Digital tomosynthesis in breast imaging

Health Technologies and Impermissible Delays: The Case of Digital Breast Tomosynthesis

This paper argues that we have a moral obligation to implement certain health technologies even if we have limited or incomplete evidence of their effectiveness. The focus is on technologies used in non-emergency settings, as opposed to "exceptional cases" such as compassionate use and emergency approvals during public health emergencies. A broadly plausible moral principle - the Ecumenical Principle - is introduced and applied to a test case: the use of Digital Breast Tomosynthesis in mammographic screening. The paper concludes by exploring the implications of the Ecumenical Principle for the adoption of other new health technologies.

Strategies for generating synthetic computed tomography-like imaging from radiographs: A scoping review

BACKGROUND

Advancements in tomographic medical imaging have revolutionized diagnostics and treatment monitoring by offering detailed 3D visualization of internal structures. Despite the significant value of computed tomography (CT), challenges such as high radiation dosage and cost barriers limit its accessibility, especially in low- and middle-income countries. Recognizing the potential of radiographic imaging in reconstructing CT images, this scoping review aims to explore the emerging field of synthesizing 3D CT-like images from 2D radiographs by examining the current methodologies.

METHODS

A scoping review was carried out following PRISMA-SR guidelines. Eligibility criteria for the articles included full-text articles published up to September 9, 2024, studying methodologies for the synthesis of 3D CT images from 2D biplanar or four-projection x-ray images. Eligible articles were sourced from PubMed MEDLINE, Embase, and arXiv.

RESULTS

76 studies were included. The majority (50.8 %, n = 30) were published between 2010 and 2020 (38.2 %, n = 29) and from 2020 onwards (36.8 %, n = 28), with European (40.8 %, n = 31), North American (26.3 %, n = 20), and Asian (32.9 %, n = 25) institutions being primary contributors. Anatomical regions varied, with 17.1 % (n = 13) of studies not using clinical data. Further, studies focused on the chest (25 %, n = 19), spine and vertebrae (17.1 %, n = 13), coronary arteries (10.5 %, n = 8), and cranial structures (10.5 %, n = 8), among other anatomical regions. Convolutional neural networks (CNN) (19.7 %, n = 15), generative adversarial networks (21.1 %, n = 16) and statistical shape models (15.8 %, n = 12) emerged as the most applied methodologies. A limited number of studies included explored the use of conditional diffusion models, iterative reconstruction algorithms, statistical shape models, and digital tomosynthesis.

CONCLUSION

This scoping review summarizes current strategies and challenges in synthetic imaging generation. The development of 3D CT-like imaging from 2D radiographs could reduce radiation risk while simultaneously addressing financial and logistical obstacles that impede global access to CT imaging. Despite initial promising results, the field encounters challenges with varied methodologies and frequent lack of proper validation, requiring further research to define synthetic imaging's clinical role.

The role and potential of digital breast tomosynthesis in neoadjuvant systemic therapy evaluation for optimising breast cancer management: a pictorial essay

Neoadjuvant therapy (NT) has become the gold standard for treating locally advanced breast cancer (BC). The assessment of pathological response (pR) post-NT plays a crucial role in predicting long-term survival, with contrast-enhanced MRI currently recognised as the preferred imaging modality for its evaluation. Traditional imaging techniques, such as digital mammography (DM) and ultrasonography (US), encounter difficulties in post-NT assessments due to breast density, lesion changes, fibrosis, and molecular patterns. Digital breast tomosynthesis (DBT) offers solutions to prevalent challenges in DM, such as tissue overlap, and facilitates a comprehensive assessment of lesion morphology, dimensions, and margins. Studies suggest that DBT correlates more accurately with pathology than DM and US, showcasing its potential advantages. This pictorial essay demonstrates the potential of DBT as a complementary tool to DM for assessing pR after NT, including instances of true- and false-positive assessments correlated with histopathological findings. In conclusion, DBT emerges as a valuable adjunct to DM, effectively addressing its limitations in post-NT assessment. The technology's potential to diminish tissue overlap, improve discrimination, and provide multi-dimensional perspectives demonstrates promising results, indicating its utility in scenarios where MRI is contraindicated or inaccessible.

Controversies in the Application of AI in Radiology-Is There Medico-Legal Support? Aspects from Romanian Practice

Background/Objectives: Artificial intelligence (AI) is gaining an increasing amount of influence in various fields, including medicine. In radiology, where diagnoses are based on collaboration between diagnostic devices and the professional experience of radiologists, AI intervention seems much easier than in other fields, but this is often not the case. Many times, the patients orient themselves according to the doctor, which is not applicable in the case of AI. Another limitation rests in the controversies regarding medico-legal liability. In the field of radio-imaging in Romania, the implementation of AI systems in diagnosis is at its beginning. An important aspect of this is raising awareness among the population about these assistive AI systems and, also, awareness of the technological evolution of AI among medical staff. This narrative review manuscript analyzes the existing literature data regarding the medico-legal aspects of AI application in radiology, highlighting the controversial aspects and the lack of statutory legislative regulations in Romania. Methods: A detailed search was conducted across three electronic databases including MEDLINE/PubMed, Scopus, and Web of Science, with 53 papers serving as the literature corpus of our review. Results: General requirements for artificial intelligence systems used in radiology have been established. In the radiological diagnostic process, there are five levels of AI system implication. Until now, completely autonomous AI systems have not been used. Regarding liability in the case of malpractice, at the currently accepted legislative level, most of the time, the radiologist is liable for their own fault or non-compliant use of diagnostic AI systems. Controversies arise in the case of radio-imaging diagnosis in which AI systems act autonomously. Conclusions: In order for AI diagnostic radio-imaging systems to be implemented, they must meet certain quality standards and be approved. The radiologist must know these systems, accept them, know their limits, and validate them in accordance with their degree of involvement in radiological diagnosis. Considering the evolution of technology in the Romanian medical system, including radiology, in the future, an alignment with the legal standards established/proposed at the European level is desired.

A class of Landweber-type iterative methods based on the Radon transform for incomplete view tomography

BACKGROUND

We study the reconstruction problem for incomplete view tomography, including sparse view tomography and limited angle tomography, by the Landweber iteration and its accelerated version. Traditional implementations of these Landweber-type iterative methods necessitate multiple large-scale matrix-vector multiplications, which in turn require substantial time and storage resources.

OBJECTIVE

This paper aims to develop and test a novel and efficient discretization approach for a class of Landweber-type methods that minimizes storage requirements by incorporating the specific structure of the incomplete view Radon transform.

METHODS

We prove that the normal operator of incomplete view Radon transform in these methods is a compact convolution operator, and derive the explicit representation of its convolution kernel. Discretized by the pixel basis, these Landweber-type iterative methods can be implemented quickly and accurately by introducing a discretized convolution operation between two small-scale matrices with minimal storage requirements.

RESULTS

For the simulated complete and limited angle data, the reconstruction results using various Landweber-type methods with our proposed discretization scheme achieve a 1-5dB improvement in PSNR and require one-third of computation time compared to the traditional approach. For the simulated sparse view data, our discretization scheme yields a valid image with the highest PSNR.

CONCLUSIONS

The Landweber-type iterative methods, when combined with our proposed discretization approach based on the Radon transform, are effective for addressing the incomplete view tomography problem.

Detection of breast cancer in digital breast tomosynthesis with vision transformers

Digital Breast Tomosynthesis (DBT) has revolutionized more traditional breast imaging through its three-dimensional (3D) visualization capability that significantly enhances lesion discernibility, reduces tissue overlap, and improves diagnostic precision as compared to conventional two-dimensional (2D) mammography. In this study, we propose an advanced Computer-Aided Detection (CAD) system that harnesses the power of vision transformers to augment DBT's diagnostic efficiency. This scheme uses a neural network to glean attributes from the 2D slices of DBT followed by post-processing that considers features from neighboring slices to categorize the entire 3D scan. By leveraging a transfer learning technique, we trained and validated our CAD framework on a unique dataset consisting of 3,831 DBT scans and subsequently tested it on 685 scans. Of the architectures tested, the Swin Transformer outperformed the ResNet101 and vanilla Vision Transformer. It achieved an impressive AUC score of 0.934 ± 0.026 at a resolution of 384 × 384. Increasing the image resolution from 224 to 384 not only maintained vital image attributes but also led to a marked improvement in performance (p-value = 0.0003). The Mean Teacher algorithm, a semi-supervised method using both labeled and unlabeled DBT slices, showed no significant improvement over the supervised approach. Comprehensive analyses across different lesion types, sizes, and patient ages revealed consistent performance. The integration of attention mechanisms yielded a visual narrative of the model's decision-making process that highlighted the prioritized regions during assessments. These findings should significantly propel the methodologies employed in DBT image analysis by setting a new benchmark for breast cancer diagnostic precision.

