Improving Screening Mammography Outcomes Through Comparison With Multiple Prior Mammograms

Prevalent vs Incident Screen: Why Does It Matter?

There are important differences in the performance and outcomes of breast cancer screening in the prevalent compared to the incident screening rounds. The prevalent screen is the first screening examination using a particular imaging technique and identifies pre-existing, undiagnosed cancers in the population. The incident screen is any subsequent screening examination using that technique. It is expected to identify fewer cancers than the prevalent screen because it captures only those cancers that have become detectable since the prior screening examination. The higher cancer detection rate at prevalent relative to incident screening should be taken into account when analyzing the medical audit and effectiveness of new screening technologies.

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

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

Does the availability of prior mammograms improve radiologists' observer performance?-a scoping review

Objective

The objective of this review was to examine the impact of previous mammogram availability on radiologists' performance from screening populations and experimental studies.

Materials and Methods

A search of the literature was conducted using five databases: MEDLINE, PubMed, Web of Science, ScienceDirect, and CINAHL as well as Google and reference lists of articles. Keywords were combined with "AND" or "OR" or "WITH" and included "prior mammograms, diagnostic performance, initial images, diagnostic efficacy, subsequent images, previous imaging, and radiologist's performance". Studies that assessed the impact of previous mammogram availability on radiologists' performance were reviewed. The Standard for Reporting Diagnostic Accuracy guidelines was used to critically appraise individual sources of evidence.

Results

A total of 15 articles were reviewed. The sample of mammogram cases used across these studies varied from 36 to 1,208,051. Prior mammograms did not affect sensitivity [with priors: 62-86% (mean = 73.3%); without priors: 69.4-87.4% (mean = 75.8%)] and cancer detection rate, but increased specificity [with priors: 72-96% (mean = 87.5%); without priors: 63-87% (mean = 80.5%)] and reduced false-positive rates [with priors: 3.7 to 36% (mean = 19.9%); without priors 13.3-49% (mean = 31.4%)], recall rates [with priors: 3.8-57% (mean = 26.6%); without priors: [4.9%-67.5% (mean = 37.9%)], and abnormal interpretation rate decreased by 4% with priors. Evidence for the associations between the availability of prior mammograms and positive-predictive value, area under the curve (AUC) from the receiver operating characteristic curve (ROC) and localisation ROC AUC, and positive-predictive value of recall is limited and unclear.

Conclusion

Availability of prior mammograms reduces recall rates, false-positive rates, abnormal interpretation rates, and increases specificity without affecting sensitivity and cancer detection rate.

Expanding Horizons: The Realities of CAD, the Promise of Artificial Intelligence, and Machine Learning's Role in Breast Imaging beyond Screening Mammography

Artificial intelligence (AI) applications in mammography have gained significant popular attention; however, AI has the potential to revolutionize other aspects of breast imaging beyond simple lesion detection. AI has the potential to enhance risk assessment by combining conventional factors with imaging and improve lesion detection through a comparison with prior studies and considerations of symmetry. It also holds promise in ultrasound analysis and automated whole breast ultrasound, areas marked by unique challenges. AI's potential utility also extends to administrative tasks such as MQSA compliance, scheduling, and protocoling, which can reduce the radiologists' workload. However, adoption in breast imaging faces limitations in terms of data quality and standardization, generalizability, benchmarking performance, and integration into clinical workflows. Developing methods for radiologists to interpret AI decisions, and understanding patient perspectives to build trust in AI results, will be key future endeavors, with the ultimate aim of fostering more efficient radiology practices and better patient care.

Digital Breast Tomosynthesis versus Digital Mammography Screening Performance on Successive Screening Rounds from the Breast Cancer Surveillance Consortium

