Search

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.

Background Mammography plays a great role in reducing breast cancer mortality as it is the standard method of breast imaging and screening. But the accuracy of mammography performance reduces in cancer detection in women with dense breast due to the summation of images and overlapping of breast tissue. ABUS and tomosynthesis both recently help to detect breast cancer in dense breasted women. This prospective study was done in the female imaging unit and approved by its research and ethical committee; all the patients did an informed consent during the period from October 2018 to March 2019. The study was conducted on 38 patients with 38 lesions subjected to digital mammography, tomosynthesis and automated breast ultrasound (ABUS), who all had dense breast in mammography. Results Automated breast ultrasound (ABUS) showed 100% in all sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) as well as accuracy, while the digital mammography tomosynthesis showed 100% in specificity, 87.5% in sensitivity, 100% in PPV, 82.4% in NPV and 92.1% accuracy. Conclusion Automated breast ultrasound (ABUS) together with tomosynthesis makes a revolution in breast screening and detecting cancer in women with dense breasts.

This article gives a brief overview of the development of artificial intelligence in clinical breast imaging. For multiple decades, artificial intelligence (AI) methods have been developed and translated for breast imaging tasks such as detection, diagnosis, and assessing response to therapy. As imaging modalities arise to support breast cancer screening programs and diagnostic examinations, including full-field digital mammography, breast tomosynthesis, ultrasound, and MRI, AI techniques parallel the efforts with more complex algorithms, faster computers, and larger data sets. AI methods include human-engineered radiomics algorithms and deep learning methods. Examples of these AI-supported clinical tasks are given along with commentary on the future.

Objectives To compare the outcome for DBT-detected and DM-detected suspicious AD, to evaluate the risk of malignancy and if is affected by the US or MRI imaging correlation. Methods All cases with suspicious AD (ultimately assigned BI-RADS 4 or 5 categories) were retrospectively included. Two radiologists independently reviewed DM and DBT images in two sessions for detection (DM vs. DBT). US and MRI imaging correlation findings were recorded. Pathologic results were compared between DBT-detected and DM-detected AD. Results Among 137 detected ADs, 103 (75.2%) were DM-detected, and 34 (24.8%) were only DBT-detected (p = 0.01). The malignancy rate was lower for DBT-detected than DM-detected AD (14.7% vs. 45.6%) (p = 0.01). Malignancy rate was higher with US-positive than US-negative correlation at DM-detected AD (49.4% vs. 27.8%) (p = 0.01). Malignancy rate was not different for DBT-detected AD with (16.7%) or without (12.5%) sonographic correlation. NPV based on radiologists' level of suspicion was high (86.2%-97.2%) but not sufficient enough to forgo biopsy. Of 34 sonographically occult ADs, a positive-MRI correlation was identified in 19 (55.9%) ADs (7 were malignant, 12 were benign). A negative-MRI correlation was identified in 15 (44.1%) ADs; all had a benign outcome (p = 0.01). Conclusions DBT-detected AD is less likely to represent malignancy than does DM-detected; however, the risk of malignancy is not low enough to forgo biopsy. MRI-negative correlation in sonographically occult AD was significantly associated with benign outcomes and can avoid unnecessary interventions.

Background Correct preoperative estimation of the malignant extent is crucial for optimal planning of breast cancer surgery. The sensitivity of mammography is lower in dense breasts, and additional imaging techniques are sometimes warranted. Contrast-enhanced mammography (CEM) has shown similar sensitivity and in some cases better specificity, than magnetic resonance imaging (MRI) in small, observational studies. CEM may be more cost-effective than MRI, and may provide better identification of the tumor extent, however, no randomized trials have been performed to date to investigate the added value of CEM. In a feasibility study, we found that the treatment was changed in 10/47 (21%) cases after additional CEM. The purpose of the present study is to evaluate the added value of CEM in preoperative staging of breast cancer in a randomized study. Method This prospective randomized study will include 440 patients with strongly suspected or established diagnosis of breast malignancy, based on assessment with mammography, ultrasound and core biopsy/cytology, and for whom primary surgery is planned. Patients will be randomized 1:1 using a web-based randomization tool to additional investigation with CEM or no further imaging. The CEM findings will be taken into consideration, which may lead to changes in primary treatment, which is the primary endpoint of this study. Secondary endpoints include rate of reoperation and number of avoidable mastectomies, as well as a cost-benefit analysis of additional CEM. Patient-reported health-related quality of life will be investigated at 1 year with the validated Breast-Q™ questionnaire. The rate of local recurrence or new cancer ipsi- or contralaterally within 5 years will be assessed from medical records and pathology reports. Discussion The aim of this trial is to explore the added value of CEM in preoperative staging of breast cancer. The results obtained from this study will contribute to our knowledge on CEM as an additional imaging method to standard investigation with digital mammography and ultrasound. The findings may also provide additional information on which patient groups would benefit from CEM, and on the economic aspects of CEM in standard preoperative practice. Trial registration This trial is registered at clinicaltrials.gov, registration no: NCT04437602, date of registration: June 18, 2020.

Purpose We conducted a systematic review and meta-analysis to compare the screening performance of synthesized mammography (SM) plus digital breast tomosynthesis (DBT) with digital mammography (DM) plus DBT or DM alone. Methods Medline, Embase, Web of Science, and the Cochrane Library databases were searched from January 2010 to January 2021. Eligible population-based studies on breast cancer screening comparing SM/DBT with DM/DBT or DM in asymptomatic women were included. A random-effect model was used in this meta-analysis. Data were summarized as risk differences (RDs), with 95 % confidence intervals (CIs). Results Thirteen studies involving 1,370,670 participants were included. Compared with DM/DBT, screening using SM/DBT had similar breast cancer detection rate (CDR) (RD = −0.1/1000 screens, 95 % CI = −0.4 to 0.2, p = 0.557, I2 = 0 %), but lower recall rate (RD = −0.56 %, 95 % CI = −1.03 to −0.08, p = 0.022, I2 = 90 %) and lower biopsy rate (RD = −0.33 %, 95 % CI = −0.56 to −0.10, p = 0.005, I2 = 78 %). Compared with DM, SM/DBT improved CDR (RD = 2.0/1000 screens, 95 % CI = 1.4 to 2.6, p, Highlights • Screening using SM/DBT has similar breast cancer detection but reduces recall and biopsy when compared with DM/DBT. • Screening using SM/DBT improves cancer detection rate when compared with DM/DBT alone. • There was no significant difference in interval cancer rate between SM/DBT and DM. • SM/DBT could replace DM/DBT in breast cancer screening to reduce radiation dose.

Background: Digital breast tomosynthesis (quasi three-dimensional [3D] mammography) is a relatively novel technique. It creates thin-slice reconstructions of the breast from low-dose digital mammographic images acquired at multiple angles. This evolution of mammography improves lesion visibility by reducing overlapping tissue. Hence, it has the potential to increase BC detection and to reduce false-positive (FP) findings. Objective: To review the role of 3D Digital Mammography in Studying of dense breast Lesions in adult female. Patients and methods: This was a retrospective study conducted on 40 patients who were eligible for examination by 3D Digital Mammography referred to WAFI center (women and fetal imaging center). The study was conducted during 12 months from January 2019 till January 2020 and was carried at Al-Azhar University Hospitals and WAFI Center (Woman and fetal imaging center). Results: There was no statistically significant difference between ultrasound (US) and tomosynthesis (TOMO) as regarding mass detection. There was a statistically significant increase as regarding calcification detection in TOMO than US. There was a statistically significant increase as regarding asymmetry detection in TOMO than US. There was no statistically significant difference between US & TOMO as regards Arch. Distortion detection. There was no statistically significant difference between US & TOMO as regards inflammatory reactions detection. There was statistically significant increase as regarding cyst detection in US than TOMO. There was a statistically significant increase as regarding dilated ducts detection in US than TOMO. There was a statistically significant increase as regarding added value detection in US than TOMO. There was no statistically significant difference between US & TOMO as regarding Breast Imaging-Reporting and Data System (BI-RADS). Conclusion: Both modalities were not similar in the ability to identify malignant lesions. Wide-angle digital breast tomosynthesis (DBT) was able to initially identify two more lesions

