Inter-reader agreement of the BI-RADS CEM lexicon

PURPOSE

The purpose of this study was to assess the inter-reader agreement of the breast imaging reporting and data system (BI-RADS) contrast-enhanced mammography (CEM) lexicon.

MATERIALS AND METHODS

In this IRB-approved, single-center, retrospective study, three breast radiologists, each with different levels of experience, reviewed 462 lesions in 421 routine clinical CEM according to the fifth edition of the BI-RADS lexicon for mammography and to the first version of the BI-RADS lexicon for CEM. Readers were blinded to patient outcomes and evaluated breast and lesion features on low-energy (LE) images (breast density, type of lesion, associated architectural distortion), lesion features on recombined (RC) images (type of enhancement, characteristic of mass enhancement, non-mass enhancement or enhancing asymmetry), and provided a final BI-RADS assessment. The inter-reader agreement was calculated for each evaluated feature using Fleiss' kappa coefficient. Sensitivity and specificity were calculated.

RESULTS

The inter-reader agreement was moderate to substantial for breast density (ĸ = 0.569), type of lesion on LE images (ĸ = 0.654), and type of enhancement (ĸ = 0.664). There was a moderate to substantial agreement on CEM mass enhancement descriptors. The agreement was fair to moderate for non-mass enhancement and enhancing asymmetry descriptors. Inter-reader agreement for LE and LE with RC BI-RADS assessment was moderate (ĸ = 0.421) and fair (ĸ = 0.364). Diagnostic performance was good and comparable for all readers.

CONCLUSION

Inter-reader agreement of the CEM lexicon was moderate to substantial for most features. There was a low agreement for some RC descriptors, such as non-mass enhancement and enhancing asymmetry, and BI-RADS assessment, but this did not impact the diagnostic performance.

KEY POINTS

Question Data on the reproducibility and inter-reader agreement for the first version of the BI-RADS lexicon dedicated to CEM are missing. Finding The inter-reader agreement for the lexicon was overall substantial to moderate, but it was lower for the descriptors for non-mass enhancement and enhancing asymmetry. Clinical relevance A common lexicon simplifies communication between specialists in clinical practice. The good inter-reader agreement confirms the effectiveness of the CEM-BIRADS in ensuring consistent communication. Detailed definitions of some descriptors (non-mass, enhancing asymmetry) are needed to ensure higher agreements.

Diagnostic performance of Kaiser score in the evaluation of breast cancer using MRI: A systematic review and meta-analysis

PURPOSE

To assess the performance of Kaiser score (KS) in detecting and characterizing breast cancer on magnetic resonance imaging (MRI).

METHODS

The protocol was pre-registered at (https://osf.io/83c6j/). We performed a comprehensive search in PubMed, Embase, Cochrane Library, and Web of Science until 30 October 2024 for studies that used KS for detection of breast cancer on MRI. The risk of bias in the included studies was evaluated utilizing Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Diagnostic values of area under the curve (AUC), sensitivity, specificity, positive and negative likelihood ratios, and diagnostic odds ratio were calculated using a random-effects bivariate model. Meta-regression was used to explore the source of heterogeneity when I2 was ≥ 50 %. P-value < 0.05 was considered statistically significant.

RESULTS

A total of 29 studies with 7918 patients and 8451 breast lesions were included. The pooled sensitivity, specificity, and AUC of KS for detecting malignant breast lesions on MRI were 95 % (95 % CI = 94 % to 96 %), 70 % (95 % CI = 64 % to 75 %), and 0.94 (95 % CI = 0.91 to 0.96), while for Breast Imaging Reporting and Data System (BI-RADS), they were 97 % (95 % CI = 92 % to 99 %), 46 % (95 % CI = 30 % to 62 %), and 0.89 (95 % CI = 0.86 to 0.91). Sensitivity difference was not statistically significant (p-value = 0.803), but specificity difference was significant (p-value = 0.001). Also, KS demonstrated slightly better diagnostic accuracy for mass lesions with a sensitivity of 96 % (95 % CI = 94 % to 97 %), specificity of 69 % (95 % CI = 60 % to 77 %), and AUC of 0.96 (95 % CI = 0.94 to 0.97) compared to non-mass lesions with 93 % (95 % CI = 88 % to 96 %), 68 % (95 % CI = 58 % to 77 %), and 0.91 (95 % CI = 0.88 to 0.94) values, respectively. KS showed better performance in larger lesions.

CONCLUSION

The KS's superior diagnostic performance compared to BI-RADS, particularly its ability to avoid unnecessary biopsies, makes it valuable for diagnostic and clinical decision-making.

Evaluation of a ductal carcinoma in situ component accompanying HER2-positive invasive breast cancer on contrast-enhanced mammography

OBJECTIVES

A DCIS component can be present accompanying HER2+ invasive breast cancer (IBC) in approximately 57 % of patients. Until now, no contrast-enhanced mammography (CEM) studies have investigated the detection of a DCIS component, which is important for surgical decision-making. This study aimed to investigate imaging findings of a DCIS component in HER2+ IBC on CEM.

METHODS

Women with HER2+ IBC with a DCIS component that underwent CEM between 2013-2021 were included. Two independent radiologists retrospectively reassessed CEM exams, and a breast pathologist reassessed histopathology specimen. The percentage and extent of suspicious calcifications and non-mass enhancement (NME) on CEM, and interobserver agreement between radiologists was determined. In the primary surgery group, the detection rate of DCIS outside of the invasive tumor was determined, and maximum diameter of imaging findings was compared to histopathology.