Background Prior cross-sectional studies have observed that breast cancer screening with digital breast tomosynthesis (DBT) has a lower recall rate and higher cancer detection rate compared with digital mammography (DM). Purpose To evaluate breast cancer screening outcomes with DBT versus DM on successive screening rounds. Materials and Methods In this retrospective cohort study, data from 58 breast imaging facilities in the Breast Cancer Surveillance Consortium were collected. Analysis included women aged 40-79 years undergoing DBT or DM screening from 2011 to 2020. Absolute differences in screening outcomes by modality and screening round were estimated during the study period by using generalized estimating equations with marginal standardization to adjust for differences in women's risk characteristics across modality and round. Results A total of 523 485 DBT examinations (mean age of women, 58.7 years ± 9.7 [SD]) and 1 008 123 DM examinations (mean age, 58.4 years ± 9.8) among 504 863 women were evaluated. DBT and DM recall rates decreased with successive screening round, but absolute recall rates in each round were significantly lower with DBT versus DM (round 1 difference, -3.3% [95% CI: -4.6, -2.1] [P < .001]; round 2 difference, -1.8% [95% CI: -2.9, -0.7] [P = .003]; round 3 or above difference, -1.2% [95% CI: -2.4, -0.1] [P = .03]). DBT had significantly higher cancer detection (difference, 0.6 per 1000 examinations [95% CI: 0.2, 1.1]; P = .009) compared with DM only for round 3 and above. There were no significant differences in interval cancer rate (round 1 difference, 0.00 per 1000 examinations [95% CI: -0.24, 0.30] [P = .96]; round 2 or above difference, 0.04 [95% CI: -0.19, 0.31] [P = .76]) or total advanced cancer rate (round 1 difference, 0.00 per 1000 examinations [95% CI: -0.15, 0.19] [P = .94]; round 2 or above difference, -0.06 [95% CI: -0.18, 0.11] [P = .43]). Conclusion DBT had lower recall rates and could help detect more cancers than DM across three screening rounds, with no difference in interval or advanced cancer rates. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Skaane in this issue.

Identification of factors associated with diagnostic performance variation in reporting of mammograms: A review

OBJECTIVES

This narrative review aims to identify what factors are linked to diagnostic performance variation for those who interpret mammograms. Identification of influential factors has potential to contribute to the optimisation of breast cancer diagnosis. PubMed, ScienceDirect and Google Scholar databases were searched using the following terms: 'Radiology', 'Radiologist', 'Radiographer', 'Radiography', 'Mammography', 'Interpret', 'read', 'observe' 'report', 'screen', 'image', 'performance' and 'characteristics.' Exclusion criteria included articles published prior to 2000 as digital mammography was introduced at this time. Non-English articles language were also excluded. 38 of 2542 studies identified were analysed.

KEY FINDINGS

Influencing factors included, new technology, volume of reads, experience and training, availability of prior images, social networking, fatigue and time-of-day of interpretation. Advancements in breast imaging such as digital breast tomosynthesis and volume of mammograms are primary factors that affect performance as well as tiredness, time-of-day when images are interpreted, stages of training and years of experience. Recent studies emphasised the importance of social networking and knowledge sharing if breast cancer diagnosis is to be optimised.

CONCLUSION

It was demonstrated that data on radiologist performance variability is widely available but there is a paucity of data on radiographers who interpret mammographic images.

IMPLICATIONS FOR PRACTICE

This scarcity of research needs to be addressed in order to optimise radiography-led reporting and set baseline values for diagnostic efficacy.

The Impact of Prior Mammograms on the Diagnostic Performance of Radiologists in Early Breast Cancer Detection: A Focus on Breast Density, Lesion Features and Vendors Using Wholly Digital Screening Cases

BACKGROUND

This study aims to investigate the diagnostic efficacy of radiologists when reading screening mammograms in the absence of previous images, and with the presence of prior images from the same and different vendors.

METHODS

612 radiologists' readings across 9 test sets, consisting of 540 screening mammograms (361-normal and 179-cancer) with 245 cases having prior images obtained from same vendor as current images, 129 from a different vendor and 166 cases having no prior images, were retrospectively analysed. True positive (sensitivity), true negative (specificity) and area under ROC curve (AUC) values of radiologists were calculated for three groups of cases (without prior images (NP), with prior images from same vendor (SP), and with prior images from different vendor (DP)). Logistic regression was used to estimate the odds ratio (OR) of true positive, true negative and true cancer localization among case groups with different levels of breast density and lesion characteristics.

RESULTS

Radiologists obtained 12.8% and 10.3% higher sensitivity in NP and DP than SP (0.803-and-0.785 vs. 0.712; p < 0.0001). Specificity in NP and DP cases were 4.8% and 2.0% lower than SP cases (0.749 and 0.771 vs. 0.787). The AUC values for NP and DP were significantly higher than SP cases across different levels of breast density (0.814-and-0.820 vs. 0.782; p < 0.0001). The odds ratio (OR) of true positive for NP relative to SP was 1.6 (p < 0.0001) and DP relative to SP was 1.5 (p < 0.0001). Radiologists were more like to detect architectural distortion in DP than SP cases (OR = 3.2; p < 0.0001), whilst the OR for abnormal calcifications was 2.85 (p < 0.0001).

