70 patients examined. MRI reported 8 additional lesions that proved to be false positives on second-look US in 6 patients, while it identified 4 lesions that were not detected by CEM and were pathological (true positives) in 3 patients.

CONCLUSIONS

CEM showed results comparable to MRI in the staging of breast cancer in our study population, with a high rate of patient acceptability.

Transfer learning for the generalization of artificial intelligence in breast cancer detection: a case-control study

BACKGROUND

Some researchers have questioned whether artificial intelligence (AI) systems maintain their performance when used for women from populations not considered during the development of the system.

PURPOSE

To evaluate the impact of transfer learning as a way of improving the generalization of AI systems in the detection of breast cancer.

MATERIAL AND METHODS

This retrospective case-control Finnish study involved 191 women diagnosed with breast cancer and 191 matched healthy controls. We selected a state-of-the-art AI system for breast cancer detection trained using a large US dataset. The selected baseline system was evaluated in two experimental settings. First, we examined our private Finnish sample as an independent test set that had not been considered in the development of the system (unseen population). Second, the baseline system was retrained to attempt to improve its performance in the unseen population by means of transfer learning. To analyze performance, we used areas under the receiver operating characteristic curve (AUCs) with DeLong's test.

RESULTS

Two versions of the baseline system were considered: ImageOnly and Heatmaps. The ImageOnly and Heatmaps versions yielded mean AUC values of 0.82±0.008 and 0.88±0.003 in the US dataset and 0.56 (95% CI=0.50-0.62) and 0.72 (95% CI=0.67-0.77) when evaluated in the unseen population, respectively. The retrained systems achieved AUC values of 0.61 (95% CI=0.55-0.66) and 0.69 (95% CI=0.64-0.75), respectively. There was no statistical difference between the baseline system and the retrained system.

CONCLUSION

Transfer learning with a small study sample did not yield a significant improvement in the generalization of the system.

Diagnostic performance of contrast-enhanced mammography for suspicious findings in dense breasts: A systematic review and meta-analysis

PURPOSE

Contrast-enhanced spectral imaging (CEM) is a new mammography technique, but its diagnostic value in dense breasts is still inconclusive. We did a systematic review and meta-analysis of studies evaluating the diagnostic performance of CEM for suspicious findings in dense breasts.

MATERIALS AND METHODS

The PubMed, Embase, and Cochrane Library databases were searched systematically until August 6, 2023. Prospective and retrospective studies were included to evaluate the diagnostic performance of CEM for suspicious findings in dense breasts. The QUADAS-2 tool was used to evaluate the quality and risk of bias of the included studies. STATA V.16.0 and Review Manager V.5.3 were used to meta-analyze the included studies.

RESULTS

A total of 10 studies (827 patients, 958 lesions) were included. These 10 studies reported the diagnostic performance of CEM for the workup of suspicious lesions in patients with dense breasts. The summary sensitivity and summary specificity were 0.95 (95% CI, 0.92-0.97) and 0.81 (95% CI, 0.70-0.89), respectively. Enhanced lesions, circumscribed margins, and malignancy were statistically correlated. The relative malignancy OR value of the enhanced lesions was 28.11 (95% CI, 6.84-115.48). The relative malignancy OR value of circumscribed margins was 0.17 (95% CI, 0.07-0.45).

CONCLUSION

CEM has high diagnostic performance in the workup of suspicious findings in dense breasts, and when lesions are enhanced and have irregular margins, they are often malignant.

Initial experience with a next-generation low-field MRI scanner: Potential for breast imaging?

PURPOSE

Broader clinical adoption of breast magnetic resonance imaging (MRI) faces challenges such as limited availability and high procedural costs. Low-field technology has shown promise in addressing these challenges. We report our initial experience using a next-generation scanner for low-field breast MRI at 0.55T.

METHODS

This initial cases series was part of an institutional review board-approved prospective study using a 0.55T scanner (MAGNETOM Free.Max, Siemens Healthcare, Erlangen/Germany: height < 2 m, weight < 3.2 tons, no quench pipe) equipped with a seven-channel breast coil (Noras, Höchberg/Germany). A multiparametric breast MRI protocol consisting of dynamic T1-weighted, T2-weighted, and diffusion-weighted sequences was optimized for 0.55T. Two radiologists with 12 and 20 years of experience in breast MRI evaluated the examinations.

RESULTS

Twelve participants (mean age: 55.3 years, range: 36-78 years) were examined. The image quality was diagnostic in all examinations and not impaired by relevant artifacts. Typical imaging phenotypes were visualized. The scan time for a complete, non-abbreviated breast MRI protocol ranged from 10:30 to 18:40 min.

CONCLUSION

This initial case series suggests that low-field breast MRI is feasible at diagnostic image quality within an acceptable examination time.

Impact of pre-operative MRI on surgical management of screening digital breast tomosynthesis-detected invasive lobular carcinoma

PURPOSE

The purpose of this study is to determine the impact of pre-operative MRI on surgical management of screening digital breast tomosynthesis (DBT)-detected invasive lobular carcinoma (ILC).

