Improving digital breast tomosynthesis reading time: A pilot multi-reader, multi-case study using concurrent Computer-Aided Detection (CAD)

How long does it take to read a mammogram? Investigating the reading time of digital breast tomosynthesis and digital mammography

PURPOSE

To analyse digital breast tomosynthesis (DBT) reading times in the screening setting, compared to 2D full-field digital mammography (FFDM), and investigate the impact of reader experience and professional group on interpretation times.

METHOD

Reading time data were recorded in the PROSPECTS Trial, a prospective randomised trial comparing DBT plus FFDM or synthetic 2D mammography (S2D) to FFDM alone, in the National Health Service (NHS) breast screening programme, from January 2019-February 2023. Time to read DBT+FFDM or DBT+S2D and FFDM alone was calculated per case and reading times were compared between modalities using dependent T-tests. Reading times were compared between readers from different professional groups (radiologists and radiographer readers) and experience levels using independent T-tests. The learning curve effect of using DBT in screening on reading time was investigated using a Kruskal-Wallis test.

RESULTS

Forty-eight readers interpreted 1,242 FFDM batches (34,210 FFDM cases) and 973 DBT batches (13,983 DBT cases). DBT reading time was doubled compared to FFDM (2.09 ± 0.64 min vs. 0.98 ± 0.30 min; p < 0.001), and DBT+S2D reading was longer than DBT + FFDM (2.24 ± 0.62 min vs. 2.04 ± 0.46 min; p = 0.006). No difference was identified in reading time between radiologists and radiographers (2.06 ± 0.71 min vs. 2.14 ± 0.46 min, respectively; p = 0.71). Readers with five or more years of experience reading DBT were quicker than those with less experience (1.86 ± 0.56 min vs. 2.37 ± 0.65 min; p = 0.008), and DBT reading time decreased after less than 9 months accrued screening experience (p = 0.01).

CONCLUSIONS

DBT reading times were double those of FFDM in the screening setting, but there was a short learning curve effect with readers showing significant improvements in reading times within the first nine months of DBT experience.

CLINICALTRIALS

gov Identifier: NCT03733106.

AI-enhanced Mammography With Digital Breast Tomosynthesis for Breast Cancer Detection: Clinical Value and Comparison With Human Performance

Purpose To compare two deep learning-based commercially available artificial intelligence (AI) systems for mammography with digital breast tomosynthesis (DBT) and benchmark them against the performance of radiologists. Materials and Methods This retrospective study included consecutive asymptomatic patients who underwent mammography with DBT (2019-2020). Two AI systems (Transpara 1.7.0 and ProFound AI 3.0) were used to evaluate the DBT examinations. The systems were compared using receiver operating characteristic (ROC) analysis to calculate the area under the ROC curve (AUC) for detecting malignancy overall and within subgroups based on mammographic breast density. Breast Imaging Reporting and Data System results obtained from standard-of-care human double-reading were compared against AI results with use of the DeLong test. Results Of 419 female patients (median age, 60 years [IQR, 52-70 years]) included, 58 had histologically proven breast cancer. The AUC was 0.86 (95% CI: 0.85, 0.91), 0.93 (95% CI: 0.90, 0.95), and 0.98 (95% CI: 0.96, 0.99) for Transpara, ProFound AI, and human double-reading, respectively. For Transpara, a rule-out criterion of score 7 or lower yielded 100% (95% CI: 94.2, 100.0) sensitivity and 60.9% (95% CI: 55.7, 66.0) specificity. The rule-in criterion of higher than score 9 yielded 96.6% sensitivity (95% CI: 88.1, 99.6) and 78.1% specificity (95% CI: 73.8, 82.5). For ProFound AI, a rule-out criterion of lower than score 51 yielded 100% sensitivity (95% CI: 93.8, 100) and 67.0% specificity (95% CI: 62.2, 72.1). The rule-in criterion of higher than score 69 yielded 93.1% (95% CI: 83.3, 98.1) sensitivity and 82.0% (95% CI: 77.9, 86.1) specificity. Conclusion Both AI systems showed high performance in breast cancer detection but lower performance compared with human double-reading. Keywords: Mammography, Breast, Oncology, Artificial Intelligence, Deep Learning, Digital Breast Tomosynthesis © RSNA, 2024.

Comparisons between artificial intelligence computer-aided detection synthesized mammograms and digital mammograms when used alone and in combination with tomosynthesis images in a virtual screening setting

PURPOSE

To compare the reader performance of artificial intelligence computer-aided detection synthesized mammograms (AI CAD SM) with that of digital mammograms (DM) when used alone or in combination with digital breast tomosynthesis (DBT) images.

MATERIALS AND METHODS

This retrospective multireader (n = 4) study compared the reader performances in 388 cases (84 cancer, 83 benign, and 221 normal or benign cases). The overall accuracy of the breast-based assessment was determined by four radiologists using two sequential reading modes: DM followed by DM + DBT; and AI CAD SM followed by AI CAD SM + DBT. Each breast was rated by each reader using five-category ratings, where 3 or higher was considered positive. The area under the receiver-operating characteristic curve (AUC) and reading time were evaluated.