CONCLUSIONS

Cases without previous mammograms or with prior mammograms obtained from different vendors were more likely to benefit radiologists in cancer detection, whilst prior mammograms undertaken from the same vendor were more useful for radiologists in evaluating normal cases.

Feature fusion siamese network for breast cancer detection comparing current and prior mammograms

PURPOSE

Automatic detection of very small and non-mass abnormalities from mammogram images has remained challenging. In clinical practice for each patient, radiologists commonly not only screen the mammogram images obtained during the examination, but also compare them with previous mammogram images to make a clinical decision. To design an AI system to mimic radiologists for better cancer detection, in this work we proposed an end-to-end enhanced Siamese convolutional neural network to detect breast cancer using previous year and current year mammogram images.

METHODS

The proposed Siamese based network uses high resolution mammogram images and fuses features of pairs of previous year and current year mammogram images to predict cancer probabilities. The proposed approach is developed based on the concept of one-shot learning that learns the abnormal differences between current and prior images instead of abnormal objects, and as a result can perform better with small sample size data sets. We developed two variants of the proposed network. In the first model, to fuse the features of current and previous images, we designed an enhanced distance learning network that considers not only the overall distance, but also the pixel-wise distances between the features. In the other model, we concatenated the features of current and previous images to fuse them.

RESULTS

We compared the performance of the proposed models with those of some baseline models that use current images only (ResNet and VGG) and also use current and prior images (LSTM and vanilla Siamese) in terms of accuracy, sensitivity, precision, F1 score and AUC. Results show that the proposed models outperform the baseline models and the proposed model with the distance learning network performs the best (accuracy: 0.92, sensitivity: 0.93, precision: 0.91, specificity: 0.91, F1: 0.92 and AUC: 0.95).

CONCLUSIONS

Integrating prior mammogram images improves automatic cancer classification, specially for very small and non-mass abnormalities. For classification models that integrate current and prior mammogram images, using an enhanced and effective distance learning network can advance the performance of the models. This article is protected by copyright. All rights reserved.

Benefits and harms of annual, biennial, or triennial breast cancer mammography screening for women at average risk of breast cancer: a systematic review for the European Commission Initiative on Breast Cancer (ECIBC)

BACKGROUND

Although mammography screening is recommended in most European countries, the balance between the benefits and harms of different screening intervals is still a matter of debate. This review informed the European Commission Initiative on Breast Cancer (BC) recommendations.

METHODS

We searched PubMed, EMBASE, and the Cochrane Library to identify RCTs, observational or modelling studies, comparing desirable (BC deaths averted, QALYs, BC stage, interval cancer) and undesirable (overdiagnosis, false positive related, radiation related) effects from annual, biennial, or triennial mammography screening in women of average risk for BC. We assessed the certainty of the evidence using the GRADE approach.

RESULTS

We included one RCT, 13 observational, and 11 modelling studies. In women 50-69, annual compared to biennial screening may have small additional benefits but an important increase in false positive results; triennial compared to biennial screening may have smaller benefits while avoiding some harms. In younger women (aged 45-49), annual compared to biennial screening had a smaller gain in benefits and larger harms, showing a less favourable balance in this age group than in women 50-69. In women 70-74, there were fewer additional harms and similar benefits with shorter screening intervals. The overall certainty of the evidence for each of these comparisons was very low.

CONCLUSIONS

In women of average BC risk, screening intervals have different trade-offs for each age group. The balance probably favours biennial screening in women 50-69. In younger women, annual screening may have a less favourable balance, while in women aged 70-74 years longer screening intervals may be more favourable.