Digital breast tomosynthesis in breast cancer screening: an ethical perspective

Although digital breast tomosynthesis has higher sensitivity than digital mammography and at least as high specificity, digital mammography remains the most common method for conducting mammographic screening. At the same time, mammography systems are now delivered "DBT-ready" and can be used for either digital mammography or digital breast tomosynthesis. In this paper, we ask whether it is ethically permissible to use such equipment for digital mammography, given its lower sensitivity. We argue it is not, and that clinics are ethically required to use their DBT-ready equipment to screen with digital breast tomosynthesis whenever this is practically possible. Our argument relies on a comparison between digital breast tomosynthesis and a hypothesized improvement in the image quality of digital mammography. CRITICAL RELEVANCE STATEMENT: Women may lose out on the benefits of screening with digital breast tomosynthesis when DBT-ready equipment is used to screen with digital mammography; we argue that this practice is ethically problematic. KEY POINTS: Digital breast tomosynthesis finds more cases of breast cancer than digital mammography. Mammography equipment can often be used to screen with both digital breast tomosynthesis and digital mammography. When they can, clinics are ethically required to use existing equipment to screen with digital breast tomosynthesis instead of digital mammography.

Imaging the dense breast

The sensitivity of mammography reduces as breast density increases, which impacts breast screening and locoregional staging in breast cancer. Supplementary imaging with other modalities can offer improved cancer detection, but this often comes at the cost of more false positives. Magnetic resonance imaging and contrast-enhanced mammography, which assess tumour enhancement following contrast administration, are more sensitive than digital breast tomosynthesis and ultrasound, which predominantly rely on the assessment of tumour morphology.

Iterative reconstruction for limited-angle CT using implicit neural representation

Objective.Limited-angle computed tomography (CT) presents a challenge due to its ill-posed nature. In such scenarios, analytical reconstruction methods often exhibit severe artifacts. To tackle this inverse problem, several supervised deep learning-based approaches have been proposed. However, they are constrained by limitations such as generalization issue and the difficulty of acquiring a large amount of paired CT images.Approach.In this work, we propose an iterative neural reconstruction framework designed for limited-angle CT. By leveraging a coordinate-based neural representation, we formulate tomographic reconstruction as a convex optimization problem involving a deep neural network. We then employ differentiable projection layer to optimize this network by minimizing the discrepancy between the predicted and measured projection data. In addition, we introduce a prior-based weight initialization method to ensure the network starts optimization with an informed initial guess. This strategic initialization significantly improves the quality of iterative reconstruction by stabilizing the divergent behavior in ill-posed neural fields. Our method operates in a self-supervised manner, thereby eliminating the need for extensive data.Main results.The proposed method outperforms other iterative and learning-based methods. Experimental results on XCAT and Mayo Clinic datasets demonstrate the effectiveness of our approach in restoring anatomical features as well as structures. This finding was substantiated by visual inspections and quantitative evaluations using NRMSE, PSNR, and SSIM. Moreover, we conduct a comprehensive investigation into the divergent behavior of iterative neural reconstruction, thus revealing its suboptimal convergence when starting from scratch. In contrast, our method consistently produced accurate images by incorporating an initial estimate as informed initialization.Significance.This work showcases the feasibility to reconstruct high-fidelity CT images from limited-angle x-ray projections. The proposed methodology introduces a novel data-free approach to enhance medical imaging, holding promise across various clinical applications.

Dedicated Cone-Beam Breast CT: Reproducibility of Volumetric Glandular Fraction with Advanced Image Reconstruction Methods

Dedicated cone-beam breast computed tomography (CBBCT) is an emerging modality and provides fully three-dimensional (3D) images of the uncompressed breast at an isotropic voxel resolution. In an effort to translate this modality to breast cancer screening, advanced image reconstruction methods are being pursued. Since radiographic breast density is an established risk factor for breast cancer and CBBCT provides volumetric data, this study investigates the reproducibility of the volumetric glandular fraction (VGF), defined as the proportion of fibroglandular tissue volume relative to the total breast volume excluding the skin. Four image reconstruction methods were investigated: the analytical Feldkamp-Davis-Kress (FDK), a compressed sensing-based fast, regularized, iterative statistical technique (FRIST), a fully supervised deep learning approach using a multi-scale residual dense network (MS-RDN), and a self-supervised approach based on Noise-to-Noise (N2N) learning. Projection datasets from 106 women who participated in a prior clinical trial were reconstructed using each of these algorithms at a fixed isotropic voxel size of (0.273 mm3). Each reconstructed breast volume was segmented into skin, adipose, and fibroglandular tissues, and the VGF was computed. The VGF did not differ among the four reconstruction methods (p = 0.167), and none of the three advanced image reconstruction algorithms differed from the standard FDK reconstruction (p > 0.862). Advanced reconstruction algorithms developed for low-dose CBBCT reproduce the VGF to provide quantitative breast density, which can be used for risk estimation.

Impact of breast density on diagnostic accuracy in digital breast tomosynthesis versus digital mammography: results from a European screening trial

BACKGROUND

The diagnostic accuracy of digital breast tomosynthesis (DBT) and digital mammography (DM) in breast cancer screening may vary per breast density subgroup. The purpose of this study was to evaluate which women, based on automatically assessed breast density subgroups, have the greatest benefit of DBT compared with DM in the prospective Malmö Breast Tomosynthesis Screening Trial.

MATERIALS AND METHODS

The prospective European, Malmö Breast Tomosynthesis Screening Trial (n = 14,848, Jan. 27, 2010-Feb. 13, 2015) compared one-view DBT and two-view DM, with consensus meeting before recall. Breast density was assessed in this secondary analysis with the automatic software Laboratory for Individualized Breast Radiodensity Assessment. DBT and DM's diagnostic accuracies were compared by breast density quintiles of breast percent density (PD) and absolute dense area (DA) with confidence intervals (CI) and McNemar's test. The association between breast density and cancer detection was analyzed with logistic regression, adjusted for ages < 55 and ≥ 55 years and previous screening participation.

RESULTS

In total, 14,730 women (median age: 58 years; inter-quartile range = 16) were included in the analysis. Sensitivity was higher and specificity lower for DBT compared with DM for all density subgroups. The highest breast PD quintile showed the largest difference in sensitivity and specificity at 81.1% (95% CI 65.8-90.5) versus 43.2% (95% CI 28.7-59.1), p < .001 and 95.5% (95% CI 94.7-96.2) versus 97.2% (95% CI 96.6-97.8), p < 0.001, respectively. Breast PD quintile was also positively associated with cancer detected via DBT at odds ratio 1.24 (95% CI 1.09-1.42, p = 0.001).

CONCLUSION

Women with the highest breast density had the greatest benefit from digital breast tomosynthesis compared with digital mammography with increased sensitivity at the cost of slightly lower specificity. These results may influence digital breast tomosynthesis's use in an individualized screening program stratified by, for instance, breast density.

TRIAL REGISTRATION

Trial registration at https://www.

CLINICALTRIALS

gov : NCT01091545, registered March 24, 2010.

A new projection correction based voting strategy for breast calcification artifact reduction

Objective.Digital Breast Tomosynthesis (DBT) is an imaging technique that combines traditional tomography with image processing and reconstruction techniques. In screening for breast cancer, high attenuation lesion will cause calcification hardening artifacts, which reduces the reconstructed image quality and limits diagnostic accuracy. We focus on the reconstruction artifacts that are caused by high-attenuation features in DBT, and aim to propose an efficient and accurate method to remove calcification artifacts and retain calcification information.Approach.The proposed method first introduces a new segmentation method, which can segment breast calcification accurately and effectively. Then an interpolation method is used to eliminate both the calcified area and artifact area in the projection images which are then used to reconstruct the image without artifacts and calcifications. Finally, the interpolated reconstructed image and the unprocessed reconstructed image are fused under the proposed voting strategy to obtain the DBT image with calcification artifacts removal.Main results.18 groups of simulated projection data and 10 groups of real projection data collected by us are used to evaluate the proposed method. Experimental results show that our algorithm can effectively reduce the calcification artifact and preserve the effective information in the image as well.Significance.The proposed method utilizes a novel projection correction based voting fusion strategy for image fusion, and is advanced in reducing breast calcification artifacts compared with other state-of-the-art methods. Our work paves the way for more efficient and precise DBT breast cancer screening.