RESULTS

Sixty-two patients were included. CEM showed suspicious calcifications (27.4 %), NME (16.1 %), both (27.4 %) or no findings (29.0 %), related to DCIS. In the primary surgery group (n = 45), CEM detected 27 of 35 DCIS components present outside of the invasive tumor (77.1 %). NME was a better predictor for DCIS diameter (ICC = 0.65) compared to suspicious calcifications (ICC = 0.43). Inter-observer agreement on detection of imaging findings was better for suspicious calcifications (κ = 0.81) compared to NME (κ = 0.47), while reliability between size measurements was comparable (ICC = 0.89 versus ICC = 0.80, respectively).

CONCLUSION

CEM was able to detect 77.1% of DCIS present outside of the invasive tumor. NME is the most accurate predictor of DCIS diameter, but requires improvements regarding inter-observer agreement.

Increased background parenchymal enhancement on peri-menopausal breast magnetic resonance imaging

Objectives

To examine the background parenchymal enhancement (BPE) levels in peri-menopausal breast MRI compared with pre- and post-menopausal breast MRI.

Methods

This study included 562 patients (55.8±12.3 years) who underwent contrast-enhanced dynamic breast MRI between 2011 and 2015 for clinical indications. We evaluated the BPE level, amount of fibroglandular tissue (FGT), and social and clinical variables. The inter-reader agreement for the amount of FGT and the BPE level was evaluated using interclass correlation coefficients. Associations between the BPE level and body mass index (BMI), ages of menarche and menopause, childbirth history, number of children, and the amount of FGT were determined using Spearman's correlation coefficients or Mann-Whitney U-test. Pearson's χ2 test was used to assess the difference in the frequency of BPE categories among the age-groups.

Results

The inter-reader agreement was 0.864 for the amount of FGT and 0.840 for the BPE level, both indicating almost perfect agreement. The BPE level showed a weak positive correlation with the amount of FGT (Spearman's ρ=0.271, P<0.001). BPE was not significantly correlated with BMI, childbirth history, number of births, or ages of menarche or menopause. BPE was greater in the peri-menopausal age-group compared with the corresponding pre- and post-menopausal age-groups, both with benign and malignant lesions.

Conclusions

BPE was greater in the peri-menopausal stage than in the pre- and post-menopausal stages. Our results suggest that BPE showed a non-linear decrease with age and that the hormonal disbalance in the peri-menopausal period has a greater effect on the BPE level than was previously assumed.

Introducing AEM-RADS: A novel reporting and data system for abdominal emergencies

PURPOSE

The Reporting and Data System (RADS) has proven successful in various medical settings, but a standardized reporting system for abdominal emergencies is lacking. In this study, the Abdominal Emergency Reporting and Data System (AEM-RADS) for urgent findings on abdominal CT scans is introduced to address the need for consistency in emergency radiology.

METHODS

In this prospective observational study, conducted over a six-month period, the urgency of abdominal CT scans was assessed using the proposed AEM-RADS scoring system. The committee developed a scale ranging from AEM-RADS 1 (normal) to AEM-RADS 5 (urgent disease). Interobserver agreement between two observers with different experience was evaluated, and robust AEM-RADS reference values were established by radiologists who were not observers. Statistical analysis used mean, standard deviations and Kendall's tau analysis for interobserver agreement.

RESULTS

Among 2656 patients who underwent CT for abdominal emergencies, the AEM-RADS distribution was 17.50% AEM-RADS 1, 28.57% AEM-RADS 2, 7.22% AEM-RADS 3, 35.61% AEM-RADS 4, and 11.06% AEM-RADS 5. Interobserver agreement was high, especially for urgent and emergent cases (p < 0.0001). Notable discrepancies were observed in AEM-RADS categories 2C-D and 3B-C, emphasizing the influence of radiologists' experience on interpretation. However, the interobserver agreement for both AEM-RADS 2C-D and 3B-C were statistically significant (p < 0.001).

CONCLUSIONS

AEM-RADS showed promising reliability, particularly in identifying urgent and emergent cases. Despite some inter-observer discrepancies, the system showed potential for standardized emergency workups. AEM-RADS could significantly enhance diagnostic accuracy in abdominal emergencies and provide a structured framework for shared decision-making between clinicians and radiologists.0.

Interrater Agreement of BT-RADS for Evaluation of Follow-up MRI in Patients with Treated Primary Brain Tumor

BACKGROUND AND PURPOSE

The Brain Tumor Reporting and Data System (BT-RADS) is a structured radiology reporting algorithm that was introduced to provide uniformity in posttreatment primary brain tumor follow-up and reporting, but its interrater reliability (IRR) assessment has not been widely studied. Our goal is to evaluate the IRR among neuroradiologists and radiology residents in the use of BT-RADS.

MATERIALS AND METHODS

This retrospective study reviewed 103 consecutive MR studies in 98 adult patients previously diagnosed with and treated for primary brain tumor (January 2019 to February 2019). Six readers with varied experience (4 neuroradiologists and 2 radiology residents) independently evaluated each case and assigned a BT-RADS score. Readers were blinded to the original score reports and the reports from other readers. Cases in which at least 1 neuroradiologist scored differently were subjected to consensus scoring. After the study, a post hoc reference score was also assigned by 2 readers by using future imaging and clinical information previously unavailable to readers. The interrater reliabilities were assessed by using the Gwet AC2 index with ordinal weights and percent agreement.