Breast lesions classifications of mammographic images using a deep convolutional neural network-based approach

Breast cancer is one of the worst illnesses, with a higher fatality rate among women globally. Breast cancer detection needs accurate mammography interpretation and analysis, which is challenging for radiologists owing to the intricate anatomy of the breast and low image quality. Advances in deep learning-based models have significantly improved breast lesions’ detection, localization, risk assessment, and categorization. This study proposes a novel deep learning-based convolutional neural network (ConvNet) that significantly reduces human error in diagnosing breast malignancy tissues. Our methodology is most effective in eliciting task-specific features, as feature learning is coupled with classification tasks to achieve higher performance in automatically classifying the suspicious regions in mammograms as benign and malignant. To evaluate the model’s validity, 322 raw mammogram images from Mammographic Image Analysis Society (MIAS) and 580 from Private datasets were obtained to extract in-depth features, the intensity of information, and the high likelihood of malignancy. Both datasets are magnificently improved through preprocessing, synthetic data augmentation, and transfer learning techniques to attain the distinctive combination of breast tumors. The experimental findings indicate that the proposed approach achieved remarkable training accuracy of 0.98, test accuracy of 0.97, high sensitivity of 0.99, and an AUC of 0.99 in classifying breast masses on mammograms. The developed model achieved promising performance that helps the clinician in the speedy computation of mammography, breast masses diagnosis, treatment planning, and follow-up of disease progression. Moreover, it has the immense potential over retrospective approaches in consistency feature extraction and precise lesions classification.

Real-time PACS-integrated longitudinal brain metastasis tracking tool provides comprehensive assessment of treatment response to radiosurgery

Background

Treatment of brain metastases can be tailored to individual lesions with treatments such as stereotactic radiosurgery. Accurate surveillance of lesions is a prerequisite but challenging in patients with multiple lesions and prior imaging studies, in a process that is laborious and time consuming. We aimed to longitudinally track several lesions using a PACS-integrated lesion tracking tool (LTT) to evaluate the efficiency of a PACS-integrated lesion tracking workflow, and characterize the prevalence of heterogenous response (HeR) to treatment after Gamma Knife (GK).

Methods

We selected a group of brain metastases patients treated with GK at our institution. We used a PACS-integrated LTT to track the treatment response of each lesion after first GK intervention to maximally seven diagnostic follow-up scans. We evaluated the efficiency of this tool by comparing the number of clicks necessary to complete this task with and without the tool and examined the prevalence of HeR in treatment.

Results

A cohort of eighty patients was selected and 494 lesions were measured and tracked longitudinally for a mean follow-up time of 374 days after first GK. Use of LTT significantly decreased number of necessary clicks. 81.7% of patients had HeR to treatment at the end of follow-up. The prevalence increased with increasing number of lesions.

Conclusions

Lesions in a single patient often differ in their response to treatment, highlighting the importance of individual lesion size assessments for further treatment planning. PACS-integrated lesion tracking enables efficient lesion surveillance workflow and specific and objective result reports to treating clinicians.

Outcomes of screening mammography performed prior to fertility treatment in women ages 40-49

OBJECTIVE

There are currently various conflicting recommendations for breast cancer screening with mammography in women between ages 40-49. There are no specific guidelines for breast cancer screening in women of this age group prior to assisted reproductive technology (ART) for the treatment of infertility. The purpose of our study was to evaluate outcomes of screening mammography, specifically ordered for the purpose of pre-fertility treatment clearance in women aged 40-49 years old.

MATERIALS AND METHODS

This was an IRB approved retrospective study of women aged 40-49 presenting for screening mammography prior to ART between January 2010 and October 2018. Clinical history, imaging, and pathology results were gathered from the electronic medical record. Descriptive statistics were performed.

RESULTS

Our study cohort consisted of 118 women with a mean age of 42 years (range 40-49). Sixteen of 118 (14%) women were recalled from screening for additional diagnostic work-up. Five of the 16 (31%) were recommended for biopsy (BI-RADS 4 or 5). One of 5 biopsies yielded a malignant result (PPV 20%). Overall cancer detection rate was 0.85% or 8.5 women per 1000 women screened. The single cancer in this cohort was an ER+ PR+ HER2- invasive ductal carcinoma.

CONCLUSION

Screening mammography in women 40-49 performed prior to initiation of ART may identify asymptomatic breast malignancy. In accordance with ACR and SBI guidelines to screen women of this age group, women of this age group should undergo screening mammography prior to ART.

Electronic Worklist Improves Timeliness of Screening Mammogram Interpretation in an Urban Underserved Population

OBJECTIVES

To evaluate the impact of an electronic workflow update on screening mammography turnaround time and time to diagnostic imaging for mammography performed on our urban mobile mammography van and at an urban community health center.

