Interval Cancers in Understanding Screening Outcomes

Interval breast cancers are not detected at routine screening and are diagnosed in the interval between screening examinations. A variety of factors contribute to interval cancers, including patient and tumor characteristics as well as the screening technique and frequency. The interval cancer rate is an important metric by which the effectiveness of screening may be assessed and may serve as a surrogate for mortality benefit.

Impact of AI for Digital Breast Tomosynthesis on Breast Cancer Detection and Interpretation Time

Purpose To develop an artificial intelligence (AI) model for the diagnosis of breast cancer on digital breast tomosynthesis (DBT) images and to investigate whether it could improve diagnostic accuracy and reduce radiologist reading time. Materials and Methods A deep learning AI algorithm was developed and validated for DBT with retrospectively collected examinations (January 2010 to December 2021) from 14 institutions in the United States and South Korea. A multicenter reader study was performed to compare the performance of 15 radiologists (seven breast specialists, eight general radiologists) in interpreting DBT examinations in 258 women (mean age, 56 years ± 13.41 [SD]), including 65 cancer cases, with and without the use of AI. Area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and reading time were evaluated. Results The AUC for stand-alone AI performance was 0.93 (95% CI: 0.92, 0.94). With AI, radiologists' AUC improved from 0.90 (95% CI: 0.86, 0.93) to 0.92 (95% CI: 0.88, 0.96) (P = .003) in the reader study. AI showed higher specificity (89.64% [95% CI: 85.34%, 93.94%]) than radiologists (77.34% [95% CI: 75.82%, 78.87%]) (P < .001). When reading with AI, radiologists' sensitivity increased from 85.44% (95% CI: 83.22%, 87.65%) to 87.69% (95% CI: 85.63%, 89.75%) (P = .04), with no evidence of a difference in specificity. Reading time decreased from 54.41 seconds (95% CI: 52.56, 56.27) without AI to 48.52 seconds (95% CI: 46.79, 50.25) with AI (P < .001). Interreader agreement measured by Fleiss κ increased from 0.59 to 0.62. Conclusion The AI model showed better diagnostic accuracy than radiologists in breast cancer detection, as well as reduced reading times. The concurrent use of AI in DBT interpretation could improve both accuracy and efficiency. Keywords: Breast, Computer-Aided Diagnosis (CAD), Tomosynthesis, Artificial Intelligence, Digital Breast Tomosynthesis, Breast Cancer, Computer-Aided Detection, Screening Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Bae in this issue.

Use of the lateral arm in tomosynthesis-guided SCOUT Reflector placement procedures

Preoperative localization procedures are important for guiding surgical excision of non-palpable findings in the breast. The SCOUT Reflector (Merit Medical, South Jordan UT, USA) is a non-wire-based localization device that has been incorporated into clinical use with great success. SCOUT Reflectors can be placed using several imaging modalities, including tomosynthesis. One drawback to SCOUT Reflector placement under tomosynthesis guidance is an inability to directly visualize the introducer needle tip, a factor that limits precision. In this brief communication, we describe the use of a lateral arm attachment for tomosynthesis guided SCOUT Reflector placement. Precise SCOUT Reflector placement can be achieved using the lateral arm due to the ability to clearly visualize the introducer needle and the SCOUT Reflector within the introducer needle bore prior to deployment.

Upright Tomosynthesis of the Lumbar Spine

RATIONALE AND OBJECTIVES

This experimental study investigates the potential of lumbar spine tomosynthesis to offset the traditional limitations of radiographic and computed tomography imaging, that is, superimposition of anatomy and disregard of physiological load-bearing.

MATERIALS AND METHODS

A gantry-free twin robotic scanner was used to obtain lateral radiographs and tomosyntheses of the lumbar spine under weight-bearing conditions in eight body donors. Tomosynthesis protocols varied in terms of sweep angle (20 versus 40°), scan time (2.4 versus 4.8 seconds), and framerate (16 versus 30 fps). Image quality and vertebral endplate assessability were evaluated by five radiologists with 4-8 years of skeletal imaging experience. Aiming to identify potential diagnostic deterioration near the scan volume margins, readers additionally determined the craniocaudal extent of clinically acceptable image quality.

RESULTS

Tomosynthesis scans effectuated a substantial dose reduction compared to standard radiographs (3.8 ± 0.2 to 15.4 ± 0.8 dGy*cm2 versus 77.7 ± 34.8 dGy*cm2; p ≤ 0.021). Diagnostic image quality and endplate assessability were deemed highest for the 30 fps wide-angle tomosynthesis protocol with good to excellent interrater reliability (intraclass correlation coefficients: 0.846 and 0.946). Accordingly, the craniocaudal extent of acceptable image quality was substantially larger compared to radiography (26.9 versus 18.9 cm; p < 0.001), whereas no significant difference was ascertained for the tomosynthesis protocols with 16 fps (15.3-22.1 cm; all p ≥ 0.058).

CONCLUSION

Combining minimal radiation dose with superimposition-free visualization, 30 fps wide-angle tomosynthesis superseded radiography in all evaluated aspects. With superior diagnostic assessability despite significant dose reduction, load-bearing tomosynthesis appears promising as an alternative for first-line lumbar spine imaging in the future.

Tomosynthesis of the Appendicular Skeleton on a Twin Robotic X-ray System: A Cadaveric Fracture Study

RATIONALE AND OBJECTIVES

Aiming to offset image quality limitations in radiographs due to superimposition, this study investigates the diagnostic potential of appendicular skeleton tomosynthesis.

MATERIALS AND METHODS

Eight cadaveric extremities (four hands and feet) were examined employing the prototypical tomosynthesis mode of a twin robotic X-ray scanner. 12 protocols with varying sweep angles (10, 20 vs. 40°), frame rates (13 vs. 26 fps), and tube voltages (60 vs. 80 kV) were compared to radiographs. Four radiologists separately evaluated cortical and trabecular bone visualization and fracture patterns. Interreader reliability was assessed based on the intraclass correlation coefficient (ICC).

RESULTS

Radiation dose in radiography was 0.59 ± 0.20 dGy * cm2 versus 0.11 ± 0.00 to 2.46 ± 0.17 dGy * cm2 for tomosynthesis. Cortical bone display was inferior for radiographs compared to 40° and 20° tomosynthesis. Best results were ascertained for the 80 kV/40°/26 fps protocol. Trabecular bone depiction was also superior in tomosynthesis (p ≤ 0.009) and best with the 80 kV/10°/26 fps setting. Interreader reliability was moderate for cortical bone display (ICC 0.521, 95% confidence interval 0.356-0.641) and good for trabecular bone (0.759, 0.697-0.810). Diagnostic accuracy for articular involvement and multifragment situations was higher in tomosynthesis (93.8-100%/92.2-100%) vs. radiography (85.9%/82.8%.). Diagnostic confidence was also better in tomosynthesis (p ≤ 0.003).

CONCLUSION

Compared to radiography, tomosynthesis allows for superior assessability of cortical and trabecular bone and fracture morphology, especially at high framerates. Operating on a multipurpose X-ray system, tomosynthesis of the appendicular skeleton can be performed without additional scanner hardware.

Comparing accuracy of tomosynthesis plus digital mammography or synthetic 2D mammography in breast cancer screening: baseline results of the MAITA RCT consortium

AIM

The analyses here reported aim to compare the screening performance of digital tomosynthesis (DBT) versus mammography (DM).

METHODS

MAITA is a consortium of four Italian trials, REtomo, Proteus, Impeto, and MAITA trial. The trials adopted a two-arm randomised design comparing DBT plus DM (REtomo and Proteus) or synthetic-2D (Impeto and MAITA trial) versus DM; multiple vendors were included. Women aged 45 to 69 years were individually randomised to one round of DBT or DM.

FINDINGS

From March 2014 to February 2022, 50,856 and 63,295 women were randomised to the DBT and DM arm, respectively. In the DBT arm, 6656 women were screened with DBT plus synthetic-2D. Recall was higher in the DBT arm (5·84% versus 4·96%), with differences between centres. With DBT, 0·8/1000 (95% CI 0·3 to 1·3) more women received surgical treatment for a benign lesion. The detection rate was 51% higher with DBT, ie. 2·6/1000 (95% CI 1·7 to 3·6) more cancers detected, with a similar relative increase for invasive cancers and ductal carcinoma in situ. The results were similar below and over the age of 50, at first and subsequent rounds, and with DBT plus DM and DBT plus synthetic-2D. No learning curve was appreciable. Detection of cancers >= 20 mm, with 2 or more positive lymph nodes, grade III, HER2-positive, or triple-negative was similar in the two arms.

INTERPRETATION

Results from MAITA confirm that DBT is superior to DM for the detection of cancers, with a possible increase in recall rate. DBT performance in screening should be assessed locally while waiting for long-term follow-up results on the impact of advanced cancer incidence.

Chest tomosynthesis deblurring using CNN with deconvolution layer for vertebrae segmentation

BACKGROUND

Limited scan angles cause severe distortions and artifacts in reconstructed tomosynthesis images when the Feldkamp-Davis-Kress (FDK) algorithm is used for the purpose, which degrades clinical diagnostic performance. These blurring artifacts are fatal in chest tomosynthesis images because precise vertebrae segmentation is crucial for various diagnostic analyses, such as early diagnosis, surgical planning, and injury detection. Moreover, because most spinal pathologies are related to vertebral conditions, the development of methods for accurate and objective vertebrae segmentation in medical images is an important and challenging research area.