METHODS

A retrospective medical record analysis was conducted of women with screening DBT-detected ILC and subsequent surgery from 2017-2021. Clinical, imaging, and pathological features were compared between women who did and did not undergo MRI, and between women with and without additional disease detected on MRI, using the Pearson's chi-squared test and Wilcoxon signed-rank test. Concordance between imaging and surgical pathology sizes was also evaluated.

RESULTS

Of 125 women (mean age 67 years, range 44-90) with screening-detected ILC, MRI was obtained in 62 women (49.6%) with a mean age of 63 years (range 45-80). Compared to women without MRI, women who had MRI examinations were younger, more likely to have dense breast tissue, and more likely to undergo mastectomy initially rather than lumpectomy (p < 0.001-0.01). Eighteen biopsies were performed based on MRI findings, of which 55.6% (10/18) were malignant. Conventional imaging more frequently underestimated ILC span at the biopsy site than MRI, using a 25% threshold difference (17.5% [7/40] versus 58.5% [24/41], p < 0.001). MRI detected more extensive disease at the biopsy site in six patients (9.7%, 6/62), additional ipsilateral disease in six patients (9.7%, 6/62), and contralateral disease in one patient (1.6%, 1/62). MRI therefore impacted surgical management in 21.0% (13/62) of patients.

CONCLUSION

MRI led to the detection of additional disease, thus impacting surgical management, in one-fifth of patients with ILC.

Women's Experiences with Digital Breast Tomosynthesis and Targeted Breast Ultrasound for Focal Breast Complaints: A Survey Study

Background: Owing to its high sensitivity, as concluded in the Breast UltraSound Trial (BUST), targeted ultrasound (US) now seems a promising accurate stand-alone modality for diagnostic evaluation of breast complaints. This approach implies omission of bilateral digital breast tomosynthesis (DBT) in women with clearly benign US findings. Within BUST, radiologists started with US followed by DBT. This side-study investigates women's experiences with DBT, their main motivation to undergo diagnostic imaging, and their view on US as a stand-alone modality. Methods: A subset of BUST participants completed a questionnaire on their DBT experiences, reason for undergoing diagnostic assessment, and view on US-only diagnostics. Responses were analyzed with descriptive statistics and logistic regression analyses. Results: In total, 778 of 838 women (response rate 92.8%) were included (M = 47, SD = 11.16). Of them, 16.8% reported no burden of DBT, 33.5% slight burden, 31.0% moderate, and 12.7% severe burden. Furthermore, 13% reported no pain, 35.3% slight pain, 33.2% moderate, and 11.3% severe pain. Moreover, 88.3% indicated that the most important reason for breast assessment was explanation of their complaint and to rule out breast cancer, whereas 3.2% wanted to "check" both breasts. And 82.4% reported satisfaction with US only in case of a nonmalignancy. Conclusions: Our study shows that most women in the diagnostic setting experience at least slight-to-moderate DBT-related burden and pain, and that explanation for their symptoms is their main interest. Also, the majority report satisfaction with US only in case of nonmalignant findings. However, exploration of women's perspectives outside this study is needed as our participants all underwent both examinations.

Biopathologic Characterization and Grade Assessment of Breast Cancer With 3-D Multiparametric Ultrasound Combining Shear Wave Elastography and Backscatter Tensor Imaging

OBJECTIVE

Despite recent improvements in medical imaging, the final diagnosis and biopathologic characterization of breast cancers currently still requires biopsies. Ultrasound is commonly used for clinical examination of breast masses. B-Mode and shear wave elastography (SWE) are already widely used to detect suspicious masses and differentiate benign lesions from cancers. But additional ultrasound modalities such as backscatter tensor imaging (BTI) could provide relevant biomarkers related to tissue organization. Here we describe a 3-D multiparametric ultrasound approach applied to breast carcinomas in the aims of (i) validating the ability of BTI to reveal the underlying organization of collagen fibers and (ii) assessing the complementarity of SWE and BTI to reveal biopathologic features of diagnostic interest.

METHODS

Three-dimensional SWE and BTI were performed ex vivo on 64 human breast carcinoma samples using a linear ultrasound probe moved by a set of motors. Here we describe a 3-D multiparametric representation of the breast masses and quantitative measurements combining B-mode, SWE and BTI.

RESULTS

Our results reveal for the first time that BTI can capture the orientation of the collagen fibers around tumors. BTI was found to be a relevant marker for assessing cancer stages, revealing a more tangent tissue orientation for in situ carcinomas than for invasive cancers. In invasive cases, the combination of BTI and SWE parameters allowed for classification of invasive tumors with respect to their grade with an accuracy of 95.7%.

CONCLUSION

Our results highlight the potential of 3-D multiparametric ultrasound imaging for biopathologic characterization of breast tumors.

Editorial for "Problem Solving MRI to Reduce False-Positive Biopsy Related to Breast US: Conductivity vs. DWI vs. Abbreviated Contrast-Enhanced MRI"

Level of Evidence

5

Technical Efficacy Stage

3

Triple assessment breast clinics: The value of clinical core biopsies

BACKGROUND

Triple Assessment Breast Clinics are designed for rapid diagnosis of symptomatic patients. When there is no concordance between clinical and radiological assessment, clinicians perform clinical core biopsies. In patients with a clinically suspicious examination (S4, S5) and normal imaging, clinically guided core biopsy should be performed as per NCCP guidelines. However, substantial research does not exist on the diagnostic value or use of clinical core biopsies in non-suspicious palpable (S3) lesions and practices differ in each health system.