To investigate the value of an artificial intelligence (AI) system in assisting radiologists to improve the assessment accuracy of BI-RADS 0 cases in mammograms. We included 34,654 consecutive digital mammography studies, collected between January 2011 and January 2019, among which, 1088 cases from 1010 unique patients with initial BI-RADS 0 assessment who were recalled during 2 years of follow-up were used in this study. Two mid-level radiologists retrospectively re-assessed these BI-RADS 0 cases with the assistance of an AI system developed by us previously. In addition, four entry-level radiologists were split into two groups to cross-read 80 cases with and without the AI. Diagnostic performance was evaluated using the follow-up diagnosis or biopsy results as the reference standard. Of the 1088 cases, 626 were actually normal (BI-RADS 1 and no recall required). Assisted by the AI system, 351 (56%) and 362 (58%) normal cases were correctly identified by the two mid-level radiologists hence can be avoided for unnecessary follow-ups. However, they would have missed 12 (10 invasive cancers and 2 ductal carcinoma in situ cancers) and 6 (invasive cancers) malignant lesions respectively as a result. These missed lesions were not highly malignant tumors. The inter-rater reliability of entry-level radiologists increased from 0.20 to 0.30 (p

BACKGROUND. Patients with a history of breast cancer are at higher risk of subsequent breast cancers and need close clinical and imaging follow-up. Limited data are available on screening of these ...

Background. Breast cancer is the most common cancer in women worldwide. Despite advances in treatment of breast cancer, early-stage breast cancer detection is limited by screening mammography and often requires additional breast imaging.The purpose of the study was to analyze available data on modern imaging techniques of additional breast visualization used for improving breast cancer screening.Material and methods. The review includes data from randomized controlled trials and meta-analyzes on the effectiveness of breast imaging techniques for early-stage breast cancer detection. The search was carried out in pubmed, Web of science, scopus and cochrane library databases. Out of 100 publications published over the past 7 years, 51 were included in the presented review.Results. Breast cancer screening using various imaging techniques has been carried out in the world for more than 30 years, and over the past 10 years significant progress has been made in improving X-ray, ultrasound and magnetic resonance technologies in the early breast cancer detection. At present, healthcare organizers are faced with the question of choosing a vector for improving the breast cancer screening program by introducing digital tomosynthesis, contrast spectral mammography, or accelerated mri. According to the current results of the analysis of literature data, contrast spectral mammography and accelerated mri have the highest sensitivity, but studies of sensitivity, specificity, positive and negative predictive values (ppv, npv) are ongoing.Conclusion. The data presented in the review confirm the necessity for finding the vector for improving the breast cancer screening program using multicenter prospective trials.

Mammography is still the only screening method for breast cancer. Although digital mammography is the most common and widely used method for detecting breast cancer, it is ineffective at detecting and assessing intratumoral heterogeneity. Due to the small size of the tissue sample or tumor, biopsies often fail to represent the entire tumor. For this reason, selecting a treatment and determining a patients prognosis becomes difficult. In this case, medical imaging is a noninvasive approach that can provide a more comprehensive view of the entire tumor, act as a virtual biopsy, and be useful for monitoring disease progression and response to therapy. Radiomics with texture analysis allows you to look at an image as a group of numerical data, moving beyond the usual visual perception and into a deeper analysis of digital, pixel data to improve the accuracy of differential diagnosis. Radiogenomics is a natural extension of radiomics that focuses on determining gene expression based on radiologic tumor phenotype. The purpose of this review is to evaluate the role of mammography in breast cancer radiomics and radiogenomics. The article presents a literature review of relevant Russian scientific articles found in databases such as PubMed, Medline, Springer, eLibrary, and Google Scholar. The information obtained was then pooled, structured, and analyzed to examine the role of mammography in breast cancer screening radiomics.

OBJECTIVES: This study was designed to compare the detection of subtle lesions (calcification clusters or masses) when using the combination of digital breast tomosynthesis (DBT) and synthetic mammography (SM) with digital mammography (DM) alone or combined with DBT. METHODS: A set of 166 cases without cancer was acquired on a DBT mammography system. Realistic subtle calcification clusters and masses in the DM images and DBT planes were digitally inserted into 104 of the acquired cases. Three study arms were created: DM alone, DM with DBT and SM with DBT. Five mammographic readers located the centre of any lesion within the images that should be recalled for further investigation and graded their suspiciousness. A JAFROC figure of merit (FoM) and lesion detection fraction (LDF) were calculated for each study arm. The visibility of the lesions in the DBT images was compared with SM and DM images. RESULTS: For calcification clusters, there were no significant differences (p > 0.075) in FoM or LDF. For masses, the FoM and LDF were significantly improved in the arms using DBT compared to DM alone (p < 0.001). On average, both calcification clusters and masses were more visible on DBT than on DM and SM images. CONCLUSIONS: This study demonstrated that masses were detected better with DBT than with DM alone and there was no significant difference (p = 0.075) in LDF between DM&DBT and SM&DBT for calcifications clusters. Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses. KEY POINTS: • The detection of masses was significantly better using DBT than with digital mammography alone. • The detection of calcification clusters was not significantly different between digital mammography and synthetic 2D images combined with tomosynthesis. • Our results support previous studies that it may be acceptable to not acquire digital mammography alongside tomosynthesis for subtle calcification clusters and ill-defined masses for the imaging technology used. ispartof: EUROPEAN RADIOLOGY vol:32 issue:2 pages:806-814 ispartof: location:Germany status: published

Background. Cardiovascular diseases are one of the main causes of death among women, and current prevention paradigms may not be sufficient in this group. In this context, it has been suggested that the detection of breast vascular calcifications can improve the screening and assessment of the risk of cardiovascular diseases in apparently healthy women.Objective: to study the role of breast vascular calcifications as a potential predictor for coronary artery calcification. Material and methods. Examinations were made in 123 patients who underwent digital mammography and cardiac computed tomography to estimate a coronary artery calcium score.Results. The use of the Wilcoxon-Mann-Whitney W-test for abnormal distribution showed a relationship between the presence of breast vascular calcifications and calcium score (p< 0.001), and that between aortic wall calcification and calcium score (p< 0.001).Conclusion. Breast vascular calcifications detected by mammography are an indicator of a higher frequency of coronary artery calcification and, apparently, a predictor for the increased risk of cardiovascular disease.

Osteoblastoma is a rare benign osseous neoplasm that accounts for 1%-3% of all primary bone tumors. Osteoblastomas can involve any part of the skeleton, but mainly occurs in the spine and other long bones, rarely in extra-skeletal areas. Extra-skeletal osteoblastomas arise from tissues outside of the bone, and only a few cases have been reported previously. To our knowledge, only one case of osteoblastoma in the breast has been described in the English literature. Here, we report another case of a breast osteoblastoma in a middle-aged woman, which was initially detected by ultrasound examination and digital mammography, and then was confirmed by histopathology. In this report, the imaging features and differential diagnosis of breast osteoblastoma are discussed.

