Mammographic Interpretation Research Articles

Mammography self-evaluation online test for screening readers: an Italian Society of Medical Radiology (SIRM) initiative.

To report and analyse the characteristics and performance of the first cohort of Italian radiologists completing the national mammography self-evaluation online test established by the Italian Society of Medical Radiology (SIRM). A specifically-built dataset of 132 mammograms (24 with screen-detected cancers and 108 negative cases) was preliminarily tested on 48 radiologists to define pass thresholds (62% sensitivity and 86% specificity) and subsequently made available online to SIRM members during a 13-month timeframe between 2018 and 2019. Associations between participants' characteristics, pass rates, and diagnostic accuracy were then investigated with descriptive statistics and univariate and multivariable regression analyses. A total of 342 radiologists completed the test, 151/342 (44.2%) with success. All individual variables, except gender, showed a significant correlation with pass rates and diagnostic sensitivity, confirmed by univariate logistic regression, while only involvement in organised screening programs and number of mammograms read per year showed a positive association with specificity at univariate logistic regression. In the multivariable regression analysis, fewer variables remained significant: > 3000 mammograms read per year for success rate; female gender, public practice setting, and higher experience self-judgement for sensitivity; no variables were significantly associated with specificity. This national self-evaluation test effectively differentiated multiple aspects of mammographic reading experience, but specific breast imaging experience was shown not to strictly guarantee good diagnostic accuracy. Due to its easy use and the validity of obtained results, this test could be extended to all Italian breast radiologists, regardless of their experience, also as a Breast Unit accreditation criterion. • This self-evaluation test was found to be able to differentiate various degrees of mammographic interpretation experience. • Breast cancer screening readers should undergo a self-assessment test, since experience parameters alone do not guarantee diagnostic ability.

Comparison of diagnostic performances in the evaluation of breast microcalcifications: synthetic mammography versus full-field digital mammography.

Although several studies proved that SM could substitute for FFDM, the efficacy of SM in microcalcification evaluation remains controversial. To investigate the diagnostic performance of synthetic mammography (SM) in the evaluation of microcalcifications in comparison with full-field digital mammography (FFDM). In this retrospective study, 76 mammograms of 76 patients who underwent FFDM and digital breast tomosynthesis (DBT) acquisitions concomitantly between 2018 and 2019 and whose final mammography interpretation revealed microcalcifications (28 malignant microcalcifications and 48 benign microcalcifications) were included. All mammograms were reviewed independently by three radiologists with different levels of breast imaging experience. Readers were blinded to patient outcomes and interpreted each case in two separate reading sessions (first FFDM, second SM + DBT), according to the BI-RADS lexicon. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated using ROC analysis in all cases for FFDM and SM + DBT sessions. The readers also assigned conspicuity scores to mammograms. The interobserver agreement was calculated using intraclass correlation coefficients (ICC). The overall AUCs for malignant microcalcifications were 0.80 (95% CI: 0.75-0.85) in FFDM and 0.85 (95% CI: 0.80-0.89) in SM, and no significant difference was found between the groups (p = 0.0603). The sensitivity of the readers increased slightly with experience. The ICC values of BI-RADS categorization between readers were 0.93 (95% CI: 0.90-0.95) and 0.94 (95% CI: 0.91-0.96) for FFDM and SM, respectively. SM had similar diagnostic performance in the evaluation of breast microcalcifications in comparison with FFDM, regardless of reader experience levels.

Radiologist Characteristics Associated with Interpretive Performance of Screening Mammography: A National Mammography Database (NMD) Study.