AIMS

The aim of this research was to assess the diagnostic value of clinical core biopsies in nonsuspicious, probably benign palpable breast lesions (S3) where image guided cores were not indicated (R1/R2).

METHODS

The cohort consisted of patients undergoing clinical core biopsies at a Symptomatic Breast Unit from January 2014 to 2019. Data regarding patient demographics, outcome of triple-assessment and incidence of malignancy were obtained from a prospectively maintained database and results were analysed using Minitab 2018.

RESULTS

Three hundred and sixty patients had a clinical core biopsy performed in this period. Clinical examination scores for these patients were S1/S2 (66), S3 (277), S4 (15), and S5 (2). Radiology Scores were R1/R2 (355) and R3(5). Two patients with clinical score S3 (0.6%) were diagnosed with breast cancer due to their clinical cores. Both patients had normal mass imaging. There was no association between uncertain palpable breast lesions (S3), and atypia or malignancy on biopsy results when breast imaging was normal (P = 0.43, χ2 test).

CONCLUSION

Despite clinical core biopsies being used in triple assessment, there is no certainty in their value except that there is high clinical suspicion. Imaging modalities are constantly improving and are already well established. When the patient is assigned a clinical score of S3 and has normal radiology, a clinical core biopsy is not required in most cases.

Multitask deep learning on mammography to predict extensive intraductal component in invasive breast cancer

OBJECTIVES

To develop a multitask deep learning (DL) algorithm to automatically classify mammography imaging findings and predict the existence of extensive intraductal component (EIC) in invasive breast cancer.

METHODS

Mammograms with invasive breast cancers from 2010 to 2019 were downloaded for two radiologists performing image segmentation and imaging findings annotation. Images were randomly split into training, validation, and test datasets. A multitask approach was performed on the EfficientNet-B0 neural network mainly to predict EIC and classify imaging findings. Three more models were trained for comparison, including a single-task model (predicting EIC), a two-task model (predicting EIC and cell receptor status), and a three-task model (combining the abovementioned tasks). Additionally, these models were trained in a subgroup of invasive ductal carcinoma. The DeLong test was used to examine the difference in model performance.

RESULTS

This study enrolled 1459 breast cancers on 3076 images. The EIC-positive rate was 29.0%. The three-task model was the best DL model with an area under the curve (AUC) of EIC prediction of 0.758 and 0.775 at the image and breast (patient) levels, respectively. Mass was the most accurately classified imaging finding (AUC = 0.915), followed by calcifications and mass with calcifications (AUC = 0.878 and 0.824, respectively). Cell receptor status prediction was less accurate (AUC = 0.625-0.653). The multitask approach improves the model training compared to the single-task model, but without significant effects.

CONCLUSIONS

A mammography-based multitask DL model can perform simultaneous imaging finding classification and EIC prediction.

CLINICAL RELEVANCE STATEMENT

The study results demonstrated the potential of deep learning to extract more information from mammography for clinical decision-making.

KEY POINTS

• Extensive intraductal component (EIC) is an independent risk factor of local tumor recurrence after breast-conserving surgery. • A mammography-based deep learning model was trained to predict extensive intraductal component close to radiologists' reading. • The developed multitask deep learning model could perform simultaneous imaging finding classification and extensive intraductal component prediction.

Predictive value of contrast-enhanced ultrasonography and ultrasound elastography for management of BI-RADS category 4 nonpalpable breast masses

PURPOSE

The objective of this study was to investigate the independent risk factors and associated predictive values of contrast-enhanced ultrasound (CEUS), shear wave elastography (SWE), and strain elastography (SE) for high-risk lesions (HRL) and malignant tumors (MT) among nonpalpable breast masses classified as BI-RADS category 4 on conventional ultrasound.

METHODS

This prospective study involved consecutively admitted patients with breast tumors from January 2018, aiming to explore the management of BI-RADS category 4 breast tumors using CEUS and elastography. We conducted a retrospective review of patient data, focusing on those with a history of a nonpalpable mass as the primary complaint. Pathologic findings after surgical resection served as the gold standard. The CEUS arterial-phase indices were analyzed using contrast agent arrival-time parametric imaging processing mode, while quantitative and qualitative indices were examined on ES images. Independent risk factors were identified through binary logistic regression multifactorial analysis. The predictive efficacy of different modalities was compared using a receiver operating characteristics curve. Subsequently, a nomogram for predicting the risk of HRL/MT was established based on a multifactorial logistic regression model.