RESULTS

The mean AUC values for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0.863, 0.895, 0.886, and 0.902, respectively. The mean AUC of AI CAD SM was significantly higher (P < 0.0001) than that of DM. The mean AUC of AI CAD SM + DBT was higher than that of DM + DBT (P = 0.094). A significant reduction in the reading time was observed after using AI CAD SM + DBT when compared with that after using DM + DBT (P < 0.001).

CONCLUSION

AI CAD SM + DBT might prove more effective than DM + DBT in a screening setting because of its lower radiation dose, noninferiority, and shorter reading time compared to DM + DBT.

Artificial intelligence computer-aided detection enhances synthesized mammograms: comparison with original digital mammograms alone and in combination with tomosynthesis images in an experimental setting

BACKGROUND

It remains unclear whether original full-field digital mammograms (DMs) can be replaced with synthesized mammograms in both screening and diagnostic settings. To compare reader performance of artificial intelligence computer-aided detection synthesized mammograms (AI CAD SMs) with that of DM alone or in combination with digital breast tomosynthesis (DBT) images in an experimental setting.

METHODS

We compared the performance of multireader (n = 4) and reading multicase (n = 388), in 84 cancers, 83 biopsy-proven benign lesions, and 221 normal or benign cases with negative results after 1-year follow-up. Each reading was independently interpreted with four reading modes: DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT. The accuracy of probability of malignancy (POM) and five-category ratings were evaluated using areas under the receiver operating characteristic curve (AUC) in the random-reader analysis.

RESULTS

The mean AUC values based on POM for DM, AI CAD SM, DM + DBT, and AI CAD SM + DBT were 0.871, 0.902, 0.895, and 0.909, respectively. The mean AUC of AI CAD SM was significantly higher (P = 0.002) than that of DM. For calcification lesions, the sensitivity of SM and DM did not differ significantly (P = 0.204). The mean AUC for AI CAD SM + DBT was higher than that of DM + DBT (P = 0.082). ROC curves based on the five-category ratings showed similar proximity of the overall performance levels.

CONCLUSIONS

AI CAD SM alone was superior to DM alone. Also, AI CAD SM + DBT was superior to DM + DBT but not statistically significant.

Artificial intelligence for digital breast tomosynthesis: Impact on diagnostic performance, reading times, and workload in the era of personalized screening

The ultimate goals of the application of artificial intelligence (AI) to digital breast tomosynthesis (DBT) are the reduction of reading times, the increase of diagnostic performance, and the reduction of interval cancer rates. In this review, after outlining the journey from computer-aided detection/diagnosis systems to AI applied to digital mammography (DM), we summarize the results of studies where AI was applied to DBT, noting that long-term advantages of DBT screening and its crucial ability to decrease the interval cancer rate are still under scrutiny. AI has shown the capability to overcome some shortcomings of DBT in the screening setting by improving diagnostic performance and by reducing recall rates (from -2 % to -27 %) and reading times (up to -53 %, with an average 20 % reduction), but the ability of AI to reduce interval cancer rates has not yet been clearly investigated. Prospective validation is needed to assess the cost-effectiveness and real-world impact of AI models assisting DBT interpretation, especially in large-scale studies with low breast cancer prevalence. Finally, we focus on the incoming era of personalized and risk-stratified screening that will first see the application of contrast-enhanced breast imaging to screen women with extremely dense breasts. As the diagnostic advantage of DBT over DM was concentrated in this category, we try to understand if the application of AI to DM in the remaining cohorts of women with heterogeneously dense or non-dense breast could close the gap in diagnostic performance between DM and DBT, thus neutralizing the usefulness of AI application to DBT.

Breast cancer screening with digital breast tomosynthesis: comparison of different reading strategies implementing artificial intelligence

Objectives

Digital breast tomosynthesis (DBT) can detect more cancers than the current standard breast screening method, digital mammography (DM); however, it can substantially increase the reading workload and thus hinder implementation in screening. Artificial intelligence (AI) might be a solution. The aim of this study was to retrospectively test different ways of using AI in a screening workflow.

Methods

An AI system was used to analyse 14,772 double-read single-view DBT examinations from a screening trial with paired DM double reading. Three scenarios were studied: if AI can identify normal cases that can be excluded from human reading; if AI can replace the second reader; if AI can replace both readers. The number of detected cancers and false positives was compared with DM or DBT double reading.

Results

By excluding normal cases and only reading 50.5% (7460/14,772) of all examinations, 95% (121/127) of the DBT double reading detected cancers could be detected. Compared to DM screening, 27% (26/95) more cancers could be detected (p < 0.001) while keeping recall rates at the same level. With AI replacing the second reader, 95% (120/127) of the DBT double reading detected cancers could be detected—26% (25/95) more than DM screening (p < 0.001)—while increasing recall rates by 53%. AI alone with DBT has a sensitivity similar to DM double reading (p = 0.689).