PURPOSE

The existing point-spread-function-(PSF)-based deblurring methods use the same PSF in all sub-volumes without considering the spatially varying property of tomosynthesis images. This increases the PSF estimation error, thus further degrading the deblurring performance. However, the proposed method estimates the PSF more accurately by using sub-CNNs that contain a deconvolution layer for each sub-system, which improves the deblurring performance.

METHODS

To minimize the effect of the spatially varying property, the proposed deblurring network architecture comprises four modules: (1) block division module, (2) partial PSF module, (3) deblurring block module, and (4) assembling block module. We compared the proposed DL-based method with the FDK algorithm, total-variation iterative reconstruction with GP-BB (TV-IR), 3D U-Net, FBPConvNet, and two-phase deblurring method. To investigate the deblurring performance of the proposed method, we evaluated its vertebrae segmentation performance by comparing the pixel accuracy (PA), intersection-over-union (IoU), and F-score values of reference images to those of the deblurred images. Also, pixel-based evaluations of the reference and deblurred images were performed by comparing their root mean squared error (RMSE) and visual information fidelity (VIF) values. In addition, 2D analysis of the deblurred images were performed by artifact spread function (ASF) and full width half maximum (FWHM) of the ASF curve.

RESULTS

The proposed method was able to recover the original structure significantly, thereby further improving the image quality. The proposed method yielded the best deblurring performance in terms of vertebrae segmentation and similarity. The IoU, F-score, and VIF values of the chest tomosynthesis images reconstructed using the proposed SV method were 53.5%, 28.7%, and 63.2% higher, respectively, than those of the images reconstructed using the FDK method, and the RMSE value was 80.3% lower. These quantitative results indicate that the proposed method can effectively restore both the vertebrae and the surrounding soft tissue.

CONCLUSIONS

We proposed a chest tomosynthesis deblurring technique for vertebrae segmentation by considering the spatially varying property of tomosynthesis systems. The results of quantitative evaluations indicated that the vertebrae segmentation performance of the proposed method was better than those of the existing deblurring methods.

Digital mammography and digital breast tomosynthesis for detecting invasive lobular and ductal carcinoma

PURPOSE

Invasive lobular carcinoma (ILC) is a distinct histological subtype of breast cancer that can make early detection with mammography challenging. We compared imaging performance of digital breast tomosynthesis (DBT) to digital mammography (DM) for diagnoses of ILC, invasive ductal carcinoma (IDC), and invasive mixed carcinoma (IMC) in a screening population.

METHODS

We included screening exams (DM; n = 1,715,249 or DBT; n = 414,793) from 2011 to 2018 among 839,801 women in the Breast Cancer Surveillance Consortium. Examinations were followed for one year to ascertain incident ILC, IDC, or IMC. We measured cancer detection rate (CDR) and interval invasive cancer rate/1000 screening examinations for each histological subtype and stratified by breast density and modality. We calculated relative risk (RR) for DM vs. DBT using log-binomial models to adjust for the propensity of receiving DBT vs. DM.

RESULTS

Unadjusted CDR per 1000 mammograms of ILC overall was 0.33 (95%CI: 0.30-0.36) for DM; 0.45 (95%CI: 0.39-0.52) for DBT, and for women with dense breasts- 0.33 (95%CI: 0.29-0.37) for DM and 0.54 (95%CI: 0.43-0.66) for DBT. Similar results were noted for IDC and IMC. Adjusted models showed a significantly increased RR for cancer detection with DBT compared to DM among women with dense breasts for all three histologies (RR; 95%CI: ILC 1.53; 1.09-2.14, IDC 1.21; 1.02-1.44, IMC 1.76; 1.30-2.38), but no significant increase among women with non-dense breasts.

CONCLUSION

DBT was associated with higher CDR for ILC, IDC, and IMC for women with dense breasts. Early detection of ILC with DBT may improve outcomes for this distinct clinical entity.

Comparing the performance of full-field digital mammography and digital breast tomosynthesis in the post-treatment surveillance of patients with a history of breast cancer: A retrospective study

INTRODUCTION

The purpose of our study was to compare the performance of 2D (FFDM) against 3D (FFDM plus DBT) examinations in the post-treatment surveillance of asymptomatic breast cancer survivors.

METHODS

A list of women with a history of breast cancer who underwent screening mammography (2D or 3D) from 5/2017 to 5/2020 was retrieved. A total of 20,210 examinations were identified and performance metrics were compared.

RESULTS

There were no statistically significant difference in cancer detection rate (CDR) (p = 0.38), recall rate (RR) (p = 0.087), or positive predictive value (PPV) (p = 0.74) between 2D vs. 3D examinations. Stratification by breast tissue identified no statistically significant difference in CDR (p = 0.581 and p = 0.428), RR (p = 0.230 and p = 0.205), or PPV (p = 0.908 and p = 0.721) between fatty/scattered and heterogeneous/extremely dense breast tissue when comparing 2D vs 3D examinations. Stratification by age did not identify a significant difference in RR or PPV between the two groups. CDR was statistically increased with 2D vs. 3D examinations in the 60-69 years group (p = 0.021). Stratification by race did not identify a significant difference in RR or PPV between the two groups. CDR was statistically increased with 3D vs. 2D examinations in white women (p = 0.036). Stratification by laterality (bilateral vs. unilateral post mastectomy) did not identify a significant difference in RR or PPV between the two groups. CDR was statistically increased in 2D vs. 3D examinations in unilateral studies (p = 0.009).

CONCLUSION

For asymptomatic women with a history of breast cancer, there is no evidence that the addition of DBT to FFDM improves CDR, RR, or PPV.

IMPLICATIONS FOR PRACTICE

More studies are needed concerning screening methodologies supplementing FFDM in the screening regimens of breast cancer survivors.

Evaluation of average glandular dose (AGD) in screening and diagnostic digital mammography and digital breast tomosynthesis (DBT) towards establishing a reference dose range band (DRB): A developing country experience

This study represents the first national survey conducted in Sri Lanka to establish national diagnostic reference levels (NDRLs) for screening and diagnostic acquisitions in digital mammography (2D-DM) and digital breast tomosynthesis (DBT). Additionally, the study investigated the relationship between average glandular dose (AGD) and compressed breast thickness (CBT) and introduced a novel concept called dose range bands (DRBs) as a tool for optimizing radiation dose in mammography. DICOM metadata was used to extract dose data and exposure parameters from women undergoing either screening (350) or diagnostic (750) digital mammography. The analysis included both craniocaudal (CC) and mediolateral oblique (MLO) views of each breast, acquired using 2D-DM and DBT imaging techniques. The NDRL (AGD per view) was 1.97 mGy and 2.01 mGy for diagnostic DM and DBT, respectively. The corresponding NDRLs for screening acquisition were 2.44 mGy and 2.30 mGy. The mean DBT/DM AGD ratio was 1.39 and 0.97 for diagnostic and screening, respectively. Further, the association between the average glandular AGD per view and CBT is stronger in digital breast tomosynthesis (DBT) than in 2D digital mammography. The study findings highlight the need for standardization of compression practices, considering factors such as the radiographer's experience, imaging equipment, breast density, age, breast size, and pain threshold.

Imaging of breast cancer-beyond the basics

Imaging of breast cancer is the backbone of breast cancer screening, diagnosis, preoperative/treatment assessment and follow-up. The main modalities are mammography, ultrasound and magnetic resonance imaging, each with its own advantages and disadvantages. New emerging technologies have also enabled each modality to improve on their weaknesses. Imaging-guided biopsies have allowed for accurate diagnosis of breast cancer, with low complication rates. The purpose of this article is to review the common modalities for breast cancer imaging in current practice with emphasis on the strengths and potential weaknesses, discuss the selection of the best imaging modality for the specific clinical question or patient population, and explore new technologies / future directions of breast cancer imaging.

Automatic and standardized quality assurance of digital mammography and tomosynthesis with deep convolutional neural networks

OBJECTIVES

The aim of this study was to develop and validate a commercially available AI platform for the automatic determination of image quality in mammography and tomosynthesis considering a standardized set of features.

MATERIALS AND METHODS

In this retrospective study, 11,733 mammograms and synthetic 2D reconstructions from tomosynthesis of 4200 patients from two institutions were analyzed by assessing the presence of seven features which impact image quality in regard to breast positioning. Deep learning was applied to train five dCNN models on features detecting the presence of anatomical landmarks and three dCNN models for localization features. The validity of models was assessed by the calculation of the mean squared error in a test dataset and was compared to the reading by experienced radiologists.

RESULTS

Accuracies of the dCNN models ranged between 93.0% for the nipple visualization and 98.5% for the depiction of the pectoralis muscle in the CC view. Calculations based on regression models allow for precise measurements of distances and angles of breast positioning on mammograms and synthetic 2D reconstructions from tomosynthesis. All models showed almost perfect agreement compared to human reading with Cohen's kappa scores above 0.9.