RESULTS

A total of 146 breast masses from 146 patients were included, comprising 80 benign tumors, 12 HRLs, and 54 MTs based on the final pathology. There was no significant difference in pathologic size between the benign and HRL/MT groups [8.00(6.25,10.00) vs. 9.00(6.00,10.00), P = 0.506]. The diagnostic efficacy of US plus CEUS exceeded that of US plus SWE/SE for BI-RADS 4 nonpalpable masses, with an AUC of 0.954 compared to 0.798/0.741 (P ＜ 0.001). Further stratified analysis revealed a more pronounced improvement for reclassification of BI-RADS 4a masses (AUC: 0.943 vs. 0.762/0.675, P ＜ 0.001) than BI-RADS 4b (AUC:0.950 vs. 0.885/0.796, P＞0.05) with the assistance of CEUS than SWE/SE. Employing downgrade CEUS strategies resulted in negative predictive values ranging from 95.2 % to 100.0 % for BI-RADS 4a and 4b masses. Conversely, using upgrade nomogram strategies, which included the independent predictive risk factors of irregular enhanced shape, poor defined enhanced margin, earlier enhanced time, increased surrounding vessels, and presence of contrast agent retention, the diagnostic performance achieved an AUC of 0.947 with good calibration.

CONCLUSION

After investigating the potential of CEUS and ES in improving risk assessment and diagnostic accuracy for nonpalpable BI-RADS category 4 breast masses, it is evident that CEUS has a more significant impact on enhancing classification compared to ES, particularly for BI-RADS 4a subgroup masses. This finding suggests that CEUS may offer greater benefits in improving risk assessment and diagnostic accuracy for this specific subgroup of breast masses.

Evaluation of breast skin and tissue stiffness using a non-invasive aspiration device and impact of clinical predictors

A personalized 3D breast model could present a real benefit for preoperative discussion with patients, surgical planning, and guidance. Breast tissue biomechanical properties have been poorly studied in vivo, although they are important for breast deformation simulation. The main objective of our study was to determine breast skin thickness and breast skin and adipose/fibroglandular tissue stiffness. The secondary objective was to assess clinical predictors of elasticity and thickness: age, smoking status, body mass index, contraception, pregnancies, breastfeeding, menopausal status, history of radiotherapy or breast surgery. Participants were included at the Montpellier University Breast Surgery Department from March to May 2022. Breast skin thickness was measured by ultrasonography, breast skin and adipose/fibroglandular tissue stiffnesses were determined with a VLASTIC non-invasive aspiration device at three different sites (breast segments I-III). Multivariable linear models were used to assess clinical predictors of elasticity and thickness. In this cohort of 196 women, the mean breast skin and adipose/fibroglandular tissue stiffness values were 39 and 3 kPa, respectively. The mean breast skin thickness was 1.83 mm. Only menopausal status was significantly correlated with breast skin thickness and adipose/fibroglandular tissue stiffness. The next step will be to implement these stiffness and thickness values in a biomechanical breast model and to evaluate its capacity to predict breast tissue deformations.

Breast lesion morphology assessment with high and standard b values in diffusion-weighted imaging at 3 Tesla

INTRODUCTION

With increasing spatial resolution, diffusion-weighted imaging (DWI) may be suitable for morphologic lesion characterization in breast MRI - an area that has traditionally been occupied by dynamic contrast-enhanced imaging (DCE). This investigation compared DWI with b values of 800 and 1600 s/mm2 to DCE for lesion morphology assessment in high-resolution breast MRI at 3 Tesla.

MATERIAL AND METHODS

Multiparametric breast MRI was performed in 91 patients with 93 histopathologically proven lesions (31 benign, 62 malignant). Two radiologists independently evaluated three datasets per patient (DWIb800; DWIb1600; DCE) and assessed lesion visibility and BIRADS morphology criteria. Diagnostic accuracy was compared among readers and datasets using Cochran's Q test and pairwise post-hoc McNemar tests. Bland-Altman analyses were conducted for lesion size comparisons.

RESULTS

Discrimination of carcinomas was superior compared to benign findings in both DWIb800 and DWIb1600 (p < 0.001) with no b value-dependent difference. Similarly, assessability of mass lesions was better than of non-mass lesions, irrespective of b value (p < 0.001). Intra-reader reliability for the analysis of morphologic BIRADS criteria among DCE and DWI datasets was at least moderate (Fleiss κ≥0.557), while at least substantial inter-reader agreement was ascertained over all assessed categories (κ≥0.776). In pairwise Bland-Altman analyses, the measurement bias between DCE and DWIb800 was 0.7 mm, whereas the difference between DCE and DWIb1600 was 2.8 mm. DWIb1600 allowed for higher specificity than DCE (p = 0.007/0.062).

CONCLUSIONS

DWI can be employed for reliable morphologic lesion characterization in high-resolution breast MRI. High b values increase diagnostic specificity, while lesion size assessment is more precise with standard 800 s/mm2 images.

Effectiveness of hybrid digital breast tomosynthesis/digital mammography compared to digital mammography in women presenting for routine screening at Maroondah BreastScreen: Study protocol for a co-designed, non-randomised prospective trial

BACKGROUND

Digital breast tomosynthesis (DBT) for breast cancer screening has been shown in international trials to increase cancer detection compared with mammography; however, results have varied across screening settings, and currently there is limited and conflicting evidence on interval cancer rates (a surrogate for screening effectiveness). Australian pilot data also indicated substantially longer screen-reading time for DBT posing a barrier for adoption. There is a critical need for evidence on DBT to inform its role in Australia, including evaluation of potentially more feasible models of implementation, and quantification of screening outcomes by breast density which has global relevance.