Background Factors affecting radiologists' performance in screening mammography interpretation remain poorly understood. Purpose To identify radiologists characteristics that affect screening mammography interpretation performance. Materials and Methods This retrospective study included 1223 radiologists in the National Mammography Database (NMD) from 2008 to 2019 who could be linked to Centers for Medicare & Medicaid Services (CMS) datasets. NMD screening performance metrics were extracted. Acceptable ranges were defined as follows: recall rate (RR) between 5% and 12%; cancer detection rate (CDR) of at least 2.5 per 1000 screening examinations; positive predictive value of recall (PPV1) between 3% and 8%; positive predictive value of biopsies recommended (PPV2) between 20% and 40%; positive predictive value of biopsies performed (PPV3) between the 25th and 75th percentile of study sample; invasive CDR of at least the 25th percentile of the study sample; and percentage of ductal carcinoma in situ (DCIS) of at least the 25th percentile of the study sample. Radiologist characteristics extracted from CMS datasets included demographics, subspecialization, and clinical practice patterns. Multivariable stepwise logistic regression models were performed to identify characteristics independently associated with acceptable performance for the seven metrics. The most influential characteristics were defined as those independently associated with the majority of the metrics (at least four). Results Relative to radiologists practicing in the Northeast, those in the Midwest were more likely to achieve acceptable RR, PPV1, PPV2, and CDR (odds ratio [OR], 1.4-2.5); those practicing in the West were more likely to achieve acceptable RR, PPV2, and PPV3 (OR, 1.7-2.1) but less likely to achieve acceptable invasive CDR (OR, 0.6). Relative to general radiologists, breast imagers were more likely to achieve acceptable PPV1, invasive CDR, percentage DCIS, and CDR (OR, 1.4-4.4). Those performing diagnostic mammography were more likely to achieve acceptable PPV1, PPV2, PPV3, invasive CDR, and CDR (OR, 1.9-2.9). Those performing breast US were less likely to achieve acceptable PPV1, PPV2, percentage DCIS, and CDR (OR, 0.5-0.7). Conclusion The geographic location of the radiology practice, subspecialization in breast imaging, and performance of diagnostic mammography are associated with better screening mammography performance; performance of breast US is associated with lower performance. ©RSNA, 2021 Online supplemental material is available for this article.

Act Like a Radiologist: Towards Reliable Multi-View Correspondence Reasoning for Mammogram Mass Detection.

Mammogram mass detection is crucial for diagnosing and preventing the breast cancers in clinical practice. The complementary effect of multi-view mammogram images provides valuable information about the breast anatomical prior structure and is of great significance in digital mammography interpretation. However, unlike radiologists who can utilize the natural reasoning ability to identify masses based on multiple mammographic views, how to endow the existing object detection models with the capability of multi-view reasoning is vital for decision-making in clinical diagnosis but remains the boundary to explore. In this paper, we propose an anatomy-aware graph convolutional network (AGN), which is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability. The proposed AGN consists of three steps. First, we introduce a bipartite graph convolutional network (BGN) to model the intrinsic geometric and semantic relations of ipsilateral views. Second, considering that the visual asymmetry of bilateral views is widely adopted in clinical practice to assist the diagnosis of breast lesions, we propose an inception graph convolutional network (IGN) to model the structural similarities of bilateral views. Finally, based on the constructed graphs, the multi-view information is propagated through nodes methodically, which equips the features learned from the examined view with multi-view reasoning ability. Experiments on two standard benchmarks reveal that AGN significantly exceeds the state-of-the-art performance. Visualization results show that AGN provides interpretable visual cues for clinical diagnosis.

The influence of breast density and key demographics of radiographers on mammography reporting performance - a pilot study.

IntroductionA high demand has been placed on radiologists to perform screen reads due to higher number of women undergoing mammography. This study aims to examine radiographer performance in reporting low compared with high‐mammographic density (MD) images; and to assess the influence of key demographics of Jordanian radiographers on their performance.MethodsThirty mammograms with varied MD were reported by 12 radiographers using the Breast Imaging‐Reporting and Data System (BI‐RADS). Radiographer performance was measured using sensitivity, specificity, positive (PPV) and negative predictive values (NPV), and area under the receiver operating characteristic curve (ROC AUC). Performance measures were compared between cases with low‐ and high‐MD and between subgroups of radiographers according to key demographics.ResultsAll performance measures were significantly higher in low‐ compared to high‐MD cases (P value < 0.0). The mean sensitivity, specificity, PPV, NPV and ROC AUC were 0.58, 0.68, 0.67, 0.63 and 0.69 respectively. PPV was significantly different for readers who had different years of experience in mammography, hours and cases per week P value = 0.023, 0.01, 0.017 respectively. ROC AUC was significantly different for radiographers with different number of hours and cases performed per week (P value = 0.001 and 0.004 respectively).ConclusionsThe results of this pilot study are encouraging however a more extensive study is required to determine if Jordanian radiographers are capable of successfully taking part in breast screen reading. The lack of skills and knowledge required for correct and consistent reporting of high‐MD images highlights the need for any formal training in mammographic interpretation to focus on the dense breast.