Digital mammography acts as a unique screening technology to protect the lives of females against breast cancer for the past few decades. Mammographic breast density is a well-known biomarker and plays a substantial role in breast cancer prediction and treatments. Breast density is calculated based on the opacity of fibro-glandular tissue reflected on digital mammograms concerning the whole area of the breast. The opacity of pectoral muscle and fibro-glandular tissue is similar to each other; hence, the small presence of the pectoral muscle in the breast area can hamper the accuracy of breast density classification. Successful removal of pectoral muscle is challenging due to changes in shape, size, and texture of pectoral muscle in every MLO and LMO views of mammogram. In this article, the depth-first search (DFS) algorithm is proposed to remove artifacts and pectoral muscle from digital mammograms. In the proposed algorithm, image enhancement is performed to improve the pixel quality of the input image. The whole breast as a single connected component is identified from the background region to remove the artifacts and tags. The depth-first search method with and without the heuristic approach is used to delineate the pectoral muscle, and then final suppression is performed on it. This algorithm is tested on 2675 images of the DDSM dataset, which is further divided into four density classes as per BIRADs classification. Segmentation results are calculated individually on each BIRADs density class of the DDSM dataset. Results are validated subjectively by the expert's Radiologist's ground truth with segmentation accuracy and objectively by the Jaccard coefficient and a dice similarity coefficient. This algorithm is found robust on each density class and provides overall segmentation accuracy of 86.18%, a mean value of Jaccard index, and a Dice similarity coefficient of 0.9315 and 0.9548, respectively. The experimental results show that the proposed algorithms applied for pectoral muscle removal follow the ground truth marked by an expert radiologist. The proposed algorithm can be part of the pre-processing unit of breast density measurement and breast cancer detection system used during clinical practice.

Objectives To evaluate the diagnostic performance in the assessment setting of three protocols: one-view wide-angle digital breast tomosynthesis (WA-DBT) with synthetic mammography (SM), two-view WA-DBT/SM, and two-view digital mammography (DM). Methods Included in this retrospective study were patients who underwent bilateral two-view DM and WA-DBT. SM were reconstructed from the WA-DBT data. The standard of reference was histology and/or 2 years follow-up. Included were 205 women with 179 lesions (89 malignant, 90 benign). Four blinded readers randomly evaluated images to assess density, lesion type, and level of suspicion according to BI-RADS. Three protocols were evaluated: two-view DM, one-view (mediolateral oblique) WA-DBT/SM, and two-view WA-DBT/SM. Detection rate, sensitivity, specificity, and accuracy were calculated and compared using multivariate analysis. Reading time was assessed. Results The detection rate was higher with two-view WA-DBT/SM (p = 0.063). Sensitivity was higher for two-view WA-DBT/SM compared to two-view DM (p = 0.001) and one-view WA-DBT/SM (p = 0.058). No significant differences in specificity were found. Accuracy was higher with both one-view WA-DBT/SM and two-view WA-DBT/SM compared to DM (p = 0.003 and > 0.001, respectively). Accuracy did not differ between one- and two-view WA-DBT/SM. Two-view WA-DBT/SM performed better for masses and asymmetries. Reading times were significantly longer when WA-DBT was evaluated. Conclusions One-view and two-view WA-DBT/SM can achieve a higher diagnostic performance compared to two-view DM. The detection rate and sensitivity were highest with two-view WA-DBT/SM. Two-view WA-DBT/SM appears to be the most appropriate tool for the assessment of breast lesions. Key Points • Detection rate with two-view wide-angle digital breast tomosynthesis (WA-DBT) is significantly higher than with two-view digital mammography in the assessment setting. • Diagnostic accuracy of one-view and two-view WA-DBT with synthetic mammography (SM) in the assessment setting is higher than that of two-view digital mammography. • Compared to one-view WA-DBT with SM, two-view WA-DBT with SM seems to be the most appropriate tool for the assessment of breast lesions.

PURPOSE Digital breast tomosynthesis (DBT) in conjunction with digital mammography (DM) is becoming the preferred imaging modality for breast cancer screening compared with DM alone, on the basis of improved recall rates (RR) and cancer detection rates (CDRs). The aim of this study was to investigate racial differences in the utilization and performance of screening modality. METHODS Retrospective data from 63 US breast imaging facilities from 2015 to 2019 were reviewed. Screening outcomes were linked to cancer registries. RR, CDR per 1,000 examinations, and positive predictive value for recall (cancers/recalled patients) were compared. RESULTS A total of 385,503 women contributed 542,945 DBT and 261,359 DM screens. A lower proportion of screenings for Black women were performed using DBT plus DM (referred to as DBT) (44% for Black, 48% for other, 63% for Asian, and 61% for White). Non-White women were less likely to undergo more than one mammographic examination. RRs were lower for DBT among all women (8.74 versus 10.06, P < .05) and lower across all races and within age categories. RRs were significantly higher for women with only one mammogram. CDRs were similar or higher in women undergoing DBT compared with DM, overall (4.73 versus 4.60, adjusted P = .0005) and by age and race. Positive predictive value for recall was greater for DBT overall (5.29 versus 4.45, adjusted P < .0001) and by age, race, and screening frequency. CONCLUSIONS All racial groups had improved outcomes with DBT screening, but disparities were observed in DBT utilization. These data suggest that reducing inequities in DBT utilization may improve the effectiveness of breast cancer screening.

Recently, computer-aided diagnosis (CAD) systems powered by deep learning (DL) algorithms have shown excellent performance in the evaluation of digital mammography for breast cancer diagnosis. However, such systems typically require pixel-level annotations by expert radiologists which is prohibitively time-consuming and expensive. Medical institutes would wonder if a high-performance breast cancer CAD system can be trained by exploring their own huge amount of historical imaging data and corresponding diagnosis reports, without additional annotations workload of their radiologists. In this study, we show that a DL classification model trained on historical mammograms with only image-level pathology labels (which can be automatically extracted from medical reports) can achieve surprisingly good diagnostic performance on newly incoming exams compared with experienced radiologists. A DL model called DenseNet was trained and cross-validated with 5979 historical exams acquired before September 2017 with biopsy-verified pathology and tested with 1194 newly obtained cases after that. For both cross-validation and test sets, the ROCs generated by DL predictions were above the ROCs generated by ratings from radiologists. For the suspicious cases which radiologists suggest biopsy (BI-RADS category 4 and 5), the DL model can reject 60% of false biopsies on benign breasts while keeping 95% sensitivity. For the mammograms based on which radiologists were not able to make a diagnosis (BI-RADS 0), the DL model still achieved an AUC score of 79%. Moreover, the model is able to localize lesions on mammograms although such information was not provided in the training phase. Finally, the impact of input image resolution and different DL model architectures on the diagnostic accuracy were also presented and analyzed.

OBJECTIVE. The objective of this study was to assess to the role of contrast-enhanced digital mammography (CEDM) as a screening tool in women at intermediate risk for developing breast cancer due to a personal history of lobular neoplasia without additional risk factors. MATERIALS AND METHODS. In this institutional review board-approved, observational, retrospective study, we reviewed our radiology department database to identify patients with a personal history of breast biopsy yielding lobular neoplasia who underwent screening CEDM at our institution between December 2012 and February 2019. A total of 132 women who underwent 306 CEDM examinations were included. All CEDM examinations were interpreted by dedicated breast imaging radiologists in conjunction with a review of the patient’s clinical history and available prior breast imaging. In statistical analysis, sensitivity, specificity, NPV, positive likelihood ratio, and accuracy of CEDM in detecting cancer were determined, with pathology or 12-month imaging follow-up serving as the reference standard. RESULTS. CEDM detected cancer in six patients and showed an overall sensitivity of 100%, specificity of 88% (95% CI, 84–92%), NPV of 100%, and accuracy of 88% (95% CI, 84–92%). The positive likelihood ratio of 8.33 suggested that CEDM findings are 8.3 times more likely to be positive in an individual with breast cancer when compared with an individual without the disease. CONCLUSION. CEDM shows promise as a breast cancer screening examination in patients with a personal history of lobular neoplasia. Continued investigation with a larger patient population is needed to determine the true sensitivity and positive predictive value of CEDM for these patients.

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. 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. 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 0.999), and PPV1s of 4.29% and 6.0% (17/396 and 15/250, respectively, p > 0.999), respectively. 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. • 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.