METHODS

This study is a prospective trial embedded in population-based Australian screening services (Maroondah BreastScreen, Eastern Health, Victoria) comparing hybrid screening comprising DBT (mediolateral oblique view) and digital mammography (cranio-caudal view) with standard mammography screening in a concurrent group attending another screening site. All eligible women aged ≥40 years attending the Maroondah service for routine screening will be enrolled (unless they do not provide verbal consent and opt-out of hybrid screening; are unable to provide consent; or where a 'pushback' image on hybrid DBT cannot be obtained). Each arm will enrol 20,000 women. The primary outcomes are cancer detection rate (per 1000 screens) and recall rate (percentage). Secondary outcomes include 'opt-out' rate; cohort characteristics; cancer characteristics; assessment outcomes; screen-reading time; and interval cancer rate at 24-month follow-up. Automated volumetric breast density will be measured to allow stratification of outcomes by mammographic density. Stratification by age and screening round will also be undertaken. An interim analysis will be undertaken after the first 5000 screens in the intervention group.

DISCUSSION

This is the first Australian prospective trial comparing hybrid DBT/mammography with standard mammography screening that is powered to show differences in cancer detection. Findings will inform future implementation of DBT in screening programs world-wide and provide evidence on whether DBT should be adopted in the broader BreastScreen program in Australia or in subgroups of screening participants.

TRIAL REGISTRATION

The trial is registered with the Australian New Zealand Clinical Trials Registry (ANZCTR, ACTRN12623001144606, https://www.anzctr.org.au/). Registration will be updated to reflect trial progress and protocol amendments.

How to manage type 2 curve dilemma in dynamic contrast-enhanced magnetic resonance imaging of the breast: diffusion-weighted imaging or early phase enhancement kinetics?

BACKGROUND

Type 2 time-intensity curves can indicate both malignant and benign breast lesions in dynamic contrast enhanced magnetic resonance imaging (DCE-MRI).

PURPOSE

To investigate whether diffusion-weighted imaging (DWI) or early phase kinetics of DCE-MRI is practical to discriminate breast masses that depict type 2 curve in DCE-MRI.

MATERIAL AND METHODS

We retrospectively included 107 lesions in 97 patients with type 2 curves in DCE-MRI. Morphological characteristics, early phase dynamic parameters on DCE-MRI, and apparent diffusion coefficient (ADC) values on DWI were evaluated. Diagnostic thresholds of ADC and early phase maximum enhancement ratio (EPMER) to distinguish between benign and malignant masses were calculated. Strongest predictors of malignancy were determined to build the most effective diagnostic model.

RESULTS

DWI, EPMER, and all morphological features were found statistically significant to discriminate malignancy (P <0.05). The thresholds of ADC and EPMER were assigned as 1.0 ×10-3 mm2/s and 72%, respectively. The sensitivity and specificity were 80% and 97% for ADC, and 93% and 60% for EPMER, respectively. Two models were established. Model 1 comprised ADC and the lesion margin. Model 2 consisted of ADC, margin, and EPMER with a high specificity (99%) and positive predictive value (97%).

CONCLUSION

When combined with DWI, early phase wash-in data provide diagnostic improvement of breast masses presenting type 2 curve in the late phase of DCE-MRI, especially for specificity. Future studies are required to support our findings for the need of a cross-validation.

Radiation doses received in the UK breast screening programmes 2019-2023

OBJECTIVE

To report the latest UK mammography dose survey results and to compare radiation doses from digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) in UK breast screening.

METHODS

Anonymized exposure factors were collected for 111 152 screening cases and 5113 assessment cases from 405 x-ray sets across the United Kingdom using an online submission system linked to a national database of mammography quality control data. Output and beam quality measurements from each set were combined with exposure data to estimate mean glandular doses (MGD).

RESULTS

FFDM doses increased by ∼10% compared to the 2016-2019 national survey but compressed breast thicknesses (CBT) remained similar. DBT doses were 34%-40% higher than FFDM overall and 34% higher than FFDM for breasts 50-60 mm thick. We found a possible overestimation of PMMA breast equivalent thicknesses at low CBTs, but the evidence was not conclusive.

CONCLUSION

Recent changes to the mix of x-ray models in use in UK breast screening have resulted in higher FFDM breast doses. DBT doses in the NHSBSP are on average higher than FFDM by ∼34%-40%.

ADVANCES IN KNOWLEDGE

This is the first national study to report DBT and FFDM MGDs in UK breast screening.

