Assessment of Background Parenchymal Enhancement at Dynamic Contrast-enhanced MRI in Predicting Breast Cancer Recurrence Risk.

Background Background parenchymal enhancement (BPE) at dynamic contrast-enhanced (DCE) MRI of cancer-free breasts increases the risk of developing breast cancer; implications of quantitative BPE in ipsilateral breasts with breast cancer are largely unexplored. Purpose To determine whether quantitative BPE measurements in one or both breasts could be used to predict recurrence risk in women with breast cancer, using the Oncotype DX recurrence score as the reference standard. Materials and Methods This HIPAA-compliant retrospective single-institution study included women diagnosed with breast cancer between January 2007 and January 2012 (development set) and between January 2012 and January 2017 (internal test set). Quantitative BPE was automatically computed using an in-house-developed computer algorithm in both breasts. Univariable logistic regression was used to examine the association of BPE with Oncotype DX recurrence score binarized into high-risk (recurrence score >25) and low- or intermediate-risk (recurrence score ≤25) categories. Models including BPE measures were assessed for their ability to distinguish patients with high risk versus those with low or intermediate risk and the actual recurrence outcome. Results The development set included 127 women (mean age, 58 years ± 10.2 [SD]; 33 with high risk and 94 with low or intermediate risk) with an actual local or distant recurrence rate of 15.7% (20 of 127) at a minimum 10 years of follow-up. The test set included 60 women (mean age, 57.8 years ± 11.6; 16 with high risk and 44 with low or intermediate risk). BPE measurements quantified in both breasts were associated with increased odds of a high-risk Oncotype DX recurrence score (odds ratio range, 1.27-1.66 [95% CI: 1.02, 2.56]; P < .001 to P = .04). Measures of BPE combined with tumor radiomics helped distinguish patients with a high-risk Oncotype DX recurrence score from those with a low- or intermediate-risk score, with an area under the receiver operating characteristic curve of 0.94 in the development set and 0.79 in the test set. For the combined models, the negative predictive values were 0.97 and 0.93 in predicting actual distant recurrence and local recurrence, respectively. Conclusion Ipsilateral and contralateral DCE MRI measures of BPE quantified in patients with breast cancer can help distinguish patients with high recurrence risk from those with low or intermediate recurrence risk, similar to Oncotype DX recurrence score. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Zhou and Rahbar in this issue.

Addition of Contrast-enhanced Mammography to Tomosynthesis for Breast Cancer Detection in Women with a Personal History of Breast Cancer: Prospective TOCEM Trial Interim Analysis.

Background Digital breast tomosynthesis (DBT) is often inadequate for screening women with a personal history of breast cancer (PHBC). The ongoing prospective Tomosynthesis or Contrast-Enhanced Mammography, or TOCEM, trial includes three annual screenings with both DBT and contrast-enhanced mammography (CEM). Purpose To perform interim assessment of cancer yield, stage, and recall rate when CEM is added to DBT in women with PHBC. Materials and Methods From October 2019 to December 2022, two radiologists interpreted both examinations: Observer 1 reviewed DBT first and then CEM, and observer 2 reviewed CEM first and then DBT. Effects of adding CEM to DBT on incremental cancer detection rate (ICDR), cancer type and node status, recall rate, and other performance characteristics of the primary radiologist decisions were assessed. Results Among the participants (mean age at entry, 63.6 years ± 9.6 [SD]), 1273, 819, and 227 women with PHBC completed year 1, 2, and 3 screening, respectively. For observer 1, year 1 cancer yield was 20 of 1273 (15.7 per 1000 screenings) for DBT and 29 of 1273 (22.8 per 1000 screenings; ICDR, 7.1 per 1000 screenings [95% CI: 3.2, 13.4]) for DBT plus CEM (P < .001). Year 2 plus 3 cancer yield was four of 1046 (3.8 per 1000 screenings) for DBT and eight of 1046 (7.6 per 1000 screenings; ICDR, 3.8 per 1000 screenings [95% CI: 1.0, 7.6]) for DBT plus CEM (P = .001). Year 1 recall rate for observer 1 was 103 of 1273 (8.1%) for (incidence) DBT alone and 187 of 1273 (14.7%) for DBT plus CEM (difference = 84 of 1273, 6.6% [95% CI: 5.3, 8.1]; P < .001). Year 2 plus 3 recall rate was 40 of 1046 (3.8%) for DBT and 92 of 1046 (8.8%) for DBT plus CEM (difference = 52 of 1046, 5.0% [95% CI: 3.7, 6.3]; P < .001). In 18 breasts with cancer detected only at CEM after integration of both observers, 13 (72%) cancers were invasive (median tumor size, 0.6 cm) and eight of nine (88%) with staging were N0. Among 1883 screenings with adequate reference standard, there were three interval cancers (one at the scar, two in axillae). Conclusion CEM added to DBT increased early breast cancer detection each year in women with PHBC, with an accompanying approximately 5.0%-6.6% recall rate increase. Clinical trial registration no. NCT04085510 © RSNA, 2024 Supplemental material is available for this article.