Deep learning algorithm performance in mammography screening: A systematic review and meta-analysis.

e13553 Background: Mammography interpretation presents some challenges however, better technological approaches have allowed increased accuracy in cancer diagnosis and nowadays, radiologists sensitivity and specificity for mammography screening vary from 84.5 to 90.6 and 89.7 to 92.0%, respectively. Since its introduction in breast image analysis, artificial intelligence (AI) has rapidly improved and deep learning methods are gaining relevance as a companion tool to radiologists. Thus, the aim of this systematic review and meta analysis was to evaluate the sensitivity and specificity of AI deep learning algorithms and radiologists for breast cancer detection through mammography. Methods: A systematic review was performed using PubMed and the words: deep learning or convolutional neural network and mammography or mammogram, from January 2015 to October 2020. All titles and abstracts were doubly checked; duplicate studies and studies in languages other than English were excluded. The remaining complete studies were doubly assessed and those with specificity and sensibility information had data collected. For the meta analysis, studies reporting specificity, sensitivity and confidence intervals were selected. Heterogeneity measures were calculated using Cochran Q test (chi-square test) and the I2 (percentage of variation). Sensitivity and specificity and 95% confidence intervals (CI) values were calculated, using Stata/MP 14.0 for Windows. Results: Among 223 studies, 66 were selected for full paper analysis and 24 were selected for data extraction. Subsequently, only papers evaluating sensitivity, especificity, CI and/or AUC were analyzed. Eleven studies compared AUC using AI with another method and for these studies, a differential AUC was calculated, however no differences were observed: AI vs Reader (n = 3; p = 0.109); AI vs AI (n = 5; p = 0.225); AI vs AI + reader (n = 2; p = 0.180); AI + Reader vs reader (n = 2; p = 0.655); AI vs reader (n &gt; 1) (n = 3; p = 0.102). Some studies had more than one comparison. A meta analysis was performed to evaluate sensitivity and specificity of the methods. Five studies were included in this analysis and a great heterogeneity among them was observed. There were studies evaluating more than one AI algorithm and studies comparing AI with readers alone or in combination with AI. Sensitivity for AI; AI + reader; reader alone, were 76.08; 84.02; 80.91, respectively. Specificity for AI; AI + reader; reader alone, were 96.62; 85.67; 84.89, respectively. Results are shown in the table. Conclusions: Although recent improvements in AI algorithms for breast cancer screening, a delta AUC between comparisons of AI algorithms and readers was not observed.[Table: see text]

Digital mammographic interpretation by UK radiographer mammographers: A JAFROC analysis of observer performance

IntroductionRadiologists utilise mammography test sets to bench mark their performance against recognised standards. Using a validated test set, this study compares the performance of radiographer readers against previous test results for radiologists. MethodsUnder similar test conditions radiographer readers were given an established test set of 60 mammograms and tasked to identify breast cancer, they were measured against their ability to identify, locate and give a confidence level for cancer being present on a standard set of mammographic images. The results were then compared to previously published results for radiologists for similar or the same test sets. ResultsThe 10 radiographer readers demonstrated similar results to radiologists and for lesion sensitivity were the highest scoring group. The study group score a sensitivity of 83; a specificity of 69.3 and lesion sensitivity of 74.8 with ROC and JAFROC scores of 0.86 and 0.74 respectively. ConclusionUnder test conditions radiographers are able to identify and accurately locate breast cancer in a range of complex mammographic backgrounds. Implications for practiceThe study was performed under experimental conditions with results comparable to breast radiologists under similar conditions, translation of these findings into clinical practice will help address access and capacity issues in the timely identification and diagnosis of breast cancer.