In situtumor model for longitudinal in silico imaging trials

Objective.In this article, we introduce a computational model for simulating the growth of breast cancer lesions accounting for the stiffness of surrounding anatomical structures.Approach.In our model, ligaments are classified as the most rigid structures while the softer parts of the breast are occupied by fat and glandular tissues As a result of these variations in tissue elasticity, the rapidly proliferating tumor cells are met with differential resistance. It is found that these cells are likely to circumvent stiffer terrains such as ligaments, instead electing to proliferate preferentially within the more yielding confines of the breast's soft topography. By manipulating the interstitial tumor pressure in direct proportion to the elastic constants of the tissues surrounding the tumor, this model thus creates the potential for realizing a database of unique lesion morphology sculpted by the distinctive topography of each local anatomical infrastructure. We modeled the growth of simulated lesions within volumes extracted from fatty breast models, developed by Graffet alwith a resolution of 50μm generated with the open-source and readily available Virtual Imaging Clinical Trials for Regulatory Evaluation (VICTRE) imaging pipeline. To visualize and validate the realism of the lesion models, we leveraged the imaging component of the VICTRE pipeline, which replicates the siemens mammomat inspiration mammography system in a digital format. This system was instrumental in generating digital mammogram (DM) images for each breast model containing the simulated lesions.Results.By utilizing the DM images, we were able to effectively illustrate the imaging characteristics of the lesions as they integrated with the anatomical backgrounds. Our research also involved a reader study that compared 25 simulated DM regions of interest (ROIs) with inserted lesions from our models with DM ROIs from the DDSM dataset containing real manifestations of breast cancer. In general the simulation time for the lesions was approximately 2.5 hours, but it varied depending on the lesion's local environment.Significance.The lesion growth model will facilitate and enhance longitudinal in silico trials investigating the progression of breast cancer.

Radiation dose to breast during digital mammography in Tanzania

The aim of this study was to evaluate the mean glandular dose (MGD), to assess the potential for optimization, and to propose diagnostic reference levels (DRLs). MGD was estimated from air kerma measurements and patient information collected during mammography examinations. The 75th percentile values were determined as the third quartile of the median MGD values for all hospitals, and DRLs set as 75th percentile of MGD values. The estimated median values of MGD ranged from 1.5 to 3.9 mGy for craniocaudal projection for median range of 15-59 mm compressed breast thickness (CBT). For a CBT range of 15-63 mm, the median MGD value was 1.5-5.1 mGy for medio-lateral oblique projection. Comparison with other studies showed that the MGD values obtained in this study were relatively high. The magnitude and wide variation of the exposure parameters suggest existing potential for optimization. The training of radiology staff was identified as a top priority.

Lesion-conditioning of synthetic MRI-derived subtraction-MIPs of the breast using a latent diffusion model

The purpose of this feasibility study is to investigate if latent diffusion models (LDMs) are capable to generate contrast enhanced (CE) MRI-derived subtraction maximum intensity projections (MIPs) of the breast, which are conditioned by lesions. We trained an LDM with n = 2832 CE-MIPs of breast MRI examinations of n = 1966 patients (median age: 50 years) acquired between the years 2015 and 2020. The LDM was subsequently conditioned with n = 756 segmented lesions from n = 407 examinations, indicating their location and BI-RADS scores. By applying the LDM, synthetic images were generated from the segmentations of an independent validation dataset. Lesions, anatomical correctness, and realistic impression of synthetic and real MIP images were further assessed in a multi-rater study with five independent raters, each evaluating n = 204 MIPs (50% real/50% synthetic images). The detection of synthetic MIPs by the raters was akin to random guessing with an AUC of 0.58. Interrater reliability of the lesion assessment was high both for real (Kendall's W = 0.77) and synthetic images (W = 0.85). A higher AUC was observed for the detection of suspicious lesions (BI-RADS ≥ 4) in synthetic MIPs (0.88 vs. 0.77; p = 0.051). Our results show that LDMs can generate lesion-conditioned MRI-derived CE subtraction MIPs of the breast, however, they also indicate that the LDM tended to generate rather typical or 'textbook representations' of lesions.

Predictive value of background parenchymal enhancement on breast magnetic resonance imaging for pathological tumor response to neoadjuvant chemotherapy in breast cancers: a systematic review

OBJECTIVES

This review aimed to assess the predictive value of background parenchymal enhancement (BPE) on breast magnetic resonance imaging (MRI) as an imaging biomarker for pathologic complete response (pCR) after neoadjuvant chemotherapy (NACT).

METHODS

Two reviewers independently performed a systemic literature search using the PubMed, MEDLINE, and Embase databases for studies published up to 11 June 2022. Data from relevant articles were extracted to assess the relationship between BPE and pCR.

RESULTS

This systematic review included 13 studies with extensive heterogeneity in population characteristics, MRI follow-up points, MRI protocol, NACT protocol, pCR definition, and BPE assessment. Baseline BPE levels were not associated with pCR, except in 1 study that reported higher baseline BPE of the younger participants (< 55 years) in the pCR group than the non-pCR group. A total of 5 studies qualitatively assessed BPE levels and indicated a correlation between reduced BPE after NACT and pCR; however, among the studies that quantitatively measured BPE, the same association was observed only in the subgroup analysis of 2 articles that assessed the status of hormone receptor and human epidermal growth factor receptor 2. In addition, the predictive ability of early BPE changes for pCR was reported in several articles and remains controversial.

CONCLUSIONS

Changes in BPE may be a promising imaging biomarker for predicting pCR in breast cancer. Because current studies remain insufficient, particularly those that quantitatively measure BPE, prospective and multicenter large-sample studies are needed to confirm this relationship.