CONCLUSIONS

An AI-based quality assessment system using a dCNN allows for precise, consistent and observer-independent rating of digital mammography and synthetic 2D reconstructions from tomosynthesis. Automation and standardization of quality assessment enable real-time feedback to technicians and radiologists that shall reduce a number of inadequate examinations according to PGMI (Perfect, Good, Moderate, Inadequate) criteria, reduce a number of recalls and provide a dependable training platform for inexperienced technicians.

Transformer-based Deep Neural Network for Breast Cancer Classification on Digital Breast Tomosynthesis Images

Purpose

To develop an efficient deep neural network model that incorporates context from neighboring image sections to detect breast cancer on digital breast tomosynthesis (DBT) images.

Materials and Methods

The authors adopted a transformer architecture that analyzes neighboring sections of the DBT stack. The proposed method was compared with two baselines: an architecture based on three-dimensional (3D) convolutions and a two-dimensional model that analyzes each section individually. The models were trained with 5174 four-view DBT studies, validated with 1000 four-view DBT studies, and tested on 655 four-view DBT studies, which were retrospectively collected from nine institutions in the United States through an external entity. Methods were compared using area under the receiver operating characteristic curve (AUC), sensitivity at a fixed specificity, and specificity at a fixed sensitivity.

Results

On the test set of 655 DBT studies, both 3D models showed higher classification performance than did the per-section baseline model. The proposed transformer-based model showed a significant increase in AUC (0.88 vs 0.91, P = .002), sensitivity (81.0% vs 87.7%, P = .006), and specificity (80.5% vs 86.4%, P < .001) at clinically relevant operating points when compared with the single-DBT-section baseline. The transformer-based model used only 25% of the number of floating-point operations per second used by the 3D convolution model while demonstrating similar classification performance.

Conclusion

A transformer-based deep neural network using data from neighboring sections improved breast cancer classification performance compared with a per-section baseline model and was more efficient than a model using 3D convolutions.Keywords: Breast, Tomosynthesis, Diagnosis, Supervised Learning, Convolutional Neural Network (CNN), Digital Breast Tomosynthesis, Breast Cancer, Deep Neural Networks, Transformers Supplemental material is available for this article. © RSNA, 2023.

Preoperative localization of breast lesions: Comparing digital breast tomosynthesis-guided radioactive seed localization versus standard 2D stereotactic radioactive seed localization

PURPOSE

To compare single seed digital breast tomosynthesis-guided radioseed localization (DBT-L) to standard 2D stereotactic-guided radioseed localization (SGL) of the breast.

METHODS

A retrospective review of a large tertiary cancer center's database yielded 68 women who underwent preoperative DBT-L from March 2019-December 2019 and a matched cohort of 65 women who underwent SGL during the same period. The electronic medical record and radiology were reviewed for patient characteristics including breast density, exam technique, pre- and post-operative pathology, exam duration, and radiation dose to the patient. To compare margin outcomes between the groups, the chi-square test of independence was used; to compare continuous outcomes such as exam duration and total dose, the Wilcoxon rank sum test was used.

RESULTS

DBT-L and SGL localization targets included biopsy marker (62/68, 91% vs 55/65, 85%), distortion (4/68, 6% vs 2/65, <3%), focal asymmetry (1/68 and 1/65, < 2% for both), calcifications (1/68, <2% vs 4/65, 6%), and anatomic landmarks (0% vs 3/65, 5%). 72% and 71% of localizations were performed for malignant pathology in the DBT-L and SGL groups, respectively. The median duration of DBT-L was 8.3 min vs 10.3 min for SGL, representing statistically significant time savings (p = 0.003). The median total organ dose of DBT-L was 8.6 mGy vs 10.4 mGy for SGL, representing statistically significant dose savings (p = 0.018). The incidence of positive margins at surgery was not statistically different between the groups (p = 0.26).

CONCLUSION

DBT-L demonstrates both time and dose savings for the patient compared to SGL without compromising surgical outcome.

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.

Performance of Wide-Angle Tomosynthesis with Synthetic Mammography in Comparison to Full Field Digital Mammography

RATIONALE AND OBJECTIVES

The purpose of this study was to test for superiority of wide-angle digital breast tomosynthesis plus synthetic mammography (Insight 2D) in comparison to full-field digital mammography (FFDM).

MATERIALS AND METHODS

In this study, twenty readers interpreted 350 screening and diagnostic cases of wide-angle digital breast tomosynthesis (DBT) plus Insight 2D and FFDM in two separate reading sessions separated by at least a 6-week washout period. Breast-level estimates of the area under the curve and sensitivity along with subject-level recall rate were measured and compared between wide-angle DBT plus Insight 2D and FFDM. The same measures were also assessed for dense breasts. A hierarchical analysis plan was used to control the study's type I error rate at 0.05.

RESULTS

The mean breast-level area under the curve for distinguishing breasts with cancer from non-cancer breasts was 0.893 with DBT plus Insight 2D versus 0.837 with FFDM, showing superiority of DBT plus Insight 2D (p < 0.001). Breast-level sensitivity was significantly superior for DBT plus Insight 2D in comparison to FFDM (0.852 vs. 0.805, p = 0.043). Subject-level recall rate for DBT plus Insight 2D was significantly lower in comparison to FFDM (0.344 vs. 0.473, p < 0.001). For dense breasts, the readers' accuracy with DBT plus Insight 2D was superior to their accuracy with FFDM (0.875 vs. 0.830, p = 0.026), and their recall rate was significantly lower for DBT plus Insight 2D in comparison to FFDM (0.338 vs. 0.441, p = 0.003).

CONCLUSION

Reader performance with wide-angle DBT plus Insight 2D is superior to that with FFDM, showing significantly higher breast-level accuracy and sensitivity and significantly lower recall rates.

Multi-perspective region-based CNNs for vertebrae labeling in intraoperative long-length images

PURPOSE

Effective aggregation of intraoperative x-ray images that capture the patient anatomy from multiple view-angles has the potential to enable and improve automated image analysis that can be readily performed during surgery. We present multi-perspective region-based neural networks that leverage knowledge of the imaging geometry for automatic vertebrae labeling in Long-Film images - a novel tomographic imaging modality with an extended field-of-view for spine imaging.

METHOD

A multi-perspective network architecture was designed to exploit small view-angle disparities produced by a multi-slot collimator and consolidate information from overlapping image regions. A second network incorporates large view-angle disparities to jointly perform labeling on images from multiple views (viz., AP and lateral). A recurrent module incorporates contextual information and enforce anatomical order for the detected vertebrae. The three modules are combined to form the multi-view multi-slot (MVMS) network for labeling vertebrae using images from all available perspectives. The network was trained on images synthesized from 297 CT images and tested on 50 AP and 50 lateral Long-Film images acquired from 13 cadaveric specimens. Labeling performance of the multi-perspective networks was evaluated with respect to the number of vertebrae appearances and presence of surgical instrumentation.

RESULTS

The MVMS network achieved an F1 score of >96% and an average vertebral localization error of 3.3 mm, with 88.3% labeling accuracy on both AP and lateral images - (15.5% and 35.0% higher than conventional Faster R-CNN on AP and lateral views, respectively). Aggregation of multiple appearances of the same vertebra using the multi-slot network significantly improved the labeling accuracy (p < 0.05). Using the multi-view network, labeling accuracy on the more challenging lateral views was improved to the same level as that of the AP views. The approach demonstrated robustness to the presence of surgical instrumentation, commonly encountered in intraoperative images, and achieved comparable performance in images with and without instrumentation (88.9% vs. 91.2% labeling accuracy).

CONCLUSION

The MVMS network demonstrated effective multi-perspective aggregation, providing means for accurate, automated vertebrae labeling during spine surgery. The algorithms may be generalized to other imaging tasks and modalities that involve multiple views with view-angle disparities (e.g., bi-plane radiography). Predicted labels can help avoid adverse events during surgery (e.g., wrong-level surgery), establish correspondence with labels in preoperative modalities to facilitate image registration, and enable automated measurement of spinal alignment metrics for intraoperative assessment of spinal curvature.

A novel few-views arrangement of the fixed X-ray tubes for tomosynthesis

PURPOSE

Tomosynthesis is a technique that reconstructs a volume image from limited-angle projection data. In conventional tomosynthesis, the examination time is long, so it can be difficult for patients to hold their breath during certain examinations, such as chest imaging. Few-views tomosynthesis, which uses a linear arrangement of fixed X-ray tubes and enables an image to be obtained within 1 s, was found to be useful in the clinical setting in our previous study. In the present study, we attempted to develop a novel few-views tomosynthesis system that can obtain images with an improved image quality.

METHODS

A novel few-views arrangement of X-ray tubes was proposed and the image reconstruction method with regularization term was applied. The linear arrangement was used for the X-ray tube arrangement in our previous few-views tomosynthesis, in contrast, a circular arrangement was proposed in this study. The validation of this system was conducted with a numerical simulation and a real data experiment.

RESULTS

The wider the scan angle, the more the object shadow spreads from "in-plane", allowing for artifact suppression. In the circular arrangement, the constant scan angle of θ is used, but in the linear arrangement the scan angle is set from 0 to θ. The artifacts in "out-of-plane" were more strongly suppressed in the circular arrangement than in the linear arrangement.