Population-based breast cancer screening programs are efficacious in reducing the mortality due to breast cancer. These programs use mammography to screen the women who are invited to participate. Digital mammography makes it possible to develop computer-assisted diagnosis (CAD) systems that promise to reduce the workload of radiologists participating in screening programs. However, various studies have shown that CAD results in a high rate of false positive diagnoses. Systems based on artificial intelligence are being more widely implemented, and studies have shown that these systems have better diagnostic performance than traditional CAD systems. This article explains the fundamentals of artificial intelligence systems and an overview of possible applications of these systems within the framework of breast cancer screening programs.

BACKGROUND There is increasing interest in noncontrast-enhanced MRI due to safety concerns for gadolinium contrast agents. PURPOSE To investigate the clinical feasibility of MR-based conductivity imaging for breast cancer detection and lesion differentiation. STUDY TYPE Prospective. SUBJECTS One hundred and ten women, with 112 known cancers and 17 benign lesions (biopsy-proven), scheduled for preoperative MRI. FIELD STRENGTH/SEQUENCE Non-fat-suppressed T2-weighted turbo spin-echo sequence (T2WI), dynamic contrast-enhanced MRI and diffusion-weighted imaging (DWI) at 3T. ASSESSMENT Cancer detectability on each imaging modality was qualitatively evaluated on a per-breast basis: the conductivity maps derived from T2WI were independently reviewed by three radiologists (R1-R3). T2WI, DWI, and pre-operative digital mammography were independently reviewed by three other radiologists (R4-R6). Conductivity and apparent diffusion coefficient (ADC) measurements (mean, minimum, and maximum) were performed for 112 cancers and 17 benign lesions independently by two radiologists (R1 and R2). Tumor size was measured from surgical specimens. STATISTICAL TESTS Cancer detection rates were compared using generalized estimating equations. Multivariable logistic regression analysis was performed to identify factors associated with cancer detectability. Discriminating ability of conductivity and ADC was evaluated by using the areas under the receiver operating characteristic curve (AUC). RESULTS Conductivity imaging showed lower cancer detection rates (20%-32%) compared to T2WI (62%-71%), DWI (85%-90%), and mammography (79%-88%) (all P

Contrast-enhanced mammography (CEM) has emerged as a viable alternative to contrast-enhanced breast MRI, and it may increase access to vascular imaging while reducing examination cost. Intravenous iodinated contrast materials are used in CEM to enhance the visualization of tumor neovascularity. After injection, imaging is performed with dual-energy digital mammography, which helps provide a low-energy image and a recombined or iodine image that depict enhancing lesions in the breast. CEM has been demonstrated to help improve accuracy compared with digital mammography and US in women with abnormal screening mammographic findings or symptoms of breast cancer. It has also been demonstrated to approach the accuracy of breast MRI in preoperative staging of patients with breast cancer and in monitoring response after neoadjuvant chemotherapy. There are early encouraging results from trials evaluating CEM in the screening of women who are at an increased risk of breast cancer. Although CEM is a promising tool, it slightly increases radiation dose and carries a small risk of adverse reactions to contrast materials. This review details the CEM technique, diagnostic and screening uses, and future applications, including artificial intelligence and radiomics. (C) RSNA, 2021

Background We assessed the clinical utility of a first-degree breast cancer family history and polygenic risk score (PRS) to inform screening decisions among women aged 30-50 years. Methods Two established breast cancer models evaluated digital mammography screening strategies in the 1985 US birth cohort by risk groups defined by family history and PRS based on 313 single nucleotide polymorphisms. Strategies varied in initiation age (30, 35, 40, 45, and 50 years) and interval (annual, hybrid, biennial, triennial). The benefits (breast cancer deaths averted, life-years gained) and harms (false-positive mammograms, overdiagnoses) were compared with those seen with 3 established screening guidelines. Results Women with a breast cancer family history who initiated biennial screening at age 40 years (vs 50 years) had a 36% (model range = 29%-40%) increase in life-years gained and 20% (model range = 16%-24%) more breast cancer deaths averted, but 21% (model range = 17%-23%) more overdiagnoses and 63% (model range = 62%-64%) more false positives. Screening tailored to PRS vs biennial screening from 50 to 74 years had smaller positive effects on life-years gained (20%) and breast cancer deaths averted (11%) but also smaller increases in overdiagnoses (10%) and false positives (26%). Combined use of family history and PRS vs biennial screening from 50 to 74 years had the greatest increase in life-years gained (29%) and breast cancer deaths averted (18%). Conclusions Our results suggest that breast cancer family history and PRS could guide screening decisions before age 50 years among women at increased risk for breast cancer but expected increases in overdiagnoses and false positives should be expected.

OBJECTIVE. One central question pertaining to mammography quality relates to discerning the optimal recall rate to maximize cancer detection while minimizing unnecessary downstream diagnostic imaging and breast biopsies. We examined the trade-offs for higher recall rates in terms of biopsy recommendations and cancer detection in a single large health care organization. MATERIALS AND METHODS. We included 2D analog, 2D digital, and 3D digital (tomosynthesis) screening mammography examinations among women 40-79 years old performed between January 1, 2005, and December 31, 2017, with cancer follow-up through 2018. There were 36, 67, and 38 radiologists who read at least 1000 2D analog examinations, 2D digital examinations, and 3D tomosynthesis examinations, respectively, who were included in these analyses. Using logistic regression with marginal standardization, we estimated radiologist-specific mean recall (abnormal interpretations/1000 mammograms), biopsy recommendation, cancer detection (screening-detected in situ and invasive cancers/1000 mammograms), and minimally invasive cancer detection rates while adjusting for differences in patient characteristics. RESULTS. Among 1,060,655 screening mammograms, the mean recall rate was 10.7%, the cancer detection rate was 4.0/1000 mammograms, and the biopsy recommendation rate was 1.60%. Recall rates between 7% and 9% appeared to maximize cancer detection while minimizing unnecessary biopsies. CONCLUSION. The results of this investigation are in contrast to those of a recent study suggesting appropriateness of higher recall rates. The "sweet spot" for optimal cancer detection appears to be in the recall rate range of 7-9% for both 2D digital mammography and 3D tomosynthesis. Too many women are being called back for diagnostic imaging, and new benchmarks could be set to reduce this burden.

Radial scar (RS) or complex sclerosing lesions (CSL) if > 10 mm is a benign lesion with an increasing incidence of diagnosis (ranging from 0.6 to 3.7%) and represents a challenge both for radiologists and for pathologists. The digital mammography and digital breast tomosynthesis appearances of RS are well documented, according to the literature. On ultrasound, variable aspects can be detected. Magnetic resonance imaging contribution to differential diagnosis with carcinoma is growing. As for the management, a vacuum-assisted biopsy (VAB) with large core is recommended after a percutaneous diagnosis of RS due to potential sampling error. According to the recent International Consensus Conference, a RS/CSL lesion, which is visible on imaging, should undergo therapeutic excision with VAB. Thereafter, surveillance is justified. The aim of this review is to provide a practical guide for the recognition of RS on imaging, illustrating radiological findings according to the most recent literature, and to delineate the management strategies that follow.

Rationale : A standard algorithm for the assessment of patients with breast trauma does not exist, as such trauma usually does not incur any significant health problems. However, according to existing clinical and work-up data and various radiological signs, posttraumatic abnormalities of the breast can mimic cancer lesions and complicate the differential diagnosis for a radiologist. Aim : To evaluate the potential of digital mammography and breast ultrasound examination in the identification of breast posttraumatic abnormalities and to describe their semiotics. Materials and methods : The study included 150 female patients aged 40 to 86 years (mean±SD, 60±11.9 years) with a history of breast trauma. Digital mammography with tomosynthesis (combined mode) and multiparametric ultrasound were able to identify breast abnormalities in 62 patients. The results of all assessments (n=62) were interpreted according to BI-RADS. Should any confirmation of the abnormalities be necessary, fine needle aspiration biopsy or core-biopsy with stereotaxic or ultrasound control were performed. Results : At mammography, the typical posttraumatic abnormality in the breast was fat necrosis (n=54). It was represented as nodular masses with round (20/34; 58.8%) or oval shape (13/34; 38.2%) and circumscribed margins. In most cases, the masses contained eggshell calcification (27/34; 79.4%). In 35.1% (19/54) of the cases fat necrosis was represented by various calcifications. At ultrasound, fat necrosis could be identified as avascular (40/40; 100%), mostly round (26/40; 65.0%), less frequently oval (12/40; 30.0%), and hypoechoic (19/40; 47.5%) masses with circumscribed margins. Atypical signs of fat necrosis (BIRADS 4) were found in 16.1% (10/62) of the cases, in which 7 (11.2%) core-biopsies with ultrasound control and 3 (4.8%) stereotaxic biopsies were performed. In all the cases, breast fat necrosis was confirmed, with various ratios of fibrous and necrotic fat tissue and lymphoid infiltration. Conclusion : In most cases, standard radiological methods used in the diagnostic algorithm for posttraumatic breast lesions are sufficient for the diagnosis. In uncertain diagnostic cases, morphological verification seems necessary.