RESULTS

Of the 98 patients evaluated (median age, 53 years; interquartile range, 41-66 years), 53% were men. The most common tumor type was astrocytoma (77%) of which 56% were grade 4 glioblastoma. Gwet index for interrater reliability among all 6 readers was 0.83 (95% CI: 0.78-0.87). The Gwet index for the neuroradiologists' group (0.84 [95% CI: 0.79-0.89]) was not statistically different from that for the residents' group (0.79 [95% CI: 0.72-0.86]) (χ2 = 0.85; P = .36). All 4 neuroradiologists agreed on the same BT-RADS score in 57 of the 103 studies, 3 neuroradiologists agreed in 21 of the 103 studies, and 2 neuroradiologists agreed in 21 of the 103 studies. Percent agreement between neuroradiologist blinded scores and post hoc reference scores ranged from 41%-52%.

CONCLUSIONS

A very good interrater agreement was found when tumor reports were interpreted by independent blinded readers by using BT-RADS criteria. Further study is needed to determine if this high overall agreement can translate into greater consistency in clinical care.

Kaiser score diagnosis of breast MRI lesions: Factors associated with false-negative and false-positive results

PURPOSE

We sought factors associated with false-negative and false-positive results in the diagnosis of breast lesions using the Kaiser score (KS) on breast magnetic resonance imaging (MRI).

METHODS

We retrospectively analyzed 1058 patients with 1058 breast lesions who underwent preoperative breast MRI with successful histopathologic results. Two radiologists assessed each lesion according to KS criteria, and clinicopathologic features and MRI findings were analyzed. Multivariate regression analysis was conducted to identify factors associated with false-negative and false-positive KS results.

RESULTS

Of the 1058 lesions, 859 were malignant and 199 were benign. Particularly high misdiagnosis rates were observed for intraductal papilloma, inflammatory lesion, and mucinous carcinoma. For breast cancer, KS yielded 821 (95.6 %) true-positive and 38 (4.4 %) false-negative results. Multivariate analysis showed that smaller lesion size (≤1 cm) (OR, 3.698; 95 %CI, 1.430-9.567; p = 0.007), absence of ipsilateral breast hypervascularity (OR, 3.029; 95 %CI, 1.370-6.693; p = 0.006), and presence of hyperintensity on T2WI (OR, 2.405; 95 %CI, 1.121-5.162; p = 0.024) were significantly associated with false-negative breast cancer results. For benign lesions, KS yielded 141 (70.9 %) true-negative and 58 (29.1 %) false-positive results. Multivariate regression analysis revealed that non-mass enhancement lesions (OR, 4.660; 95 %CI, 2.018-10.762; p＜0.001), moderate/high background parenchymal enhancement (OR, 2.402; 95 %CI, 1.180-4.892; p = 0.016), and the presence of hyperintensity on T2WI (OR, 2.986; 95 %CI, 1.386-6.433; p = 0.005) were significantly associated with false-positive KS results.

CONCLUSION

Several clinicopathologic and MRI features influence the accuracy of KS diagnosis. Understanding these factors may facilitate appropriate use of KS and guide alternative diagnostic approaches, ultimately improving diagnostic accuracy in the evaluation of breast lesions.

Explainable Precision Medicine in Breast MRI: A Combined Radiomics and Deep Learning Approach for the Classification of Contrast Agent Uptake

In DCE-MRI, the degree of contrast uptake in normal fibroglandular tissue, i.e., background parenchymal enhancement (BPE), is a crucial biomarker linked to breast cancer risk and treatment outcome. In accordance with the Breast Imaging Reporting & Data System (BI-RADS), it should be visually classified into four classes. The susceptibility of such an assessment to inter-reader variability highlights the urgent need for a standardized classification algorithm. In this retrospective study, the first post-contrast subtraction images for 27 healthy female subjects were included. The BPE was classified slice-wise by two expert radiologists. The extraction of radiomic features from segmented BPE was followed by dataset splitting and dimensionality reduction. The latent representations were then utilized as inputs to a deep neural network classifying BPE into BI-RADS classes. The network's predictions were elucidated at the radiomic feature level with Shapley values. The deep neural network achieved a BPE classification accuracy of 84 ± 2% (p-value < 0.00001). Most of the misclassifications involved adjacent classes. Different radiomic features were decisive for the prediction of each BPE class underlying the complexity of the decision boundaries. A highly precise and explainable pipeline for BPE classification was achieved without user- or algorithm-dependent radiomic feature selection.

Deep-learning model for background parenchymal enhancement classification in contrast-enhanced mammography

Background.Breast background parenchymal enhancement (BPE) is correlated with the risk of breast cancer. BPE level is currently assessed by radiologists in contrast-enhanced mammography (CEM) using 4 classes: minimal, mild, moderate and marked, as described inbreast imaging reporting and data system(BI-RADS). However, BPE classification remains subject to intra- and inter-reader variability. Fully automated methods to assess BPE level have already been developed in breast contrast-enhanced MRI (CE-MRI) and have been shown to provide accurate and repeatable BPE level classification. However, to our knowledge, no BPE level classification tool is available in the literature for CEM.Materials and methods.A BPE level classification tool based on deep learning has been trained and optimized on 7012 CEM image pairs (low-energy and recombined images) and evaluated on a dataset of 1013 image pairs. The impact of image resolution, backbone architecture and loss function were analyzed, as well as the influence of lesion presence and type on BPE assessment. The evaluation of the model performance was conducted using different metrics including 4-class balanced accuracy and mean absolute error. The results of the optimized model for a binary classification: minimal/mild versus moderate/marked, were also investigated.Results.The optimized model achieved a 4-class balanced accuracy of 71.5% (95% CI: 71.2-71.9) with 98.8% of classification errors between adjacent classes. For binary classification, the accuracy reached 93.0%. A slight decrease in model accuracy is observed in the presence of lesions, but it is not statistically significant, suggesting that our model is robust to the presence of lesions in the image for a classification task. Visual assessment also confirms that the model is more affected by non-mass enhancements than by mass-like enhancements.Conclusion.The proposed BPE classification tool for CEM achieves similar results than what is published in the literature for CE-MRI.