METHOD

Prior to 10/15/2019, screening exams for the mammography van and urban community health center were made available for interpretation to a single designated radiologist via a manually generated paper list. On 10/15/2019, screening exams were routed electronically onto PACS for any breast radiologist across our Network to interpret. Screening mammogram turnaround time (defined as time form image acquisition to report finalization), time to diagnostic imaging, and time to tissue sampling were collected for pre- and post-implementation periods (6/1-9/30/2019 and 11/1/2019-2/29/2020, respectively) and compared via student t-test and statistical process control analyses.

RESULTS

The number of screening exams in the pre- and post-implementation periods were 851 and 728 exams, respectively. Patients were predominately Black and/or African American (400/1579, 25%), non-English speaking (858/1579, 54%) and insured by Medicaid (751/1579, 48%). After implementation of the electronic workflow, turnaround time decreased from 101.0 to 36.4 hours (63.9%, P <0.001) and statistical process control analyses showed sustained decrease in mean turnaround time. However, mean time to diagnostic imaging and tissue sampling were unchanged after implementation (39 vs 45, days; P = 0.330 and 43 vs 59; P = 0.187, respectively).

CONCLUSION

Electronic workflow management can reduce screening mammography turnaround time for underserved populations, but additional efforts are warranted to improve time to imaging follow-up for abnormal screening mammograms.

Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review

The relatively recent reintroduction of deep learning has been a revolutionary force in the interpretation of diagnostic imaging studies. However, the technology used to acquire those images is undergoing a revolution itself at the very same time. Digital breast tomosynthesis (DBT) is one such technology, which has transformed the field of breast imaging. DBT, a form of three-dimensional mammography, is rapidly replacing the traditional two-dimensional mammograms. These parallel developments in both the acquisition and interpretation of breast images present a unique case study in how modern AI systems can be designed to adapt to new imaging methods. They also present a unique opportunity for co-development of both technologies that can better improve the validity of results and patient outcomes. In this review, we explore the ways in which deep learning can be best integrated into breast cancer screening workflows using DBT. We first explain the principles behind DBT itself and why it has become the gold standard in breast screening. We then survey the foundations of deep learning methods in diagnostic imaging, and review the current state of research into AI-based DBT interpretation. Finally, we present some of the limitations of integrating AI into clinical practice and the opportunities these present in this burgeoning field.

Evaluation of the quality of mammographic breast positioning: a quality improvement study

BACKGROUND

Although there are concerns that inadequate breast positioning in mammographic examinations may lead to cancers being missed, few studies have examined the quality of breast positioning, especially in the Canadian context. Our objective was to assess the quality of breast positioning in mammographic examinations in a Quebec-wide representative sample of technologists.

METHODS

This quality improvement study was part of a professional inspection launched by the Ordre des technologues en imagerie médicale, en radio-oncologie et en électrophysiologie médicale du Québec among its members. The inspection was conducted between May and July 2017 on a proportionate stratified random sample of all active technologists certified in mammography in Quebec. Each technologist provided images from 15 consecutive mammographic examinations they performed in the previous 6 months. The quality of positioning was then evaluated by senior technologists using a quality assessment tool specifically developed for this inspection. A technologist was deemed to have failed the professional inspection when at least 7 of the 15 mammographic examinations were scored as critical failures. Proportions were calculated accounting for sampling weights and correction for finite population.

RESULTS

Among the 520 technologists certified in mammography in Quebec, 76 technologists (14.6%) were randomly selected for the professional inspection and contributed images from 1127 mammographic examinations. Thirty-eight technologists (weighted percentage 50.3%, 95% confidence interval [CI] 37.6% to 63.0%) failed the professional inspection. Overall, 492 mammographic examinations (43.7%, 95% CI 38.6% to 48.8%) had at least 1 image scored as a critical failure.

INTERPRETATION

Half of the technologists performing mammographic examinations in Quebec who participated in this study failed the inspection, and a substantial proportion of their mammographic examinations demonstrated critical failures in breast positioning. Overall, our findings are concordant with those of previous studies and highlight the need for additional investigations assessing the quality of breast positioning in mammographic examinations in other jurisdictions.

Batch Reading and Interrupted Interpretation of Digital Screening Mammograms Without and With Tomosynthesis

OBJECTIVE

To compare batch reading and interrupted interpretation for modern screening mammography.

METHODS

We retrospectively reviewed digital mammograms without and with tomosynthesis that were originally interpreted with batch reading or interrupted interpretation between January 2015 and June 2017. The following performance metrics were compared: recall rate (per 100 examinations), cancer detection rate (per 1,000 examinations), and positive predictive values for recall and biopsy.