CONCLUSIONS

Artifacts spreading in the z-direction were more strongly suppressed using the circular arrangement than the linear arrangement. Therefore, the circular arrangement was deemed appropriate for few-views tomosynthesis.

Breast cancer screening in average and high-risk women

Breast cancer is the most common cancer among females worldwide with rising incidence. In the United States, screening mammography and advances in therapy have lowered mortality by 41% since 1990. Screening mammography is supported by randomized control trials (RCT), observational studies, and computer model data. Digital breast tomosynthesis is a new technology that addresses limitations in mammography resulting from overlapping breast tissue, improving its sensitivity and specificity. Patients at high risk for breast cancer include those with a ≥20% lifetime risk, high-risk germline mutation, or history of thoracic radiation treatment between 10-30 years of age. Such patients are recommended to undergo annual screening mammography and adjunctive annual screening breast MRI. Patients unable to undergo MRI may undergo whole breast ultrasound or contrast-enhanced mammography. Pregnant and lactating patients at average risk for breast cancer are recommended to undergo age-appropriate screening mammography.

Mapping of a multilayer panoramic radiography device

OBJECTIVE

To map the shape, location, and thickness of the focal trough of a panoramic radiography device with a multilayer imaging program.

METHODS

An acrylic plate (148 × 148 × 3 mm) containing 1156 holes distributed in a matrix of 34 × 34 rows was placed in the OP300 Maxio at the levels of the maxilla and mandible. 20 metal spheres (3.5 mm in diameter) were placed on the holes of the plate under 15 different arrangements and panoramic images were acquired for each arrangement at 66 kV, 8 mA, and an exposure time of 16 s. The resulting panoramic radiographs from the five image layers were exported, the horizontal and vertical dimensions of the metal spheres were measured in all images using the Image J software, and the magnification and distortion rates of the spheres were calculated. All metal spheres presenting a magnification rate lower than 30% in both vertical and horizontal dimensions and a distortion rate lower than 10% were considered to map the focal troughs of each of the five image layers.

RESULTS

All panoramic image layers had a curved shape ranging from 39° to 51° for both dental arches and varied in position and thickness. The anterior region of maxilla was anteriorly displaced when compared to the anterior region of the mandible for all layers. Image layers are thicker at the level of the mandible than those at the level of the maxilla; also, inner layers were thinner and outer layers were thicker.

CONCLUSION

All image layers in the studied panoramic radiography device had a curved shape and varied in position and thickness. The anterior region of maxilla was anteriorly displaced when compared to that of the mandible for all layers.

Assessment of the uterine dose in digital mammography and digital breast tomosynthesis

INTRODUCTION

Digital Mammography (DM-2D) and more recently Digital Breast Tomosynthesis (DBT), are two of the most effective imaging modalities for breast cancer detection, often used in screening programmes. It may happen that exams using these two imaging modalities are inadvertently performed to pregnant women. The objective of this study is to assess the dose in the uterus due to DM-2D and DBT exams, according to two main irradiation scenarios: in the 1st scenario the exposure parameters were pre-selected directly by the imaging system, while in the 2nd scenario, the maximum exposure parameters were chosen.

METHODS

The mammography equipment used was a Siemens Mammomat Inspiration. A physical anthropomorphic phantom, PMMA plates (simulating a breast thickness of 6 cm) and thermoluminescent dosimeters (TLDs) were used to measure entrance air kerma values on the phantom's breast and abdomen in order to successively estimate the mean glandular dose (MGD) and the dose in the uterus. For the two irradiation scenarios chosen, two-breast imaging modalities were selected: 1) DBT in Cranio-Caudal (CC) view (with 28 kV and 160 mAs as exposure parameters), 2) DBT and DM in Medio Lateral-Oblique (MLO) and CC views (with 34 kV and 250 mAs as exposure parameters).

RESULTS

In the 1st scenario, the TLD measurements did not detect significant dose values in the abdomen whereas the MGD estimated using the D.R. Dance model was in close agreement with data available in the literature. In the 2nd scenario, there was no significant difference in MGD estimation between the different views, whereas the air kerma values in the abdomen (in DBT mode, CC and MLO) were 0.049 mGy and 0.004 mGy respectively. In CC DM-2D mode the abdomen air kerma value was 0.026 mGy, with no significant detected value in MLO view.

CONCLUSIONS

For the dose in the uterus, the obtained values seem to indicate that DM-2D and DBT examinations inadvertently performed during pregnancy do not pose a significant radiological risk, even considering the case of overexposure in both breasts.

IMPLICATIONS FOR PRACTICE

The accurate knowledge of the doses in DM-2D and DBT will contribute to raise the awareness among medical practitioners involved in breast imaging empowering them to provide accurate information about dose levels in the uterus, improving their radiation risk communication skills and consequently helping to reduce the anxiety of pregnant women undergoing this type of examinations.

BI-RADS 3 on dense breast screening ultrasound after digital mammography versus digital breast tomosynthesis

OBJECTIVE

Compare the BI-RADS 3 rate and follow-up of dense breast ultrasound (US) screening following digital mammography (DM) versus digital breast tomosynthesis (DBT).

METHODS

IRB-approved, HIPAA compliant retrospective search was performed of databases at two tertiary breast centers and an office practice for BI-RADS 3 screening US examinations performed 10/1/14-9/30/16. Prior DM versus DBT, downgrade and upgrade rate, and timing and pathology results were recorded. Differences were compared using the two-sample proportions test.

RESULTS

3183 screening US examinations were performed, 1434/3183 (45.1%) after DM and 1668/3183 (52%) after DBT (2.5% (81/3183) no prior mammogram available). 13.9% (199/1434) had BI-RADS 3 results after DM and 10.6% (177/1668) after DBT (p < 0.01). Median imaging follow-up after DM was 12 months (IQR 6, 24) versus 18 after DBT (IQR 11, 25), p = 0.02. 19.5% (73/375) of patients were lost to follow-up (19.2% (38/198) after DM (68.4% (26/38) no follow-up after initial exam) versus 19.8% (35/177) after DBT (54.3% (19/35) no follow-up after initial exam). 1.3% (5/375) of patients elected biopsy (1.5% (3/198) after DM and 1.1% (2/177) after DBT). 75.2% (282/375) of patients were downgraded (75.3% (149/198) after DM and 75.1% (133/177) after DBT). 2.5% (5/198) were upgraded after DM and 0.6% (1/177) after DBT. Median time to upgrade was 6 months after both DM and DBT. 0.3% (1/375) of patients with BI-RADS 3 results had cancer on follow-up.

CONCLUSION

Patients with prior DBT had a lower risk of encountering BI-RADS 3 findings on screening ultrasound. BI-RADS 3 findings on screening ultrasound had an extremely low rate of being cancer.

Sight Unseen: Diagnostic Yield and Safety Outcomes of a Novel Multimodality Navigation Bronchoscopy Platform with Real-Time Target Acquisition

BACKGROUND

Several advanced bronchoscopy platforms are currently available, but the clinical data supporting their use vary. Electromagnetic navigation bronchoscopy (ENB) remains the dominant technology; it is limited by its reliance on preoperative computed tomography, which only approximates patient anatomy during the procedure. Recently, ENB was enhanced with the (1) addition of digital tomosynthesis-based navigation correction, (2) improvements in planning algorithms, and (3) continuous real-time guidance (Illumisite™; Medtronic, Minneapolis, MN, USA). There are currently no clinical data on the diagnostic yield and safety profile of this system.

OBJECTIVES

The primary objective of this study is to describe the diagnostic yield of the first 100 pulmonary parenchymal lesions sampled using the multimodality navigation bronchoscopy (MNB) platform. The secondary objective is to describe safety.

METHODS

In this single-center prospective observational study, a database was maintained to track patient, procedural, and outcome data for the first 100 consecutive lesions sampled using the MNB platform at an academic quaternary referral center. Descriptive statistics and univariate and multivariate analyses are reported.

RESULTS

The overall diagnostic yield of samples acquired was 79% (79/100). In the cohort where digital tomosynthesis was used, the diagnostic yield was 83% (69/83). Sensitivity for malignancy was 71% (52/73). Overall complication rates were low: pneumothorax (n = 3, 3%) and bleeding requiring intervention (n = 2, 2%). There were no procedural-related hospital admissions.

CONCLUSIONS

The MNB system performed favorably. Platform superiority cannot be established without future prospective and comparative studies.

Reader performances in breast lesion characterization via DBT: One or two views and which view?

PURPOSE

To compare the performance in breast lesion characterization of one-view mediolateral (MLO) digital mammography plus digital breast tomosynthesis (DM-DBT) versus one-view craniocaudal (CC) DM-DBT versus two-view DM-DBT.

MATERIALS AND METHODS

The institutional review board approved this retrospective study conducted on 138 women from the population of a previous prospective multicenter study, with 69 consecutive patients with benign or high-risk lesions and 69 randomized patients with breast cancer, all confirmed at pathology. Four radiologists (two senior and two junior) blinded to the clinical, mammographic and pathological data independently reviewed the MLO DM-DBT views, the CC DM-DBT views and the MLO + CC DM-DBT views using the American College of Radiology Breast Imaging-Reporting and Data System criteria for index lesion characterization. Areas under the receiver were calculated and compared for each reader and imaging protocol.

