Search Results (77)

Background: Standardised breast positioning and optimal compression are critical components of effective breast cancer screening. This scoping review aims to report the current landscape of automated software tools developed for image quality assessment and mammographic technique evaluation, and to examine their reported impact. Methods: A scoping review was undertaken across PubMed (MEDLINE), Scopus, and Emcare. Eligible studies were published between January 2014 and March 2025 and investigated the use of automated software or artificial intelligence-based tools to assess image quality, breast positioning, or compression in mammography or digital breast tomosynthesis. Results: Automated software was predominantly utilised in high-resource settings, where it provided benchmarked feedback, reduced the subjectivity inherent in traditional visual grading systems, and supported radiographer learning and skill development with measurable improvements. However, radiographer training in these systems, the impact of software on clinical workflow, and barriers to implementation, particularly in low-resource settings, were insufficiently addressed in the literature. Furthermore, no studies reported on the relationship between software-generated metrics and breast cancer screening outcomes. Conclusions: Automated software for image quality evaluation represents a significant advancement in breast screening, illustrating the potential of technology to strengthen the screening-to-treatment continuum in breast cancer care. Nonetheless, widespread adoption requires evidence that these tools directly contribute to improved cancer detection outcomes to justify their uptake. Full article

Background/Objectives: There is significant interest in using texture features to extract hidden image-based information. In medical imaging applications using radiomics, AI, or personalized medicine, the quest is to extract patient or disease specific information while being insensitive to other system or processing variables. While we use digital breast tomosynthesis (DBT) to show these effects, our results would be generally applicable to a wider range of other imaging modalities and applications. Methods: We examine factors in texture estimation methods, such as quantization, pixel distance offset, and region of interest (ROI) size, that influence the magnitudes of these readily computable and widely used image texture features (specifically Haralick’s gray level co-occurrence matrix (GLCM) textural features). Results: Our results indicate that quantization is the most influential of these parameters, as it controls the size of the GLCM and range of values. We propose a new multi-resolution normalization (by either fixing ROI size or pixel offset) that can significantly reduce quantization magnitude disparities. We show reduction in mean differences in feature values by orders of magnitude; for example, reducing it to 7.34% between quantizations of 8–128, while preserving trends. Conclusions: When combining images from multiple vendors in a common analysis, large variations in texture magnitudes can arise due to differences in post-processing methods like filters. We show that significant changes in GLCM magnitude variations may arise simply due to the filter type or strength. These trends can also vary based on estimation variables (like offset distance or ROI) that can further complicate analysis and robustness. We show pathways to reduce sensitivity to such variations due to estimation methods while increasing the desired sensitivity to patient-specific information such as breast density. Finally, we show that our results obtained from simulated DBT images are consistent with what we see when applied to clinical DBT images. Full article

Background and Objectives: The aim of our study was to assess the diagnostic accuracy of four imaging modalities—digital mammography (DM), digital breast tomosynthesis (DBT), ultrasound (US), and breast magnetic resonance imaging (MRI)—applied individually and in combination in early cancer detection in women with dense breasts. Methods: This single-center retrospective study was conducted from January 2021 to September 2024 at the Oncology Institute of Vojvodina in Serbia and included 168 asymptomatic and symptomatic women with dense breasts. Based on the exclusion criteria, the final number of women who were screened with all four imaging methods was 156. The reference standard for checking the diagnostic accuracy of these methods is the result of a histopathological examination, if a biopsy is performed, or a stable radiological finding in the next 12–24 months. Results: The findings underscore the superior diagnostic performance of breast MRI with the highest sensitivity (95.1%), specificity (78.7%), and overall accuracy (87.2%). In contrast, DM showed the lowest sensitivity (87.7%) and low specificity (49.3%). While the combination of DM + DBT + US demonstrated improved sensitivity to 96.3%, its specificity drastically decreased to 32%, illustrating as ensitivity–specificity trade-off. Notably, the integration of all four modalities increased sensitivity to 97.5% but decreased specificity to 29.3%, suggesting an overdiagnosis risk. DBT significantly improved performance over DM alone, likely due to enhanced tissue differentiation. US proved valuable in dense breast tissue but was associated with a high false-positive rate. Breast MRI, even when used alone, confirmed its status as the gold standard for dense breast imaging. However, its widespread use is constrained by economic and logistical barriers. ROC curve analysis further emphasized MRI’s diagnostic superiority (AUC = 0.958) compared with US (0.863), DBT (0.828), and DM (0.820). Conclusions: This study provides a unique, comprehensive comparison of all four imaging modalities within the same patient cohort, offering a rare model for optimizing diagnostic pathways in women with dense breasts. The findings support the strategic integration of complementary imaging approaches to improve early cancer detection while highlighting the risk of increased false-positive rates. In settings where MRI is not readily accessible, a combined DM + DBT + US protocol may serve as a pragmatic alternative, though its limitations in specificity must be carefully considered. Full article