Conclusion

AI can open up possibilities for implementing DBT screening and detecting more cancers with the total reading workload unchanged. Considering the potential legal and psychological implications, replacing the second reader with AI would probably be most the feasible approach.

Key Points

• Breast cancer screening with digital breast tomosynthesis and artificial intelligence can detect more cancers than mammography screening without increasing screen-reading workload.

• Artificial intelligence can either exclude low-risk cases from double reading or replace the second reader.

• Retrospective study based on paired mammography and digital breast tomosynthesis screening data.

Automatic Classification of Simulated Breast Tomosynthesis Whole Images for the Presence of Microcalcification Clusters Using Deep CNNs

Microcalcification clusters (MCs) are among the most important biomarkers for breast cancer, especially in cases of nonpalpable lesions. The vast majority of deep learning studies on digital breast tomosynthesis (DBT) are focused on detecting and classifying lesions, especially soft-tissue lesions, in small regions of interest previously selected. Only about 25% of the studies are specific to MCs, and all of them are based on the classification of small preselected regions. Classifying the whole image according to the presence or absence of MCs is a difficult task due to the size of MCs and all the information present in an entire image. A completely automatic and direct classification, which receives the entire image, without prior identification of any regions, is crucial for the usefulness of these techniques in a real clinical and screening environment. The main purpose of this work is to implement and evaluate the performance of convolutional neural networks (CNNs) regarding an automatic classification of a complete DBT image for the presence or absence of MCs (without any prior identification of regions). In this work, four popular deep CNNs are trained and compared with a new architecture proposed by us. The main task of these trainings was the classification of DBT cases by absence or presence of MCs. A public database of realistic simulated data was used, and the whole DBT image was taken into account as input. DBT data were considered without and with preprocessing (to study the impact of noise reduction and contrast enhancement methods on the evaluation of MCs with CNNs). The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance. Very promising results were achieved with a maximum AUC of 94.19% for the GoogLeNet. The second-best AUC value was obtained with a new implemented network, CNN-a, with 91.17%. This CNN had the particularity of also being the fastest, thus becoming a very interesting model to be considered in other studies. With this work, encouraging outcomes were achieved in this regard, obtaining similar results to other studies for the detection of larger lesions such as masses. Moreover, given the difficulty of visualizing the MCs, which are often spread over several slices, this work may have an important impact on the clinical analysis of DBT images.

The Economic Impact of AI on Breast Imaging

This article explores the development of computer-aided detection (CAD) and artificial or augmented intelligence (AI) for breast radiology examinations and describes the current applications of AI in breast imaging. Although radiologists in other subspecialties may be less familiar with the use of these technologies in their practices, CAD has been used in breast imaging for more than two decades, as mammography CAD programs have been commercially available in the United States since the late 1990s. Likewise, breast radiologists have seen payment for CAD in mammography and breast MRI evolve over time. With the rapid expansion of AI products in radiology in recent years, many new applications for these technologies in breast imaging have emerged. This article outlines the current state of reimbursement for breast radiology AI algorithms within the traditional fee-for-service model used by Medicare and commercial insurers as well as potential future payment pathways. In addition, the inherent challenges of employing the existing payment framework in the United States to AI programs in radiology are detailed for the reader. This article aims to give breast radiologists a better understanding of how AI will be reimbursed as they seek to further incorporate these emerging technologies into their practices to advance patient care and improve workflow efficiency.

Can a Computer-Aided Mass Diagnosis Model Based on Perceptive Features Learned From Quantitative Mammography Radiology Reports Improve Junior Radiologists' Diagnosis Performance? An Observer Study

Radiologists' diagnostic capabilities for breast mass lesions depend on their experience. Junior radiologists may underestimate or overestimate Breast Imaging Reporting and Data System (BI-RADS) categories of mass lesions owing to a lack of diagnostic experience. The computer-aided diagnosis (CAD) method assists in improving diagnostic performance by providing a breast mass classification reference to radiologists. This study aims to evaluate the impact of a CAD method based on perceptive features learned from quantitative BI-RADS descriptions on breast mass diagnosis performance. We conducted a retrospective multi-reader multi-case (MRMC) study to assess the perceptive feature-based CAD method. A total of 416 digital mammograms of patients with breast masses were obtained from 2014 through 2017, including 231 benign and 185 malignant masses, from which we randomly selected 214 cases (109 benign, 105 malignant) to train the CAD model for perceptive feature extraction and classification. The remaining 202 cases were enrolled as the test set for evaluation, of which 51 patients (29 benign and 22 malignant) participated in the MRMC study. In the MRMC study, we categorized six radiologists into three groups: junior, middle-senior, and senior. They diagnosed 51 patients with and without support from the CAD model. The BI-RADS category, benign or malignant diagnosis, malignancy probability, and diagnosis time during the two evaluation sessions were recorded. In the MRMC evaluation, the average area under the curve (AUC) of the six radiologists with CAD support was slightly higher than that without support (0.896 vs. 0.850, p = 0.0209). Both average sensitivity and specificity increased (p = 0.0253). Under CAD assistance, junior and middle-senior radiologists adjusted the assessment categories of more BI-RADS 4 cases. The diagnosis time with and without CAD support was comparable for five radiologists. The CAD model improved the radiologists' diagnostic performance for breast masses without prolonging the diagnosis time and assisted in a better BI-RADS assessment, especially for junior radiologists.