RESULTS

No significant differences in breast cancer characterization were observed between single MLO and CC views for all the readers. The added value of a second view was statistically significant for characterization in pooled data and for junior readers but not for senior readers (p ranging from 0.15 to 0.57 depending on the view and the senior reader). Finally, in 4 breast cancer cases, lesions were only detectable on the CC DM-DBT view in two cases and on the MLO DM-DBT view in the two other cases.

CONCLUSION

Our results support the use of two-view DM-DBT for breast lesion characterization when the readers are inexperienced. There is no significant difference between CC and MLO views when diagnosis is performed with one view.

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.

Safety and efficacy of tomosynthesis-guided breast biopsies in the prone position: monocentric study and review of the literature

PURPOSE

The purpose of this study is to describe the safety and efficacy of 9G needle biopsy under tomosynthesis guidance with the patient in the prone position.

MATERIALS AND METHODS

This is a retrospective observational study conducted on patients with non-palpable breast mass exclusively detectable through tomosynthesis, performed from the 1st January 2018 to the 1st August 2020. The procedures were performed by taking 12 tissue samples from each mass. The evaluated technical success was considered as a conclusive sample for histological diagnosis. We performed a comparison between the procedural data of interventions in patients who have a lesion < or = 10 mm and > 10 mm and between high-contrast and low-contrast masses. The histological data of the samples were analyzed.

RESULTS

Five hundred biopsies of the total 1500 performed from the 1st January 2018 to the 1st August 2020 were included in the study; repetitions for inadequate withdrawal occurred 0.4% (3/500). No major complications have ever been observed. Two cases (0.2%) of minor bleeding were observed with self-limited bleeding from the skin breach at 90 min without clinical sequelae in an asymptomatic patient. The biopsy samples showed carcinoma in 55.2% (276/500).

CONCLUSION

Our study suggests that the 9G needle sampling biopsy procedure through tomosynthesis guide with prone patient is a safe and effective procedure for the characterization of indeterminate breast mass.

Breast cancer screening in women with and without implants: retrospective study comparing digital mammography to digital mammography combined with digital breast tomosynthesis

OBJECTIVES

Compare four groups being screened: women without breast implants undergoing digital mammography (DM), women without breast implants undergoing DM with digital breast tomosynthesis (DM/DBT), women with implants undergoing DM, and women with implants undergoing DM/DBT.

METHODS

Mammograms from February 2011 to March 2017 were retrospectively reviewed after 13,201 were excluded for a unilateral implant or prior breast cancer. Patients had been allowed to choose between DM and DM/DBT screening. Mammography performance metrics were compared using chi-square tests.

RESULTS

Six thousand forty-one women with implants and 91,550 women without implants were included. In mammograms without implants, DM (n = 113,973) and DM/DBT (n = 61,896) yielded recall rates (RRs) of 8.53% and 6.79% (9726/113,973 and 4204/61,896, respectively, p < .001), cancer detection rates per 1000 exams (CDRs) of 3.96 and 5.12 (451/113,973 and 317/61,896, respectively, p = .003), and positive predictive values for recall (PPV1s) of 4.64% and 7.54% (451/9726 and 317/4204, respectively, p < .001), respectively. In mammograms with implants, DM (n = 6815) and DM/DBT (n = 5138) yielded RRs of 5.81% and 4.87% (396/6815 and 250/5138, respectively, p = .158), CDRs of 2.49 and 2.92 (17/6815 and 15/5138, respectively, p > 0.999), and PPV1s of 4.29% and 6.0% (17/396 and 15/250, respectively, p > 0.999), respectively.

CONCLUSIONS

DM/DBT significantly improved recall rates, cancer detection rates, and positive predictive values for recall compared to DM alone in women without implants. DM/DBT performance in women with implants trended towards similar improvements, though no metric was statistically significant.

KEY POINTS

• Digital mammography with tomosynthesis improved recall rates, cancer detection rates, and positive predictive values for recall compared to digital mammography alone for women without implants. • Digital mammography with tomosynthesis trended towards improving recall rates, cancer detection rates, and positive predictive values for recall compared to digital mammography alone for women with implants, but these trends were not statistically significant - likely related to sample size.

Preoperative breast MR imaging in newly diagnosed breast cancer: Comparison of outcomes based on mammographic modality, breast density and breast parenchymal enhancement

PURPOSE

To compare the role of MR for assessment of extent of disease in women newly diagnosed with breast cancer imaged with digital mammography (DM) alone versus digital breast tomosynthesis (DBT).

METHODS

Retrospective review was conducted of 401 consecutive breast MR exams (10/1/2013-7/31/2015) from women who underwent preoperative MR for newly diagnosed breast cancer by either DM or DBT, leaving 388 exams (201 DM and 187 DBT). MR detection of additional, otherwise occult, disease was stratified by modality, breast density, and background parenchymal enhancement. A true-positive finding was defined as malignancy in the ipsilateral-breast >2 cm away from the index-lesion or in the contralateral breast.

RESULTS

50 additional malignancies were detected in 388 exams (12.9%), 37 ipsilateral and 13 contralateral. There was no difference in the MR detection of additional disease in women imaged by either DM versus DBT (p = 0.53). In patients with DM, there was no significant difference in the rate of MR additional cancer detection in dense versus non-dense breasts (p = 0.790). However, in patients with DBT, MR detected significantly more additional sites of malignancy in dense compared to non-dense breasts (p = 0.017). There was no difference in false-positive MR exams (p = 0.470) for DM versus DBT. For both DM and DBT cohorts, higher MR background parenchymal enhancement was associated with higher false-positive (p = 0.040) but no significant difference in true-positive exams.

CONCLUSIONS

Among patients with DBT imaging at cancer diagnosis, women with dense breasts appear to benefit more from preoperative MR than non-dense women. In women imaged only with DM, MR finds additional malignancy across all breast densities.

Endorectal digital prostate tomosynthesis (endoDPT): a proof-of-concept study

In this study we present endorectal digital prostate tomosynthesis (endoDPT), a proposed method of high resolution prostate imaging using an endorectal x-ray sensor and an external x-ray source. endoDPT may be useful for visualizing the fine detail of small structures such as low dose rate brachytherapy (LDRBT) seeds that are difficult to visualize with current methods. The resolution of endoDPT was characterized through measurement of the modulation transfer function (MTF) and artifact spread function (ASF) in computational and physical phantoms. The qualitative resolution of endoDPT was assessed relative to computed tomography (CT) through imaging of LDRBT seeds implanted inex vivocanine prostates. The x-ray sensor MTF reached 10% at 11.50 mm^-1, the reconstruction algorithm MTF reached a maximum at 7.08 mm^-1, and the ASF was 2.5 mm (full-width at half-maximum). Fine structures in LDRBT seeds like the 0.05 mm thick shell were visible with endoDPT but not CT. All endoDPT images exhibited an overshoot artifact. The measured MTFs were consistent with other studies using similar x-ray sensors and demonstrated improved resolution compared to digital breast tomosynthesis; this result was due to the smaller endoDPT x-ray sensor detection element size and quantitatively demonstrates the high resolution of endoDPT. The ASF demonstrated worse depth resolution compared to in-plane resolution, due to partial angular sampling; partial angular sampling also caused the observed overshoot artifact in the endoDPT images. However, endoDPT still was able to visualize fine structures such as the LDRBT seed shell to a much higher degree than CT. This high-resolution visualization may be useful for improvements in patient specific LDRBT dosimetry. Overall, these results indicate endoDPT is capable of high in-plane spatial resolution and is thus well poised for optimization and studies assessing clinical utility.

[Diagnosis of breast diseases in a certified breast center]

The beginning of the 21st century has seen immense improvements in the quality of diagnosis and treatment of breast cancer due to several, simultaneous developments. In particular, the introduction of a certification program from the German Cancer Society based on level III guidelines has enhanced the transparency and quality of treatment of breast diseases for all actors. As a result, patients have benefited from intensified cooperation especially between core disciplines in breast disease, gynecology, pathology, and radiology. The standardized and synoptic reading of multiple diagnostic modalities has enabled precise sampling of histologic specimen, which has improved prognosis and the successful individualization of therapy. In this article the benefits of breast cancer diagnosis and therapy in a certified breast center are illustrated using four case examples.

Digital breast tomosynthesis (DBT)-guided biopsy of calcifications: pearls and pitfalls

As digital breast tomosynthesis (DBT) is quickly becoming the standard of care in clinical practice, DBT-guided procedures are being more frequently utilized. DBT-guided biopsies of calcifications are efficient and easy to perform. As radiologists seek proficiency in these biopsies, there are some unique features of DBT-guided biopsies that they must consider. In this review, we provide a step-by-step guide on performing DBT-guided biopsies of calcifications, with a focus on pearls and pitfalls for problem solving in difficult biopsy cases.

Is There a Difference in the Diagnostic Outcomes of Calcifications Initially Identified on Synthetic Tomosynthesis Versus Full-Field Digital Mammography Screening?