Stationary inverse-geometry digital tomosynthesis (s-IGDT) causes truncation artifacts in reconstructed images due to its geometric characteristics. This study introduces a deep convolutional generative adversarial network (DCGAN)-based out-painting method for mitigating truncation artifacts in s-IGDT images. The proposed network employed an encoder–decoder architecture for the generator, and a dilated convolution block was added between the encoder and decoder. A dual-discriminator was used to distinguish the artificiality of generated images for truncated and non-truncated regions separately. During network training, the generator was able to selectively learn a target task for the truncated regions using binary mask images. The performance of the proposed method was compared to conventional methods in terms of signal-to-noise ratio (SNR), normalized root-mean-square error (NRMSE), peak SNR (PSNR), and structural similarity (SSIM). The results showed that the proposed method led to a substantial reduction in truncation artifacts. On average, the proposed method achieved 62.31, 16.66, and 14.94% improvements in the SNR, PSNR, and SSIM, respectively, compared to the conventional methods. Meanwhile, the NRMSE values were reduced by an average of 37.22%. In conclusion, the proposed out-painting method can offer a promising solution for mitigating truncation artifacts in s-IGDT images and improving the clinical availability of the s-IGDT. Full article

Background: Digital breast tomosynthesis (DBT) is a valuable imaging modality for breast cancer detection; however, its interpretation remains time-consuming and subject to inter-reader variability. This study aimed to develop and evaluate two deep learning (DL) models based on transfer learning for the binary classification of breast lesions (benign vs. malignant) using DBT images to support clinical decision-making and risk stratification. Methods: In this retrospective monocentric study, 184 patients with histologically or clinically confirmed benign (107 cases, 41.8%) or malignant (77 cases, 58.2%) breast lesions were included. Each case underwent DBT with a single lesion manually segmented for radiomic analysis. Two convolutional neural network (CNN) architectures—ResNet50 and DenseNet201—were trained using transfer learning from ImageNet weights. A 10-fold cross-validation strategy with ensemble voting was applied. Model performance was evaluated through ROC–AUC, accuracy, sensitivity, specificity, PPV, and NPV. Results: The ResNet50 model outperformed DenseNet201 across most metrics. On the internal testing set, ResNet50 achieved a ROC–AUC of 63%, accuracy of 60%, sensitivity of 39%, and specificity of 75%. The DenseNet201 model yielded a lower ROC–AUC of 55%, accuracy of 55%, and sensitivity of 24%. Both models demonstrated relatively high specificity, indicating potential utility in ruling out malignancy, though sensitivity remained suboptimal. Conclusions: This study demonstrates the feasibility of using transfer learning-based DL models for lesion classification on DBT. While the overall performance was moderate, the results highlight both the potential and current limitations of AI in breast imaging. Further studies and approaches are warranted to enhance model robustness and clinical applicability. Full article

Background: Synthetic 2D mammography was developed to decrease radiation exposure, but to our knowledge there have been no studies evaluating the impact of implementation of full field synthetic mammography/digital breast tomosynthesis (FFSM/DBT) on indications for stereotactic biopsy. Objective: To compare indications and biopsy outcomes for stereotactic biopsy for full field digital mammography (FFDM/DBT) to those of FFSM/DBT. Methods: Retrospective chart review of stereotactic biopsies performed from July 2014 to September 2018. Reports were reviewed and indication for biopsy, lesion size, and final pathology were recorded. Comparison between the two groups following transition to FFSM/DBT in 2016 was performed. Results: 66 of 361 stereotactic biopsies performed in the FFDM/DBT group were malignant (PPV 18.3%), compared to 60 of the 391 biopsies performed in the FFSM/DBT group (PPV 15.4%) with no significant difference in PPV (p = 0.281). There were statistically significant changes in indications for biopsies after transitioning to FFSM/DBT: with a decrease in calcifications referred for biopsy (68.03% vs. 89.75%; p < 0.001), and a statistically significant increase in referral of masses (10.74% vs. 4.43%; p < 0.001), asymmetries (15.60% vs. 5.26%; p < 0.001), and architectural distortion (5.63% vs. 0.55%; p < 0.001). PPV across all indications (21.8% in FFSM/DBT vs. 20.3% in FFDM; p = 0.213), and invasive cancer yield (5.63% vs. 3.32%; p = 0.129) remained comparable following transition to FFSM/DBT without statistically significant differences. Conclusions: Following transition to FFSM/DBT, statistically significant shifts in indications for biopsies were observed with a decrease in referral of calcifications and an increase for masses, asymmetries and architectural distortions. PPV for stereotactic biopsy was not significantly different and cancer yield across all indications remained similar, with an increase in invasive cancer diagnosis. Full article