Digital Breast Tomosynthesis: Potential Benefits in Routine Clinical Practice

Digital breast tomosynthesis (DBT) is gradually being implemented in routine clinical breast imaging practice. The technique of image acquisition reduces the confounding effect of overlapping breast tissue, which substantially affects cancer detection, abnormal recall, and interval cancer rates in a screening/ surveillance setting. In a diagnostic setting, tomosynthesis also allows for improved lesion localization and characterization over conventional imaging, which potentially improves the accuracy and improved workflow efficiency. To optimize the utility of tomosynthesis, imagers should be aware of the pertinent aspects of image acquisition as it relates to interpretation, the appearance of benign and malignant pathologies, and sources of possible misinterpretation. This article aims to provide a practical knowledge base of DBT and demonstrate its potential benefits when incorporated into routine clinical practice.

Radiomics: A Primer for Breast Radiologists

Radiomics has a long-standing history in breast imaging with computer-aided detection (CAD) for screening mammography developed in the late 20th century. Although conventional CAD had widespread adoption, the clinical benefits for experienced breast radiologists were debatable due to high false-positive marks and subsequent increased recall rates. The dramatic growth in recent years of artificial intelligence-based analysis, including machine learning and deep learning, has provided numerous opportunities for improved modern radiomics work in breast imaging. There has been extensive radiomics work in mammography, digital breast tomosynthesis, MRI, ultrasound, PET-CT, and combined multimodality imaging. Specific radiomics outcomes of interest have been diverse, including CAD, prediction of response to neoadjuvant therapy, lesion classification, and survival, among other outcomes. Additionally, the radiogenomics subfield that correlates radiomics features with genetics has been very proliferative, in parallel with the clinical validation of breast cancer molecular subtypes and gene expression assays. Despite the promise of radiomics, there are important challenges related to image normalization, limited large unbiased data sets, and lack of external validation. Much of the radiomics work to date has been exploratory using single-institution retrospective series for analysis, but several promising lines of investigation have made the leap to clinical practice with commercially available products. As a result, breast radiologists will increasingly be incorporating radiomics-based tools into their daily practice in the near future. Therefore, breast radiologists must have a broad understanding of the scope, applications, and limitations of radiomics work.

Performance and reading time of lung nodule identification on multidetector CT with or without an artificial intelligence-powered computer-aided detection system

AIM

To compare the performance and reading time of different readers using automatic artificial intelligence (AI)-powered computer-aided detection (CAD) to detect lung nodules in different reading modes.

MATERIALS AND METHODS

One hundred and fifty multidetector computed tomography (CT) datasets containing 340 nodules ≤10 mm in diameter were collected retrospectively. A CAD with vessel-suppressed function was used to interpret the images. Three junior and three senior readers were assigned to read (1) CT images without CAD, (2) second-read using CAD in which CAD was applied only after initial unassisted assessment, and (3) a concurrent read with CAD in which CAD was applied at the start of assessment. Diagnostic performances and reading times were compared using analysis of variance.

RESULTS

For all readers, the mean sensitivity improved from 64% (95% confidence interval [CI]: 62%, 66%) for the without-CAD mode to 82% (95% CI: 80%, 84%) for the second-reading mode and to 80% (95% CI: 79%, 82%) for the concurrent-reading mode (p<0.001). There was no significant difference between the two modes in terms of the mean sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) for both junior and senior readers and all readers (p>0.05). The reading time of all readers was significantly shorter for the concurrent-reading mode (124 ± 25 seconds) compared to without CAD (156 ± 34 seconds; p<0.001) and the second-reading mode (197 ± 46 seconds; p<0.001).

CONCLUSION

In CAD for lung nodules at CT, the second-reading mode and concurrent-reading mode may improve detection performance for all readers in both screening and clinical routine practice. Concurrent use of CAD is more efficient for both junior and senior readers.

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.

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.

Are artificial intelligence systems useful in breast cancer screening programs?

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.

Deep learning in breast radiology: current progress and future directions

This review provides an overview of current applications of deep learning methods within breast radiology. The diagnostic capabilities of deep learning in breast radiology continue to improve, giving rise to the prospect that these methods may be integrated not only into detection and classification of breast lesions, but also into areas such as risk estimation and prediction of tumor responses to therapy. Remaining challenges include limited availability of high-quality data with expert annotations and ground truth determinations, the need for further validation of initial results, and unresolved medicolegal considerations. KEY POINTS: • Deep learning (DL) continues to push the boundaries of what can be accomplished by artificial intelligence (AI) in breast imaging with distinct advantages over conventional computer-aided detection. • DL-based AI has the potential to augment the capabilities of breast radiologists by improving diagnostic accuracy, increasing efficiency, and supporting clinical decision-making through prediction of prognosis and therapeutic response. • Remaining challenges to DL implementation include a paucity of prospective data on DL utilization and yet unresolved medicolegal questions regarding increasing AI utilization.