Effects of bariatric surgery on breast density in adult obese women: systematic review and meta-analysis

Introduction

Bariatric surgery is one of the most effective methods for treating obesity. It can effectively reduce body weight and reduce the incidence of obesity-related breast cancer. However, there are different conclusions about how bariatric surgery changes breast density. The purpose of this study was to clarify the changes in breast density from before to after bariatric surgery.

Methods

The relevant literature was searched through PubMed and Embase to screen for studies. Meta-analysis was used to clarify the changes in breast density from before to after bariatric surgery.

Results

A total of seven studies were included in this systematic review and meta-analysis, including a total of 535 people. The average body mass index decreased from 45.3 kg/m2 before surgery to 34.4 kg/m2 after surgery. By the Breast Imaging Reporting and Data System score, the proportion of grade A breast density from before to after bariatric surgery decreased by 3.83% (183 vs. 176), grade B (248 vs. 263) increased by 6.05%, grade C (94 vs. 89) decreased by 5.32%, and grade D (1 vs. 4) increased by 300%. There was no significant change in breast density from before to after bariatric surgery (OR=1.27, 95% confidence interval (CI) [0.74, 2.20], P=0.38). By the Volpara density grade score, postoperative volumetric breast density increased (standardized mean difference = -0.68, 95% CI [-1.08, -0.27], P = 0.001).

Discussions

Breast density increased significantly after bariatric surgery, but this depended on the method of detecting breast density. Further randomized controlled studies are needed to validate our conclusions.

History of Mammography: Analysis of Breast Imaging Diagnostic Achievements over the Last Century

Breast cancer is the most common forms of cancer and a leading cause of mortality in women. Early and correct diagnosis is, therefore, essential to save lives. The development of diagnostic imaging applied to the breast has been impressive in recent years and the most used diagnostic test in the world is mammography, a low-dose X-ray technique used for imaging the breast. In the first half of the 20th century, the diagnosis was in practice only clinical, with consequent diagnostic delay and an unfavorable prognosis in the short term. The rise of organized mammography screening has led to a remarkable reduction in mortality through the early detection of breast malignancies. This historical review aims to offer a complete panorama of the development of mammography and breast imaging during the last century. Through this study, we want to understand the foundations of the pillar of radiology applied to the breast through to the most modern applications such as contrast-enhanced mammography (CEM), artificial intelligence, and radiomics. Understanding the history of the development of diagnostic imaging applied to the breast can help us understand how to better direct our efforts toward an increasingly personalized and effective diagnostic approach. The ultimate goal of imaging applied to the detection of breast malignancies should be to reduce mortality from this type of disease as much as possible. With this paper, we want to provide detailed documentation of the main steps in the evolution of breast imaging for the diagnosis of breast neoplasms; we also want to open up new scenarios where the possible current and future applications of imaging are aimed at being more precise and personalized.

GaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows

Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities. However, greater expertise is required to develop DL algorithms, and the variability of implementations hinders their reproducibility, translation, and deployment. Here we present the community-driven Generally Nuanced Deep Learning Framework (GaNDLF), with the goal of lowering these barriers. GaNDLF makes the mechanism of DL development, training, and inference more stable, reproducible, interpretable, and scalable, without requiring an extensive technical background. GaNDLF aims to provide an end-to-end solution for all DL-related tasks in computational precision medicine. We demonstrate the ability of GaNDLF to analyze both radiology and histology images, with built-in support for k -fold cross-validation, data augmentation, multiple modalities and output classes. Our quantitative performance evaluation on numerous use cases, anatomies, and computational tasks supports GaNDLF as a robust application framework for deployment in clinical workflows.

The increasing complexity of the implementation and operation of deep learning techniques hinders their reproducibility and deployment at scale, especially in healthcare. Pati and colleagues introduce a deep learning framework to analyse healthcare data without requiring extensive computational experience, facilitating the integration of artificial intelligence in clinical workflows.

Xenon-enhanced dual-energy tomosynthesis for functional imaging of respiratory disease-Concept and phantom study

BACKGROUND

Xenon-enhanced dual-energy (DE) computed tomography (CT) and hyperpolarized noble-gas magnetic resonance imaging (MRI) provide maps of lung ventilation that can be used to detect chronic obstructive pulmonary disease (COPD) early in its development and predict respiratory exacerbations. However, xenon-enhanced DE-CT requires high radiation doses and hyper-polarized noble-gas MRI is expensive and only available at a handful of institutions globally.

PURPOSE

To present xenon-enhanced dual-energy tomosynthesis (XeDET) for low-dose, low-cost functional imaging of respiratory disease in an experimental phantom study.

METHODS

We propose using digital tomosynthesis to produce Xe-enhanced low-energy (LE) and high-energy (HE) coronal images. DE subtraction of the LE and HE images is used to suppress soft tissues. We used an imaging phantom to investigate image quality in terms of the area under the reciever operating characteristic curve (AUC) for the Non-PreWhitening model observer with an Eye filter and internal noise (NPWEi). The phantom simulated anatomic clutter due to lung parenchyma and attenuation due to soft tissue and lung tissue. Aluminum slats were used to simulate rib structures. A stepwedge consisting of an acrylic casing with sealed cylindrical air-filled cavities was used to simulate ventilation defects with step thicknesses of 0.5, 1, and 2 cm and cylindrical radii of 0.5, 0.75, and 1 cm. The phantom was ventilated with Xe and projection data were acquired using a flat-panel detector, a tube-voltage combination of 60/140 kV with 1.2  mm of copper filtration on the HE spectrum and an angular range of ± 15 ∘ $\pm 15^{\circ}$ in 1° increments. The AUC of a NPWEi observer that has access only to a single coronal slice was calculated from measurements of the three-dimensional noise power spectrum and signal template. The AUC was calculated as a function of ventilation defect thickness and radius for total patient entrance air kermas ranging from 1.42 to 2.84 mGy with and without rib-simulating Al slats. For the AUC analysis, the observer internal noise level was obtained from an ad hoc calibration to a high-dose data set.

RESULTS

XeDET was able to suppress parenchyma-simulating clutter in coronal images enabling visualization of the simulated ventilation defects, but the limited angle acquisition resulted in residual clutter due to out-of-plane bone-mimmicking structures. The signal power of the defects increased linearly with defect radius and showed a ten-fold to fifteen-fold increase in signal power when the defect thickness increased from 0.5 to 2 cm. These trends agreed with theoretical predictions. Along the depth dimension, the power of the defects decreased exponentially with distance from the center of the defects with full-width half maxima that varied from 1.85 to 2.85 cm depending on the defect thickness and radius. The AUCs of the 1-cm-radius defect that was 2 cm in thickness ranged from good (0.8-0.9) to excellent (0.9-1.0) over the range of air kermas considered.

CONCLUSIONS

Xenon-enhanced DE tomosynthesis has the potential to enable functional imaging of respiratory disease and should be further investigated as a low-cost alternative to MRI-based approaches and a low-dose alternative to CT-based approaches.

Artificial Intelligence in Breast X-Ray Imaging

This topical review is focused on the clinical breast x-ray imaging applications of the rapidly evolving field of artificial intelligence (AI). The range of AI applications is broad. AI can be used for breast cancer risk estimation that could allow for tailoring the screening interval and the protocol that are woman-specific and for triaging the screening exams. It also can serve as a tool to aid in the detection and diagnosis for improved sensitivity and specificity and as a tool to reduce radiologists' reading time. AI can also serve as a potential second 'reader' during screening interpretation. During the last decade, numerous studies have shown the potential of AI-assisted interpretation of mammography and to a lesser extent digital breast tomosynthesis; however, most of these studies are retrospective in nature. There is a need for prospective clinical studies to evaluate these technologies to better understand their real-world efficacy. Further, there are ethical, medicolegal, and liability concerns that need to be considered prior to the routine use of AI in the breast imaging clinic.