Discriminative Factors of Malignancy of Ipsilateral Nonmass Enhancement in Women With Newly Diagnosed Breast Cancer on Initial Staging Breast MRI

BACKGROUND

Nonmass enhancement (NME) on breast MRI impacts surgical planning.

PURPOSE

To evaluate positive predictive values (PPVs) and identify malignancy discriminators of NME ipsilateral to breast cancer on initial staging MRI.

STUDY TYPE

Retrospective.

SUBJECTS

Eighty-six women (median age, 48 years; range, 26-75 years) with 101 NME lesions (BI-RADS 4 and 5) ipsilateral to known cancers and confirmed histopathology.

FIELD STRENGTH/SEQUENCE

1.5 T and 3.0 T dynamic contrast-enhanced fat-suppressed T1-weighted fast spoiled gradient-echo.

ASSESSMENT

Three radiologists blinded to pathology independently reviewed MRI features (distribution, internal enhancement pattern, and enhancement kinetics) of NME, locations relative to index cancers (contiguous, non-contiguous, and different quadrants), associated mammographic calcifications, lymphovascular invasion (LVI), axillary node metastasis, and radiology-pathology correlations. Clinical factors, NME features, and cancer characteristics were analyzed for associations with NME malignancy.

STATISTICAL TESTS

Fisher's exact, Chi-square, Wilcoxon rank sum tests, and mixed-effect multivariable logistic regression were used. Significance threshold was set at P < 0.05.

RESULTS

Overall NME malignancy rate was 48.5% (49/101). Contiguous NME had a significantly higher malignancy rate (86.7%) than non-contiguous NME (25.0%) and NME in different quadrants (10.7%), but no significant difference was observed by distance from cancer for non-contiguous NME, P = 0.68. All calcified NME lesions contiguous to the calcified index cancer were malignant. NME was significantly more likely malignant when index cancers were masses compared to NME (52.9% vs. 21.4%), had mammographic calcifications (63.2% vs. 39.7%), LVI (81.8% vs. 44.4%), and axillary node metastasis (70.8% vs. 41.6%). NME features with highest PPVs were segmental distribution (85.7%), clumped enhancement (66.7%), and nonpersistent kinetics (77.1%). On multivariable analysis, contiguous NME, segmental distribution, and nonpersistent kinetics were associated with malignancy.

DATA CONCLUSION

Malignancy discriminators of ipsilateral NME on staging MRI included contiguous location to index cancers, segmental distribution, and nonpersistent kinetics.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study

Background The performance of publicly available large language models (LLMs) remains unclear for complex clinical tasks. Purpose To evaluate the agreement between human readers and LLMs for Breast Imaging Reporting and Data System (BI-RADS) categories assigned based on breast imaging reports written in three languages and to assess the impact of discordant category assignments on clinical management. Materials and Methods This retrospective study included reports for women who underwent MRI, mammography, and/or US for breast cancer screening or diagnostic purposes at three referral centers. Reports with findings categorized as BI-RADS 1-5 and written in Italian, English, or Dutch were collected between January 2000 and October 2023. Board-certified breast radiologists and the LLMs GPT-3.5 and GPT-4 (OpenAI) and Bard, now called Gemini (Google), assigned BI-RADS categories using only the findings described by the original radiologists. Agreement between human readers and LLMs for BI-RADS categories was assessed using the Gwet agreement coefficient (AC1 value). Frequencies were calculated for changes in BI-RADS category assignments that would affect clinical management (ie, BI-RADS 0 vs BI-RADS 1 or 2 vs BI-RADS 3 vs BI-RADS 4 or 5) and compared using the McNemar test. Results Across 2400 reports, agreement between the original and reviewing radiologists was almost perfect (AC1 = 0.91), while agreement between the original radiologists and GPT-4, GPT-3.5, and Bard was moderate (AC1 = 0.52, 0.48, and 0.42, respectively). Across human readers and LLMs, differences were observed in the frequency of BI-RADS category upgrades or downgrades that would result in changed clinical management (118 of 2400 [4.9%] for human readers, 611 of 2400 [25.5%] for Bard, 573 of 2400 [23.9%] for GPT-3.5, and 435 of 2400 [18.1%] for GPT-4; P < .001) and that would negatively impact clinical management (37 of 2400 [1.5%] for human readers, 435 of 2400 [18.1%] for Bard, 344 of 2400 [14.3%] for GPT-3.5, and 255 of 2400 [10.6%] for GPT-4; P < .001). Conclusion LLMs achieved moderate agreement with human reader-assigned BI-RADS categories across reports written in three languages but also yielded a high percentage of discordant BI-RADS categories that would negatively impact clinical management. © RSNA, 2024 Supplemental material is available for this article.

Using the Kaiser Score as a clinical decision rule for breast lesion classification: Does computer-assisted curve type analysis improve diagnosis?

PURPOSE

We aimed to investigate the effect of using visual or automatic enhancement curve type assessment on the diagnostic performance of the Kaiser Score (KS), a clinical decision rule for breast MRI.

METHOD

This IRB-approved retrospective study analyzed consecutive conventional BI-RADS 0, 4 or 5 patients who underwent biopsy after 1.5T breast MRI according to EUSOBI recommendations between 2013 and 2015. The KS includes five criteria (spiculations; signal intensity (SI)-time curve type; margins of the lesion; internal enhancement; and presence of edema) resulting in scores from 1 (=lowest) to 11 (=highest risk of breast cancer). Enhancement curve types (Persistent, Plateau or Wash-out) were assessed by two radiologists independently visually and using a pixel-wise color-coded computed parametric map of curve types. KS diagnostic performance differences between readings were compared by ROC analysis.