Deep learning of longitudinal mammogram examinations for breast cancer risk prediction.

Information in digital mammogram images has been shown to be associated with the risk of developing breast cancer. Longitudinal breast cancer screening mammogram examinations may carry spatiotemporal information that can enhance breast cancer risk prediction. No deep learning models have been designed to capture such spatiotemporal information over multiple examinations to predict the risk. In this study, we propose a novel deep learning structure, LRP-NET, to capture the spatiotemporal changes of breast tissue over multiple negative/benign screening mammogram examinations to predict near-term breast cancer risk in a case-control setting. Specifically, LRP-NET is designed based on clinical knowledge to capture the imaging changes of bilateral breast tissue over four sequential mammogram examinations. We evaluate our proposed model with two ablation studies and compare it to three models/settings, including 1) a "loose" model without explicitly capturing the spatiotemporal changes over longitudinal examinations, 2) LRP-NET but using a varying number (i.e., 1 and 3) of sequential examinations, and 3) a previous model that uses only a single mammogram examination. On a case-control cohort of 200 patients, each with four examinations, our experiments on a total of 3200 images show that the LRP-NET model outperforms the compared models/settings.

Predicting cell invasion in breast tumor microenvironment from radiological imaging phenotypes.

BACKGROUND: The abundance of immune and stromal cells in the tumor microenvironment (TME) is informative of levels of inflammation, angiogenesis, and desmoplasia. Radiomics, an approach of extracting quantitative features from radiological imaging to characterize diseases, have been shown to predict molecular classification, cancer recurrence risk, and many other disease outcomes. However, the ability of radiomics methods to predict the abundance of various cell types in the TME remains unclear. In this study, we employed a radio-genomics approach and machine learning models to predict the infiltration of 10 cell types in breast cancer lesions utilizing radiomic features extracted from breast Dynamic Contrast Enhanced Magnetic Resonance Imaging. METHODS: We performed a retrospective study utilizing 73 patients from two independent institutions with imaging and gene expression data provided by The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA), respectively. A set of 199 radiomic features including shape-based, morphological, texture, and kinetic characteristics were extracted from the lesion volumes. To capture one-to-one relationships between radiomic features and cell type abundance, we performed linear regression on each radiomic feature/cell type abundance combination. Each regression model was tested for statistical significance. In addition, multivariate models were built for the cell type infiltration status (i.e. "high" vs "low") prediction. A feature selection process via Recursive Feature Elimination was applied to the radiomic features on the training set. The classification models took the form of a binary logistic extreme gradient boosting framework. Two evaluation methods including leave-one-out cross validation and external independent test, were used for radiomic model learning and testing. The models' performance was measured via area under the receiver operating characteristic curve (AUC). RESULTS: Univariate relationships were identified between a set of radiomic features and the abundance of fibroblasts. Multivariate models yielded leave-one-out cross validation AUCs ranging from 0.5 to 0.83, and independent test AUCs ranging from 0.5 to 0.68 for the multiple cell type invasion predictions. CONCLUSIONS: On two independent breast cancer cohorts, breast MRI-derived radiomics are associated with the tumor's microenvironment in terms of the abundance of several cell types. Further evaluation with larger cohorts is needed.

Diagnostic Performance of MRI, Molecular Breast Imaging, and Contrast-enhanced Mammography in Women with Newly Diagnosed Breast Cancer.