An Enhanced Visualization of DBT Imaging Using Blind Deconvolution and Total Variation Minimization Regularization

Digital Breast Tomosynthesis (DBT) presents out-of-plane artifacts caused by features of high intensity. Given observed data and knowledge about the point spread function (PSF), deconvolution techniques recover data from a blurred version. However, a correct PSF is difficult to achieve and these methods amplify noise. When no information is available about the PSF, blind deconvolution can be used. Additionally, Total Variation (TV) minimization algorithms have achieved great success due to its virtue of preserving edges while reducing image noise. This work presents a novel approach in DBT through the study of out-of-plane artifacts using blind deconvolution and noise regularization based on TV minimization. Gradient information was also included. The methodology was tested using real phantom data and one clinical data set. The results were investigated using conventional 2D slice-by-slice visualization and 3D volume rendering. For the 2D analysis, the artifact spread function (ASF) and Full Width at Half Maximum (FWHMM_ASF) of the ASF were considered. The 3D quantitative analysis was based on the FWHM of disks profiles at 90°, noise and signal to noise ratio (SNR) at 0° and 90°. A marked visual decrease of the artifact with reductions of FWHM_ASF (2D) and FWHM_90° (volume rendering) of 23.8% and 23.6%, respectively, was observed. Although there was an expected increase in noise level, SNR values were preserved after deconvolution. Regardless of the methodology and visualization approach, the objective of reducing the out-of-plane artifact was accomplished. Both for the phantom and clinical case, the artifact reduction in the z was markedly visible.

Digital Breast Tomosynthesis Slab Thickness: Impact on Reader Performance and Interpretation Time

Background Digital breast tomosynthesis (DBT) helps reduce recall rates and improve cancer detection compared with two-dimensional (2D) mammography but has a longer interpretation time. Purpose To evaluate the effect of DBT slab thickness and overlap on reader performance and interpretation time in the absence of 1-mm slices. Materials and Methods In this retrospective HIPAA-compliant multireader study of DBT examinations performed between August 2013 and July 2017, four fellowship-trained breast imaging radiologists blinded to final histologic findings interpreted DBT examinations by using a standard protocol (10-mm slabs with 5-mm overlap, 1-mm slices, synthetic 2D mammogram) and an experimental protocol (6-mm slabs with 3-mm overlap, synthetic 2D mammogram) with a crossover design. Among the 122 DBT examinations, 74 mammographic findings had final histologic findings, including 31 masses (26 malignant), 20 groups of calcifications (12 malignant), 18 architectural distortions (15 malignant), and five asymmetries (two malignant). Durations of reader interpretations were recorded. Comparisons were made by using receiver operating characteristic curves for diagnostic performance and paired t tests for continuous variables. Results Among 122 women, mean age was 58.6 years ± 10.1 (standard deviation). For detection of malignancy, areas under the receiver operating characteristic curves were similar between protocols (range, 0.83-0.94 vs 0.84-0.92; P ≥ .63). Mean DBT interpretation time was shorter with the experimental protocol for three of four readers (reader 1, 5.6 minutes ± 1.7 vs 4.7 minutes ± 1.4 [P < .001]; reader 2, 2.8 minutes ± 1.1 vs 2.3 minutes ± 1.0 [P = .001]; reader 3, 3.6 minutes ± 1.4 vs 3.3 minutes ± 1.3 [P = .17]; reader 4, 4.3 minutes ± 1.0 vs 3.8 minutes ± 1.1 [P ≤ .001]), with 72% reduction in both mean number of images and mean file size (P < .001 for both). Conclusion A digital breast tomosynthesis reconstruction protocol that uses 6-mm slabs with 3-mm overlap, without 1-mm slices, had similar diagnostic performance compared with the standard protocol and led to a reduced interpretation time for three of four readers. © RSNA, 2020 See also the editorial by Chang in this issue.

Impact of total variation minimization in volume rendering visualization of breast tomosynthesis data

BACKGROUND AND OBJECTIVE

Total Variation (TV) minimization algorithms have achieved great attention due to the virtue of decreasing noise while preserving edges. The purpose of this work is to implement and evaluate two TV minimization methods in 3D. Their performance is analyzed through 3D visualization of digital breast tomosynthesis (DBT) data with volume rendering.

METHODS

Both filters were studied with real phantom and one clinical DBT data. One algorithm was applied sequentially to all slices and the other was applied to the entire volume at once. The suitable Lagrange multiplier used in each filter equation was studied to reach the minimum 3D TV and the maximum contrast-to-noise ratio (CNR). Imaging blur was measured at 0° and 90° using two disks with different diameters (0.5 mm and 5.0 mm) and equal thickness. The quality of unfiltered and filtered data was analyzed with volume rendering at 0° and 90°.