Deep Learning-Based Artificial Intelligence for Mammography.

During the past decade, researchers have investigated the use of computer-aided mammography interpretation. With the application of deep learning technology, artificial intelligence (AI)-based algorithms for mammography have shown promising results in the quantitative assessment of parenchymal density, detection and diagnosis of breast cancer, and prediction of breast cancer risk, enabling more precise patient management. AI-based algorithms may also enhance the efficiency of the interpretation workflow by reducing both the workload and interpretation time. However, more in-depth investigation is required to conclusively prove the effectiveness of AI-based algorithms. This review article discusses how AI algorithms can be applied to mammography interpretation as well as the current challenges in its implementation in real-world practice.

Artificial intelligence in breast cancer screening: primary care provider preferences.

Artificial intelligence (AI) is increasingly being proposed for use in medicine, including breast cancer screening (BCS). Little is known, however, about referring primary care providers' (PCPs') preferences for this technology. We identified the most important attributes of AI BCS for ordering PCPs using qualitative interviews: sensitivity, specificity, radiologist involvement, understandability of AI decision-making, supporting evidence, and diversity of training data. We invited US-based PCPs to participate in an internet-based experiment designed to force participants to trade off among the attributes of hypothetical AI BCS products. Responses were analyzed with random parameters logit and latent class models to assess how different attributes affect the choice to recommend AI-enhanced screening. Ninety-one PCPs participated. Sensitivity was most important, and most PCPs viewed radiologist participation in mammography interpretation as important. Other important attributes were specificity, understandability of AI decision-making, and diversity of data. We identified 3 classes of respondents: "Sensitivity First" (41%) found sensitivity to be more than twice as important as other attributes; "Against AI Autonomy" (24%) wanted radiologists to confirm every image; "Uncertain Trade-Offs" (35%) viewed most attributes as having similar importance. A majority (76%) accepted the use of AI in a "triage" role that would allow it to filter out likely negatives without radiologist confirmation. Sensitivity was the most important attribute overall, but other key attributes should be addressed to produce clinically acceptable products. We also found that most PCPs accept the use of AI to make determinations about likely negative mammograms without radiologist confirmation.

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization.

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we propose a novel neural network model to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, our model outperforms (AUC=0.93) ResNet-34 and Faster R-CNN in classifying breasts with malignant findings. On the CBIS-DDSM dataset, our model achieves performance (AUC=0.858) on par with state-of-the-art approaches. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11.

Transitioning to Practice: Getting up to Speed in Efficiency and Accuracy.

The transition from trainee to breast radiologist is challenging. The many new responsibilities that breast radiologists acquire while establishing themselves as clinicians may increase stress and anxiety. Taking inventory of existing knowledge and skills and addressing deficits toward the end of one's training can be beneficial. New breast radiologists should expect to be slower and gain proficiency in the first several years out of training. Having realistic expectations for oneself with respect to screening mammography interpretation and following up on the subsequent diagnostic imaging workup of screening callback examinations can increase competence and confidence. Familiarity with the available literature to guide management in the diagnostic setting can increase efficiency. Planning ahead for localizations and biopsies also allows for efficiency while alleviating anxiety. Ultimately, adapting to a new work environment using a collaborative approach with primary healthcare providers, pathologists, and surgeons while remembering to have mentors within and beyond the field of radiology allows for a more successful transition.