Background Staging newly diagnosed breast cancer by using dynamic contrast material-enhanced MRI is limited by access, high cost, and false-positive findings. The utility of contrast-enhanced mammography (CEM) and 99mTc sestamibi-based molecular breast imaging (MBI) in this setting is largely unknown. Purpose To compare extent-of-disease assessments by using MRI, CEM, and MBI versus pathology in women with breast cancer. Materials and Methods In this HIPAA-compliant prospective study, women with biopsy-proven breast cancer underwent MRI, CEM, and MBI between October 2014 and April 2018. Eight radiologists independently interpreted each examination result prospectively and were blinded to interpretations of findings with the other modalities. Visibility of index malignancies, lesion size, and additional suspicious lesions (malignant or benign) were compared during pathology review. Accuracy of index lesion sizing and detection of additional lesions in women without neoadjuvant chemotherapy were compared. Results A total of 102 women were enrolled and 99 completed the study protocol (mean age, 51 years ± 11 [standard deviation]; range, 32-77 years). Lumpectomy or mastectomy was performed in 71 women (79 index malignancies) without neoadjuvant chemotherapy and in 28 women (31 index malignancies) with neoadjuvant chemotherapy. Of the 110 index malignancies, MRI, CEM, and MBI depicted 102 (93%; 95% confidence interval [CI]: 86%, 97%), 100 (91%; 95% CI: 84%, 96%), and 101 (92%; 95% CI: 85%, 96%) malignancies, respectively. In patients without neoadjuvant chemotherapy, pathologic size of index malignancies was overestimated with all modalities (P = .02). MRI led to overestimation of 24% (17 of 72) of malignancies by more than 1.5 cm compared with 11% (eight of 70) with CEM and 15% (11 of 72) with MBI. MRI depicted more (P = .007) nonindex lesions, with sensitivity similar to that of CEM or MBI, resulting in lower positive predictive value of additional biopsies (13 of 46 [28%; 95% CI: 17%, 44%] for MRI; 14 of 27 [52%; 95% CI: 32%, 71%] for CEM; and 11 of 25 [44%; 95% CI: 24%, 65%] for MBI (overall P = .01). Conclusion Contrast-enhanced mammography, molecular breast imaging, and MRI showed similar detection of all malignancies. MRI depicted more nonindex suspicious benign lesions than did contrast-enhanced mammography or molecular breast imaging, leading to lower positive predictive value of additional biopsies. All three modalities led to overestimation of index tumor size, particularly MRI. © RSNA, 2019 Online supplemental material is available for this article.

Breast MRI contrast enhancement kinetics of normal parenchyma correlate with presence of breast cancer.

BACKGROUND: We investigated dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) contrast enhancement kinetic variables quantified from normal breast parenchyma for association with presence of breast cancer, in a case-control study. METHODS: Under a Health Insurance Portability and Accountability Act compliant and Institutional Review Board-approved protocol, DCE-MRI scans of the contralateral breasts of 51 patients with cancer and 51 controls (matched by age and year of MRI) with biopsy-proven benign lesions were retrospectively analyzed. Applying fully automated computer algorithms on pre-contrast and multiple post-contrast MR sequences, two contrast enhancement kinetic variables, wash-in slope and signal enhancement ratio, were quantified from normal parenchyma of the contralateral breasts of both patients with cancer and controls. Conditional logistic regression was employed to assess association between these two measures and presence of breast cancer, with adjustment for other imaging factors including mammographic breast density and MRI background parenchymal enhancement (BPE). The area under the receiver operating characteristic curve (AUC) was used to assess the ability of the kinetic measures to distinguish patients with cancer from controls. RESULTS: When both kinetic measures were included in conditional logistic regression analysis, the odds ratio for breast cancer was 1.7 (95 % CI 1.1, 2.8; p = 0.017) for wash-in slope variance and 3.5 (95 % CI 1.2, 9.9; p = 0.019) for signal enhancement ratio volume, respectively. These odds ratios were similar on respective univariate analysis, and remained significant after adjustment for menopausal status, family history, and mammographic density. While percent BPE was associated with an odds ratio of 3.1 (95 % CI 1.2, 7.9; p = 0.018), in multivariable analysis of the three measures, percent BPE was non-significant (p = 0.897) and the two kinetics measures remained significant. For the differentiation of patients with cancer and controls, the unadjusted AUC was 0.71 using a combination of the two measures, which significantly (p = 0.005) outperformed either measure alone (AUC = 0.65 for wash-in slope variance and 0.63 for signal enhancement ratio volume). CONCLUSIONS: Kinetic measures of wash-in slope and signal enhancement ratio quantified from normal parenchyma in DCE-MRI are jointly associated with presence of breast cancer, even after adjustment for mammographic density and BPE.

Core Breast Biopsies Showing Lobular Carcinoma In Situ Should Be Excised and Surveillance Is Reasonable for Atypical Lobular Hyperplasia.