In this paper, we investigate the classification of microscopic tumours using full digital mammography images. Firstly, to address the shortcomings of traditional image segmentation methods, two different deep learning methods are designed to achieve the segmentation of uterine fibroids. The deep lab model is used to optimize the lesion edge detailed information by using the void convolution algorithm and fully connected CRF, and the two semantic segmentation networks are compared to obtain the best results. The Mask RCNN case segmentation model is used to effectively extract features through the ResNet structure, combined with the RPN network to achieve effective use and fusion of features, and continuously optimize the network training to achieve a fine segmentation of the lesion area, and demonstrate the accuracy and feasibility of the two models in medical image segmentation. Histopathology was used to obtain ER, PR, HER scores, and Ki-67 percentage values for all patients. The Kaplan-Meier method was used for survival estimation, the Log-rank test was used for single-factor analysis, and Cox proportional risk regression was used for multifactor analysis. The prognostic value of each factor was calculated, as well as the factors affecting progression-free survival. This study was done to compare the imaging characteristics and diagnostic value of mammography and colour Doppler ultrasonography in nonspecific mastitis, improve the understanding of the imaging characteristics of nonspecific mastitis in these two examinations, improve the accuracy of the diagnosis of this type of disease, improve the ability of distinguishing it from breast cancer, and reduce the rate of misdiagnosis.

Screening mammography reduces breast cancer mortality; however, when used to examine women with dense breasts, its performance and resulting benefits are reduced. Increased breast density is an independent risk factor for breast cancer. Digital breast tomosynthesis (DBT), ultrasound (US), molecular breast imaging (MBI), MRI, and contrast-enhanced mammography (CEM) each have shown improved cancer detection in dense breasts when compared with 2D digital mammography (DM). DBT is the preferred mammographic technique for producing a simultaneous reduction in recalls (i.e., additional imaging). US further increases cancer detection after DM or DBT and reduces interval cancers (cancers detected in the interval between recommended screening examinations), but it also produces substantial additional false-positive findings. MBI improves cancer detection with an effective radiation dose that is approximately fourfold that of DM or DBT but is still within accepted limits. MRI provides the greatest increase in cancer detection and reduces interval cancers and late-stage disease; abbreviated techniques will reduce cost and improve availability. CEM appears to offer performance similar to that of MRI, but further validation is needed. Dense breast notification will soon be a national standard; therefore, understanding the performance of mammography and supplemental modalities is necessary to optimize screening for women with dense breasts.

Background Among breast cancer survivors, detecting a breast cancer when it is asymptomatic (rather than symptomatic) improves survival; thus, imaging surveillance in these patients is warranted. Digital breast tomosynthesis (DBT) is used for screening, but data on DBT for surveillance in this high-risk population are limited. Purpose To determine whether DBT leads to improved screening performance metrics when compared with two-dimensional digital mammography among breast cancer survivors. Materials and Methods In this study, screening mammograms obtained in breast cancer survivors before and after DBT implementation were retrospectively reviewed (March 2008-February 2011 for the digital mammography group; January 2013-December 2017 for the DBT group). Mammograms were interpreted by breast imaging radiologists with the assistance of computer-aided detection. Performance metrics and tumor characteristics between the groups were compared using multivariable logistic regression models. Results The digital mammography and DBT groups were composed of 9019 and 22 887 mammographic examinations, respectively, in 8170 women (mean age, 62 years ± 12 [standard deviation]). In the DBT group, the abnormal interpretation rate was lower (5.8% [1331 of 22 887 examinations] vs 6.2% [563 of 9019 examinations]; odds ratio [OR], 0.80; 95% CI: 0.71, 0.91

Background Mammography has been the mainstay for the detection of breast cancer over decades. It has gradually advanced from screen film to full-field digital mammography. Tomosynthesis has evolved as advanced imaging for early diagnosis of breast lesions with a promising role in both diagnostic and screening settings, particularly in dense and treated breasts. Results This study included 90 female patients according to our inclusion criteria. All patients perform full-field digital mammography (FFDM) and digital breast tomosynthesis (DBT) and were classified according to breast density and age groups. Breast imaging reporting and data system (BI-RADS) scoring was assigned for each case. This was correlated with the final diagnosis; the diagnostic indices of mammography were a sensitivity of 64.44%, a specificity of 77.78%, a positive predictive value (PPV) 74.63%, a negative predictive value (NPV) of 68.63%, and a diagnostic accuracy of 71.11%. Diagnostic indices of DBT were a sensitivity of 100%, a specificity of 97.77%, PPV 97.78%, NPV 100%, and diagnostic accuracy of 97.7%. In patients with dense breasts American College of Radiology (ACR) (c and d), 61% of cases had changed their BIRADS scoring with the addition of tomosynthesis. Yet, in non-dense breast ACR (a and b), 45% of cases had changed BIRADS scoring with the addition of DBT to FFDM. Conclusion DBT is a promising imaging modality offering better detection and characterization of different breast abnormalities, especially in young females, and those with dense breasts with an increase of sensitivity and specificity than FFDM. This leads to a reduction in the recalled cases, negative biopsies, and assessing the efficacy of therapy as it enables improving detection of breast cancer and different breast lesions not visualized by conventional mammography

Background: Dual-energy contrast-enhanced spectral mammography (CESM) is one of the latest methods for breast lesions characterization, where structural and functional (i.e., vascularization) assessment are combined. Nowadays an interpretation of contrast-enhanced images is based only on the degree of contrast enhancement, but we propose a more detailed assessment of the structure of the hypervascular lesions by highlighting the contrast enhancement patterns. Purpose: To evaluate the diagnostic performance of contrast-enhanced spectral mammography (CESM) using the contrast enhancement patterns in malignant and benign lesions. Material and Methods: Study included 332 women examined from February 2018 to June 2020. The mean age of the women was 50 years. Of 428 lesions totally revealed, 172 (40.2%) were histologically verified as malignant and 256 (59.8%) as benign. We proposed 9 types of contrast enhancement patterns to describe lesions: reticular, granular, annular, diffuse-spherical, lacunar, cloud-like, heterogeneous-annular, point, cotton-like. Results: We showed that diagnostic performance of CESM increased sensitivity if an additional diagnostic feature of contrast enhancement pattern was used: sensitivity increased from 79.7% to 94.8% (p = 0.26), specificity from 82.4% to 95.3% (p = 0.013) and accuracy from 81.3 to 95.1% (p = 0.004), in comparison with using of only one feature of contrast enhancement intensity in the differential diagnosis of malignant and benign lesions. Conclusion: Thus, using contrast enhancement pattern allows to increase the efficiency of CESM in breast cancer detection.