PURPOSE

To compare the outcomes of microcalcifications recalled on full-field digital (FFDM) and FFDM and combined tomosynthesis (Combo) to synthetic (SM) screening mammograms.

METHOD

We reviewed medical records, radiology, and pathology reports of all patients found to have abnormal calcifications requiring further evaluation on mammography screening at our institution between 11/1/2016-11/1/2018 and collected patient demographics, calcification morphology and distribution, and mammography technique (SM, FFDM, or Combo). We used biopsy pathology or at least 1-year imaging follow-up to establish overall diagnostic outcome (benign or malignant). Fisher's exact test was used to compare validation rates at diagnostic work-up, BI-RADS category, and final outcome of calcifications identified on each screening technique. T-test was used for continuous variables.

RESULTS

Of 699 calcifications in 596 women recalled, 176 (30%) of 596 were from SM and 420 (70%) FFDM/Combo. There was a significantly higher rate of calcifications unvalidated at diagnostic work-up for SM compared to FFDM/Combo (0.8% vs. 10%, p < 0.0001). SM calcifications were more likely to receive BI-RADS 2/3 at diagnostic work-up compared to FFDM/Combo ones (55% vs. 42%, p = 0.003). Of 346 (49%) calcifications that underwent biopsy, 88 (25%) were malignant (36% of SM vs. 22% of FFDM/Combo, OR:0.5 [95% CI: 0.3, 0.8] p = 0.01). Of 622 lesions with established diagnostic outcome, there was no difference between having an overall benign or malignant outcome between SM and FFDM/Combo (17% vs. 13%, OR: 0.8 [95% Cl: 0.5, 1.2] p = 0.27).

CONCLUSIONS

Synthetic tomosynthesis screening results in a higher rate of false positive and unvalidated calcification recalls compared to FFDM/Combo.

Two cases of accidental ingestion of a press-through package (PTP) sheet, diagnosed by tomosynthesis prior to endoscopy

The accidental ingestion of a press-through package (PTP) sheet is associated with the risk of gastrointestinal injury and puncture. When pain occurs in the laryngeal pharynx, the PTP may already be stuck in the upper esophageal region, and urgent endoscopic treatment is necessary. A plain chest X-ray image should be performed first to identify the ingested PTP, but this was not successful in the present two patients. As a next step, a CT scan (which involves high radiation exposure) is commonly used. In our patients (a 76-year-old woman and a 59-year-old man), tomosynthesis was used to confirm the presence and location of a PTP sheet as a pre-endoscopic diagnosis. With tomosynthesis, the level of radiation exposure was reduced to approx. 1/10 of that of simple CT; the imaging time is also shorter at ~ 5 s. Tomosynthesis can be performed at approx. 1/3-1/4 the cost of simple CT. The usefulness of tomosynthesis as a pre-endoscopic diagnostic tool was demonstrated in our patients, and its further utilization is expected.

Correlation between imaging features and molecular subtypes of breast cancer in young women (≤30 years old)

OBJECTIVES

To analyze the features of digital mammography (DM) plus digital breast tomosynthesis (DBT), ultrasonography (US) and magnetic resonance imaging (MRI) of breast cancer in young women (≤30 years old) and the correlation with molecular subtypes.

MATERIALS AND METHODS

We performed a retrospective study of imaging features of consecutive young women aged ≤30 years who were treated and surgically confirmed with breast cancer between January 2013 and December 2019 in our institution. All patients were Chinese women. DM + DBT and US were available for 170 lesions, MRI for 41 lesions. The imaging features were analysed by univariate and multivariate logistic regression analyses to find the predictive factors of the molecular subtypes.

RESULTS

The predictive factors of the luminal B(HER2-) subtype (n = 51) were the mass with microcalcifications, irregular shape, spiculated margins, and shadowing posterior features (all P < 0.01). The predictive factors of the luminal B(HER2+) subtype (n = 26) were the spiculated margins (DBT + DM), angular margins (US), shadowing posterior features, and high vascularity (all P < 0.05). The predictive factors of the luminal A subtype (n = 37) were the mass without microcalcifications, spiculated margins, shadowing posterior features, and low vascularity (all P < 0.05). The predictive factors of the triple-negative subtype (n = 31) were the mass without microcalcifications, oval/round shape, circumscribed margins, enhancement of posterior features, and rim enhancement (MRI) (all P < 0.005). The predictive factors of the human-epidermal-growth-factor-receptor-2-enriched subtype (n = 26) were the only microcalcifications, microlobulated margins, and combined posterior feature (all P < 0.05).

CONCLUSION

Compared with the general population of breast cancer, this young female population presents a different molecular phenotype distribution. Some imaging features of breast cancer in young women ≤30 years old can be used to predict certain tumor molecular subtypes.

Artificial intelligence for breast cancer detection in mammography and digital breast tomosynthesis: State of the art

Screening for breast cancer with mammography has been introduced in various countries over the last 30 years, initially using analog screen-film-based systems and, over the last 20 years, transitioning to the use of fully digital systems. With the introduction of digitization, the computer interpretation of images has been a subject of intense interest, resulting in the introduction of computer-aided detection (CADe) and diagnosis (CADx) algorithms in the early 2000's. Although they were introduced with high expectations, the potential improvement in the clinical realm failed to materialize, mostly due to the high number of false positive marks per analyzed image. In the last five years, the artificial intelligence (AI) revolution in computing, driven mostly by deep learning and convolutional neural networks, has also pervaded the field of automated breast cancer detection in digital mammography and digital breast tomosynthesis. Research in this area first involved comparison of its capabilities to that of conventional CADe/CADx methods, which quickly demonstrated the potential of this new technology. In the last couple of years, more mature and some commercial products have been developed, and studies of their performance compared to that of experienced breast radiologists are showing that these algorithms are on par with human-performance levels in retrospective data sets. Although additional studies, especially prospective evaluations performed in the real screening environment, are needed, it is becoming clear that AI will have an important role in the future breast cancer screening realm. Exactly how this new player will shape this field remains to be determined, but recent studies are already evaluating different options for implementation of this technology. The aim of this review is to provide an overview of the basic concepts and developments in the field AI for breast cancer detection in digital mammography and digital breast tomosynthesis. The pitfalls of conventional methods, and how these are, for the most part, avoided by this new technology, will be discussed. Importantly, studies that have evaluated the current capabilities of AI and proposals for how these capabilities should be leveraged in the clinical realm will be reviewed, while the questions that need to be answered before this vision becomes a reality are posed.

The cost-effectiveness of digital breast tomosynthesis in a population breast cancer screening program

OBJECTIVES

To evaluate at which sensitivity digital breast tomosynthesis (DBT) would become cost-effective compared to digital mammography (DM) in a population breast cancer screening program, given a constant estimate of specificity.

METHODS

In a microsimulation model, the cost-effectiveness of biennial screening for women aged 50-75 was simulated for three scenarios: DBT for women with dense breasts and DM for women with fatty breasts (scenario 1), DBT for the whole population (scenario 2) or maintaining DM screening (reference). For DM, sensitivity was varied depending on breast density from 65 to 87%, and for DBT from 65 to 100%. The specificity was set at 96.5% for both DM and DBT. Direct medical costs were considered, including screening, biopsy and treatment costs. Scenarios were considered to be cost-effective if the incremental cost-effectiveness ratio (ICER) was below €20,000 per life year gain (LYG).

RESULTS

For both scenarios, the ICER was more favourable at increasing DBT sensitivity. Compared with DM screening, 0.8-10.2% more LYGs were found when DBT sensitivity was at least 75% for scenario 1, and 4.7-18.7% when DBT sensitivity was at least 80% for scenario 2. At €96 per DBT, scenario 1 was cost-effective at a DBT sensitivity of at least 90%, and at least 95% for scenario 2. At €80 per DBT, these values decreased to 80% and 90%, respectively.

CONCLUSION

DBT is more likely to be a cost-effective alternative to mammography in women with dense breasts. Whether DBT could be cost-effective in a general population highly depends on DBT costs.

KEY POINTS

• DBT could be a cost-effective screening modality for women with dense breasts when its sensitivity is at least 90% at a maximum cost per screen of €96. • DBT has the potential to be cost-effective for screening all women when sensitivity is at least 90% at a maximum cost per screen of €80. • Whether DBT could be used as an alternative to mammography for screening all women is highly dependent on the cost of DBT per screen.

Evaluation of average glandular dose and investigation of the relationship with compressed breast thickness in dual energy contrast enhanced digital mammography and digital breast tomosynthesis

PURPOSE

To quantitatively assess the dose of Dual energy contrast enhanced digital mammography (CEDM) and digital breast tomosynthesis (DBT) and to investigate the relationship between average absorbed glandular dose (AGD), compressed breast thickness (CBT) and compression force (CF).

MATERIALS AND METHODS

All CEDM and DBT examinations were performed in cranio-caudal (CC) and medio-lateral oblique (MLO) view. Exposure parameters of 135 mammographic procedures that using AEC (automatic exposure control) mode were recorded. AGDs were calculated. Kruskal Wallis test was performed.