RESULTS

In total 220 lesions (147 benign, 73 malignant) including mass (n = 148) and non-mass lesions (n = 72) were analyzed. KS reading performance in distinguishing benign from malignant lesions did not differ between visual analysis and parametric map (P = 0.119; visual: AUC 0.875, sensitivity 95 %, specificity 63 %; and map: AUC 0.901, sensitivity 97 %, specificity 65 %). Additionally, analyzing mass and non-mass lesions separately, showed no difference between parametric map based and visual curve type-based KS analysis as well (P = 0.130 and P = 0.787).

CONCLUSIONS

The performance of the Kaiser Score is largely independent of the curve type assessment methodology, confirming its robustness as a clinical decision rule for breast MRI in any type of breast lesion in clinical routine.

How Does Diagnostic Accuracy Evolve with Increased Breast MRI Experience?

Introduction: Our institution is part of a provincial program providing annual breast MRI screenings to high-risk women. We assessed how MRI experience, background parenchymal enhancement (BPE), and the amount of fibroglandular tissue (FGT) affect the biopsy-proven predictive value (PPV3) and accuracy for detecting suspicious MRI findings. Methods: From all high-risk screening breast MRIs conducted between 1 July 2011 and 30 June 2020, we reviewed all BI-RADS 4/5 observations with pathological tissue diagnoses. Overall and annual PPV3s were computed. Radiologists with fewer than ten observations were excluded from performance analyses. PPV3s were computed for each radiologist. We assessed how MRI experience, BPE, and FGT impacted diagnostic accuracy using logistic regression analyses, defining positive cases as malignancies alone (definition A) or malignant or high-risk lesions (definition B). Findings: There were 536 BI-RADS 4/5 observations with tissue diagnoses, including 77 malignant and 51 high-risk lesions. A total of 516 observations were included in the radiologist performance analyses. The average radiologist's PPV3 was 16 ± 6% (definition A) and 25 ± 8% (definition B). MRI experience in years correlated significantly with positive cases (definition B, OR = 1.05, p = 0.03), independent of BPE or FGT. Diagnostic accuracy improved exponentially with increased MRI experience (definition B, OR of 1.27 and 1.61 for 5 and 10 years, respectively, p = 0.03 for both). Lower levels of BPE significantly correlated with increased odds of findings being malignant, independent of FGT and MRI experience. Summary: More extensive MRI reading experience improves radiologists' diagnostic accuracy for high-risk or malignant lesions, even in MRI studies with increased BPE.

Clinical and imaging modality factors impacting radiological interpretation of breast screening in young women with neurofibromatosis type 1

Young women with Neurofibromatosis type 1 (NF1) have a high risk of developing breast cancer and poorer survival following breast cancer diagnosis. International guidelines recommend commencing breast screening between 30 and 35 years; however, the optimal screening modality is unestablished, and previous reports suggest that breast imaging may be complicated by the presence of intramammary and cutaneous neurofibromas (cNFs). The aim of this study was to explore potential barriers to implementation of breast screening for young women with NF1.Twenty-seven women (30-47 years) with NF1 completed breast screening with breast MRI, mammogram and breast ultrasound. Nineteen probably benign/suspicious lesions were detected across 14 women. Despite the presence of breast cNFs, initial biopsy rate for participants with NF1 (37%), were comparable to a BRCA pathogenic variant (PV) cohort (25%) (P = 0.311). No cancers or intramammary neurofibromas were identified. Most participants (89%) returned for second round screening.The presence of cNF did not affect clinician confidence in 3D mammogram interpretation, although increasing breast density, frequently seen in young women, impeded confidence for 2D and 3D mammogram. Moderate or marked background parenchymal enhancement on MRI was higher in the NF1 cohort (70.4%) than BRCA PV carriers (47.3%), which is an independent risk factor for breast cancer.Breast MRI was the preferred mode of screening over mammogram, as the majority (85%) with NF1 demonstrated breast density (BI-RADS 3C/4D), which hinders mammogram interpretation. For those with high breast density and high cNF breast coverage, 3D rather than 2D mammogram is preferred, if MRI is unavailable.

Cracking open the eristic rhetoric of contralateral prophylactic mastectomy research or why surgeons should not be so certain about this controversial breast cancer treatment

Contralateral prophylactic mastectomy (CPM) is a controversial breast cancer treatment in which both breasts are removed when only one is affected by cancer. Rates of CPM have been rising since the late 1990s, despite surgeons' strong agreement that the procedure should not be performed for average-risk women. This essay analyses that agreement as it is demonstrated in the surgical literature on CPM, arguing that it forms a 'rhetoric of certainty' built on the stark epistemological divide between objective and subjective forms of knowledge that operates in some areas of medicine. Further, the essay argues that this rhetoric of certainty has the potential to function as a kind of eristic rhetoric in which the right conclusion is known prior to any rhetorical exchange. As a way to 'crack open' this certainty, the essay compares the rhetoric of the surgical literature on CPM to the rhetoric of uncertainty in the radiological literature on breast cancer screening for women with a personal history of the disease. The goal of this comparison is not to suggest surgeons should support all choices for CPM. Rather, the aim is to demonstrate that choices against the procedure are not as straightforward as the surgical literature indicates and that the uncertainty affecting women's preferences for CPM is not solely the result of patient misunderstanding and/or emotional instability.