To investigate the value of full-field digital mammography-based deep learning (DL) in predicting malignancy of Breast Imaging Reporting and Data System (BI-RADS) 4 microcalcifications. A total of 384 patients with 414 pathologically confirmed microcalcifications (221 malignant and 193 benign) were randomly allocated into the training, validation, and testing datasets (272/71/71 lesions) in this retrospective study. A combined DL model was developed incorporating mammography and clinical variables. Model performance was evaluated by using areas under the receiver operating characteristic curve (AUC) and compared with the clinical model, stand-alone DL image model, and BI-RADS approach. The predictive performance for malignancy was also compared between the combined model and human readers (2 juniors and 2 seniors). The combined DL model demonstrated favorable AUC, sensitivity, and specificity of 0.910, 85.3%, and 91.9% in predicting BI-RADS 4 malignant microcalcifications in the testing dataset, which outperformed the clinical model, DL image model, and BI-RADS with AUCs of 0.799, 0.841, and 0.804, respectively. The combined model achieved non-inferior performance as senior radiologists (p = 0.860, p = 0.800) and outperformed junior radiologists (p = 0.155, p = 0.029). The diagnostic performance of two junior radiologists was improved after artificial intelligence assistance with AUCs increased to 0.854 and 0.901 from 0.816 (p = 0.556) and 0.773 (p = 0.046), while the interobserver agreement was improved with a kappa value increased to 0.843 from 0.331. The combined deep learning model can improve the malignancy prediction of BI-RADS 4 microcalcifications in screening mammography and assist junior radiologists to achieve better performance, which can facilitate clinical decision-making. • The combined deep learning model demonstrated high diagnostic power, sensitivity, and specificity for predicting malignant BI-RADS 4 mammographic microcalcifications. • The combined model achieved similar performance with senior breast radiologists, while it outperformed junior breast radiologists. • Deep learning could improve the diagnostic performance of junior radiologists and facilitate clinical decision-making.

Objective The aim: Comparing sensitivity and specificity of digital breast tomosynthesis and full-field digital mammography in breast cancer detection associated with four different types of asymmetries according to BI-RADS Atlas. Patients and methods Materials and methods: Study included 201 patients with four types of asymmetries according BI-RADS atlas (asymmetry - 81 (40,3%), focal asymmetry - 82 (40,8%), global asymmetry - 36 (17,9%) and developing asymmetry - 2 (1,0%)) who underwent full-field digital mammography, digital breast tomosynthesis and hand-held full breast ultrasound from January 2017 to June 2018. The general rate of breast cancer for the 201 patients with asymmetries was 8 cases (4,0%) (IBC, n=6 (3,0%); DCIS, n=2 (1,0%) other findings associated with asymmetries were non-malignant, n=10 (5,0%) (sclerosing adenosis, n=5 (2,5%); fibroadenomatosis, n=3 (1,5%); simple cyst, n=1 (0,5%); radial scar associated with papilloma, typical ductal hyperplasia and sclerosing adenosis, n=1 (0,5%). Results Results: Analysis of the results showed that sensitivity of digital breast tomosynthesis was 75.0% [95% CI, 34.91% to 96.81%] and specificity was 94.8% [95% CI, 90.68% to 97.49%] which was superior to full-field digital mammography sensitivity 50.0% [95% CI, 15.70% to 84.30%] and specificity 91.19% [95% CI, 86.27% to 94.78%] for breast cancer detection associated with different types of asymmetries. Conclusion Conclusions: Using of digital breast tomosynthesis in assessment of breast asymmetries can improve sensitivity and specificity in breast cancer detection and reduce number of unnecessary biopsies and short-interval follow-up examinations.

Objective The aim: The aim of our study was to determine if digital breast tomosynthesis improves breast cancer detection associated with architectural distortion in comparison with full-field digital mammography in the absence of appropriate history of trauma or surgery. Patients and methods Materials and methods: The overall rate of breast cancer involvement for the 34 patients with architectural distortion was 15 cases (44,1%) (invasive breast cancers, n=12 (36,4%); ductal cancer in situ, n= 3 (8,8%)) other findings associated with architectural distortion were high-risk lesions and benign findings (radial scar, n=5 (14,7%); sclerosing adenosis, n=9 (26,5%); typical lobular hyperplasia, n=3 (8,8%); typical ductal hyperplasia, n=2 cases (5,9%)). Results Results: Overall of 17/34 (50.0%) architectural distortions were identified at digital breast tomosynthesis that were missed at full-field digital mammography what was statistically significant difference ([95% CI, 2.56-7.45]; p=0.00001). Analysis of the results showed that sensitivity of full-field digital mammography for digital breast tomosynthesis detected breast cancers associated with architectural distortion was 53.3% [95% CI, 26.59% to 78.73%] and specificity was 52.63% [95% CI, 28.86% to 75.55%]. Conclusion Conclusions: Our study suggests that digital breast tomosynthesis detects more breast cancers represented as architectural distortion which are occult on full-field digital mammography. Presence of microcalcifications within architectural distortion, in the absence of appropriate history of trauma or surgery, has a high likelihood of malignancy and obligatorily requires biopsy.

Purpose Breast cancer is the most common cause of death from neoplastic disease in women. Among all breast anatomy types, glandular type is the most problematic concerning evaluation. While digital mammography still remains the basic diagnostic tool, one must be aware of its limitations in dense breasts. Although magnetic resonance imaging (MRI) has greatly improved sensitivity, its specificity is low. Moreover, there are contraindications for MRI for some patients, so a substitute has been searched for. This study was performed to check if contrast-enhanced spectral mammography (CESM) can be a viable option for patients with dense breasts. Material and methods The study involved 121 patients with abnormalities detected on base-line diagnostic imaging (ultrasound or mammography). The patients had subsequent examinations, both CESM and MRI performed within a maximum 2-month time interval. The sensitivity and specificity of both methods in the whole group as well as in specific breast structure types were measured and compared. Results Contrast enhancement was visible in all 121 cases on MRI, while on CESM lack of enhancement was noted in 13 cases. All of those 13 lesions turned out to be benign. There were 40 (33%) benign and 81 (69%) malignant tumours. The analysed group included 53 (44%) glandular type breast patients, 39 (32%) mixed type, and 29 (23%) fatty type. Although MRI proved to be slightly more effective in dense breasts, both methods showed similar results in the whole study group. Conclusion CESM can be used with confidence in patients with glandular breast type when MRI is not available or there are reported contraindications to MRI.

Background Few results are available about subsequent outcomes after screening with digital breast tomosynthesis (DBT). Purpose To compare the diagnostic accuracy of a screening round with DBT plus synthetic mammography (SM) (hereafter, DBT+SM) and the repeat screening round with DBT with SM (hereafter, DBT+SM) or full-field digital mammography (FFDM) with FFDM screening. Materials and Methods This prospective study (Verona Pilot Study, clinical trial identification: 2015/1238) included women screened with DBT+SM between April 2015 and March 2017 and rescreened with DBT+SM or FFDM between April 2017 and March 2019. Screening performance (recall rate, cancer detection rate [CDR], and positive predictive value of recall [PPV1]) was compared with that obtained from 28 680 women screened with FFDM between 2013 and 2014 (control group). Cancer stages were compared between modalities and screening rounds. A χ

Background Our objective was to perform a systematic review and meta-analysis comparing the breast cancer detection rate (CDR), invasive CDR, recall rate, and positive predictive value 1 (PPV1) of digital mammography (DM) alone, combined digital breast tomosynthesis (DBT) and DM, combined DBT and synthetic 2-dimensional mammography (S2D), and DBT alone. Methods MEDLINE and Embase were searched until April 2020 to identify comparative design studies reporting on patients undergoing routine breast cancer screening. Random effects model proportional meta-analyses estimated CDR, invasive CDR, recall rate, and PPV1. Meta-regression modeling was used to compare imaging modalities. All statistical tests were 2-sided. Results Forty-two studies reporting on 2 606 296 patients (13 003 breast cancer cases) were included. CDR was highest in combined DBT and DM (6.36 per 1000 screened, 95% confidence interval [CI] = 5.62 to 7.14, P Conclusions Our findings provide evidence on key performance metrics for DM, DBT alone, combined DBT and DM, and combined DBT and S2D, which may inform optimal application of these modalities for breast cancer screening.