Contrast CT classification of asymptomatic and symptomatic carotids in stroke and transient ischaemic attack with deep learning and interpretability

Abstract Background Convolutional neural networks (CNNs), part of deep learning, are used widely for computer vision tasks and in some medical domains, such as mammography interpretation. The application of deep learning to carotid artery imaging is scarce. We investigated the ability of deep learning to correctly classify contrast CT images of the carotid arteries without the need for prior feature selection. Purpose (1) To assess the ability of deep learning to differentiate symptomatic patients (had prior stroke or transient ischaemic attack [TIA]) from asymptomatic patients (no prior stroke/TIA) using contrast CT scans alone. (2) To investigate whether deep learning can further discriminate between culprit and non-culprit carotid arteries in symptomatic patients. (3) To assess the interpretability of the deep learning models. Methods Carotid contrast CT scans of consented research subjects were included in the study. Symptomatic patients had confirmed carotid artery-related ischaemic stroke or TIA in the 7 days before CT imaging, and asymptomatic patients had no prior cerebrovascular events. The dataset comprised 1148 axial symptomatic slices (covering a 3cm area of each carotid artery in 41 patients; 41 culprit and 41 non-culprit carotids) and 700 asymptomatic slices (from the bilateral carotid arteries of 25 patients). The dataset was split such that 75% was used for training and 25% for testing. A 30x30 bounding box was used to create patches of the carotid arteries from these axial slices for use as input to the CNN, a modified VGG16 architecture initialised with ImageNet weights to leverage transfer learning (the application of a model trained in one domain to a different domain) implemented in Python. Data augmentation was applied to the training set and the model was trained for 100 epochs using a cyclic learning rate, the RMSProp optimizer and binary cross-entropy loss. Class activation heatmaps were generated using the GradCAM method to highlight the areas of the image that were most important to the model for making its classification decision. Results The deep learning model was 92% accurate in correctly identifying carotid arteries from symptomatic patients versus those from asymptomatic patients. Discriminating between culprit versus non-culprit carotid arteries in symptomatic patients alone was 71% accurate. The class activation heatmaps demonstrated how the model learnt to localise the carotid artery within the image patch, and to ignore the arterial lumen when making its classification decision. Conclusions Deep learning can be used to differentiate between symptomatic and asymptomatic carotid CT scans from stroke/TIA subjects without the need for prior feature engineering. The model learns to identify relevant features in the image that predict the patients' symptom state. If further validated, this approach could be used to identify high-risk patients for intensive medical therapy. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): EPVL is undertaking a PhD funded by the Cambridge School of Clinical Medicine and the Medical Research Council's Doctoral Training Partnership

Mammographic interpretation in Vietnam: Tailored educational strategies are needed to increase clinicians' expertise.

Breast cancer incidence is rapidly increasing throughout South East Asia, highlighting the need for high-quality early diagnosis and treatment. This study aims to investigate the efficacy of mammography detection in Hanoi and Ho Chi Minh City (HCMC), Vietnam, using data from Australian radiologists as a benchmark; factors that influence performance will be highlighted. A total of 53, 35 and 52 clinicians from Australia, HCMC and Hanoi, respectively, examined and diagnosed a test set of 60 mammograms, 20 of which contained cancers. Each clinician completed an accompanying questionnaire establishing demographic and experiential characteristics. The performance metrics of specificity, sensitivity, area under the receiver operating characteristic curve (AUC), location sensitivity and Jackknife free-response ROC (JAFROC) figure of merit were used to evaluate clinicians performance. Mann-Whitney and Kruskal-Wallis statistical methods were employed to establish significance. Vietnamese radiologists demonstrated significantly lower sensitivity, AUC, lesion sensitivity and JAFROC scores compared to Australian radiologists. There was no difference in performance between clinicians from Hanoi and HCMC. However, certain performance features (older and more experienced clinicians compared with their younger, less experienced counterparts, readers who read more compared with fewer mammograms per week, clinicians with greater radiological experience and clinicians that completed a fellowship) demonstrated significantly better performances. The significant difference in diagnostic efficacy of mammograms between Vietnam and Australia identifies the need for improvements in breast radiology training, management and practice. Cost-effective solutions are available that can improve the reading efficacy of clinicians, and consequently health outcomes for Vietnamese women.