RESULTS

For phantom data, with the sequential filter, a decrease of 25% in 3D TV value and an increase of 19% and 30% in CNR at 0° and 90°, respectively, were observed. When the filter is applied directly in 3D, TV value was reduced by 35% and an increase of 36% was achieved both for CNR at 0° and 90°. For the smaller disk, variations of 0% in width at half maximum (FWHM) at 0° and a decrease of about 2.5% for FWHM at 90° were observed for both filters. For the larger disk, there was a 2.5% increase in FWHM at 0° for both filters and a decrease of 6.28% and 1.69% in FWHM at 90° with the sequential filter and the 3D filter, respectively. When applied to clinical data, the performance of each filter was consistent with that obtained with the phantom.

CONCLUSIONS

Data analysis confirmed the relevance of these methods in improving quality of DBT images. Additionally, this type of 3D visualization showed that it may play an important complementary role in DBT imaging. It allows to visualize all DBT data at once and to analyze properly filters applied to all the three dimensions. Concise Abstract Total Variation (TV) minimization algorithms are one compressed sensing technique that has achieved great attention due to the virtue of decrease noise while preserve edges transitions. The purpose of this work is to solve the same TV minimization problem in DBT data, by studying two 3D filters. The obtained results were analyzed at 0° and 90° with a 3D visualization through volume rendering. The filters differ in their application. One considers a slice-by-slice optimization, sequentially traversing all slices of the data. The other considers the intensity values of adjacent slices to make this optimization on each voxel. The performance of each filter was also tested with a clinical case. The results obtained were very encouraging with a significantly increased contrast to noise ratio at 0° and 90° and a small reduction in blur at 90° (slight reduction of the out-of-plane artifact).

New Frontiers: An Update on Computer-Aided Diagnosis for Breast Imaging in the Age of Artificial Intelligence

OBJECTIVE

The purpose of this article is to compare traditional versus machine learning-based computer-aided detection (CAD) platforms in breast imaging with a focus on mammography, to underscore limitations of traditional CAD, and to highlight potential solutions in new CAD systems under development for the future.

CONCLUSION

CAD development for breast imaging is undergoing a paradigm shift based on vast improvement of computing power and rapid emergence of advanced deep learning algorithms, heralding new systems that may hold real potential to improve clinical care.

Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives

Although computer-aided diagnosis (CAD) is widely used in mammography, conventional CAD programs that use prompts to indicate potential cancers on the mammograms have not led to an improvement in diagnostic accuracy. Because of the advances in machine learning, especially with use of deep (multilayered) convolutional neural networks, artificial intelligence has undergone a transformation that has improved the quality of the predictions of the models. Recently, such deep learning algorithms have been applied to mammography and digital breast tomosynthesis (DBT). In this review, the authors explain how deep learning works in the context of mammography and DBT and define the important technical challenges. Subsequently, they discuss the current status and future perspectives of artificial intelligence-based clinical applications for mammography, DBT, and radiomics. Available algorithms are advanced and approach the performance of radiologists-especially for cancer detection and risk prediction at mammography. However, clinical validation is largely lacking, and it is not clear how the power of deep learning should be used to optimize practice. Further development of deep learning models is necessary for DBT, and this requires collection of larger databases. It is expected that deep learning will eventually have an important role in DBT, including the generation of synthetic images.

Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis

Purpose

To evaluate the use of artificial intelligence (AI) to shorten digital breast tomosynthesis (DBT) reading time while maintaining or improving accuracy.

Materials and Methods

A deep learning AI system was developed to identify suspicious soft-tissue and calcified lesions in DBT images. A reader study compared the performance of 24 radiologists (13 of whom were breast subspecialists) reading 260 DBT examinations (including 65 cancer cases) both with and without AI. Readings occurred in two sessions separated by at least 4 weeks. Area under the receiver operating characteristic curve (AUC), reading time, sensitivity, specificity, and recall rate were evaluated with statistical methods for multireader, multicase studies.

Results

Radiologist performance for the detection of malignant lesions, measured by mean AUC, increased 0.057 with the use of AI (95% confidence interval [CI]: 0.028, 0.087; P < .01), from 0.795 without AI to 0.852 with AI. Reading time decreased 52.7% (95% CI: 41.8%, 61.5%; P < .01), from 64.1 seconds without to 30.4 seconds with AI. Sensitivity increased from 77.0% without AI to 85.0% with AI (8.0%; 95% CI: 2.6%, 13.4%; P < .01), specificity increased from 62.7% without to 69.6% with AI (6.9%; 95% CI: 3.0%, 10.8%; noninferiority P < .01), and recall rate for noncancers decreased from 38.0% without to 30.9% with AI (7.2%; 95% CI: 3.1%, 11.2%; noninferiority P < .01).

Conclusion

The concurrent use of an accurate DBT AI system was found to improve cancer detection efficacy in a reader study that demonstrated increases in AUC, sensitivity, and specificity and a reduction in recall rate and reading time.© RSNA, 2019See also the commentary by Hsu and Hoyt in this issue.