OBJECTIVE: The purpose of this article is to determine the upgrade rate to ductal carcinoma in situ (DCIS) or invasive carcinoma at excision at the same site after percutaneous breast biopsy findings of atypical lobular hyperplasia (ALH) or lobular carcinoma in situ (LCIS) using current imaging and strict pathologic criteria. MATERIALS AND METHODS: From January 2006 through September 2013, 32,960 breast core biopsies were performed; 1084 (3.3%) core biopsies found ALH or classic LCIS. For 447 lesions in 433 women, this was the only high-risk lesion at that site, with no ipsilateral malignancy, and results of excision were available. RESULTS: Among the 447 lesions, 22 (4.9%) were malignant at excision, including 10 invasive carcinomas (two grade 2 and eight grade 1; all node negative) and 12 DCIS. The upgrade rate of LCIS was 9.3% (10/108; 95% CI, 5.1-16.2%) and that of ALH was 3.5% (12/339; 95% CI, 2.0-6.1%; p = 0.02). After excluding five cases with radiologic-pathologic discordance and reclassifying one core from ALH to LCIS at review, the upgrade rate for LCIS remained higher (8.4%; 9/107; 95% CI, 4.5-15.2%) than that for ALH (2.4%; 8/335; 95% CI, 1.2-4.6%; p = 0.01). CONCLUSION: Excision is recommended for LCIS on core biopsy because of its 8.4-9.3% upgrade rate. Excluding discordant cases, patients with other high-risk lesions or concurrent malignancy, the risk of upgrade of ALH was 2.4%. Surveillance at 6, 12, and 24 months can be performed in lieu of excision because a short delay in diagnosis of the few malignancies is not expected to cause harm.

Effect of the Availability of Prior Full-Field Digital Mammography and Digital Breast Tomosynthesis Images on the Interpretation of Mammograms.

PURPOSE: To assess the effect of and interaction between the availability of prior images and digital breast tomosynthesis (DBT) images in decisions to recall women during mammogram interpretation. MATERIALS AND METHODS: Verbal informed consent was obtained for this HIPAA-compliant institutional review board-approved protocol. Eight radiologists independently interpreted twice deidentified mammograms obtained in 153 women (age range, 37-83 years; mean age, 53.7 years ± 9.3 [standard deviation]) in a mode by reader by case-balanced fully crossed study. Each study consisted of current and prior full-field digital mammography (FFDM) images and DBT images that were acquired in our facility between June 2009 and January 2013. For one reading, sequential ratings were provided by using (a) current FFDM images only, (b) current FFDM and DBT images, and (c) current FFDM, DBT, and prior FFDM images. The other reading consisted of (a) current FFDM images only, (b) current and prior FFDM images, and (c) current FFDM, prior FFDM, and DBT images. Fifty verified cancer cases, 60 negative and benign cases (clinically not recalled), and 43 benign cases (clinically recalled) were included. Recall recommendations and interaction between the effect of prior FFDM and DBT images were assessed by using a generalized linear model accounting for case and reader variability. RESULTS: Average recall rates in noncancer cases were significantly reduced with the addition of prior FFDM images by 34% (145 of 421) and 32% (106 of 333) without and with DBT images, respectively (P < .001). However, this recall reduction was achieved at the cost of a corresponding 7% (23 of 345) and 4% (14 of 353) reduction in sensitivity (P = .006). In contrast, availability of DBT images resulted in a smaller reduction in recall rates (false-positive interpretations) of 19% (76 of 409) and 26% (71 of 276) without and with prior FFDM images, respectively (P = .001). Availability of DBT images resulted in 4% (15 of 338) and 8% (25 of 322) increases in sensitivity, respectively (P = .007). The effects of the availability of prior FFDM images or DBT images did not significantly change regardless of the sequence in presentation (P = .81 and P = .47 for specificity and sensitivity, respectively). CONCLUSION: The availability of prior FFDM or DBT images is a largely independent contributing factor in reducing recall recommendations during mammographic interpretation.

Comparison of two-dimensional synthesized mammograms versus original digital mammograms alone and in combination with tomosynthesis images.

PURPOSE: To assess interpretation performance and radiation dose when two-dimensional synthesized mammography (SM) images versus standard full-field digital mammography (FFDM) images are used alone or in combination with digital breast tomosynthesis images. MATERIALS AND METHODS: A fully crossed, mode-balanced multicase (n = 123), multireader (n = 8), retrospective observer performance study was performed by using deidentified images acquired between 2008 and 2011 with institutional review board approved, HIPAA-compliant protocols, during which each patient signed informed consent. The cohort included 36 cases of biopsy-proven cancer, 35 cases of biopsy-proven benign lesions, and 52 normal or benign cases (Breast Imaging Reporting and Data System [BI-RADS] score of 1 or 2) with negative 1-year follow-up results. Accuracy of sequentially reported probability of malignancy ratings and seven-category forced BI-RADS ratings was evaluated by using areas under the receiver operating characteristic curve (AUCs) in the random-reader analysis. RESULTS: Probability of malignancy-based mean AUCs for SM and FFDM images alone was 0.894 and 0.889, respectively (difference, -0.005; 95% confidence interval [CI]: -0.062, 0.054; P = .85). Mean AUC for SM with tomosynthesis and FFDM with tomosynthesis was 0.916 and 0.939, respectively (difference, 0.023; 95% CI: -0.011, 0.057; P = .19). In terms of the reader-specific AUCs, five readers performed better with SM alone versus FFDM alone, and all eight readers performed better with combined FFDM and tomosynthesis (absolute differences from 0.003 to 0.052). Similar results were obtained by using a nonparametric analysis of forced BI-RADS ratings. CONCLUSION: SM alone or in combination with tomosynthesis is comparable in performance to FFDM alone or in combination with tomosynthesis and may eliminate the need for FFDM as part of a routine clinical study.