RESULTS

In all, 9,832 digital mammograms were batch read, yielding a recall rate of 9.98%, cancer detection rate of 4.27, and positive predictive values for recall and biopsy of 4.40% and 35.5%, respectively. There were 49,496 digital mammograms that were read with interrupted interpretation, yielding a recall rate of 11.3%, cancer detection rate of 4.44, and positive predictive values for recall and biopsy of 3.92% and 30.1%, respectively. Of the digital mammograms with tomosynthesis, 7,075 were batch read, yielding a recall rate of 6.98%, cancer detection rate of 5.37, and positive predictive values for recall and biopsy of 7.69% and 38.0%, respectively. Of the digital mammograms with tomosynthesis, 24,380 were read with interrupted interpretation, yielding a recall rate of 8.30%, cancer detection rate of 5.41, and positive predictive values for recall and biopsy of 6.52% and 33.3%, respectively. For both digital mammograms without and with tomosynthesis, recall rates improved with batch reading compared with interrupted interpretation (P < .001), but no significant differences were seen for other metrics.

DISCUSSION

Batch reading digital mammograms without and with tomosynthesis improves recall rates while maintaining cancer detection rates and positive predictive values compared with interrupted interpretation.

The Effect of Prior Comparison MRI on Interpretive Performance of Screening Breast MRI

OBJECTIVE

To evaluate the effect of prior comparison MRI on interpretive performance of screening breast MRI.

METHODS

After institutional review board approval, all screening breast MRI examinations performed from January 2011 through December 2014 were retrospectively reviewed. Screening performance metrics were estimated and compared for exams with and without a prior comparison MRI, using logistic regression models to adjust for age and screening indication (BRCA mutation or thoracic radiation versus breast cancer history versus high-risk lesion history versus breast cancer family history).

RESULTS

Most exams, 4509 (87%), had a prior comparison MRI (incidence round), while 661 (13%) did not (prevalence round). Abnormal interpretation rate (6% vs 20%, P < 0.01), biopsy rate (3% vs 9%, P < 0.01), and false-positive biopsy recommendation rate per 1000 exams (21 vs 71, P < 0.01) were significantly lower in the incidence rounds compared to the prevalence rounds, while specificity was significantly higher (95% vs 81%, P < 0.01). There was no difference in cancer detection rate (CDR) per 1000 exams (12 vs 20, P = 0.1), positive predictive value of biopsies performed (PPV3) (35% vs 23%, P = 0.1), or sensitivity (86% vs 76%, P = 0.4).

CONCLUSION

Presence of a prior comparison significantly improves incidence round screening breast MRI examination performance compared with prevalence round screening. Consideration should be given to updating the BI-RADS breast MRI screening benchmarks and auditing prevalence and incidence round examinations separately.

Deep convolutional neural networks for mammography: advances, challenges and applications

BACKGROUND

The limitations of traditional computer-aided detection (CAD) systems for mammography, the extreme importance of early detection of breast cancer and the high impact of the false diagnosis of patients drive researchers to investigate deep learning (DL) methods for mammograms (MGs). Recent breakthroughs in DL, in particular, convolutional neural networks (CNNs) have achieved remarkable advances in the medical fields. Specifically, CNNs are used in mammography for lesion localization and detection, risk assessment, image retrieval, and classification tasks. CNNs also help radiologists providing more accurate diagnosis by delivering precise quantitative analysis of suspicious lesions.

RESULTS

In this survey, we conducted a detailed review of the strengths, limitations, and performance of the most recent CNNs applications in analyzing MG images. It summarizes 83 research studies for applying CNNs on various tasks in mammography. It focuses on finding the best practices used in these research studies to improve the diagnosis accuracy. This survey also provides a deep insight into the architecture of CNNs used for various tasks. Furthermore, it describes the most common publicly available MG repositories and highlights their main features and strengths.

CONCLUSIONS

The mammography research community can utilize this survey as a basis for their current and future studies. The given comparison among common publicly available MG repositories guides the community to select the most appropriate database for their application(s). Moreover, this survey lists the best practices that improve the performance of CNNs including the pre-processing of images and the use of multi-view images. In addition, other listed techniques like transfer learning (TL), data augmentation, batch normalization, and dropout are appealing solutions to reduce overfitting and increase the generalization of the CNN models. Finally, this survey identifies the research challenges and directions that require further investigations by the community.