Background: Digital tomosynthesis (DTS) is an advanced imaging modality that enhances diagnostic accuracy by offering three-dimensional visualization from two-dimensional projections, which is particularly beneficial in breast and lung imaging. However, this increased imaging capability raises concerns about patient exposure to ionizing radiation. Methods: This study explores the energy and angular dependence of thermoluminescent dosimeters (TLDs), specifically TLD100H, to improve the accuracy of organ dose assessment during DTS. Using a comprehensive experimental approach, organ doses were measured in both DTS and traditional RX modes. Results: The results showed lung doses of approximately 3.21 mGy for the left lung and 3.32 mGy for the right lung during DTS, aligning with the existing literature. In contrast, the RX mode yielded significantly lower lung doses of 0.33 mGy. The heart dose during DTS was measured at 2.81 mGy, corroborating findings from similar studies. Conclusions: These results reinforce the reliability of TLD100H dosimetry in assessing radiation exposure and highlight the need for optimizing imaging protocols to minimize doses. Overall, this study contributes to the ongoing dialogue on enhancing patient safety in diagnostic imaging and advocates for collaboration among medical physicists, radiologists, and technologists to establish best practices. Full article

The aim of this patient dose review is to establish a thorough diagnostic reference level (DRL) system. This entails calculating a DRL value for each possible image technique/view considered to perform a diagnostic mammogram in our practice. Diagnostic mammographies from a total of 1191 patients who underwent a diagnostic mammogram study in our designated diagnostic mammography center were collected and retrospectively analyzed. The DRL representing our health sector was set as the median of the mean glandular dose (MGD) for each possible image technique/view, including the 2D standard bilateral craniocaudal (LCC/RCC) and mediolateral oblique (LMLO/RMLO), the 2D bilateral spot compression CC and MLO (RSCC/LSCC and RSMLO/LSMLO), the 2D bilateral spot compression with magnification (RMSCC/LMSCC and RMSMLO/LMSMLO), the 3D digital breast tomosynthesis CC and MLO (RCC/LCC and RMLO/LMLO), the 2D bilateral implant CC and MLO (RIMCC/LIMCC and RIMMLO/LIMMLO), the 2D bilateral contrast enhanced CC and MLO (RCECC/LCECC and RCEMLO/LCEMLO) and the 2D bilateral stereotactic biopsy guided CC (SBRCC/SBLCC). This patient dose review revealed that the highest MGD was associated with the 2D bilateral spot compression with magnification (MSCC/MSMLO) image view. For the compressed breast thickness (CBT) group 60–69 mm, the median and 75th percentile of the MGD values obtained were MSCC: 3.35 and 3.96, MSMLO: 4.14 and 5.25 mGy respectively. Obvious MGD variations were witnessed across the different possible views even for the same CBT group. Our results are in line with the published DRLs when using same statistical quantity and CBT group. Full article

Background/Objectives: The accurate detection of microcalcifications in mammograms is critical for the early detection of breast cancer. However, the variability between different manufacturers is significant, particularly with digital breast tomosynthesis (DBT). Manufacturers have many design differences, including sweep angles, detector types, reconstruction techniques, filters, and focal spot construction. This study outlined the development of an innovative phantom model using crystallizations to improve the accuracy of imaging microcalcifications in DBT. The goal of these models was to achieve consistent evaluations, thereby reducing the variability between different scanners. Methods: We created a novel phantom model that simulates different types of breast tissue densities with calcifications. Furthermore, these crystalline-grown phantoms can more accurately represent the physiological shapes and compositions of microcalcifications than do other available phantoms for calcifications and can be evaluated on different systems. Microcalcification patterns were generated using the evaporation of sodium chloride, transplantation of calcium carbonate crystals, and/or injection of hydroxyapatite. These patterns were embedded in multiple layers within the wax to simulate various depths and distributions of calcifications with the ability to generate a large variety of patterns. Results: The tomosynthesis imaging revealed phantoms that utilized calcium carbonate crystals showed demonstrable visualization differences between the 3D DBT reconstructions and the magnification/2D view, illustrating the model’s value. The phantom was able to highlight changes in the contrast and resolution, which is crucial for accurate microcalcification evaluation. Conclusions: Based on the crystalline growth, this phantom model offers an important new standardized target for evaluating DBT systems. By promoting standardization, especially through the development of advanced breast calcification phantoms, this work and design aimed to contribute to improving earlier and more accurate breast cancer detection. Full article