Diagnostic accuracy and recall rates for digital mammography and digital mammography combined with one-view and two-view tomosynthesis: results of an enriched reader study.

OBJECTIVE: The purpose of this study was to compare two methods of combining tomosynthesis with digital mammography by assessing diagnostic accuracy and recall rates for digital mammography alone and digital mammography combined with one-view tomosynthesis and two-view tomosynthesis. SUBJECTS AND METHODS: Three hundred ten cases including biopsy-proven malignancies (51), biopsy-proven benign findings (47), recalled screening cases (138), and negative screening cases (74) were reviewed by 15 radiologists sequentially using digital mammography, adding one-view tomosynthesis, and then two-view tomosynthesis. Cases were assessed for recall and assigned a BI-RADS score and probability of malignancy for each imaging method. Diagnostic accuracy was assessed using receiver operating characteristic (ROC) analysis. Screening recall rates were compared using pooled logistical regression analysis. A p value of < 0.0167 was considered significant. RESULTS: The area under the ROC curve (AUC) for digital mammography (DM), DM plus one-view tomosynthesis, and DM plus two-view tomosynthesis was 0.828, 0.864, and 0.895, respectively. Both one-view and two-view tomosynthesis plus DM were significantly better than DM alone (Δ AUCs 0.036 [p = 0.009] and 0.068 [p < 0.001]). Average noncancer recall rates for digital mammography, DM plus one-view tomosynthesis, and DM plus two-view tomosynthesis were 44.2%, 27.2%, and 24.0%, respectively. Combined with DM, one-view and two-view tomosynthesis both showed significantly lower noncancer recall rates than digital mammography alone (p < 0.001). Digital mammography with two-view tomosynthesis showed a significantly lower recall rate than digital mammography with one-view tomosynthesis (p < 0.001). Diagnostic accuracy for dense (Δ AUC, 0.091%; p < 0.001) and nondense (Δ AUC, 0.035%; p = 0.001) breasts improved with DM plus two-view tomosynthesis compared with digital mammography alone. Compared with digital mammography, diagnostic sensitivity for invasive cancers increased with the addition of both one-view (Δ12.0%, p < 0.001) and two-view (Δ21.7%, p < 0.001) tomosynthesis. CONCLUSION: The addition of one-view tomosynthesis to conventional digital mammography improved diagnostic accuracy and reduced the recall rate; however, the addition of two-view tomosynthesis provided twice the performance gain in diagnostic accuracy while further reducing the recall rate.

State of Academic Radiology: Current Challenges, Future Adaptations.

There are approximately 200 academic radiology departments in the United States. While academic medical centers vary widely depending on their size, complexity, medical school affiliation, research portfolio, and geographic location, they are united by their 3 core missions: patient care, education and training, and scholarship. Despite inherent differences, the current challenges faced by all academic radiology departments have common threads; potential solutions and future adaptations will need to be tailored and individualized-one size will not fit all. In this article, we provide an overview based on our experiences at 4 academic centers across the United States, from relatively small to very large size, and discuss creative and innovative ways to adapt, including community expansion, hybrid models of faculty in-person vs teleradiology (traditional vs non-traditional schedule), work-life integration, recruitment and retention, mentorship, among others.

Assessing radiologist performance using combined digital mammography and breast tomosynthesis compared with digital mammography alone: results of a multicenter, multireader trial.