THUBreast: an open-source breast phantom generation software for x-ray imaging and dosimetry

Objective. Establishing realistic phantoms of human anatomy is a continuing concern within virtual clinical trials of breast x-ray imaging. However, little attention has been paid to glandular distribution within these phantoms. The principal objective of this study was to develop breast phantoms considering the clinical glandular distribution.Approach. This research introduces an innovative method for integrating glandular distribution information into breast phantoms. We have developed an open-source software, THUBreast44http://github.com/true02Hydrogen/THUBreast/, which generates breast phantoms that accurately replicate both the structural texture and glandular distribution, two crucial elements in breast x-ray imaging and dosimetry. To validate the efficacy of THUBreast, we assembled three groups of breast phantoms (THUBreast, patient-based, homogeneous) for irradiation simulation and calculated the power-law exponents (β) and mean glandular dose (Dg), indicators of texture realism and radiation risk, respectively, utilizing MC-GPU.Main results. Upon the computation of theDgfor the THUBreast phantoms, it was found to be in agreement with that absorbed by the phantoms based on patients, with an average deviation of 4%. The estimates of averageDgthus obtained were on average 23% less than those computed for the homogeneous phantoms. It was observed that the homogeneous phantoms did overestimate the averageDgby 30% when compared to the phantoms based on patients. The mean value ofβfor the images of THUBreast phantoms was found to be 2.92 ± 0.08, which shows a commendable agreement with the findings of prior investigations.Significance. It is evidently clear from the results that THUBreast phantoms have a preliminary good performance in both imaging and dosimetry in terms of indicators of texture realism and glandular dose. THUBreast represents a further step towards developing a powerful toolkit for comprehensive evaluation of image quality and radiation risk.

Diagnostic value of synthetic diffusion-weighted imaging on breast magnetic resonance imaging assessment: comparison with conventional diffusion-weighted imaging

PURPOSE

To compare images generated by synthetic diffusion-weighted imaging (sDWI) with those from conventional DWI in terms of their diagnostic performance in detecting breast lesions when performing breast magnetic resonance imaging (MRI).

METHODS

A total of 128 consecutive patients with 135 enhanced lesions who underwent dynamic MRI between 2018 and 2021 were included. The sDWI and DWI signals were compared by three radiologists with at least 10 years of experience in breast radiology.

RESULTS

Of the 82 malignant lesions, 91.5% were hyperintense on sDWI and 73.2% were hyperintense on DWI. Of the 53 benign lesions, 71.7% were isointense on sDWI and 37.7% were isointense on DWI. sDWI provides accurate signal intensity data with statistical significance compared with DWI (P < 0.05). The diagnostic performance of DWI and sDWI to differentiate malignant breast masses from benign masses was as follows: sensitivity 73.1% [95% confidence interval (CI): 62-82], specificity 37.7% (95% CI: 24-52); sensitivity 91.5% (95% CI: 83-96), specificity 71.7% (95% CI: 57-83), respectively. The diagnostic accuracy of DWI and sDWI was 59.2% and 83.7%, respectively. However, when the DWI images were evaluated with apparent diffusion coefficient mapping and compared with the sDWI images, the sensitivity was 92.68% (95% CI: 84-97) and the specificity was 79.25% (95% CI: 65-89) with no statistically significant difference. The inter-reader agreement was almost perfect (P < 0.001).

CONCLUSION

Synthetic DWI is superior to DWI for lesion visibility with no additional acquisition time and should be taken into consideration when conducting breast MRI scans. The evaluation of sDWI in routine MRI reporting will increase diagnostic accuracy.

Application Value of Ultrasound Elastography Combined With Contrast-Enhanced Ultrasound (CEUS) Quantitative Analysis in Differentiation of Nodular Fibrocystic Changes of the Breast From Invasive Ductal Carcinoma

This study aimed to compare the value of ultrasound elastography combined with contrast-enhanced ultrasound (CEUS) quantitative analysis in the differentiation of nodular fibrocystic breast change (FBC) from breast invasive ductal carcinoma (BIDC). We selected 50 patients each with nodular FBC and BIDC, who were admitted to the Affiliated Hospital of Zunyi Medical University from January 2018 to December 2021. Their ultrasonic elastic images and CEUS videos were collected, their ultrasound elastography scores and the ratio of strain rate (SR) of the lesions were determined, and the exported DICOM format videos of CEUS were quantitatively analyzed using VueBox software to obtain quantitative perfusion parameters. The differences between the ultrasound elastography score and SR while comparing nodular FBC and BIDC cases were statistically significant (p < .05). The sensitivity, specificity, and accuracy of ultrasound elastography scores in the differential diagnoses of nodular FBC and BIDC were 74%, 88%, and 81%, respectively. Additionally, the sensitivity, specificity, and accuracy of SR in the differential diagnosis of nodular FBC and BIDC were 94%, 78%, and 86%, respectively. Statistically significant differences were observed in the CEUS quantitative perfusion parameters PE, AUC (WiAUC, WoAUC, WiWoAUC), and WiPI in both nodular FBC and BIDC according to the VueBox software (p < .05). The sensitivity, specificity, and accuracy of CEUS quantitative analysis in the differential diagnoses of nodular FBC and BIDC were 66%, 82%, and 74%, respectively. Using the pathological findings as the gold standard, ROC curves were established, and the area under the curve (AUC) of the CEUS quantitative analysis, elasticity score, SR, and ultrasound elastography combined with CEUS quantitative analysis were 0.731, 0.838, and 0.892, as well as 0.945, respectively. Ultrasound elasticity scoring, SR and CEUS quantitative analysis have certain application value for differentiating nodular FBC cases from BIDC; however, ultrasound elasticity imaging combined with CEUS quantitative analysis can help in improving the differential diagnostic efficacy of nodular FBC cases from BIDC.