Computer-aided detection (CADe) of masses in digital breast tomosynthesis (DBT) is crucial for early breast cancer diagnosis. However, the variability in the size and morphology of breast masses and their resemblance to surrounding tissues present significant challenges. Current CNN-based CADe methods, particularly those that use Feature Pyramid Networks (FPN), often fail to integrate multi-scale information effectively and struggle to handle dense glandular tissue with high-density or iso-density mass lesions due to the unidirectional integration and progressive attenuation of features, leading to high false positive rates. Additionally, the commonly indistinct boundaries of breast masses introduce uncertainty in boundary localization, which makes traditional Dirac boundary modeling insufficient for precise boundary regression. To address these issues, we propose the CU-Net network, which efficiently fuses multi-scale features and accurately models blurred boundaries. Specifically, the CU-Net introduces the Cross-Attention Adaptive Feature Pyramid Network (CA-FPN), which enhances the effectiveness and accuracy of feature interactions through a cross-attention mechanism to capture global correlations across multi-scale feature maps. Simultaneously, the Breast Density Perceptual Module (BDPM) incorporates breast density information to weight intermediate features, thereby improving the network’s focus on dense breast regions susceptible to false positives. For blurred mass boundaries, we introduce Uncertainty Boundary Modeling (UBM) to model the positional distribution function of predicted bounding boxes for masses with uncertain boundaries. In comparative experiments on an in-house clinical DBT dataset and the BCS-DBT dataset, the proposed method achieved sensitivities of 89.68% and 72.73% at 2 false positives per DBT volume (FPs/DBT), respectively, significantly outperforming existing state-of-the-art detection methods. This method offers clinicians rapid, accurate, and objective diagnostic assistance, demonstrating substantial potential for clinical application. Full article

Since its introduction, digital breast tomosynthesis (DBT) has been widely incorporated in screening for breast cancer due to its lesser recall and higher cancer detection rates. Some screen-detected lesions may be visible only by DBT, requiring biopsy using DBT guidance. This review article dissects the different steps of tomosynthesis-guided biopsy and discusses the different obstacles that might be encountered during each step while providing the appropriate solutions, hence allowing physicians to perform a successful biopsy with the least patient discomfort. Full article

Background/Objectives: Digital mammography (DM) has long been the standard for breast cancer screening, while digital breast tomosynthesis (DBT) offers an advanced 3D imaging modality capable of generating 2D Synthetic Mammography (SM) images. Despite SM’s potential to reduce radiation exposure, many clinics favor DM, with DBT and SM, due to its perceived diagnostic reliability. This study investigates whether radiologists can replace DM with SM in breast cancer screening and diagnosis or if both modalities are necessary. Methods: We retrospectively analyzed DM and SM images from 375 women aged 40–65 who underwent DM with DBT at King Khaled University Hospital from 2020–2022. Three radiologists evaluated the images using ACR BI-RADS, assessing diagnostic accuracy via the area under the receiver operating characteristic (ROC) curve (AUC). The agreement in cancer conspicuity, breast density, size, and calcifications were measured using weighted kappa (κ). Results: Among 57 confirmed cancer cases and 290 cancer-free cases, DM demonstrated higher sensitivity (82.5% vs. 78.9%) and diagnostic accuracy (AUC 0.800 vs. 0.783, p < 0.05) compared to SM. However, SM detected more suspicious calcifications in cancer cases (75.6% vs. 51.2%, p < 0.05). Agreement was fair for conspicuity (κ = 0.288) and calcifications (κ = 0.409), moderate for density (κ = 0.591), and poor for size (κ = 0.254). Conclusions: while SM demonstrates enhanced effectiveness in detecting microcalcifications, DM still proves superior in overall diagnostic accuracy and image clarity. Therefore, although SM offers certain advantages, it remains slightly inferior to DM and cannot yet replace DM in breast cancer screening. Full article