RESULTS

CBT population ranged from 23 to 94 mm with a thickness median value of 52 mm in CC view and of 57 mm in MLO views. CEDM AGD median value was significatively lower than DBT AGD in each views (p << 0.01). AGD showed a positive correlation and linear regression with CBT for both CEDM and DBT while CF did not show a correlation and linear regression with AGD. The highest values were found for MLO view: R² of 0.74 for CEDM and R² of 0.61 for DBT. Kruskal Wallis test shows that there was a difference statistically significant between AGD values of CEDM and DBT in CC view respect to MLO views (p < 0.01).

CONCLUSIONS

Dose values of both techniques meet the recommendations for maximum dose in mammography. The results of the present study indicated that there was significant difference between AGD for CEDM and DBT exposure in different views (AGD in CC views had the lowest value) and that CBT could influence the AGD while CF was not correlated to AGD.

Imaging Follow-up Versus Surgical Excision for Radial Scars Identified on Tomosynthesis-Guided Core Needle Biopsy

RATIONALE AND OBJECTIVES

We investigated if imaging or pathology features could determine when imaging follow-up is appropriate after diagnosis of radial scar on digital breast tomosynthesis (DBT)-guided core needle biopsy (CNB).

MATERIALS AND METHODS

We conducted a retrospective review of all patients diagnosed with radial scars on DBT-guided CNB at our institution between November 2014 and December 2016. Cases were excluded if DCIS or invasive malignancy was present in the same core specimens. Patient age; needle size; number of cores; visibility on full-field digital mammography versus DBT; lesion size; presence of architectural distortion, mass, or calcifications; imaging stability; presence or absence of atypia; length of imaging follow-up, and excisional pathology were collected.

RESULTS

Of 45 eligible biopsies, 6 cases had radial scars with associated atypia and 39 cases had no associated atypia. Twenty-four patients underwent surgical excision, including all patients with atypia on CNB. One case (4%) was upstaged to DCIS on surgical excision after CNB revealed a radial scar with associated ADH. There was also a case without atypia on CNB, but excisional pathology revealed associated ADH. In cases with radial scars and associated atypia on CNB, the upstage rate was 17%. In cases without atypia on CNB that underwent surgical excision, the upstage rate was 0%. Imaging follow-up was available in 13 patients who did not undergo surgical excision, with stability in all 13 with a median follow-up of 18 months.

CONCLUSION

Annual imaging follow-up appears reasonable in selected patients with radial scars but no atypia on DBT-guided CNB.

Assessment of MRI-detected lesions on screening tomosynthesis in patients with newly diagnosed breast cancer

OBJECTIVES

The purpose of this study is to retrospectively evaluate the presence of screening digital breast tomosynthesis (DBT) correlates for suspicious lesions detected on pre-operative staging magnetic resonance imaging (MRI) in patients with newly diagnosed breast cancer.

METHODS

After approval from the institutional review board (IRB), screening DBTs on breast cancer patients with BI-RADS 4 or 5 staging MRI exams between 8/1/17 and 8/1/18 were assessed for presence of DBT correlates for suspicious MRI findings. The pathology of the index lesion, type of additional MRI finding (mass, non-mass enhancement, or focus), correlative finding on tomosynthesis (mass, asymmetry/focal asymmetry, distortion, or calcifications), size on MRI and tomosynthesis, breast density, and pathology of the additional lesion were recorded. The chi-square test of association was used unless otherwise specified. Confidence intervals for proportions were estimated using the Wilson's score method.

RESULTS

17/70 (24%) of additional lesions seen on pre-operative MRI exams in patients with newly diagnosed cancer had a mammographic correlate on corresponding screening DBT. There was no significant relationship between the presence of a mammographic correlate and the type of MRI finding (mass, NME, or focus), breast density, size of lesion, pathology of index cancer, or pathology of the additional lesion (p≥ 0.05).

CONCLUSIONS

76% of additional lesions seen on pre-operative staging MRI in patients with newly diagnosed breast cancer are not seen retrospectively on screening DBT. Since about 24% of MRI-detected additional lesions may have a DBT correlate, DBT exams should be reviewed in patients recalled for further workup of findings seen on pre-operative MRI since this may facilitate DBT-guided biopsy of suspicious lesions, which is preferable to MRI-guided biopsy for cost and patient comfort reasons.

A method for the automated classification of benign and malignant masses on digital breast tomosynthesis images using machine learning and radiomic features

In digital mammography, which is used for the early detection of breast tumors, oversight may occur due to overlap between normal tissues and lesions. However, since digital breast tomosynthesis can acquire three-dimensional images, tissue overlapping is reduced, and, therefore, the shape and distribution of the lesions can be easily identified. However, it is often difficult to distinguish between benign and malignant breast lesions on images, and the diagnostic accuracy can be reduced due to complications from radiological interpretations, owing to acquisition of a higher number of images. In this study, we developed an automated classification method for diagnosing breast lesions on digital breast tomosynthesis images using radiomics to comprehensively analyze the radiological images. We extracted an analysis area centered on the lesion and calculated 70 radiomic features, including the shape of the lesion, existence of spicula, and texture information. The accuracy was compared by inputting the obtained radiomic features to four classifiers (support vector machine, random forest, naïve Bayes, and multi-layer perceptron), and the final classification result was obtained as an output using a classifier with high accuracy. To confirm the effectiveness of the proposed method, we used 24 cases with confirmed pathological diagnosis on biopsy. We also compared the classification results based on the presence or absence of dimension reduction using least absolute shrinkage and a selection operator (LASSO). As a result, when the support vector machine was used as a classifier, the correct identification rate of the benign tumors was 55% and that of malignant tumors was 84%, with best results. These results indicate that the proposed method may help in more accurately diagnosing cases that are difficult to classify on images.

Cost differences between digital tomosynthesis and standard digital mammography in a breast cancer screening programme: results from the To-Be trial in Norway

BACKGROUND

Several studies in Europe and the US have shown promising results favouring digital breast tomosynthesis compared to standard digital mammography (DM). However, the costs of implementing the technology in screening programmes are not yet known.

METHODS

A randomised controlled trial comparing the results from digital breast tomosynthesis including synthetic mammograms (DBT) vs. DM was performed in Bergen during 2016 and 2017 as a part of BreastScreen Norway. The trial included 29,453 women and allowed for a detailed comparison of procedure use and screening, recall and treatment costs estimated at the individual level.

RESULTS

The increased cost of equipment, examination and reading time with DBT vs. DM was €8.5 per screened woman (95% CI 8.4-8.6). Costs of DBT remained significantly higher after adding recall assessment costs, €6.2 (95% CI 4.6-7.9). Substantial reductions in either examination and reading times, price of DBT equipment or price of IT storage and connectivity did not change the conclusion. Adding treatment costs resulted in too wide confidence intervals to draw definitive conclusions (additional costs of tomosynthesis €9.8, 95% CI -56 to 74). Performing biopsy at recall, radiation therapy and chemotherapy was significantly more frequent among women screened with DBT.

CONCLUSION

The results showed lower incremental costs of DBT vs. DM, compared to what is found in previous cost analyses of DBT and DM. However, the incremental costs were still higher for DBT compared with DM after including recall costs. Further studies with long-term treatment data are needed to understand the complete costs of implementing DBT in screening.

Quantitative Volumetric K-Means Cluster Segmentation of Fibroglandular Tissue and Skin in Breast MRI

Mammographic breast density (MBD) is the most commonly used method to assess the volume of fibroglandular tissue (FGT). However, MRI could provide a clinically feasible and more accurate alternative. There were three aims in this study: (1) to evaluate a clinically feasible method to quantify FGT with MRI, (2) to assess the inter-rater agreement of MRI-based volumetric measurements and (3) to compare them to measurements acquired using digital mammography and 3D tomosynthesis. This retrospective study examined 72 women (mean age 52.4 ± 12.3 years) with 105 disease-free breasts undergoing diagnostic 3.0-T breast MRI and either digital mammography or tomosynthesis. Two observers analyzed MRI images for breast and FGT volumes and FGT-% from T1-weighted images (0.7-, 2.0-, and 4.0-mm-thick slices) using K-means clustering, data from histogram, and active contour algorithms. Reference values were obtained with Quantra software. Inter-rater agreement for MRI measurements made with 2-mm-thick slices was excellent: for FGT-%, r = 0.994 (95% CI 0.990-0.997); for breast volume, r = 0.985 (95% CI 0.934-0.994); and for FGT volume, r = 0.979 (95% CI 0.958-0.989). MRI-based FGT-% correlated strongly with MBD in mammography (r = 0.819-0.904, P < 0.001) and moderately to high with MBD in tomosynthesis (r = 0.630-0.738, P < 0.001). K-means clustering-based assessments of the proportion of the fibroglandular tissue in the breast at MRI are highly reproducible. In the future, quantitative assessment of FGT-% to complement visual estimation of FGT should be performed on a more regular basis as it provides a component which can be incorporated into the individual's breast cancer risk stratification.