Deep learning tomographic reconstruction through hierarchical decomposition of domain transforms

Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve non-local and space-variant integral transforms between the input and output domains, for which no efficient neural network models are readily available. A prior attempt to solve tomographic reconstruction problems with supervised learning relied on a brute-force fully connected network and only allowed reconstruction with a 128⁴ system matrix size. This cannot practically scale to realistic data sizes such as 512⁴ and 512⁶ for three-dimensional datasets. Here we present a novel framework to solve such problems with DL by casting the original problem as a continuum of intermediate representations between the input and output domains. The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture, with exponentially fewer parameters than a fully connected network would need. We applied the approach to computed tomography (CT) image reconstruction for a 512⁴ system matrix size. This work introduces a new kind of data-driven DL solver for full-size CT reconstruction without relying on the structure of direct (analytical) or iterative (numerical) inversion techniques. This work presents a feasibility demonstration of full-scale learnt reconstruction, whereas more developments will be needed to demonstrate superiority relative to traditional reconstruction approaches. The proposed approach is also extendable to other imaging problems such as emission and magnetic resonance reconstruction. More broadly, hierarchical DL opens the door to a new class of solvers for general inverse problems, which could potentially lead to improved signal-to-noise ratio, spatial resolution and computational efficiency in various areas.

Performance evaluation of digital mammography, digital breast tomosynthesis and ultrasound in the detection of breast cancer using pathology as gold standard: an institutional experience

Background

Mammography is the primary imaging modality for diagnosing breast cancer in women more than 40 years of age. Digital breast tomosynthesis (DBT), when supplemented with digital mammography (DM), is useful for increasing the sensitivity and improving BIRADS characterization by removing the overlapping effect. Ultrasonography (US), when combined with the above combination, further increases the sensitivity and diagnostic confidence. Since most of the research regarding tomosynthesis has been in screening settings, we wanted to quantify its role in diagnostic mammography. The purpose of this study was to assess the performance of DM alone vs. DM combined with DBT vs. DM plus DBT and ultrasound in diagnosing malignant breast neoplasms with the gold standard being histopathology or cytology.

Results

A prospective study of 1228 breasts undergoing diagnostic or screening mammograms was undertaken at our institute. Patients underwent 2 views DM, single view DBT and US. BIRADS category was updated after each step. Final categorization was made with all three modalities combined and pathological correlation was done for those cases in which suspicious findings were detected, i.e. 256 cases. Diagnosis based on pathology was done for 256 cases out of which 193 (75.4%) were malignant and the rest 63 (24.6%) were benign. The diagnostic accuracy of DM alone was 81.1%. Sensitivity, Specificity, PPV and NPV were 87.8%, 60%, 81.3% and 61.1%, respectively. With DM + DBT the diagnostic accuracy was 84.8%. Sensitivity, Specificity, PPV and NPV were 92%, 56.5%, 89% and 65%, respectively. The diagnostic accuracy of DM + DBT + US was found to be 85.1% and Sensitivity, Specificity, PPV and NPV were 96.3%, 50.7%, 85.7% and 82%, respectively.

Conclusion

The combination of DBT to DM led to higher diagnostic accuracy, sensitivity and PPV. The addition of US to DM and DBT further increased the sensitivity and diagnostic accuracy and significantly increased the NPV even in diagnostic mammograms and should be introduced in routine practice for characterizing breast neoplasms.

Artificial intelligence assistance for women who had spot compression view: reducing recall rates for digital mammography

Background

Mammography yields inevitable recall for indeterminate findings that need to be confirmed with additional views.

Purpose

To explore whether the artificial intelligence (AI) algorithm for mammography can reduce false-positive recall in patients who undergo the spot compression view.

Material and Methods

From January to December 2017, 236 breasts from 225 women who underwent the spot compression view due to focal asymmetry, mass, or architectural distortion on standard digital mammography were included. Three readers who were blinded to the study purpose, patient information, previous mammograms, following spot compression views, and any clinical or pathologic reports retrospectively reviewed 236 standard mammograms and determined the necessity of patient recall and the probability of malignancy per breast, first without and then with AI assistance. The performances of AI and the readers were evaluated with the recall rate, area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.

Results

Among 236 examinations, 8 (3.4%) were cancers and 228 (96.6%) were benign. The recall rates of all three readers significantly decreased with AI assistance ( P < 0.05). The reader-averaged recall rates significantly decreased with AI assistance regardless of breast composition (fatty breasts: 32.7% to 24.1%m P = 0.002; dense breasts: 33.6% to 21.2%, P < 0.001). The reader-averaged AUC increased with AI assistance and was comparable to that of standalone AI (0.835 vs. 0.895; P = 0.234). The reader-averaged specificity (71.2% to 79.8%, P < 0.001) and accuracy (71.3% to 79.7%, P  < 0.001) significantly improved with AI assistance.

Conclusion

AI assistance significantly reduced false-positive recall without compromising cancer detection in women with focal asymmetry, mass, or architectural distortion on standard digital mammography regardless of mammographic breast density.

Performance evaluation of digital breast tomosynthesis systems: physical methods and experimental data

Digital breast tomosynthesis (DBT) has become a well-established breast imaging technique, whose performance has been investigated in many clinical studies, including a number of prospective clinical trials. Results from these studies generally point to non-inferiority in terms of microcalcification detection and superior mass-lesion detection for DBT imaging compared to digital mammography (DM). This modality has become an essential tool in the clinic for assessment and ad-hoc screening but is not yet implemented in most breast screening programmes at a state or national level. While evidence on the clinical utility of DBT has been accumulating, there has also been progress in the development of methods for technical performance assessment and quality control of these imaging systems. DBT is a relatively complicated ‘pseudo-3D’ modality whose technical assessment poses a number of difficulties. This paper reviews methods for the technical performance assessment of DBT devices, starting at the component level in part one and leading up to discussion of system evaluation with physical test objects in part two. We provide some historical and basic theoretical perspective, often starting from methods developed for DM imaging. Data from a multi-vendor comparison are also included, acquired under the medical physics quality control protocol developed by EUREF and currently being consolidated by a European Federation of Organisations for Medical Physics working group. These data and associated methods can serve as a reference for the development of reference data and provide some context for clinical studies.

[Patterns in the Use and Perception of Digital Breast Tomosynthesis: A Survey of Korean Breast Radiologists]

Purpose

To evaluate the pattern of use and the perception of digital breast tomosynthesis (DBT) among Korean breast radiologists.

Materials and Methods

From March 22 to 29, 2021, an online survey comprising 27 questions was sent to members of the Korean Society of Breast Imaging. Questions related to practice characteristics, utilization and perception of DBT, and research interests. Results were analyzed based on factors using logistic regression.

Results

Overall, 120 of 257 members responded to the survey (response rate, 46.7%), 67 (55.8%) of whom reported using DBT. The overall satisfaction with DBT was 3.31 (1-5 scale). The most-cited DBT advantages were decreased recall rate (55.8%), increased lesion conspicuity (48.3%), and increased cancer detection (45.8%). The most-cited DBT disadvantages were extra cost for patients (46.7%), insufficient calcification characterization (43.3%), insufficient improvement in diagnostic performance (39.2%), and radiation dose (35.8%). Radiologists reported increased storage requirements and interpretation time for barriers to implementing DBT.

Conclusion

Further improvement of DBT techniques reflecting feedback from the user's perspective will help increase the acceptance of DBT in Korea.

Breast dosimetry in alternative X-ray-based imaging modalities used in current clinical practices

In X-ray breast imaging, Digital Mammography (DM) and Digital Breast Tomosynthesis (DBT), are the standard and largely used techniques, both for diagnostic and screening purposes. Other techniques, such as dedicated Breast Computed Tomography (BCT) and Contrast Enhanced Mammography (CEM) have been developed as an alternative or a complementary technique to the established ones. The performance of these imaging techniques is being continuously assessed to improve the image quality and to reduce the radiation dose. These imaging modalities are predominantly used in the diagnostic setting to resolve incomplete or indeterminate findings detected with conventional screening examinations and could potentially be used either as an adjunct or as a primary screening tool in select populations, such as for women with dense breasts. The aim of this review is to describe the radiation dosimetry for these imaging techniques, and to compare the mean glandular dose with standard breast imaging modalities, such as DM and DBT.