PURPOSE: To compare radiologists' diagnostic accuracy and recall rates for breast tomosynthesis combined with digital mammography versus digital mammography alone. MATERIALS AND METHODS: Institutional review board approval was obtained at each accruing institution. Participating women gave written informed consent. Mediolateral oblique and craniocaudal digital mammographic and tomosynthesis images of both breasts were obtained from 1192 subjects. Two enriched reader studies were performed to compare digital mammography with tomosynthesis against digital mammography alone. Study 1 comprised 312 cases (48 cancer cases) with images read by 12 radiologists; study 2, 312 cases (51 cancer cases) with 15 radiologists. Study 1 readers recorded only that an abnormality requiring recall was present; study 2 readers had additional training and recorded both lesion type and location. Diagnostic accuracy was compared with receiver operating characteristic analysis. Recall rates of noncancer cases, sensitivity, specificity, and positive and negative predictive values determined by analyzing Breast Imaging Reporting and Data System scores were compared for the two methods. RESULTS: Diagnostic accuracy for combined tomosynthesis and digital mammography was superior to that of digital mammography alone. Average difference in area under the curve in study 1 was 7.2% (95% confidence interval [CI]: 3.7%, 10.8%; P < .001) and in study 2 was 6.8% (95% CI: 4.1%, 9.5%; P < .001). All 27 radiologists increased diagnostic accuracy with addition of tomosynthesis. Recall rates for noncancer cases for all readers significantly decreased with addition of tomosynthesis (range, 6%-67%; P < .001 for 25 readers, P < .03 for all readers). Increased sensitivity was largest for invasive cancers: 15% and 22% in studies 1 and 2 versus 3% for in situ cancers in both studies. CONCLUSION: Addition of tomosynthesis to digital mammography offers the dual benefit of significantly increased diagnostic accuracy and significantly reduced recall rates for noncancer cases. SUPPLEMENTAL MATERIAL: http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.12120674/-/DC1.

Digital breast tomosynthesis versus supplemental diagnostic mammographic views for evaluation of noncalcified breast lesions.

PURPOSE: To compare the diagnostic performance of breast tomosynthesis versus supplemental mammography views in classification of masses, distortions, and asymmetries. MATERIALS AND METHODS: Eight radiologists who specialized in breast imaging retrospectively reviewed 217 consecutively accrued lesions by using protocols that were HIPAA compliant and institutional review board approved in 182 patients aged 31-60 years (mean, 50 years) who underwent diagnostic mammography and tomosynthesis. The lesions in the cohort included 33% (72 of 217) cancers and 67% (145 of 217) benign lesions. Eighty-four percent (182 of 217) of the lesions were masses, 11% (25 of 217) were asymmetries, and 5% (10 of 217) were distortions that were initially detected at clinical examination in 8% (17 of 217), at mammography in 80% (173 of 217), at ultrasonography (US) in 11% (25 of 217), or at magnetic resonance imaging in 1% (2 of 217). Histopathologic examination established truth in 191 lesions, US revealed a cyst in 12 lesions, and 14 lesions had a normal follow-up. Each lesion was interpreted once with tomosynthesis and once with supplemental mammographic views; both modes included the mediolateral oblique and craniocaudal views in a fully crossed and balanced design by using a five-category Breast Imaging Reporting and Data System (BI-RADS) assessment and a probability-of-malignancy score. Differences between modes were analyzed with a generalized linear mixed model for BI-RADS-based sensitivity and specificity and with modified Obuchowski-Rockette approach for probability-of-malignancy-based area under the receiver operating characteristic (ROC) curve. RESULTS: Average probability-of-malignancy-based area under the ROC curve was 0.87 for tomosynthesis versus 0.83 for supplemental views (P < .001). With tomosynthesis, the false-positive rate decreased from 85% (989 of 1160) to 74% (864 of 1160) (P < .01) for cases that were rated BI-RADS category 3 or higher and from 57% (663 of 1160) to 48% (559 of 1160) for cases rated BI-RADS category 4 or 5 (P < .01), without a meaningful change in sensitivity. With tomosynthesis, more cancers were classified as BI-RADS category 5 (39% [226 of 576] vs 33% [188 of 576]; P = .017) without a decrease in specificity. CONCLUSION: Tomosynthesis significantly improved diagnostic accuracy for noncalcified lesions compared with supplemental mammographic views.

Contrast-enhanced Mammography-guided Biopsy: Initial Trial and Experience.

OBJECTIVE: Evaluate lesion visibility and radiologist confidence during contrast-enhanced mammography (CEM)-guided biopsy. METHODS: Women with BI-RADS ≥4A enhancing breast lesions were prospectively recruited for 9-g vacuum-assisted CEM-guided biopsy. Breast density, background parenchymal enhancement (BPE), lesion characteristics (enhancement and conspicuity), radiologist confidence (scale 1-5), and acquisition times were collected. Signal intensities in specimens were analyzed. Patient surveys were collected. RESULTS: A cohort of 28 women aged 40-81 years (average 57) had 28 enhancing lesions (7/28, 25% malignant). Breast tissue was scattered (10/28, 36%) or heterogeneously dense (18/28, 64%) with minimal (12/28, 43%), mild (7/28, 25%), or moderate (9/28, 32%) BPE on CEM. Twelve non-mass enhancements, 11 masses, 3 architectural distortions, and 2 calcification groups demonstrated weak (12/28, 43%), moderate (14/28, 50%), or strong (2/28, 7%) enhancement. Specimen radiography demonstrated lesion enhancement in 27/28 (96%). Radiologists reported complete lesion removal on specimen radiography in 8/28 (29%). Average time from contrast injection to specimen radiography was 18 minutes (SD = 5) and, to post-procedure mammogram (PPM), 34 minutes (SD = 10). Contrast-enhanced mammography PPM was performed in 27/28 cases; 13/19 (68%) of incompletely removed lesions on specimen radiography showed residual enhancement; 6/19 (32%) did not. Across all time points, average confidence was 2.2 (SD = 1.2). Signal intensities of enhancing lesions were similar to iodine. Patients had an overall positive assessment. CONCLUSION: Lesion enhancement persisted through PPM and was visible on low energy specimen radiography, with an average "confident" score. Contrast-enhanced mammography-guided breast biopsy is easily implemented clinically. Its availability will encourage adoption of CEM.