Medicare Access and Children's Health Insurance Program Reauthorization Act: The Basics for the Breast Imaging Radiologist

Breast imaging radiologists are considered by many to be leaders among diagnostic radiologists in the transition to value-based care. Many strategies for success in the changing healthcare landscape are exemplified by the day-to-day practice of breast imaging, including well-developed quality measures, standardized accepted best practices and terminology, and a prominent role in communicating with patients and coordinating care. Further development of these strategies will be important for continued success in both the Merit-Based Incentive Payment System and in alternative payment models.

Specialized Second Opinion Review of Breast MRI Impacts Management and Increases Cancer Detection

OBJECTIVE

The aim of our study is to determine MRI review discrepancy frequency and the subsequent impact on patient management for patients pursuing breast imaging second opinions.

METHODS

A retrospective chart review was conducted on 1,000 consecutive patients with second opinion radiology interpretations performed by subspecialty-trained breast radiologists at a dedicated cancer center July 1 through December 31, 2016. Of these, 205 included review of outside breast MRI. Outside imaging reports were compared with second opinion reports to categorize breast MRI review discrepancies. These included relevant BI-RADS category changes or identification of additional extent of disease >4 cm. The discrepancy frequency, relevant alterations in patient management, and incremental cancer detection were measured. Statistical analyses were performed using Fisher's exact test.

RESULTS

Discrepant second opinion breast MRI review was seen in 36 of 205 patients (18%). Additional cancer was detected through image-guided biopsy in 3 of these 36 patients and through excision in 2 (5 of 205, 2%). Additionally, five biopsies yielded high-risk pathologic results without upstage on excision. Findings suspicious for additional extent of disease >4 cm were noted in five patients (2%) treated with mastectomies. Finally, five patients had BI-RADS category downgrades. Ultimately, completion of second opinion MRI review recommendations resulted in altered management in 10% of patients (20 of 205). The absence of prior imaging studies for comparison was associated with increased discrepancy frequency (P = .005).

CONCLUSION

Second opinion breast MRI review by subspecialized breast imaging radiologists increases cancer detection and results in clinically relevant changes in patient management.

A blueprint for cancer screening and early detection: Advancing screening's contribution to cancer control

From the mid-20th century, accumulating evidence has supported the introduction of screening for cancers of the cervix, breast, colon and rectum, prostate (via shared decisions), and lung. The opportunity to detect and treat precursor lesions and invasive disease at a more favorable stage has contributed substantially to reduced incidence, morbidity, and mortality. However, as new discoveries portend advancements in technology and risk-based screening, we fail to fulfill the greatest potential of the existing technology, in terms of both full access among the target population and the delivery of state-of-the art care at each crucial step in the cascade of events that characterize successful cancer screening. There also is insufficient commitment to invest in the development of new technologies, incentivize the development of new ideas, and rapidly evaluate promising new technology. In this report, the authors summarize the status of cancer screening and propose a blueprint for the nation to further advance the contribution of screening to cancer control.

Microcalcifications Detected at Screening Mammography: Synthetic Mammography and Digital Breast Tomosynthesis versus Digital Mammography

Purpose To compare the performance of two-dimensional synthetic mammography (SM) plus digital breast tomosynthesis (DBT) versus conventional full-field digital mammography (FFDM) in the detection of microcalcifications on screening mammograms. Materials and Methods In this retrospective multireader observer study, 72 consecutive screening mammograms recalled for microcalcifications from June 2015 through August 2016 were evaluated with both FFDM and DBT. The data set included 54 mammograms with benign microcalcifications and 18 mammograms with malignant microcalcifications, and 20 additional screening mammograms without microcalcifications used as controls. FFDM alone was compared to synthetic mammography plus DBT. Four readers independently reviewed each data set and microcalcification recalls were tabulated. Sensitivity and specificity for microcalcification detection were calculated for SM plus DBT and for FFDM alone. Interreader agreement was calculated with Fleiss kappa values. Results Reader agreement was kappa value of 0.66 (P < .001) for FFDM and 0.63 (P < .001) for SM plus DBT. For FFDM, the combined reader sensitivity for all microcalcifications was 80% (229 of 288; 95% confidence interval [CI]: 74%, 84%) and for malignant microcalcifications was 92% (66 of 72; 95% CI: 83%, 97%). For SM plus DBT, the combined reader sensitivity for all microcalcifications was 75% (215 of 288; 95% CI: 69%, 80%) and for malignant microcalcifications was 94% (68 of 72; 95% CI: 86%, 98%). For FFDM, the combined reader specificity for all microcalcifications was 98% (78 of 80; 95% CI: 91%, 100%) and for malignant microcalcifications was 98% (78 of 80; 95% CI: 91%, 100%). For SM plus DBT, combined reader specificity for all microcalcifications was 95% (76 of 80; 95% CI: 88%, 99%) and for malignant microcalcifications was 95% (76 of 80; 95% CI: 88%, 99%). Mixed-effects model concluded no differences between modalities (‒0.03; 95% CI: ‒0.08, 0.01; P = .13). Conclusion Relative to full-field digital mammography, synthetic mammography plus digital breast tomosynthesis had similar sensitivity and specificity for the detection of microcalcifications previously identified for recall at screening mammography. © RSNA, 2018 See also the editorial by Bae and Moon in this issue.