Local Diagnostic Reference Levels for Full-Field Digital Mammography and Digital Breast Tomosynthesis in a Tertiary Hospital in Malaysia

A set of national diagnostic reference levels (DRLs) was established in Malaysia for a range of breast thicknesses in 2013, but no updates for full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT). Due to the increasing number of DBTs used and concern over radiation exposure, this study aimed to explore and establish local diagnostic reference levels for FFDM and DBT in Malaysia health facilities at different compressed breast thickness (CBT) ranges. The CBT, kilovoltage peak (kVp), Entrance surface dose (ESD), and average glandular dose (AGD) were retrospectively extracted from the mammography Digital Imaging and Communications in Medicine (DICOM) header. The 75th and 95th percentile values were obtained for the AGD distribution of each mammography projection for three sets of CBT range. The difference in AGD values between FFDM and DBT at three CBT ranges was determined. The DRLs for FFDM were 1.13 mGy, 1.52 mGy, and 2.87 mGy, while DBT were 1.18 mGy, 1.88 mGy, and 2.78 mGy at CBT ranges of 20−39 mm, 40−59 mm, and 60−99 mm, respectively. The AGD of DBT was significantly higher than FFDM for both mammographic views (p < 0.005). All three CBT groups showed a significant difference in AGD values for FFDM and DBT (p < 0.005). The local DRLs from this study were lower than the national DRLs, with the AGD of FFDM significantly lower than DBT.

XCIST-an open access x-ray/CT simulation toolkit

Objective. X-ray-based imaging modalities including mammography and computed tomography (CT) are widely used in cancer screening, diagnosis, staging, treatment planning, and therapy response monitoring. Over the past few decades, improvements to these modalities have resulted in substantially improved efficacy and efficiency, and substantially reduced radiation dose and cost. However, such improvements have evolved more slowly than would be ideal because lengthy preclinical and clinical evaluation is required. In many cases, new ideas cannot be evaluated due to the high cost of fabricating and testing prototypes. Wider availability of computer simulation tools could accelerate development of new imaging technologies. This paper introduces the development of a new open-access simulation environment for x-ray-based imaging. The main motivation of this work is to publicly distribute a fast but accurate ray-tracing x-ray and CT simulation tool along with realistic phantoms and 3D reconstruction capability, building on decades of developments in industry and academia.Approach. The x-ray-based Cancer Imaging Simulation Toolkit (XCIST) is developed in the context of cancer imaging, but can more broadly be applied. XCIST is physics-based, written in Python and C/C++, and currently consists of three major subsets: digital phantoms, the simulator itself (CatSim), and image reconstruction algorithms; planned future features include a fast dose-estimation tool and rigorous validation. To enable broad usage and to model and evaluate new technologies, XCIST is easily extendable by other researchers. To demonstrate XCIST's ability to produce realistic images and to show the benefits of using XCIST for insight into the impact of separate physics effects on image quality, we present exemplary simulations by varying contributing factors such as noise and sampling.Main results. The capabilities and flexibility of XCIST are demonstrated, showing easy applicability to specific simulation problems. Geometric and x-ray attenuation accuracy are shown, as well as XCIST's ability to model multiple scanner and protocol parameters, and to attribute fundamental image quality characteristics to specific parameters.Significance. This work represents an important first step toward the goal of creating an open-access platform for simulating existing and emerging x-ray-based imaging systems. While numerous simulation tools exist, we believe the combined XCIST toolset provides a unique advantage in terms of modeling capabilities versus ease of use and compute time. We publicly share this toolset to provide an environment for scientists to accelerate and improve the relevance of their research in x-ray and CT.

Current and future diagnostic and treatment strategies for patients with invasive lobular breast cancer

BACKGROUND

Invasive lobular breast cancer (ILC) is the second most common type of breast cancer after invasive breast cancer of no special type (NST), representing up to 15% of all breast cancers.

DESIGN

Latest data on ILC are presented, focusing on diagnosis, molecular make-up according to the European Society for Medical Oncology Scale for Clinical Actionability of molecular Targets (ESCAT) guidelines, treatment in the early and metastatic setting and ILC-focused clinical trials.

RESULTS

At the imaging level, magnetic resonance imaging-based and novel positron emission tomography/computed tomography-based techniques can overcome the limitations of currently used imaging techniques for diagnosing ILC. At the pathology level, E-cadherin immunohistochemistry could help improving inter-pathologist agreement. The majority of patients with ILC do not seem to benefit as much from (neo-)adjuvant chemotherapy as patients with NST, although chemotherapy might be required in a subset of high-risk patients. No differences in treatment efficacy are seen for anti-human epidermal growth factor receptor 2 (HER2) therapies in the adjuvant setting and cyclin-dependent kinases 4 and 6 inhibitors in the metastatic setting. The clinical utility of the commercially available prognostic gene expression-based tests is unclear for patients with ILC. Several ESCAT alterations differ in frequency between ILC and NST. Germline BRCA1 and PALB2 alterations are less frequent in patients with ILC, while germline CDH1 (gene coding for E-cadherin) alterations are more frequent in patients with ILC. Somatic HER2 mutations are more frequent in ILC, especially in metastases (15% ILC versus 5% NST). A high tumour mutational burden, relevant for immune checkpoint inhibition, is more frequent in ILC metastases (16%) than in NST metastases (5%). Tumours with somatic inactivating CDH1 mutations may be vulnerable for treatment with ROS1 inhibitors, a concept currently investigated in early and metastatic ILC.

CONCLUSION

ILC is a unique malignancy based on its pathological and biological features leading to differences in diagnosis as well as in treatment response, resistance and targets as compared to NST.

Prospective Comparison of Synthesized Mammography with DBT and Full-Field Digital Mammography with DBT Uncovers Recall Disagreements That may Impact Cancer Detection

RATIONALE AND OBJECTIVES

Synthesized mammography with digital breast tomosynthesis (SM+DBT) and full-field digital mammography with DBT were prospectively evaluated for recall rate (RR), cancer detection rate (CDR), positive predictive value 1 (PPV1), lesion recall differences, and disagreements in recall for additional imaging.

MATERIALS AND METHODS

From December 15, 2015 to January 15, 2017, after informed consent was obtained for this Health Insurance Portability and Accountability Act compliant study, each enrolled patient's SM+DBT and FFDM+DBT were interpreted sequentially by one of eight radiologists. RR, CDR, PPV1, and imaging findings (asymmetry, focal asymmetry, mass, architectural distortion, and calcifications) recalled were reviewed.

RESULTS

For SM+DBT and FFDM+DBT in 1022 patients, RR was 7.3% and 7.9% (SM+DBT vs. FFDM+DBT: diff= -0.6%; 90% CI= -1.4%, 0.1%); CDR was 6.8 and 7.8 per 1000 (SM+DBT vs. FFDM+DBT: diff= -1.0, 95% CI= -5.5, 2.8, p = 0.317); PPV1 was 9.3% and 9.9% (relative positive predictive value for SM+DBT vs. FFDM+DBT: 0.95, 95% CI: 0.73-1.22, p = 0.669). FFDM+DBT detected eight cancers; SM+DBT detected seven (missed 1 cancer with calcifications). SM+DBT and FFDM+DBT disagreed on patient recall for additional imaging in 19 patients, with majority (68%, 13/19 patients) in the recall of patients for calcifications. For calcifications, SM+DBT recalled six patients that FFDM+DBT did not recall, and FFDM+DBT recalled seven patients that SM+DBT did not recall, even though the total number of calcifications finding recalled was similar overall for both SM+DBT and FFDM+DBT.

CONCLUSION

Disagreement in recall of patients for calcifications may impact cancer detection by SM+DBT, warranting further investigation.