The added value of apparent diffusion coefficient and microcalcifications to the Kaiser score in the evaluation of BI-RADS 4 lesions

PURPOSE

To explore the added value of combining microcalcifications or apparent diffusion coefficient (ADC) with the Kaiser score (KS) for diagnosing BI-RADS 4 lesions.

METHODS

This retrospective study included 194 consecutive patients with 201 histologically verified BI-RADS 4 lesions. Two radiologists assigned the KS value to each lesion. Adding microcalcifications, ADC, or both these criteria to the KS yielded KS1, KS2, and KS3, respectively. The potential of all four scores to avoid unnecessary biopsies was assessed using the sensitivity and specificity. Diagnostic performance was evaluated by the area under the curve (AUC) and compared between KS and KS1.

RESULTS

The sensitivity of KS, KS1, KS2, and KS3 ranged from 77.1% to 100.0%.KS1 yielded significantly higher sensitivity than other methods (P < 0.05), except for KS3 (P > 0.05), most of all, when assessing NME lesions. For mass lesions, the sensitivity of these four scores was comparable (p > 0.05). The specificity of KS, KS1, KS2, and KS3 ranged from 56.0% to 69.4%, with no statistically significant differences(P > 0.05), except between KS1 and KS2 (p < 0.05).The AUC of KS1 (0.877) was significantly higher than that of KS (0.837; P = 0.0005), particularly for assessing NME (0.847 vs 0.713; P < 0.0001).

CONCLUSION

KS can stratify BI-RADS 4 lesions to avoid unnecessary biopsies. Adding microcalcifications, but not adding ADC, as an adjunct to KS improves diagnostic performance, particularly for NME lesions. ADC provides no additional diagnostic benefit to KS. Thus, only combining microcalcifications with KS is most conducive to clinical practice.

Multiparametric MRI: From Simultaneous Rapid Acquisition Methods and Analysis Techniques Using Scoring, Machine Learning, Radiomics, and Deep Learning to the Generation of Novel Metrics

ABSTRACT

With the recent advancements in rapid imaging methods, higher numbers of contrasts and quantitative parameters can be acquired in less and less time. Some acquisition models simultaneously obtain multiparametric images and quantitative maps to reduce scan times and avoid potential issues associated with the registration of different images. Multiparametric magnetic resonance imaging (MRI) has the potential to provide complementary information on a target lesion and thus overcome the limitations of individual techniques. In this review, we introduce methods to acquire multiparametric MRI data in a clinically feasible scan time with a particular focus on simultaneous acquisition techniques, and we discuss how multiparametric MRI data can be analyzed as a whole rather than each parameter separately. Such data analysis approaches include clinical scoring systems, machine learning, radiomics, and deep learning. Other techniques combine multiple images to create new quantitative maps associated with meaningful aspects of human biology. They include the magnetic resonance g-ratio, the inner to the outer diameter of a nerve fiber, and the aerobic glycolytic index, which captures the metabolic status of tumor tissues.

Radiomics model to classify mammary masses using breast DCE-MRI compared to the BI-RADS classification performance

BACKGROUND

Recent advanced in radiomics analysis could help to identify breast cancer among benign mammary masses. The aim was to create a radiomics signature using breast DCE-MRI extracted features to classify tumors and to compare the performances with the BI-RADS classification.

MATERIAL AND METHODS

From September 2017 to December 2019 images, exams and records from consecutive patients with mammary masses on breast DCE-MRI and available histology from one center were retrospectively reviewed (79 patients, 97 masses). Exclusion criterion was malignant uncertainty. The tumors were split in a train-set (70%) and a test-set (30%). From 14 kinetics maps, 89 radiomics features were extracted, for a total of 1246 features per tumor. Feature selection was made using Boruta algorithm, to train a random forest algorithm on the train-set. BI-RADS classification was recorded from two radiologists.

RESULTS

Seventy-seven patients were analyzed with 94 tumors, (71 malignant, 23 benign). Over 1246 features, 17 were selected from eight kinetic maps. On the test-set, the model reaches an AUC = 0.94 95 CI [0.85-1.00] and a specificity of 33% 95 CI [10-70]. There were 43/94 (46%) lesions BI-RADS4 (4a = 12/94 (13%); 4b = 9/94 (10%); and 4c = 22/94 (23%)). The BI-RADS score reached an AUC = 0.84 95 CI [0.73-0.95] and a specificity of 17% 95 CI [3-56]. There was no significant difference between the ROC curves for the model or the BI-RADS score (p = 0.19).

CONCLUSION

A radiomics signature from features extracted using breast DCE-MRI can reach an AUC of 0.94 on a test-set and could provide as good results as BI-RADS to classify mammary masses.

Estimation of the organ of origin of peri-ampullary malignancy by preoperative CT scan

BACKGROUND

Tumors occurring within the pancreatic head commonly arise from the pancreas, duodenal ampulla, distal bile duct, or duodenum. However, they are difficult to distinguish on standard preoperative imaging.

PURPOSE

To assess the ability of specialist reporting of preoperative computed tomography (CT) scans to determine the organ of origin of pancreatic cancer (PC).

MATERIAL AND METHODS

Blinded re-reporting of preoperative imaging from five hospitals was undertaken of a consecutive cohort of 411 patients undergoing surgery for PC between January 2006 and May 2014. Radiological identification of tumor site was determined by the presence of the main tumor bulk within the pancreatic head parenchyma and estimation of the pathological organ of origin of the PC was based on all the reported features.