Evaluation of an AI system for breast cancer screening in mammograms of young women.

e14068 Background: The interpretation of the mammography is challenging, especially in young women, who have dense breasts. Artificial intelligence (AI) promises to improve breast cancer detection; however these systems should be tested on different datasets. Our aim is to evaluate the performance of a publicly available deep convolutional neural network, developed by Wu et al. (IEEE Trans. Med. Imaging, 2019), applied to mammograms of young women. Methods: The test dataset consisted of mammograms obtained on a single occasion from 135 young women (up to 40 years old) on a Siemens mammography system. Each exam consisted of 4 full-field digital mammography images and had two labels (left malignant and right malignant). Mammograms were analyzed by a single mammography trained radiologist, using BI-RADS reporting tool. Among 270 labels, 170 were malignant and 100 were non-malignant. We used the program developed by Wu et al. that, according to the authors, presents AUC of 0.895 for the general population. As a preliminary test, we ran this program in a publicly available dataset named INbreast and obtained AUC of 0.8708, very close to the result reported by the authors. Results: We applied the program to our dataset of young women and obtained AUC of 0.876. We computed its standard error, obtaining 0.0290. At equal error rate point of the ROC curve, specificity and sensitivity are both 0.774. With this result we conclude that, at least for our dataset, cancer detection in young women is not substantially more difficult than in general population for an AI system. We fine-tuned the weights of the original network to the population of young women using transfer learning and obtained a slight improvement in AUC: 0.9018±0.0528, where the mean and the standard error were obtained using 5-fold cross validation. As the improvement was small and the standard errors are large, we would have to test on a larger test set to ensure that the observed improvement is real. Conclusions: We conclude, based on the experimental data, that there is no substantial degradation in accuracy when a mammogram screening program for general population is used for young women. We also conclude that it seems to be possible to obtain a slight improvement in accuracy by fine-tuning the network for the population of young women.

Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms

Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.

Telemammography: Technical Advances Improve Patient Access in Breast Care.

Screening mammography's efficacy in reducing breast cancer deaths depends on patient compliance with screening recommendations and the radiologist's interpretative skills. Reasons for suboptimal screening compliance may be multifactorial, including possible limitations in access. Additionally, while studies show experienced breast radiologists are more accurate in their mammographic interpretation, only a minority of the nation's mammograms are interpreted by breast imaging specialists. To simultaneously optimize the benefit of early breast cancer detection while minimizing the harms associated with a false positive interpretation, delivery models that help improve access to breast expertise should be considered. Telemammography is one such delivery model that may be underutilized in current practice. While radiologists and other stakeholders of healthcare have accepted teleradiology interpretation of non-mammography studies as routine, telemammography use and acceptance is less well known. In this article, we review the operational components of a telemammography practice in today's information- and technology-dependent society. Current use of telemammography and remaining potential challenges are discussed. Telemammography can improve healthcare delivery and access by bringing together patients and breast expertise. If accepted, use of telemammography can help meet Centers for Disease Control's Healthy People 2020 goals related to breast cancer.

Evaluation of the applicability of BI-RADS® MRI for the interpretation of contrast-enhanced digital mammography

ObjectiveTo determine the usefulness of BI-RADS® MRI for the morphological description and categorization of images obtained with contrast-enhanced digital mammography in comparison with the final diagnosis. Material and methodsWe included patients who had palpable breast lesions, those who needed clarification regarding abnormalities identified with another imaging technique, and those who needed a complementary evaluation of heterogeneously dense breast parenchyma. Three radiologists working independently used a template with the BI-RADS® MRI qualitative descriptors to evaluate the breast lesions studied with contrast-enhanced digital mammography. In a second phase, two other experienced radiologists reached a consensus about discrepant interpretations. Readers also classified each lesion (both benign and malignant lesions) on the BI-RADS® scale (1–5). All the results were compared with the real state of disease (determined by the appropriate gold standard for each type of lesion), and the statistical significance was assessed with the chi-square test. ResultsA total of 218 benign lesions and 426 malignant lesions were included. The interobserver agreement among the three radiologists was high (Fleiss-Cohen kappa = 0.805; 95% CI: 0.728–0.837). Similarly to what has been reported about breast MRI, on contrast-enhanced digital mammography, malignant lesions with mass effect tended to have an irregular shape with spiculated or ill-defined margins and a pattern of intense and heterogeneous enhancement (p < 0.001). Nevertheless, unlike on breast MRI, ring enhancement was not an independent criterion of malignancy on contrast-enhanced digital mammography. For lesions without a mass effect, the only significant descriptor was the intensity of contrast material uptake (p < 0.05). Applying the BI-RADS® MRI material to contrast-enhanced digital mammography images enabled the correct classification of 85% of lesions in the benign categories (BI-RADS 1 and BI-RADS 2 and 3 lesions) and of 93% of the lesions in the malignant categories (BI-RADS 4–5); these values are similar to those reported for breast MRI. ConclusionsThe morphological descriptors used in BI-RADS® MRI can be applied to the morphological analysis of breast lesions studied with contrast-enhanced digital mammography. The partial discrepancies in the interpretation did not influence the final BI-RADS® score, and the score enabled good differentiation between benign and malignant lesions.