The Impact of Dense Breasts on the Stage of Breast Cancer at Diagnosis: A Review and Options for Supplemental Screening

The purpose of breast cancer screening is to find cancers early to reduce mortality and to allow successful treatment with less aggressive therapy. Mammography is the gold standard for breast cancer screening. Its efficacy in reducing mortality from breast cancer was proven in randomized controlled trials (RCTs) conducted from the early 1960s to the mid 1990s. Panels that recommend breast cancer screening guidelines have traditionally relied on the old RCTs, which did not include considerations of breast density, race/ethnicity, current hormone therapy, and other risk factors. Women do not all benefit equally from mammography. Mortality reduction is significantly lower in women with dense breasts because normal dense tissue can mask cancers on mammograms. Moreover, women with dense breasts are known to be at increased risk. To provide equity, breast cancer screening guidelines should be created with the goal of maximizing mortality reduction and allowing less aggressive therapy, which may include decreasing the interval between screening mammograms and recommending consideration of supplemental screening for women with dense breasts. This review will address the issue of dense breasts and the impact on the stage of breast cancer at the time of diagnosis, and discuss options for supplemental screening.

Two-phase learning-based 3D deblurring method for digital breast tomosynthesis images

In digital breast tomosynthesis (DBT) systems, projection data are acquired from a limited number of angles. Consequently, the reconstructed images contain severe blurring artifacts that might heavily degrade the DBT image quality and cause difficulties in detecting lesions. In this study, we propose a two-phase learning approach for artifact compensation in a coarse-to-fine manner to mitigate blurring artifacts effectively along all viewing directions of the DBT image volume (i.e., along the axial, coronal, and sagittal planes) to improve the detection performance of lesions. The proposed method employs a convolutional neural network model comprising two submodels/phases, with Phase 1 performing three-dimensional (3D) deblurring and Phase 2 performing additional 2D deblurring. To investigate the effects of loss functions on the proposed model’s deblurring performance, we evaluated several loss functions, such as the pixel-based loss function, adversarial-based loss function, and perception-based loss function. Compared with the DBT image, the mean squared error of the image and the root mean squared errors of the gradient of the image decreased by 82.8% and 44.9%, respectively, and the contrast-to-noise ratio increased by 183.4% in the in-focus plane. We verified that the proposed method sequentially restored the missing frequency components as the DBT images were processed through the Phase 1 and Phase 2 steps. These results indicate that the proposed method performs effective 3D deblurring, significantly reducing the blurring artifacts in the in-focus plane and other planes of the DBT image, thus improving the detection performance of lesions.

A Realistic Breast Phantom Proposal for 3D Image Reconstruction in Digital Breast Tomosynthesis

Objectives: Iterative (eg, simultaneous algebraic reconstruction technique [SART]) and analytical (eg, filtered back projection [FBP]) image reconstruction techniques have been suggested to provide adequate three-dimensional (3D) images of the breast for capturing microcalcifications in digital breast tomosynthesis (DBT). To decide on the reconstruction method in clinical DBT, it must first be tested in a simulation resembling the real clinical environment. The purpose of this study is to introduce a 3D realistic breast phantom for determining the reconstruction method in clinical applications. Methods: We designed a 3D realistic breast phantom with varying dimensions (64³-512³) mimicking some structures of a real breast such as milk ducts, lobules, and ribs using TomoPhantom software. We generated microcalcifications, which mimic cancerous cells, with a separate MATLAB code and embedded them into the phantom for testing and benchmark studies in DBT. To validate the characterization of the phantom, we tested the distinguishability of microcalcifications by performing 3D image reconstruction methods (SART and FBP) using Laboratory of Computer Vision (LAVI) open-source reconstruction toolbox. Results: The creation times of the proposed realistic breast phantom were seconds of 2.5916, 8.4626, 57.6858, and 472.1734 for 64³, 128³, 256³, and 512³, respectively. We presented reconstructed images and quantitative results of the phantom for SART (1-2-4-8 iterations) and FBP, with 11 to 23 projections. We determined qualitatively and quantitatively that SART (2-4 iter.) yields better results than FBP. For example, for 23 projections, the contrast-to-noise ratio (CNR) values of SART (2 iter.) and FBP were 2.871 and 0.497, respectively. Conclusions: We created a computationally efficient realistic breast phantom that is eligible for reconstruction and includes anatomical structures and microcalcifications, successfully. By proposing this breast phantom, we provided the opportunity to test which reconstruction methods can be used in clinical applications vary according to various parameters such as the No. of iterations and projections in DBT.

Retrieval of 3D information in X-ray dark-field imaging with a large field of view

X-ray dark-field imaging is a widely researched imaging technique, with many studies on samples of very different dimensions and at very different resolutions. However, retrieval of three-dimensional (3D) information for human thorax sized objects has not yet been demonstrated. We present a method, similar to classic tomography and tomosynthesis, to obtain 3D information in X-ray dark-field imaging. Here, the sample is moved through the divergent beam of a Talbot-Lau interferometer. Projections of features at different distances from the source seemingly move with different velocities over the detector, due to the cone beam geometry. The reconstruction of different focal planes exploits this effect. We imaged a chest phantom and were able to locate different features in the sample (e.g. the ribs, and two sample vials filled with water and air and placed in the phantom) to corresponding focal planes. Furthermore, we found that image quality and detectability of features is sufficient for image reconstruction with a dose of 68 μSv at an effective pixel size of [Formula: see text]. Therefore, we successfully demonstrated that the presented method is able to retrieve 3D information in X-ray dark-field imaging.

Evaluation of Breast Galactography Using Digital Breast Tomosynthesis: A Clinical Exploratory Study

Objectives: To compare the application value of digital breast tomosynthesis (DBT) and full-field digital mammography (FFDM) in breast galactography. Materials and Methods: A total of 128 patients with pathological nipple discharge (PND) were selected to undergo galactography. DBT and FFDM were performed for each patient after injecting the contrast agent; the radiation dose of DBT and FFDM was calculated, and the image quality was evaluated in consensus by two senior breast radiologists. Histopathologic data were found in 49 of the 128 patients. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for both FFDM- and DBT-galactography were calculated using histopathologic results as a reference standard. Data were presented as percentages along with their 95% confidence intervals (CI). Results: The average age of the 128 patients was 46.53 years. The average glandular dose (AGD) of DBT-galactography was slightly higher than that of FFDM-galactography (p < 0.001). DBT-galactography was 30.7% higher than FFDM-galactography in CC view, while DBT-galactography increased by 21.7% compared with FFDM-galactography in ML view. Regarding catheter anatomic distortion, structure detail, and overall image quality groups, DBT scores were higher than FFDM scores, and the differences were significant for all measures (p < 0.05). In 49 patients with pathological nipple discharge, we found that the DBT-galactography had higher sensitivity, specificity, PPV, and NPV (93.3%, 75%, 97.7%, and 50%, respectively) than FFDM-galactography (91.1%, 50%, 95.3%, and 33.3%, respectively). Conclusions: Compared to FFDM-galactography, within the acceptable radiation dose range, DBT-galactography increases the sensitivity and specificity of lesion detection by improving the image quality, providing more confidence for the diagnosis of clinical ductal lesions.

Supplemental Cancer Screening for Women With Dense Breasts: Guidance for Health Care Professionals

Mammography is the standard for breast cancer screening. The sensitivity of mammography in identifying breast cancer, however, is reduced for women with dense breasts. Thirty-eight states have passed laws requiring that all women be notified of breast tissue density results in their mammogram report. The notification includes a statement that differs by state, encouraging women to discuss supplemental screening options with their health care professionals (HCPs). Several supplemental screening tests are available for women with dense breast tissue, but no established guidelines exist to direct HCPs in their recommendation of preferred supplemental screening test. Tailored screening, which takes into consideration the patient's mammographic breast density and lifetime breast cancer risk, can guide breast cancer screening strategies that are more comprehensive. This review describes the benefits and limitations of the various available supplemental screening tests to guide HCPs and patients in choosing the appropriate breast cancer screening.

Comparative evaluation of tomosynthesis, computed tomography, and magnetic resonance imaging findings for metacarpophalangeal joints from equine cadavers

OBJECTIVE

To describe the technique and assess the diagnostic potential and limitations of tomosynthesis for imaging of the metacarpophalangeal joint (MCPJ) of equine cadavers; compare the tomosynthesis appearance of pathological lesions with their conventional radiographic, CT, and MRI appearances; and evaluate all imaging findings with gross lesions of a given MCPJ.

SAMPLE

Distal portions of 4 forelimbs from 4 equine cadavers.