Performance and Reading Time of Automated Breast US with or without Computer-aided Detection

BackgroundComputer-aided detection (CAD) systems may be used to help radiologists interpret automated breast (AB) US images. However, the optimal use of CAD with AB US has, to the knowledge of the authors, not been determined.PurposeTo compare the performance and reading time of different readers by using AB US CAD system to detect breast cancer in different reading modes.Materials and MethodsIn this retrospective study, 1485 AB US images (282 with malignant lesions, 695 with benign lesions, and 508 healthy) in 1452 women (mean age, 43.7 years; age range, 19-82 years) including 529 (36.4%) women who were asymptomatic were collected between 2016 and 2017. A CAD system was used to interpret the images. Three novice readers with 1-3 years of US experience and three experienced readers with 5-10 years of US experience were assigned to read AB US images without CAD, at a second reading (after the reader completed a full unaided interpretation), and at concurrent reading (use of CAD at the start of the assessment). Diagnostic performances and reading times were compared by using analysis of variance.ResultsFor all readers, the mean area under the receiver operating characteristic curve improved from 0.88 (95% confidence interval [CI]: 0.85, 0.91) at without-CAD mode to 0.91 (95% CI: 0.89, 0.92; P < .001) at the second-reading mode and 0.90 (95% CI: 0.89, 0.92; P = .002) at the concurrent-reading mode. The mean sensitivity of novice readers in women who were asymptomatic improved from 67% (95% CI: 63%, 74%) at without-CAD mode to 88% (95% CI: 84%, 89%) at both the second-reading mode and the concurrent-reading mode (P = .003). Compared with the without-CAD and second-reading modes, the mean reading time per volume of concurrent reading was 16 seconds (95% CI: 11, 22; P < .001) and 27 seconds (95% CI: 21, 32; P < .001) shorter, respectively.ConclusionComputer-aided detection (CAD) was helpful for novice readers to improve cancer detection at automated breast US in women who were asymptomatic. CAD was more efficient when used concurrently for all readers.© RSNA, 2019Online supplemental material is available for this article.See also the editorial by Slanetz in this issue.

Breast tomosynthesis: state of the art

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

Comparing two visualization protocols for tomosynthesis in screening: specificity and sensitivity of slabs versus planes plus slabs

OBJECTIVES

Tomosynthesis (DBT) has proven to be more sensitive than digital mammography, but it requires longer reading time. We retrospectively compared accuracy and reading times of a simplified protocol with 1-cm-thick slabs versus a standard protocol of slabs + 1-mm-spaced planes, both integrated with synthetic 2D.

METHODS

We randomly selected 894 DBTs (including 12 cancers) from the experimental arm of the RETomo trial. DBTs were read by two radiologists to estimate specificity. A second set of 24 cancers (8 also present in the first set) mixed within 276 negative DBTs was read by two radiologists. In total, 28 cancers with 64 readings were used to estimate sensitivity. Radiologists read with both protocols separated by a 3-month washout. Only women that were positive at the screening reading were assessed. Variance was estimated taking into account repeated measures.

RESULTS

Sensitivity was 82.8% (53/64, 95% confidence interval (95% CI) 67.2-92.2) and 90.6% (95% CI 80.2-95.8) with simplified and standard protocols, respectively. In the random screening setting, specificity was 97.9% (1727/1764, 95% CI 97.1-98.5) and 96.3% (95% CI 95.3-97.1), respectively. Inter-reader agreement was 0.68 and 0.54 with simplified and standard protocols, respectively. Median reading times with simplified protocol were 20% to 30% shorter than with standard protocol.

CONCLUSIONS

A simplified protocol reduced reading time and false positives but may have a negative impact on sensitivity.

KEY POINTS

• The adoption of digital breast tomosynthesis (DBT) in screening, more sensitive than mammography, could be limited by its potential effect on the radiologists' workload, i.e., increased reading time and fatigue. • A DBT simplified protocol with slab only, compared to a standard protocol (slab plus planes) both integrated with synthetic 2D, reduced time and false positives but had a negative impact on sensitivity.

Calcifications at Digital Breast Tomosynthesis: Imaging Features and Biopsy Techniques