Consensus Meeting of Breast Imaging: BI-RADS® and Beyond

Organizers of medical educational courses are often confronted with questions that are clinically relevant yet trespassing the frontiers of scientifically proven, evidence-based medicine at the point of care. Therefore, since 2007 organizers of breast teaching courses in German language met biannually to find a consensus in clinically relevant questions that have not been definitely answered by science. The questions were prepared during the 3 months before the meeting according to a structured process and finally agreed upon the day before the consensus meeting. At the consensus meeting, the open questions concerning 2D/3D mammography, breast ultrasound, MR mammography, interventions as well as risk-based imaging of the breast were presented first for electronic anonymized voting, and then the results of the audience were separately displayed from the expert votes. Thereafter, an introductory statement of the moderator was followed by pros/cons of two experts, and subsequently the final voting was performed. With ≥75% of votes of the expert panel, an answer qualified as a consensus statement. Seventeen consensus statements were gained, addressing for instance the use of 2D/3D mammography, breast ultrasound in screening, MR mammography in women with intermediate breast cancer risk, markers for localization of pathologic axillary lymph nodes, and standards in risk-based imaging of the breast. After the evaluation, comments from the experts on each field were gathered supplementarily. Methodology, transparency, and soundness of statements achieve a unique yield for all course organizers and provide solid pathways for decision making in breast imaging.

Comparison of Resource Utilization and Clinical Outcomes Following Screening with Digital Breast Tomosynthesis Versus Digital Mammography: Findings From a Learning Health System

RATIONALE AND OBJECTIVES

To compare outcomes associated with breast cancer screening with digital mammography (DM) alone versus in combination with digital breast tomosynthesis (DBT) in a large representative cohort.

MATERIALS AND METHODS

A total of 325,729 screening mammograms from 247,431 women were analyzed, across two healthcare systems, from June 2015 to September 2017. Patient level demographic, calculated risk levels, and clinical outcomes were extracted from radiology information system and electronic medical records. Multivariable regression modeling adjusting for institution, age, breast density, and first exam was conducted to compare patient characteristics, recall rates, time to biopsy and final diagnosis, clinical outcomes, and diagnostic performance. Participating institutions and the Coordinating Center received Institutional Review Board approval for a waiver of consent to collect and link data and perform analysis.

RESULTS

A total of 194,437 (59.7%) screens were DBT versus 131,292 (40.3%) with DM. Women with dense breasts and higher calculated risk were more likely to be screened with DBT. Recall rates were lower for DBT overall (8.83% DBT vs 10.98% DM, adjusted odds ratio, 95% confidence interval = 0.85, 0.83-0.87) and across all age groups, races, and breast densities, and at facilities that used predominantly DBT (8.05%) versus predominantly DM (11.22%), or a combination (10.73%). The most common diagnostic pathway after recall was mammography and ultrasound. Women recalled from DBT were more likely to proceed directly to ultrasound. The median time to biopsy (18 vs 22 days) and final diagnosis (10 vs 13 days) was shorter for DBT. The adjusted cancer rate, cancer detection rate, and specificity were higher for DBT.

CONCLUSION

DBT demonstrated a more efficient screening pathway and improved quality measures with lower recall rates in all patient types, reduced diagnostic mammography and shorter time to biopsy and final diagnosis.

Breast density implications and supplemental screening

Digital breast tomosynthesis (DBT) has been widely implemented in place of 2D mammography, although it is less effective in women with extremely dense breasts. Breast ultrasound detects additional early-stage, invasive breast cancers when combined with mammography; however, its relevant limitations, including the shortage of trained operators, operator dependence and small field of view, have limited its widespread implementation. Automated breast sonography (ABS) is a promising technique but the time to interpret and false-positive rates need to be improved. Supplemental screening with contrast-enhanced magnetic resonance imaging (MRI) in high-risk women reduces late-stage disease; abbreviated MRI protocols may reduce cost and increase accessibility to women of average risk with dense breasts. Contrast-enhanced digital mammography (CEDM) and molecular breast imaging improve cancer detection but require further validation for screening and direct biopsy guidance should be implemented for any screening modality. This article reviews the status of screening women with dense breasts. KEY POINTS: • The sensitivity of mammography is reduced in women with dense breasts. Supplemental screening with US detects early-stage, invasive breast cancers. • Tomosynthesis reduces recall rate and increases cancer detection rate but is less effective in women with extremely dense breasts. • Screening MRI improves early diagnosis of breast cancer more than ultrasound and is currently recommended for women at high risk. Risk assessment is needed, to include breast density, to ascertain who should start early annual MRI screening.

Breast tomosynthesis: state of the art

Breast tomosynthesis is a continually improving tool for diagnostic radiologists. This update about tomosynthesis reviews the advantages of the technique both in patients with suspected or known disease and in screening, as well as its limitations, of which the dose of radiation is the most important. The more recent advent of synthesized mammography, computer-assisted detection, and tomosynthesis-guided biopsy have helped to reduce the dose of radiation used and have improved the diagnostic performance of tomosynthesis, so they are also discussed in this review.

Overview of Breast Cancer Screening and Diagnosis

Screening mammography saves lives. The mainstay of screening has been mammography. Multiple alternative options, however, for supplemental imaging are now available. Some are just improved anatomic delineation whereas others include physiology added to anatomy. A third group (molecular imaging) is purely physiologic. This article describes and compares the available options and for which patient populations they should be used.

Application of a pixel-shifted linear interpolation technique for reducing the projection number in tomosynthesis imaging

Tomosynthesis images are reconstructed from several projections. However, the number of projections is proportional to the exposure dose, and a reduction in the number of projections would result in a reduction of radiation dose to the patient but also degradation of image quality. The purpose of this study was to propose a new computerized method to supply interpolation images instead of real projection images for maintaining the number of projection images and image quality of reconstructed tomosynthesis images. A set of images comprising one-half the number of projection images [37 projections (Half set)], selected from the original full set of projection images [73 projections (Full set)], was used at an interval of one by one. In this study, the authors used a new linear interpolation technique (Shift-Linear method), which takes into account shifted distances between two corresponding pixels on two projection images. The image quality of tomosynthesis images reconstructed from the full set and the quasi-full projection images, which were produced from the Half set using the Shift-Linear method, was compared. Image quality was assessed in terms of modulation transfer function, noise power spectrum, contrast-to-noise ratio, and the detective quantum efficiency. Using this proposed method, the image quality of reconstructed tomosynthesis images could be maintained with the reduction of approximately 50% exposure dose.

Agreement between digital breast tomosynthesis and pathologic tumour size for staging breast cancer, and comparison with standard mammography

PURPOSE

Tomosynthesis is proposed to improve breast cancer assessment and staging. We compared tomosynthesis and mammography in estimating the size of newly-diagnosed breast cancers.

METHODS

All pathologically-confirmed cancers detected in the STORM-2 trial (90 cancers, 85 women) were retrospectively measured on tomosynthesis by two independent readers. One reader also measured cancers on mammography. Relative mean differences (MDs) and 95% limits of agreement (LOA) with pathology were estimated for tomosynthesis and mammography within a single reader (Analysis 1) and between two readers (Analysis 2).

RESULTS

Where cancers were detected and hence measured by both tests, tomosynthesis overestimated pathologic size relative to mammography (Analysis 1: MD 5% versus 1%, Analysis 2: 7% versus 3%; P = 0.10 both analyses). There was similar, large measurement variability for both tests (LOA range: -60% to +166%). Overestimation by tomosynthesis was attributable to the subgroup with dense breasts (MDs = 12-13% versus 4% for mammography). There was low average bias for both tests in the low-density subgroup (MDs = 0-4%). LOA were larger in dense breasts for both tomosynthesis and mammography (P ≤ 0.02 all comparisons). Cancers detected only by tomosynthesis were more frequently in dense breasts (60-68%): for those tumours size was estimated with increased measurement variability (LOA ranging from -75% to +293%).

CONCLUSIONS

On average, tomosynthesis overestimates pathologic tumour size in women with dense breasts; that difference is more likely to impact management in women with larger tumours. The main advantage of tomosynthesis appears to be detecting mammographically-occult cancers; however tomosynthesis less accurately measured those cancers in dense breasts (large measurement variability).

An adaptive multiscale anisotropic diffusion regularized image reconstruction method for digital breast tomosynthesis

As a special case of tomography, digital breast tomosynthesis (DBT) can realize quasi-3D image reconstruction for breast lesion detection from few-view and limited-angle projection data. For DBT image reconstruction, iterative algorithms are needed to suppress artifacts due to undersampling, and adaptive regularizations are necessary for preserving the edges of masses and calcifications. This paper presents a novel reconstruction method by regularizing projection onto convex sets (POCS) with multiscale Tikhonov-total variation (MTTV). The regularization, known as adaptive multiscale anisotropic diffusion, is able to preserve edges to a considerable extent and selectively suppress noise without introducing artifacts. The proposed method is referred to as MTTV-POCS and is evaluated quantitatively using 3D numerical breast and Shepp-Logan phantoms as well as two clinical volume images acquired from an advanced DBT machine. Experimental results show that the proposed method has better performance in metrics of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) over two existing methods: adaptive-steepest-descent-POCS (ASD-POCS) and selective-diffusion regularized simultaneous algebraic reconstruction technique (SD-SART). As indicated by the results, the proposed method is applicable to DBT for high-quality image reconstruction.