PROCEDURES

The MCPJs underwent radiography, tomosynthesis (with a purpose-built benchtop unit), CT, and MRI; thereafter, MCPJs were disarticulated and evaluated for the presence of gross lesions. The ability to identify pathological lesions on all images was assessed, followed by semiobjective scoring for quality of the overall image and appearance of the subchondral bone, articular cartilage, periarticular margins, and adjacent trabecular bone of the third metacarpal bone, proximal phalanx, and proximal sesamoid bones of each MCPJ.

RESULTS

Some pathological lesions in the subchondral bone of the third metacarpal bone were detectable with tomosynthesis but not with radiography. Overall, tomosynthesis was comparable to radiography, but volumetric imaging modalities were superior to tomosynthesis and radiography for imaging of subchondral bone, articular cartilage, periarticular margins, and adjacent bone.

CONCLUSIONS AND CLINICAL RELEVANCE

With regard to the diagnostic characterization of equine MCPJs, tomosynthesis may be more accurate than radiography for identification of lesions within subchondral bone because, in part, of its ability to reduce superimposition of regional anatomic features. Tomosynthesis may be useful as an adjunctive imaging technique, highlighting subtle lesions within bone, compared with standard radiographic findings.

A neural network with encoded visible edge prior for limited-angle computed tomography reconstruction

PURPOSE

Limited-angle computed tomography is a challenging but important task in certain medical and industrial applications for nondestructive testing. The limited-angle reconstruction problem is highly ill-posed and conventional reconstruction algorithms would introduce heavy artifacts. Various models and methods have been proposed to improve the quality of reconstructions by introducing different priors regarding to the projection data or ideal images. However, the assumed priors might not be practically applicable to all limited-angle reconstruction problems. Convolutional neural network (CNN) exhibits great promise in the modeling of data coupling and has recently become an important technique in medical imaging applications. Although existing CNN methods have demonstrated promising results, their robustness is still a concern. In this paper, in light of the theory of visible and invisible boundaries, we propose an alternating edge-preserving diffusion and smoothing neural network (AEDSNN) for limited-angle reconstruction that builds the visible boundaries as priors into its structure. The proposed method generalizes the alternating edge-preserving diffusion and smoothing (AEDS) method for limited-angle reconstruction developed in the literature by replacing its regularization terms by CNNs, by which the piecewise constant assumption assumed by AEDS is effectively relaxed.

METHODS

The AEDSNN is derived by unrolling the AEDS algorithm. AEDSNN consists of several blocks, and each block corresponds to one iteration of the AEDS algorithm. In each iteration of the AEDS algorithm, three subproblems are sequentially solved. So, each block of AEDSNN possesses three main layers: data matching layer, x -direction regularization layer for visible edges diffusion, and y -direction regularization layer for artifacts suppressing. The data matching layer is implemented by conventional ordered-subset simultaneous algebraic reconstruction technique (OS-SART) reconstruction algorithm, while the two regularization layers are modeled by CNNs for more intelligent and better encoding of priors regarding to the reconstructed images. To further strength the visible edge prior, the attention mechanism and the pooling layers are incorporated into AEDSNN to facilitate the procedure of edge-preserving diffusion from visible edges.

RESULTS

We have evaluated the performance of AEDSNN by comparing it with popular algorithms for limited-angle reconstruction. Experiments on the medical dataset show that the proposed AEDSNN effectively breaks through the piecewise constant assumption usually assumed by conventional reconstruction algorithms, and works much better for piecewise smooth images with nonsharp edges. Experiments on the printed circuit board (PCB) dataset show that AEDSNN can better encode and utilize the visible edge prior, and its reconstructions are consistently better compared to the competing algorithms.

CONCLUSIONS

A deep-learning approach for limited-angle reconstruction is proposed in this paper, which significantly outperforms existing methods. The superiority of AEDSNN consists of three aspects. First, by the virtue of CNN, AEDSNN is free of parameter-tuning. This is a great facility compared to conventional reconstruction methods; Second, AEDSNN is quite fast. Conventional reconstruction methods usually need hundreds even thousands of iterations, while AEDSNN just needs three to five iterations (i.e., blocks); Third, the learned regularizer by AEDSNN enjoys a broader application capacity, which could work well with piecewise smooth images and surpass the piecewise constant assumption frequently assumed for computed tomography images.

Upright Tomosynthesis-guided Breast Biopsy: Tips, Tricks, and Troubleshooting

The advent and implementation of digital breast tomosynthesis (DBT) have had a significant effect on breast cancer detection and image-guided breast procedures. DBT has been shown to improve the visualization of architectural distortions and noncalcified masses. With the incorporation of DBT imaging, biopsy of those findings seen only with DBT is feasible, and the need for localization and surgical excision to determine the pathologic diagnosis is avoided. The additional benefits of reduced procedural time, better localization, and increased technical success support the use of DBT for breast biopsy. DBT-guided biopsy can be performed with the patient prone or upright, depending on the table or unit used. Upright positioning enables improved patient comfort, particularly in patients who have restricted mobility, weight-related limitations, and/or difficulty lying prone for an extended period. Upright DBT-guided breast procedures require a cohesive team approach with overlapping radiologist and technologist responsibilities. Since this is a common breast procedure, the radiologist should be familiar with preprocedural considerations, patient preparations, and use of the biopsy equipment. The basic principles of upright DBT-guided breast biopsy are described in this comprehensive review. The various procedural components, including alternative approaches and techniques, are discussed. Tips and tricks for navigating the biopsy procedure to minimize complications, imaging examples of crucial steps, and supporting diagrams are provided. In addition, the challenges of performing upright DBT-guided biopsy, with troubleshooting techniques to ensure a successful procedure, are reviewed. ^©RSNA, 2021.

Impact of switching from digital mammography to tomosynthesis plus digital mammography on breast cancer screening in Alberta, Canada

OBJECTIVES

To compare abnormal call rates (ACR), cancer detection rates (CDR), positive predictive values (PPVs), and annual return to screen recommendations after switching from digital mammography (DM) to digital breast tomosynthesis plus DM (DBT + DM) for breast cancer screening.

SETTING

The Alberta Breast Cancer Screening Program collects screening data from clinics throughout the province of Alberta, Canada.

METHODS

This study retrospectively collected data, between 2015 and 2018, on women aged 40+ who underwent breast cancer screening at two large volume multisite radiology groups to compare metrics one year prior and one year after DBT + DM implementation. Comparisons between modalities were carried out within age groups, within breast density categories, and for initial vs. subsequent screens.

RESULTS

A total of 125,432 DM and 128,912 DBT + DM screening exams were performed. For women aged 50-74, the DBT + DM group had a higher ACR (p < 0.01) but lower annual return to screens (p < 0.01). CDR was higher post-DBT + DM implementation for women with scattered (6.0 per 1000 vs. 4.4 per 1000; p = 0.001) or heterogeneously dense breasts (6.5 per 1000 vs. 4.2 per 1000; p < 0.001). PPV was higher with DBT + DM for all age groups, with women 50-74 having a PPV of 8.3% using DBT + DM vs. 7.1% with DM (p = 0.009).

CONCLUSION

All metrics improved or stayed the same after switching to DBT + DM except for ACR. However, the increase in ACR could be attributed to a trend already occurring prior to the switch. Longer term monitoring is needed to confirm these findings.

Design, implementation, and pitfalls of TMIST

The early detection of breast cancer has been shown to reduce deaths through randomized, controlled trials. Numerous observational studies, failure analyses, and "incidence of death" studies have confirmed that screening reduces deaths in the general population. Digital Breast Tomosynthesis (DBT) which collects mammographic images from different angles and uses them to synthesize planes through the breast is simply another advance in mammography among others that have been made over the years. DBT "absolutely" detects more cancers at a time when cure is more likely while also having the advantage of reducing recall rates. The Tomosynthesis Mammographic Imaging Screening Trial (TMIST) has been designed to compare DBT with 2-Dimensional Full Field Digital Mammography (FFDM), but it's major design issues may provide misleading results. Instead of using a reduction in deaths as the endpoint, benefit in TMIST is predicated on a reduction in advanced cancers in the DBT group. This is a questionable "endpoint" (a reduction in advanced cancers is not necessary as proof of benefit). In addition, the trial may be underpowered so that even if DBT shows a benefit it may not be able to achieve "statistical significance". The six CISNET models of the National Cancer Institute have shown that annual mammography beginning at the age of 40 will save the most lives. Yet TMIST will only include women ages 45 and over and will screen postmenopausal women every two years instead of annually. Consequently, TMIST results may be used, inappropriately, to limit access to breast cancer screening starting at the age of 45, and only offer biennial screening for post-menopausal women.