The Results of Surveillance Imaging After Breast Conservation Surgery and Partial Breast Reconstruction With Chest Wall Perforator Flaps; A Qualitative Analysis Compared With Standard Breast-Conserving Surgery for Breast Cancer

IntroductionPartial breast reconstruction (PBR) using chest wall perforator flaps (CWPF) allows for excision of tumors in the outer quadrant of the breast in women with small to moderate non-ptotic breasts resulting in a good aesthetic outcome. There are limited data available in the literature regarding long-term follow-up and the effect of CWPF on subsequent surveillance mammographic interpretation and recall rates. A retrospective audit with qualitative analysis of initial mammograms was performed to assess this. Patients and MethodsThis retrospective analysis of a prospectively maintained database included all consecutive patients who underwent either PBR with CWPF or wide local excision (WLE) between January 2013 and December 2014 by a single surgeon in a tertiary referral center. Qualitative analysis of the postoperative mammograms was performed after review by 2 blinded radiologists. ResultsThirty-six patients were included in the study, 18 in each arm. The CWPF group was younger and had larger tumor size anticipated on preoperative imaging, which correlated with larger specimens excised. Both groups were comparable with respect to tumor pathological characteristics. Comparing the first postoperative mammograms, both groups were similar in features reported such as calcifications, fat necrosis, volume loss, and radiotherapy changes. During the follow-up period (median 4 years), 138 surveillance mammograms were performed. One patient was recalled for further imaging in the CWPF group. There was no significant difference in the need for diagnostic imaging and biopsy between the groups. ConclusionPatients who underwent PBR using CWPF had similar features on postoperative surveillance mammograms compared with that post WLE.

Globally-Aware Multiple Instance Classifier for Breast Cancer Screening.

Deep learning models designed for visual classification tasks on natural images have become prevalent in medical image analysis. However, medical images differ from typical natural images in many ways, such as significantly higher resolutions and smaller regions of interest. Moreover, both the global structure and local details play important roles in medical image analysis tasks. To address these unique properties of medical images, we propose a neural network that is able to classify breast cancer lesions utilizing information from both a global saliency map and multiple local patches. The proposed model outperforms the ResNet-based baseline and achieves radiologist-level performance in the interpretation of screening mammography. Although our model is trained only with image-level labels, it is able to generate pixel-level saliency maps that provide localization of possible malignant findings.

Moscow screening: breast cancer screening with mammography as a method of improving early stage cancer detection

A list of organizational, management, and clinical steps that are crucial for creating an effective breast cancer screening program as part of the state medical benefits scheme in Moscow is presented. We identified key performance indicators for each stage of the screening program. Performance of radiologists and radiology technicians was evaluated, including assessing the accuracy of both single and double reading of mammograms. We streamlined an efficient system for patient routing between the stages of the screening program and developed methodological materials for patients and medical specialists. A shortened structured protocol for mammography interpretation, including second reading, was created in compliance with terms of Moscow Compulsory Medical Insurance Fund. We conceived a framework of educational activities to assess and improve skills and knowledge of radiologists and other specialists participating in the screening.