Architectural distortion (AD) is the earliest sign of breast cancer that can be detected on a mammogram, and it is usually associated with malignant tumors. Breast cancer is one of the major causes of death among women, and the chance of cure can increase significantly when detected early. Computer-aided detection (CAD) systems have been used in clinical practice to assist radiologists with the task of detecting breast lesions. However, due to the complexity and subtlety of AD, its detection is still a challenge, even with the assistance of CAD. Recently, the fusion of descriptors has become a trend for improving the performance of computer vision algorithms. In this work, we evaluated some local texture descriptors and their possible combinations, considering different fusion approaches, for application in CAD systems to improve AD detection. In addition, we present a novel fusion-based texture descriptor, the Completed Mean Local Mapped Pattern (CMLMP), which is based on complementary information between three LMP operators (signal, magnitude and center) and the local differences between pixel values and the mean value of a neighborhood. We compared the performance of the proposed descriptor with two other well-known descriptors: the Completed Local Binary Pattern (CLBP) and the Completed Local Mapped Pattern (CLMP), for the task of detecting AD in 350 digital mammography clinical images. The results showed that the descriptor proposed in this work outperforms the others, for both individual and fused approaches. Moreover, the choice of the fusion operator is crucial because it results in different detection performances.

The purpose of this study is to confirm the position of DBT in breast cancer screening in Japan, to assess cancer detection rates, recall rates, positive predictive value (PPV), and to evaluate the type of mammographic findings of cancer with the use of digital mammography alone (2DDM) and combined with digital breast tomosynthesis (DBT). 11,894 examinations of the opportunistic breast cancer screening using only 2DDM and 2DDM plus DBT were performed from May 1, 2017 to March 31, 2019. The 11,894 women [3535 women who received DBT in addition to 2DDM (3D group) and 8359 who received 2DDM only (2D group)] participated in this study. The study was approved by the Institute's Ethics Committee and all participants provided written informed consent. The recall rate was 2.6% for the 3D group and 3.6% for the 2D group (p

OBJECTIVE To determine the variability of breast density assessment and the need for additional imaging using computed radiography (CR) mammography versus digital radiography (DR) mammography. STUDY DESIGN Cohort study. PLACE AND DURATION OF STUDY Department of Radiology, The Aga Khan University Hospital, Karachi from March to June 2018. METHODOLOGY Patients who underwent screening CR mammography, followed by DR mammography a year later, were selected. Only disease-free individuals were included in the study. Evaluation of breast density was done subjectively, using the breast imaging reporting and data system (BI-RADS) by two independent experienced radiologists. Statistical analysis was performed using the Wilcox Signed Rank-sum test to compare both modalities. Fisher Exact method was used to compare the need for ultrasound imaging. Results: A total of 295 patients were included in the study. The mean age of the patients was 52.76 ± 0.64 years. There was a significant difference in the change of breast density when comparing both modalities (Z= -11.839, p

Incidence of interval cancers is an important outcome in assessing efficacy of screening. Our primary objective was to compare the incidence of interval cancers detected with two-dimensional digital mammography (DM) versus digital breast tomosynthesis (DBT) in a large community health system. Our secondary objectives were to compare the patient and tumor characteristics of interval cancers, cancer detection rate, and recall rate. Interval cancers before and after implementation of DBT (2012-2014 DM group; 2016-2018 DBT group) were reviewed. Patient factors (age, race, breast density, personal history of breast cancer, family history of breast cancer, known BRCA-1 or BRCA-2 genetic mutation, baseline mammogram, and presentation) and tumor characteristics (in situ versus invasive, grade, size, hormone receptor status, and nodal status) were compared with the chi-squared test or the MidP exact test. Rates (detection and recall) were compared using a z-score. The rates of interval cancers with DM (0.30 per 1000 [35/117 099]) and DBT (0.33 per 1000 [40/119 746]) were similar (P = .3). Proportion of node-positive interval cancers was lower in the DBT group (22.9% [8/35] vs 48% [15/31], p.01). Otherwise, the patient and tumor characteristics were similar. The cancer detection rate increased (5.9 per 1000 [709/119 746] vs 3.5 per 1000 [411/117 099], P = .0001), and the recall rate decreased with DBT (8.6% [10 347/119 746] versus 10.7% [12 508/117 099], (P < .0001). Although the cancer detection rate was higher with DBT, the rate of interval breast cancers was similar in both groups. Node-positive invasive interval cancers were decreased with DBT.

Objective To perform a radiological review of mammograms from prior screening and diagnosis of screen-detected breast cancer in BreastScreen Norway, a population-based screening program. Methods We performed a consensus-based informed review of mammograms from prior screening and diagnosis for screen-detected breast cancers. Mammographic density and findings on screening and diagnostic mammograms were classified according to the Breast Imaging-Reporting and Data System®. Cases were classified based on visible findings on prior screening mammograms as true (no findings), missed (obvious findings), minimal signs (minor/non-specific findings), or occult (no findings at diagnosis). Histopathologic tumor characteristics were extracted from the Cancer Registry of Norway. The Bonferroni correction was used to adjust for multiple testing; p Results The study included mammograms for 1225 women with screen-detected breast cancer. Mean age was 62 years ± 5 (SD); 46% (567/1225) were classified as true, 22% (266/1225) as missed, and 32% (392/1225) as minimal signs. No difference in mammographic density was observed between the classification categories. At diagnosis, 59% (336/567) of true and 70% (185/266) of missed cancers were classified as masses (p = 0.004). The percentage of histological grade 3 cancers was higher for true (30% (138/469)) than for missed (14% (33/234)) cancers (p < 0.001). Estrogen receptor positivity was observed in 86% (387/469) of true and 95% (215/234) of missed (p < 0.001) cancers. Conclusions We classified 22% of the screen-detected cancers as missed based on a review of prior screening mammograms with diagnostic images available. One main goal of the study was quality improvement of radiologists’ performance and the program. Visible findings on prior screening mammograms were not necessarily indicative of screening failure. Key Points • After a consensus-based informed review, 46% of screen-detected breast cancers were classified as true, 22% as missed, and 32% as minimal signs. • Less favorable prognostic and predictive tumor characteristics were observed in true screen-detected breast cancer compared with missed. • The most frequent mammographic finding for all classification categories at the time of diagnosis was mass, while the most frequent mammographic finding on prior screening mammograms was a mass for missed cancers and asymmetry for minimal signs.

Objectives To evaluate if artificial intelligence (AI) can discriminate recalled benign from recalled malignant mammographic screening abnormalities to improve screening performance. Methods A total of 2257 full-field digital mammography screening examinations, obtained 2011–2013, of women aged 50–69 years which were recalled for further assessment of 295 malignant out of 305 truly malignant lesions and 2289 benign lesions after independent double-reading with arbitration, were included in this retrospective study. A deep learning AI system was used to obtain a score (0–95) for each recalled lesion, representing the likelihood of breast cancer. The sensitivity on the lesion level and the proportion of women without false-positive ratings (non-FPR) resulting under AI were estimated as a function of the classification cutoff and compared to that of human readers. Results Using a cutoff of 1, AI decreased the proportion of women with false-positives from 89.9 to 62.0%, non-FPR 11.1% vs. 38.0% (difference 26.9%, 95% confidence interval 25.1–28.8%; p < .001), preventing 30.1% of reader-induced false-positive recalls, while reducing sensitivity from 96.7 to 91.1% (5.6%, 3.1–8.0%) as compared to human reading. The positive predictive value of recall (PPV-1) increased from 12.8 to 16.5% (3.7%, 3.5–4.0%). In women with mass-related lesions (n = 900), the non-FPR was 14.2% for humans vs. 36.7% for AI (22.4%, 19.8–25.3%) at a sensitivity of 98.5% vs. 97.1% (1.5%, 0–3.5%). Conclusion The application of AI during consensus conference might especially help readers to reduce false-positive recalls of masses at the expense of a small sensitivity reduction. Prospective studies are needed to further evaluate the screening benefit of AI in practice. Key Points • Integrating the use of artificial intelligence in the arbitration process reduces benign recalls and increases the positive predictive value of recall at the expense of some sensitivity loss. • Application of the artificial intelligence system to aid the decision to recall a woman seems particularly beneficial for masses, where the system reaches comparable sensitivity to that of the readers, but with considerably reduced false-positives. • About one-fourth of all recalled malignant lesions are not automatically marked by the system such that their evaluation (AI score) must be retrieved manually by the reader. A thorough reading of screening mammograms by readers to identify suspicious lesions therefore remains mandatory.