RESULTS

Each pathological tumor type was noted to have distinct radiological features. Localization of a visible tumor within the pancreatic parenchyma was seen most commonly in PC (92%) than other tumor types (P < 0.0001). Local invasion into the duodenum was a characteristic feature seen in 79% of patients with ampullary tumors and isolated dilation of the bile duct without dilation of the pancreatic duct was seen most commonly in patients with ampullary or bile duct cancer. In the assessment of tumor origin, good agreement (kappa = 0.6, 0.51-0.68) was noted between the consensus radiology opinion and the final histology result. Overall accuracy was greatest for ampullary cancer (88.1%) and lowest for PC (83.2%).

CONCLUSION

Radiological assessment of preoperative imaging provides a high degree of accuracy in predicting the organ of origin of peri-ampullary cancer.

Background Parenchymal Enhancement at Postoperative Surveillance Breast MRI: Association with Future Second Breast Cancer Risk

Background Background parenchymal enhancement (BPE) is a known risk factor for breast cancer. However, studies on the association between BPE and second breast cancer risk are still lacking. Purpose To investigate whether BPE at surveillance breast MRI is associated with subsequent second breast cancer risk in women with a personal history of breast cancer. Materials and Methods A retrospective search of the imaging database of an academic medical center identified consecutive surveillance breast MRI examinations performed between January 2008 and December 2017 in women who underwent surgery for primary breast cancer and had no prior diagnosis of second breast cancer. BPE at surveillance breast MRI was qualitatively assessed using a four-category classification of minimal, mild, moderate, or marked. Future second breast cancer was defined as ipsilateral breast tumor recurrence or contralateral breast cancer diagnosed at least 1 year after each surveillance breast MRI examination. Factors associated with future second breast cancer risk were evaluated using the multivariable Fine-Gray subdistribution hazard model. Results Among the 2668 women (mean age at baseline surveillance breast MRI, 49 years ± 8 [SD]), 109 developed a second breast cancer (49 ipsilateral, 58 contralateral, and two ipsilateral and contralateral) at a median follow-up of 5.8 years. Mild, moderate, or marked BPE at surveillance breast MRI (hazard ratio [HR], 2.1 [95% CI: 1.4, 3.1]; P < .001), young age (<45 years) at initial breast cancer diagnosis (HR, 3.4 [95% CI: 1.7, 6.4]; P < .001), positive results from a BRCA1/2 genetic test (HR, 6.5 [95% CI: 3.5, 12.0]; P < .001), and negative hormone receptor expression in the initial breast cancer (HR, 1.6 [95% CI: 1.1, 2.6]; P = .02) were independently associated with an increased risk of future second breast cancer. Conclusion Background parenchymal enhancement at surveillance breast MRI was associated with future second breast cancer risk in women with a personal history of breast cancer. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Niell in this issue.

BI-RADS 3 Assessment on MRI: A Lesion-Based Review for Breast Radiologists

Unlike mammography and US, limited data exist to establish well-defined criteria for MRI findings that have a ≤2% likelihood of malignancy. Therefore, determining which findings are appropriate for a BI-RADS 3 assessment on MRI remains challenging and variable among breast radiologists. Emerging data suggest that BI-RADS 3 should be limited to baseline MRI examinations (or examinations with less than two years of prior comparisons) performed for high-risk screening and only used for masses with all of the typical morphological and kinetic features suggestive of a fibroadenoma or dominant enhancing T2 hypointense foci that is distinct from background parenchymal enhancement and without suspicious kinetics. This article presents an updated discussion of BI-RADS 3 assessment (probably benign) for breast MRI using current evidence.

Can DWI provide additional value to Kaiser score in evaluation of breast lesions

OBJECTIVES

To explore added value of diffusion-weighted imaging (DWI) as an adjunct to Kaiser score (KS) for differentiation of benign from malignant lesions on breast magnetic resonance imaging (MRI).

METHODS

Two hundred forty-six patients with 273 lesions (155 malignancies) were included in this retrospective study from January 2015 to December 2019. All lesions were proved by pathology. Two radiologists blind to pathological results evaluated lesions according to KS. Lesions with score > 4 were considered malignant. Four thresholds of ADC values -1.3 × 10^-3mm²/s, 1.4 × 10^-3mm²/s, 1.53 × 10^-3mm²/s, and 1.6 × 10^-3mm²/s were used to distinguish benign from malignant lesions. For combined diagnosis, a lesion with KS > 4 and ADC values below the preset cutoffs was considered as malignant; otherwise, it was benign. Sensitivity, specificity, and area under the curve (AUC) were compared between KS, DWI, and combined diagnosis.

RESULTS

The AUC of KS was significantly higher than that of DWI alone (0.941 vs 0.901, p = 0.04). The sensitivity of KS (96.8%) and DWI (97.4 - 99.4%) was comparable (p > 0.05) while the specificity of KS (83.9%) was significantly higher than that of DWI (19.5-56.8%) (p < 0.05). Adding DWI as an adjunct to KS resulted in a 0-2.5% increase of specificity and a 0.1-1.3% decrease of sensitivity; however, the difference did not reach statistical significance (p > 0.05).

CONCLUSION

KS showed higher diagnostic performance than DWI alone for discrimination of breast benign and malignant lesions. DWI showed no additional value to KS for characterizing breast lesions.

KEY POINTS

• KS showed higher diagnostic performance than DWI alone for differentiation of benign from breast malignant lesions. • DWI alone showed a high sensitivity but a low specificity for characterizing breast lesions. • Diagnostic performance did not improve using DWI as an adjunct to KS.

Breast MRI: does a clinical decision algorithm outweigh reader experience?