Mammogram mass segmentation and classification based on cross-view VAE and spatial hidden factor disentanglement

Breast masses are the most important clinical findings of breast carcinomas. The mass segmentation and classification in mammograms remain a crucial yet challenging topic in computer-aided diagnosis systems, as the masses show their irregularities in shape, size and texture. In this paper, we propose a new framework for mammogram mass classification and segmentation. Specifically, to utilize the complementary information within the mammographic cross-views, cranio caudal and mediolateral oblique, a cross-view based variational autoencoder (CV-VAE) combined with a spatial hidden factor disentanglement module is presented, where the two views can be reconstructed from each other through two explicitly disentangled hidden factors: class related (specified) and background common (unspecified). Then, the specified factor is not only divided into two categories: benign and malignant by a new introduced feature pyramid networks based mass classifier, but also used to predict the mass mask label based on a U-Net-like decoder. By integrating the two complementary modules, more discriminative morphological and semantic features can be learned to solve the mass classification and segmentation problems simultaneously. The proposed method is evaluated on two most used public mammography datasets, CBIS-DDSM and INbreast, achieving the Dice similarity coefficient (DSC) of 92.46% and 93.70% for segmentation and the area under receiver operating characteristic curve (AUC) of 93.20% and 95.01% for classification, respectively. Compared with other state-of-the-art approaches, it gives competitive results.

Radiologic-Pathologic Correlation of Nonmass Enhancement Contiguous with Malignant Index Breast Cancer Masses at Preoperative Breast MRI

Purpose To determine the pathologic features of nonmass enhancement (NME) directly adjacent to biopsy-proven malignant masses (index masses) at preoperative MRI and determine imaging characteristics that are associated with a malignant pathologic condition. Materials and Methods This retrospective study involved the review of breast MRI and mammography examinations performed for evaluating disease extent in patients newly diagnosed with breast cancer from July 1, 2016, to September 30, 2019. Inclusion criteria were limited to patients with an index mass and the presence of NME extending directly from the mass margins. Wilcoxon rank sum test, Fisher exact test, and χ2 test were used to analyze cancer, patient, and imaging characteristics associated with the NME diagnosis. Results Fifty-eight patients (mean age, 58 years ± 12 [SD]; all women) were included. Malignant pathologic findings for mass-associated NME occurred in 64% (37 of 58) of patients, 43% (16 of 37) with ductal carcinoma in situ and 57% (21 of 37) with invasive carcinoma. NME was more likely to be malignant when associated with an index cancer that had a low Ki-67 index (<20%) (P = .04). The presence of calcifications at mammography correlating with mass-associated NME was not significantly associated with malignant pathologic conditions (P = .19). The span of suspicious enhancement measured at MRI overestimated the true span of disease at histologic evaluation (P < .001), while there was no evidence of a difference between span of calcifications at mammography and true span of disease at histologic evaluation (P = .27). Conclusion Mass-associated NME at preoperative MRI was malignant in most patients with newly diagnosed breast cancer. The span of suspicious enhancement measured at MRI overestimated the true span of disease found at histologic evaluation. Keywords: Breast, Mammography © RSNA, 2024 See also the commentary by Newell in this issue.

Automated 3-D Ultrasound Elastography of the Breast: An In Vivo Validation Study

OBJECTIVE

Studies have indicated that adding 2-D quasi-static elastography to B-mode ultrasound imaging improved the specificity for malignant lesion detection, as malignant lesions are often stiffer (increased strain ratio) compared with benign lesions. This method is limited by its user dependency and so unsuitable for breast screening. To overcome this limitation, we implemented quasi-static elastography in an automated breast volume scanner (ABVS), which is an operator-independent 3-D ultrasound system and is especially useful for screening women with dense breasts. The study aim was to investigate if 3-D quasi-static elastography implemented in a clinically used ABVS can discriminate between benign and malignant breast lesions.

METHODS

Volumetric breast ultrasound radiofrequency data sets of 82 patients were acquired before and after automated transducer lifting. Lesions were annotated and strain was calculated using an in-house-developed strain algorithm. Two strain ratio types were calculated per lesion: using axial and maximal principal strain (i.e., strain in dominant direction).

RESULTS

Forty-four lesions were detected: 9 carcinomas, 23 cysts and 12 other benign lesions. A significant difference was found between malignant (median: 1.7, range: [1.0-3.2]) and benign (1.0, [0.6-1.9]) using maximal principal strain ratios. Axial strain ratio did not reveal a significant difference between benign (0.6, [-12.7 to 4.9]) and malignant lesions (0.8, [-3.5 to 5.1]).

CONCLUSION

Three-dimensional strain imaging was successfully implemented on a clinically used ABVS to obtain, visualize and analyze in vivo strain images in three dimensions. Results revealed that maximal principal strain ratios are significantly increased in malignant compared with benign lesions.