Background The low subject contrast between cancerous and fibroglandular tissue could obscure breast abnormalities. Purpose To investigate radiologists’ performance for detection of breast cancer in low and high mammographic density (MD) when cases are digitally acquired. Material and Methods A test set of 60 digital mammography cases, of which 20 were cancerous, were examined by 17 radiologists. Mammograms were categorized as low (≤50%) or high (>50%) MD and rated for suspicion of malignancy using the Royal Australian and New Zealand College of Radiology (RANZCR) classification system. Radiologist demographics including cases read per year, age, subspecialty, and years of reporting were recorded. Radiologist performance was analyzed by the following metrics: sensitivity; specificity; area under the receiver operating characteristic (ROC) curve (AUC), location sensitivity, and jackknife free-response ROC (JAFROC) figure of merit (FOM). Results Comparing high to low MD cases, radiologists showed a significantly higher sensitivity ( P = 0.015), AUC ( P = 0.003), location sensitivity ( P = 0.002), and JAFROC FOM ( P = 0.001). In high compared to low MD cases, radiologists with Conclusion In this experimental situation, radiologists’ performance was higher when reading cases with high compared to low MD. Experienced radiologists were able to precisely localize lesions in breasts with higher MD. Further studies in unselected screening materials are needed to verify the results.

Introduction To investigate compliance to the ‘30% rule’ and key factors which may influence visualisation of the pectoralis major muscle (PMM) on the craniocaudal (CC) view of the breast. Methods A retrospective review of 2688 paired full‐field digital mammography (FFDM) CC view mammograms of women attending BreastScreen NSW between August and October 2015 was undertaken. PMM visualisation and measurements of PMM width and length, compressed breast thickness, the posterior nipple line (PNL) and age were recorded. Statistical analysis was performed using descriptive and inferential statistics to investigate associations between key breast measurements, age and PMM visualisation. Results PMM visualisation was reported in 10.4% of images unilaterally (one breast, left or right only), 14.1% bilaterally (both left and right breasts) and 24.5% overall (unilateral and bilateral combined). There was little or no correlations between PMM length or width and age, breast compressed thickness or PNL. Multiple logistic regression analysis found that up to 15% of the variance in visualisation of the PMM was accounted for by the predictors overall. While some predictors provided a statistically significant contribution to the model, the contribution was small and the odds ratio for all predictors approximated 1. Conclusion This research could not replicate the ‘30% rule’, and visualisation of the PMM was determined not to be influenced by the variables investigated. The significance of the ‘rule’ itself must be challenged where the vast majority of images (70–85%) do not comply, and there is no requirement for repeat imaging if the ‘rule’ is not met. Further research should be undertaken to validate this study including analysis of diagnostic images for comparison., The ‘30% rule’ was first documented 27 years ago, in the film screen era, by Bassett et al., establishing that the pectoralis major muscle (PMM) was able to be visualised in 32% of craniocaudal breast images. Subsequently, a wide range of visualisation rates (11–48%) has been cited. This study reports that the ‘30% rule’ is not being achieved in the Australian digital screening setting. The overall visualisation rate of the PMM was 24.5% with only 14.1% of images depicting the PMM bilaterally. No significant associations between PMM visualisation and age, compressed breast thickness or breast size were identified.

Introduction There are increasing concerns about radiation exposure among women who undergo full‐field digital mammography (FFDM) and digital breast tomosynthesis (DBT). The main aim of this study was to compare the entrance surface dose (ESD) and average glandular dose (AGD) from FFDM and DBT for different breast thicknesses. Methods The ESD and AGD for FFDM in craniocaudal, mediolateral oblique and DBT in craniocaudal projection were recorded from a GE Senographe Essential FFDM unit. The accuracy of the ESD and AGD from the FFDM unit was verified during regular quality assurance programme. Patients were categorised according to their compressed breast thicknesses. X‐ray tube potential and target filter combinations were varied with ESD and AGD recorded directly from the FFDM unit. The non‐parametric Kruskal–Wallis, Mann–Whitney and Wilcoxon signed‐rank tests were performed. Results The median and interquartile range (IQR) age of the patients were 48 and 11 years, respectively. The highest median for ESD and median total AGD for different breast thicknesses were ranged from 3.3 to 9.1 mGy and 3.3 to 6.0 mGy, respectively, for two‐view FFDM. However, it ranged from 3.1 to 8.9 mGy and 1.8 to 4.0 mGy, respectively, for single‐view DBT. Both ESD and AGD were significantly lower for DBT (P, There are some concerns about increasing the radiation dose among women undergoing both full‐field digital mammography (FFDM) and digital breast tomosynthesis (DBT). In our study, we found that the entrance skin dose (ESD) and total average glandular dose (AGD) are lower in DBT than FFDM techniques. This offers opportunities for the implementation of DBT in the breast cancer detection.

Breast cancer is the most frequent in females. Mammography has proven to be the most effective method for the early detection of this type of cancer. Mammographic images are sometimes difficult to understand, due to the nature of the anomalies, the low contrast image and the composition of the mammary tissues, as well as various technological factors such as spatial resolution of the image or noise. Computer-aided diagnostic systems have been developed to increase the accuracy of mammographic examinations and be used by physicians as a second opinion in obtaining the final diagnosis, and thus reduce human errors. Convolutional neural networks are a current trend in computer vision tasks, due to the great performance they have achieved. The present investigation was based on this type of networks to classify into three classes, normal, benign and malignant tumour. Due to the fact that the miniMIAS database used has a low number of images, the transfer learning technique was applied to the Inception v3 pre-trained network. Two convolutional neural network architectures were implemented, obtaining in the architecture with three classes, 86.05% accuracy. On the other hand, in the architecture with two neural networks in series, an accuracy of 88.2% was reached.

Objectives The aim of this feasibility study was to evaluate the added value of contrast-enhanced mammography (CEM) in preoperative staging of malignant breast lesions, beyond standard assessment with digital mammography and ultrasound, as a base for a future prospective randomized trial. Materials and methods Forty-seven patients, with confirmed or strongly suspected malignant breast lesions after standard assessment (digital mammography (DM) and ultrasound (US)), scheduled for primary surgery, were invited to undergo CEM as an additional preoperative procedure. The primary endpoint was change in treatment due to CEM findings, defined as mastectomy instead of partial mastectomy or contrariwise, bilateral surgery instead of unilateral or neoadjuvant treatment instead of primary surgery. Accuracy in tumour extent estimation compared to histopathology was evaluated by Bland-Altman statistics. Number of extra biopsies and adverse events were recorded. Results In 10/47 patients (21%), findings from CEM affected the primary treatment. Agreement with histopathology regarding extent estimation was better for CEM (mean difference − 1.36, SD ± 18.45) in comparison with DM (− 4.18, SD ± 26.20) and US (− 8.36, SD ± 24.30). Additional biopsies were taken from 19 lesions in 13 patients. Nine biopsies showed malignant outcome. No major adverse events occurred. Conclusion The feasibility of preoperative additional CEM was found to be satisfactory without any serious negative effects. Results imply an added value of CEM in preoperative staging of breast cancer. Further evaluation in larger prospective randomized trials is needed. Trial registration ClinicalTrials.gov, NCT03402529. Registered 18 January 2018—retrospectively registered