Baseline Mammography: What Is It and Why Is It Important? A Cross-Sectional Survey of Women Undergoing Screening Mammography

OBJECTIVES

Studies have shown that having a baseline mammogram, the first screening mammogram, available for comparison at the time of interpreting a subsequent mammogram significantly decreases the potential of a false-positive examination. Our aim was to evaluate knowledge of and perception about the significance of baseline mammograms in those women undergoing screening mammography.

MATERIALS AND METHODS

A cross-sectional prospective survey study was conducted in women without a history of breast cancer presenting for their screening mammogram. Respondents were surveyed anonymously between March and April 2017. The questionnaire was developed by primary care providers and radiologists and pretested for readability and clarity.

RESULTS

In all, 401 women (87% white, 93% educated beyond high school) completed surveys in which 77% of women reported having yearly mammograms, 31% reported having a history of an abnormal mammogram, and 45% had not heard the term baseline mammogram. Of those who had heard the term, the most commonly reported source was their primary care provider (31%). Although 74% chose the correct definition of a baseline mammogram, 67% did not think that a baseline mammogram was important for decreasing associated cost, time, and discomfort due to the number of mammograms incorrectly read as abnormal.

CONCLUSION

In a group of educated women who routinely get mammograms, almost one-half had not heard the term baseline mammogram. Furthermore, most women did not think baseline mammography was important for decreasing associated cost, time, and discomfort due to mammograms incorrectly read as abnormal. This study suggests that efforts to improve women's understanding of baseline mammograms and their importance are warranted, with greatest opportunity for health care providers and radiologists.

Availability of prior mammograms affects incomplete report rates in mobile screening mammography

PURPOSE

Mobile mammography can improve access to screening mammography in rural areas and underserved populations. We evaluated the frequency of incomplete reports in mobile mammography screening and the relationships between prior mammograms and recall rates.

METHODS

The frequency of incomplete mammogram reports, the subgroups of those needing prior comparison mammograms, recalls for additional imaging, and availability of prior mammograms of a mobile screening mammography unit were compared with fixed site mammography from January 1, 2007 through December 31, 2009. All mobile unit mammograms were full field digital mammography (FFDM). Differences between rates of recall, incomplete reports, and availability of prior mammograms were calculated using the Chi-Square statistic.

RESULTS

Of 2640 mobile mammography cases, 21.9% (578) reports were incomplete, versus 15.2% (7653) (p ≤ 0.001) of 50325 fixed site reports. Of incomplete cases, recall for additional imaging occurred among 8.3% (218) of mobile mammography reports versus 11.3% (5708) (p ≤ 0.001) of fixed site reports. Prior mammograms were needed among 13.6% (360) of mobile mammography versus 3.9% (1945) (p ≤ 0.001) of fixed site reports. Mobile mammography recall rate varied with availability of prior mammograms: 16.0% (54) when no prior mammograms, 7.6% (127) when prior mammograms were elsewhere but unavailable and 5.9% (37) when prior FFDM were immediately available (p ≤ 0.001).

CONCLUSIONS

Incomplete reports were more frequent in mobile mammography than the fixed site. The availability of prior comparison mammograms at time of interpretation decreased the rate of incomplete mammogram reports. Recall rates were higher without prior comparison mammograms and lowest when comparison FFDM mammograms were available.