Risk of malignancy when microscopic radial scars and microscopic papillomas are found at percutaneous biopsy.

OBJECTIVE: The objective of our study was to assess the incidence of associated malignancy when microscopic radial scars and microscopic intraductal papillomas are encountered at percutaneous biopsy for lesions that otherwise reveal benign histopathology. MATERIALS AND METHODS: A search of the pathology database for the period from December 14, 2006, through December 21, 2009, identified patients with a microscopic radial scar, a microscopic intraductal papilloma, or both at percutaneous biopsy. Patients whose percutaneous biopsy was performed for a lesion that revealed carcinoma or a high-risk pathology result were excluded to avoid confounding bias, as were patients who had only imaging follow-up. Only patients who underwent surgery solely for the study lesion were included. The lesion type that prompted core biopsy, biopsy guidance and device, sample number, and surgical outcomes were recorded. The incidences of benign, high-risk, and malignant pathology findings from surgery were calculated. RESULTS: The search revealed 35 patients (18 microscopic radial scars, 17 microscopic papillomas) who underwent surgery solely for the study lesion. Stereotactic guidance was used for 15 (43%); ultrasound, for 12 (34%); and MRI, for eight (23%). At surgery, 12 patients (34%) had high-risk histopathology results and 23 (66%) had benign results. No study lesions were upgraded to malignancy. CONCLUSION: Our study found no evidence of associated malignancy at surgical excision when microscopic radial scars and microscopic intraductal papillomas were encountered at percutaneous biopsy in patients who otherwise had benign histopathology results; thus, routine imaging follow-up may be performed.

A GMM-based breast cancer risk stratification using a resonance-frequency electrical impedance spectroscopy.

PURPOSE: The authors developed and tested a multiprobe-based resonance-frequency-based electrical impedance spectroscopy (REIS) system. The purpose of this study was to preliminarily assess the performance of this system in classifying younger women into two groups, those ultimately recommended for biopsy during imaging-based diagnostic workups that followed screening and those rated as negative during mammography. METHODS: A seven probe-based REIS system was designed, assembled, and is currently being tested in the breast imaging facility. During an examination, contact is made with the nipple and six concentric points on the breast skin. For each measurement channel between the center probe and one of the six external probes, a set of electrical impedance spectroscopy (EIS) signal sweeps is performed and signal outputs ranging from 200 to 800 kHz at 5 kHz interval are recorded. An initial subset of 174 examinations from an ongoing prospective clinical study was selected for this preliminary analysis. An initial set of 35 features, 33 of which represented the corresponding EIS signal differences between the left and right breasts, was established. A Gaussian mixture model (GMM) classifier was developed to differentiate between "positive" (biopsy recommended) cases and "negative" (nonbiopsy) cases. Selecting an optimal feature set was performed using genetic algorithms with an area under a receiver operating characteristic curve (AUC) as the fitness criterion. RESULTS: The recorded EIS signal sweeps showed that, in general, negative (nonbiopsy) examinations have a higher level of electrical impedance symmetry between the two breasts than positive (biopsy) examinations. Fourteen features were selected by genetic algorithm and used in the optimized GMM classifier. Using a leave-one-case-out test, the GMM classifier yielded a performance level of AUC = 0.78, which compared favorably to other three widely used classifiers including support vector machine, classification tree, and linear discriminant analysis. These results also suggest that the REIS signal based GMM classifier could be used as a prescreening tool to correctly identify a fraction of younger women at higher risk of developing breast cancer (i.e., 47% sensitivity at 90% specificity). CONCLUSIONS: The study confirms that asymmetry in electrical impedance characteristics between two breasts provides valuable information regarding the presence of a developing breast abnormality; hence, REIS data may be useful in classifying younger women into two groups of "average" and "significantly higher than average" risk of having or developing a breast abnormality that would ultimately result in a later imaging-based recommendation for biopsy.