There are variations in the assessment pathways for women recalled at screening, and the imaging assessment pathway with the best diagnostic outcome is poorly understood. This paper examines the efficacy of five imaging modalities for the assessment of screen-recalled breast lesions. Methods: The Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) strategy was employed to identify studies that assessed the efficacy of imaging modalities in the assessment of lesions recalled at screening from the following eight databases: Medline, Web of Science, Embase, Scopus, Science Direct, PubMed, CINAHL, and Global Health. Search terms included “Breast assessment” AND “Diagnostic Workup” OR “Mammography” AND “Digital Breast tomosynthesis” AND “contrast enhanced mammography and Magnetic Resonance imaging” AND “breast ultrasound”. Studies that examined the performance of digital mammography (DM), digital breast tomosynthesis (DBT), handheld ultrasound (HHUS), contrast-enhanced mammography (CEM), and magnetic resonance imaging (MRI) in screen-recalled lesions were reviewed. Meta-analyses of these studies were conducted using the MetaDisc 2.0 software package. Results: Fifty-four studies met the inclusion criteria and examined between one and three imaging modalities. Pooled results of each imaging modality demonstrated that CEM has the highest sensitivity (95; 95% CI: 90–97) followed by MRI (93; 95% CI: 88–96), DBT (91; 95% CI: 87–94), HHUS (90; 95% CI: 86–93), and DM (85; 95% CI: 78–90). The DBT demonstrated the highest specificity (85; 95% CI: 75–91) followed by DM (77; 95% CI: 66–85), CEM (73; 95% CI: 63–81), MRI (69; 95% CI: 55–81), and HHUS (65; 95% CI: 46–80). Conclusions: The CEM, MRI, DBT, and HHUS demonstrate excellent performance in correctly identifying and classifying cancer lesions referred for diagnostic work-up, but HHUS, MRI, and CEM have a more limited ability to discriminate benign lesions than DBT and DM. Full article

Mammographic density (MD) assessment is subject to inter- and intra-observer variability. An automated method, such as Quantra software, could be a useful tool for an objective and reproducible MD assessment. Our purpose was to evaluate the performance of Quantra software in assessing MD, according to BI-RADS^® Atlas Fifth Edition recommendations, verifying the degree of agreement with the gold standard, given by the consensus of two breast radiologists. A total of 5009 screening examinations were evaluated by two radiologists and analysed by Quantra software to assess MD. The agreement between the three assigned values was expressed as intraclass correlation coefficients (ICCs). The agreement between the software and the two readers (R1 and R2) was moderate with ICC values of 0.725 and 0.713, respectively. A better agreement was demonstrated between the software’s assessment and the average score of the values assigned by the two radiologists, with an index of 0.793, which reflects a good correlation. Quantra software appears a promising tool in supporting radiologists in the MD assessment and could be part of a personalised screening protocol soon. However, some fine-tuning is needed to improve its accuracy, reduce its tendency to overestimate, and ensure it excludes high-density structures from its assessment. Full article

The current study proposed and evaluated “residual squeeze and excitation attention gate” (rSEAG), a novel network that can improve image quality by reducing distortion attributed to artifacts. This method was established by modifying the Cycle Generative Adversarial Network (cycleGAN)-based generator network using projection data for pre-reconstruction processing in digital breast tomosynthesis. Residual squeeze and excitation were installed in the bridge of the generator network, and the attention gate was installed in the skip connection between the encoder and decoder. Based on the radiation dose index (exposure index and division index) incident on the detector, the cases approved by the ethics committee and used for the study were classified as reference (675 projection images) and object (675 projection images). For the cases, unsupervised data containing a mixture of cases with and without masses were used. The cases were trained using cycleGAN with rSEAG and the conventional networks (ResUNet and U-Net). For testing, predictive processing was performed on cases (60 projection images) that were not used for learning. Images were generated using filtered backprojection reconstruction (kernel: Ramachandran and Lakshminarayanan) from projection data for testing data and without pre-reconstruction processing data (evaluation: in-focus plane). The distortion was evaluated using perception-based image quality evaluation (PIQE) analysis, texture analysis (feature: “Homogeneity” and “Contrast”), and a statistical model with a Gumbel distribution. PIQE has a low rSEAG value. Texture analysis showed that rSEAG and a network without cycleGAN were similar in terms of the “Contrast” feature. In dense breasts, ResUNet had the lowest “Contrast” feature and U-Net had differences between cases. The maximal variations in the Gumbel plot, rSEAG reduced the high-frequency ripple artifacts. In this study, rSEAG could improve distortion and reduce ripple artifacts. Full article