Full-field digital mammography (FFDM), the standard of care for breast cancer screening, has some limitations. With the advent of digital breast tomosynthesis (DBT), improvements including decreased recall rates and increased cancer detection rates have been observed. The quasi-three-dimensional capability of DBT reduces breast tissue overlap, a significant limitation of FFDM. However, early studies demonstrate that a few cancers detected at FFDM may not be diagnosed at DBT-only screening, and lesions with calcifications as the dominant feature may look less suspicious at DBT or not be visible at all. These findings support the use of combined FFDM and DBT protocols to optimize screening performance. However, this combination would approximately double the patient's radiation exposure. The development of computer algorithms that generate two-dimensional synthesized mammography (SM) views from DBT has improved calcification conspicuity and sensitivity. Therefore, SM may substitute for FFDM in screening protocols, reducing radiation exposure. DBT plus SM demonstrates significantly better performance than that of FFDM alone, although there are reports of missed malignant calcifications. Thus, some centers continue to perform FFDM with DBT. Use of DBT in breast imaging has also necessitated the development of DBT-guided biopsy. DBT-guided biopsy may have a higher success rate than that of stereotactic biopsy, with a shorter procedure time. While DBT brings substantial improvements to breast cancer imaging, it is important to be aware of its strengths and limitations regarding detection of calcifications. This article reviews the imaging appearance of breast calcifications at DBT, discusses calcification biopsy techniques, and provides an overview of the current literature. Online supplemental material is available for this article. ^©RSNA, 2019 An earlier incorrect version of this article appeared online. This article was corrected on February 13, 2019.

Decrease in interpretation time for both novice and experienced readers using a concurrent computer-aided detection system for digital breast tomosynthesis

OBJECTIVES

To compare the diagnostic performance and interpretation time of digital breast tomosynthesis (DBT) for both novice and experienced readers with and without using a computer-aided detection (CAD) system for concurrent read.

METHODS

CAD system was developed for concurrent read in DBT interpretation. In this observer performance study, we used an enriched sample of 100 DBT cases including 70 with and 30 without breast cancers. Image interpretation was performed by four radiologists with different experience levels (two experienced and two novice). Each reader completed two reading sessions (at a minimum 2-month interval), once with and once without CAD. Three different rating scales were used to record each reader's interpretation. Reader performance with and without CAD was reported and compared for each radiologist. Reading time for each case was also recorded.

RESULTS

Average area under the receiver operating characteristic curve values for BI-RADS scale on using CAD were 0.778 and 0.776 without using CAD, demonstrating no statistically significant differences. Results were consistent when the probability of malignancy and percentage probability of malignancy scales were used. Reading times per case were 72.07 s and 62.03 s (SD, 37.54 s vs 34.38 s) without and with CAD, respectively. The average difference in reading time on using CAD was a statistically significant decrease of 10.04 ± 1.85 s, providing 14% decrease in time. The time-reducing effect was consistently observed in both novice and experienced readers.

CONCLUSION

DBT combined with CAD reduced interpretation time without diagnostic performance loss to novice and experienced readers.

KEY POINTS

• The use of a concurrent DBT-CAD system shortened interpretation time. • The shortened interpretation time with DBT-CAD did not come at a cost to diagnostic performance to novice or experienced readers. • The concurrent DBT-CAD system improved the efficiency of DBT interpretation.

A review of computer aided detection in mammography

Breast screening with mammography is widely recognized as the most effective method of detecting early breast cancer and has consistently demonstrated a 20-40% decrease in mortality among screened women. Despite this, the sensitivity of mammography ranges between 70 and 90%. Computer aided detection (CAD) is an artificial intelligence (AI) technique that utilizes pattern recognition to highlight suspicious features on imaging and marks them for the radiologist to review and interpret. It aims to decrease oversights made by interpreting radiologists. Here we review the efficacy of CAD and potential future directions.

Evaluation of a computer-aided detection (CAD)-enhanced 2D synthetic mammogram: comparison with standard synthetic 2D mammograms and conventional 2D digital mammography

AIM

To evaluate the diagnostic performance of computer-aided detection (CAD)-enhanced synthetic mammograms in comparison with standard synthetic mammograms and full-field digital mammography (FFDM).

MATERIALS AND METHODS

A CAD-enhanced synthetic mammogram, a standard synthetic mammogram, and FFDM were available in 68 breast-screening cases recalled for soft-tissue abnormalities (masses, parenchymal deformities, and asymmetric densities). Two radiologists, blinded to image type and final assessment outcome, retrospectively read oblique and craniocaudal projections for each type of mammogram. The resulting 204 pairs of 2D images were presented in random order and scored on a five-point scale (1, normal to 5, malignant) without access to the Digital breast tomosynthesis (DBT) slices. Receiver operating characteristic (ROC) curve analysis was performed.

RESULTS

There were 34 biopsy-proven malignancies and 34 normal/benign cases. Diagnostic accuracy was significantly improved for the CAD-enhanced synthetic mammogram compared to the standard synthetic mammogram (area under the ROC curve [AUC]=0.846 and AUC=0.683 respectively, p=0.004) and compared to the conventional 2D FFDM (AUC=0.724, p=0.027). The CAD-enhanced synthetic mammogram had the highest diagnostic accuracy for all soft-tissue abnormalities, and for malignant lesions sensitivity was not affected by tumour size. For all 68 cases, there was an average of 3.2 areas enhanced per image. For the 34 cancer cases, 97.4% of lesions were correctly enhanced, with 2.1 false areas enhanced per image.

CONCLUSIONS

CAD enhancement significantly improves performance of synthetic 2D mammograms and also exhibits improved diagnostic accuracy compared to conventional 2D FFDM.