X-ray source translation based computed tomography (STCT)

Micro computed tomography (µCT) allows the noninvasive visualization and 3D reconstruction of internal structures of objects with high resolution. However, the current commercial µCT system relatively rotates the source-detector or objects to collect projections, referred as RCT in this paper, and has difficulties in imaging large objects with high resolutions because fabrication of large-area, inexpensive flat-panel detectors remains a challenge. In this paper, we proposed a source translation based CT (STCT) for imaging large objects with high resolution to get rid of the limitation of the detector size, where the field of view is primarily determined by the source translation distance. To compensate for the deficiency of incomplete data in STCT, we introduced multi-scanning STCT (mSTCT), from which the projections theoretically meet the conditions required for accurate reconstructions. Theoretical and numerical studies showed that mSTCT has the ability to accurately image large objects without any visible artifacts. Numerical simulations also indicated that mSTCT has a potential capability to precisely image the region of interest (ROI) inside objects, which remains a challenge in RCT due to truncated projections. In addition, an experimental platform for mSTCT has been established, from which the 2D and 3D reconstructed results demonstrated its feasibility for µCT applications. Moreover, STCT also has a great potential for security inspection and product screening by using two perpendicular STCTs, with advantages of low-cost equipment and high-speed examination.

Is there any added value to substitute the 2D digital MLO projection for a MLO tomosynthesis projection and its synthetic view when a 2D standard digital mammography is used in a one-stop-shop immediate reading mammography screening?

OBJECTIVES

Breast cancer screening consists of batch interpretation of two-view (cranio-caudal CC- and medio-lateral oblique MLO) digital mammography (DM) per breast. The DM-MLO view was substituted by an MLO-digital breast tomosynthesis (DBT) and its synthetic (2D-synthetic mammography (SM)-MLO) view. The performance of this hybrid protocol was evaluated in a one-stop-shop screening visit, providing immediate reading and additional work up.

METHODS

Retrospective, observational review, comparing the cancer detection rate (CDR), breast US rates, and biopsy rates in 13,048 women screened with DM from June 2015 to November 2016 and 8639 women screened with SM-DBT/DM from January 2017 to July 2018. Chi-square tests or Fisher's exact tests were used to compare proportions between the two screening imaging methods.

RESULTS

SM + DBT/DM significantly increased the overall CDR (10.8‰) versus DM (7.5‰) (p = 0.0120) with more invasive lobular carcinoma (14% versus 4%) (p = 0.0357) detected and overall more invasive cancers among women with breast density type B (p = 0.0411) and those aged between 60 and 70 (p = 0.0306). This was achieved at the expense of additional sonographic examinations performed (33.5% in DBT group versus 26.7% in DM group) (p < 0.0001), more BI-RADS category III assigned (1.8% in SM-DBT/DM group versus 1.5% in DM group) (p = 0.0443) and more biopsy rates (3.0 % in SM-DBT/DM group versus 1.7% in DM group) (p < 0.0001).

CONCLUSIONS

Hybrid mammographic protocol replacing 2D-MLO by DBT-MLO and SM-MLO views in a one-stop-shop screening visit improved CDR, at the expense of more sonographic examinations, biopsies, and BI-RADS III lesions. Breast US alone detected 9.2% of all breast cancers in this cohort.

KEY POINTS

• Hybrid protocol including MLO (DBT + SM) with 2D DM CC may improve CDR compared to standard 4 views 2D DM in a screening program providing immediate interpretation. • Adding screening breast US, when perceived necessary, in the same visit of a screening mammography, increases cancer detection rate of 9.2%. • Based on our results, hybrid protocol including DBT + SM in MLO plane and DM in CC plane could be safely implemented as a transition towards DBT and SM alone, without any compromise in the cancer detection ability. Our results may vary according to the properties of machines from different vendors.

Evaluation of microcalcification contrast in clinical images for digital mammography and synthetic mammography

PURPOSE

The aim of this work was to compare, in a clinical study, digital mammography and synthetic mammography imaging by evaluating the contrast in microcalcifications of different sizes.

METHODS

A retrospective review of microcalcifications from 46 patients was undertaken. A Hologic 3-Dimensions mammography system and a HD Combo protocol was used for simultaneous acquisition of the digital and synthetic images. Microcalcifications were classified in accordance with their size, and patient breast images were classified in accordance with their density as adipose, moderately dense and dense. The contrast of the microcalcifications was measured and the contrast ratio between synthetic and digital images was compared. An additional qualitative assessment of the images was presented to correlate the conspicuity of the microcalcifications with the suppression of the structure noise.

RESULTS

Microcalcifications in adipose background always exhibit a comparable or better contrast on synthetic images, regardless their size. For moderately dense background, synthetic images show a better contrast in 91.2 % of cases for small microcalcifications and in 90.9 % of cases for large microcalcifications. For a dense background, better contrast is seen in 89.5 % of cases for small microcalcifications, and in 85.7 % of cases for large microcalcifications. The contrast ratio increases with increasing breast glandularity. The suppression of structure noise also contributes to the enhancement of microcalcifications in the synthetic images.

CONCLUSIONS

Synthetic mammography imaging is superior to digital mammography imaging in terms of microcalcification contrast, regardless their size and breast density.

Lesion Detectability and Radiation Dose in Spiral Breast CT With Photon-Counting Detector Technology: A Phantom Study

OBJECTIVES

The aim of the article was to evaluate the lesion detectability, image quality, and radiation dose of a dedicated clinical spiral breast computed tomography (CT) system equipped with a photon-counting detector, and to propose optimal scan parameter settings to achieve low patient dose levels and optimal image quality.

METHODS

A breast phantom containing inserts mimicking microcalcifications (diameters 196, 290, and 400 μm) and masses (diameters 1.8, 3.18, 4.76, and 6.32 mm) was examined in a spiral breast CT system with systematic variations of x-ray tube currents between 5 and 125 mA, using 2 slabs of 100 and 160 mm. Signal-to-noise ratio and contrast-to-noise ratio measurements were performed by region of interest analysis. Two experienced radiologists assessed the detectability of the inserts. The average absorbed dose was calculated in Monte Carlo simulations.

RESULTS

Microcalcifications in diameters of 290 and 400 μm and masses in diameters of 3.18, 4.76, and 6.32 mm were visible for all tube currents between 5 and 125 mA. Soft tissue masses in a diameter of 1.8 mm were visible at tube currents of 25 mA and higher. Microcalcifications with a diameter of 196 μm were detectable at a tube current of 25 mA and higher in the small, and at a tube current of 40 mA and higher in the large slab. For the small and large breast, at a tube current of 25 and 40 mA, an average dose value of 4.30 ± 0.01 and 5.70 ± 0.02 mGy was calculated, respectively.

CONCLUSIONS

Optimizing tube current of spiral breast CT according to the breast size enables the visualization of microcalcifications as small as 196 μm while keeping dose values in the range of conventional mammography.

Directional-TV algorithm for image reconstruction from limited-angular-range data

Investigation of image reconstruction from data collected over a limited-angular range in X-ray CT remains a topic of active research because it may yield insight into the development of imaging workflow of practical significance. This reconstruction problem is well-known to be challenging, however, because it is highly ill-conditioned. In the work, we investigate optimization-based image reconstruction from data acquired over a limited-angular range that is considerably smaller than the angular range in short-scan CT. We first formulate the reconstruction problem as a convex optimization program with directional total-variation (TV) constraints applied to the image, and then develop an iterative algorithm, referred to as the directional-TV (DTV) algorithm for image reconstruction through solving the optimization program. We use the DTV algorithm to reconstruct images from data collected over a variety of limited-angular ranges for breast and bar phantoms of clinical- and industrial-application relevance. The study demonstrates that the DTV algorithm accurately recovers the phantoms from data generated over a significantly reduced angular range, and that it considerably diminishes artifacts observed otherwise in reconstructions of existing algorithms. We have also obtained empirical conditions on minimal-angular ranges sufficient for numerically accurate image reconstruction with the DTV algorithm.