Localized detection and classification of abnormalities on FFDM and tomosynthesis examinations rated under an FROC paradigm.

OBJECTIVE: The purpose of our study was to assess diagnostic performance when retrospectively interpreting full-field digital mammography (FFDM) and breast tomosynthesis examinations under a free-response receiver operating characteristic (FROC) paradigm. MATERIALS AND METHODS: We performed FROC analysis of a previously reported study in which eight experienced radiologists interpreted 125 examinations, including 35 with verified cancers. The FROC paradigm involves detecting, locating, and rating each suspected abnormality. Radiologists reviewed and rated both FFDM alone and a combined display mode of FFDM and digital breast tomosynthesis (DBT) (combined). Observer performance levels were assessed and compared with respect to the fraction of correctly identified abnormalities, the number of reported location-specific findings (both true and false), and their associated ratings. The analysis accounts for the number and locations of findings and the location-based ratings using a summary performance index (Λ), which is the FROC analog of the area between the receiver operating characteristic curve and the diagonal (chance) line. RESULTS: Under the FROC paradigm, each reader detected more true abnormalities associated with cancer, or a higher true-positive fraction, under the combined mode. In an analysis focused on both the number of findings and associated location-based ratings, each of the radiologists performed better under the combined mode compared with FFDM alone, with increases in Λ ranging from 5% to 34%. On average, under the combined mode radiologists achieved a 16% improvement in Λ compared with the FFDM alone mode (95% CI, 7-26%; p < 0.01). CONCLUSION: We showed that DBT-based breast imaging in combination with FFDM could result in better performance under the FROC paradigm.

Detection and classification of calcifications on digital breast tomosynthesis and 2D digital mammography: a comparison.

OBJECTIVE: The purpose of this article is to compare the ability of digital breast tomosynthesis and full field digital mammography (FFDM) to detect and characterize calcifications. MATERIALS AND METHODS: One hundred paired examinations were performed utilizing FFDM and digital breast tomosynthesis. Twenty biopsy-proven cancers, 40 biopsy-proven benign calcifications, and 40 randomly selected negative screening studies were retrospectively reviewed by five radiologists in a crossed multireader multimodal observer performance study. Data collected included the presence of calcifications and forced BI-RADS scores. Receiver operator curve analysis using BI-RADS was performed. RESULTS: Overall calcification detection sensitivity was higher for FFDM (84% [95% CI, 79-88%]) than for digital breast tomosynthesis (75% [95% CI, 70-80%]). [corrected] In the cancer cohort, 75 (76%) of 99 interpretations identified calcification in both modes. Of those, a BI-RADS score less than or equal to 2 was rendered in three (4%) and nine (12%) cases with FFDM and digital breast tomosynthesis, respectively. In the benign cohort, 123 (62%) of 200 interpretations identified calcifications in both modes. Of those, a BI-RADS score greater than or equal to 3 was assigned in 105 (85%) and 93 (76%) cases with FFDM and digital breast tomosynthesis, respectively. There was no significant difference in the nonparametric computed area under the receiver operating characteristic curves (AUC) using the BI-RADS scores (FFDM, AUC = 0.76 and SD = 0.03; digital breast tomosynthesis, AUC = 0.72 and SD = 0.04 [p = 0.1277]). CONCLUSION: In this small data set, FFDM appears to be slightly more sensitive than digital breast tomosynthesis for the detection of calcification. However, diagnostic performance as measured by area under the curve using BI-RADS was not significantly different. With improvements in processing algorithms and display, digital breast tomosynthesis could potentially be improved for this purpose.

Radiomics-informed Deep Curriculum Learning for Breast Cancer Diagnosis.

Convolutional Neural Networks (CNNs) are traditionally trained solely using the given imaging dataset. Additional clinical information is often available along with imaging data but is mostly ignored in the current practice of data-driven deep learning modeling. In this work, we propose a novel deep curriculum learning method that utilizes radiomics information as a source of additional knowledge to guide training using customized curriculums. Specifically, we define a new measure, termed radiomics score, to capture the difficulty of classifying a set of samples. We use the radiomics score to enable a newly designed curriculum-based training scheme. In this scheme, the loss function component is weighted and initialized by the corresponding radiomics score of each sample, and furthermore, the weights are continuously updated in the course of training based on our customized curriculums to enable curriculum learning. We implement and evaluate our methods on a typical computer-aided diagnosis of breast cancer. Our experiment results show benefits of the proposed method when compared to a direct use of radiomics model, a baseline CNN without using any knowledge, the standard curriculum learning using data resampling, an existing difficulty score from self-teaching, and previous methods that use radiomics features as additional input to CNN models.