Objectives

Due to its high sensitivity, DCE MRI of the breast (MRIb) is increasingly used for both screening and assessment purposes. The Kaiser score (KS) is a clinical decision algorithm, which formalizes and guides diagnosis in breast MRI and is expected to compensate for lesser reader experience. The aim was to evaluate the diagnostic performance of untrained residents using the KS compared to off-site radiologists experienced in breast imaging using only MR BI-RADS.

Methods

Three off-site, board-certified radiologists, experienced in breast imaging, interpreted MRIb according to the MR BI-RADS scale. The same studies were read by three residents in radiology without prior training in breast imaging using the KS. All readers were blinded to clinical information. Histology was used as the gold standard. Statistical analysis was conducted by comparing the AUC of the ROC curves.

Results

A total of 80 women (median age 52 years) with 93 lesions (32 benign, 61 malignant) were included. The individual within-group performance of the three expert readers (AUC 0.723–0.742) as well as the three residents was equal (AUC 0.842–0.928), p > 0.05, respectively. But, the rating of each resident using the KS significantly outperformed the experts’ ratings using the MR BI-RADS scale (p ≤ 0.05).

Conclusion

The KS helped residents to achieve better results in reaching correct diagnoses than experienced radiologists empirically assigning MR BI-RADS categories in a clinical “problem solving MRI” setting. These results support that reporting breast MRI benefits more from using a diagnostic algorithm rather than expert experience.

Key Points

• Reporting breast MRI benefits more from using a diagnostic algorithm rather than expert experience in a clinical “problem solving MRI” setting.

• The Kaiser score, which provides a clinical decision algorithm for structured reporting, helps residents to reach an expert level in breast MRI reporting and to even outperform experienced radiologists using MR BI-RADS without further formal guidance.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-09015-8.

Diagnosis of Breast Cancer Using Radiomics Models Built Based on Dynamic Contrast Enhanced MRI Combined With Mammography

Objective

To build radiomics models using features extracted from DCE-MRI and mammography for diagnosis of breast cancer.

Materials and Methods

266 patients receiving MRI and mammography, who had well-enhanced lesions on MRI and histologically confirmed diagnosis were analyzed. Training dataset had 146 malignant and 56 benign, and testing dataset had 48 malignant and 18 benign lesions. Fuzzy-C-means clustering algorithm was used to segment the enhanced lesion on subtraction MRI maps. Two radiologists manually outlined the corresponding lesion on mammography by consensus, with the guidance of MRI maximum intensity projection. Features were extracted using PyRadiomics from three DCE-MRI parametric maps, and from the lesion and a 2-cm bandshell margin on mammography. The support vector machine (SVM) was applied for feature selection and model building, using 5 datasets: DCE-MRI, mammography lesion-ROI, mammography margin-ROI, mammography lesion+margin, and all combined.

Results

In the training dataset evaluated using 10-fold cross-validation, the diagnostic accuracy of the individual model was 83.2% for DCE-MRI, 75.7% for mammography lesion, 64.4% for mammography margin, and 77.2% for lesion+margin. When all features were combined, the accuracy was improved to 89.6%. By adding mammography features to MRI, the specificity was significantly improved from 69.6% (39/56) to 82.1% (46/56), p<0.01. When the developed models were applied to the independent testing dataset, the accuracy was 78.8% for DCE-MRI and 83.3% for combined MRI+Mammography.

Conclusion

The radiomics model built from the combined MRI and mammography has the potential to provide a machine learning-based diagnostic tool and decrease the false positive diagnosis of contrast-enhanced benign lesions on MRI.

Inter-reader reliability of contrast-enhanced ultrasound Liver Imaging Reporting and Data System: a meta-analysis

PURPOSE

To systematically determine the inter-reader reliability of the contrast-enhanced ultrasound (CEUS) Liver Imaging Reporting and Data System (LI-RADS), with emphasis on its major features for hepatocellular carcinoma (HCC) and LR-M (LI-RADS category M) features for non-HCC malignancy.

METHODS

MEDLINE, EMBASE, and Cochrane databases were searched from January 2016 to March 2021 to identify original articles reporting the inter-reader reliability of CEUS LI-RADS. Meta-analytic pooled kappa values (κ) were calculated for major features [nonrim arterial-phase hyperenhancement (APHE), mild and late washout], LR-M features (rim APHE, early washout), and LI-RADS categorization using the DerSimonian-Laird random-effects model. Meta-regression analysis was performed to explore any causes of study heterogeneity.

RESULTS

Twelve studies with a total of 2862 lesions were included. The meta-analytic pooled κ of nonrim APHE, mild and late washout, rim APHE, early washout, and LI-RADS categorization were 0.73 [95% confidence interval (CI), 0.67 - 0.79], 0.69 (95% CI, 0.54-0.84), 0.54 (95% CI, 0.37-0.71), 0.62 (95% CI, 0.45-0.79), and 0.75 (95% CI, 0.64-0.87), respectively. Compared with the major features, LR-M features had a lower meta-analytic pooled κ. Substantial study heterogeneity was noted in the LI-RADS categorization, and lesion size (p = 0.03) and the homogeneity in reader experience (p = 0.03) were significantly associated with study heterogeneity.

CONCLUSIONS

CEUS LI-RADS showed substantial inter-reader reliability for major features and LI-RADS categorization, but relatively lower reliability was found for LR-M features. In our opinion, the definitions of imaging features require further refinement to improve the inter-reader reliability of CEUS LI-RADS.

Glandular Tissue Component and Breast Cancer Risk in Mammographically Dense Breasts at Screening Breast US

Background Breast density at mammography is an established risk factor for breast cancer, but it cannot be used to distinguish between glandular and fibrous tissue. Purpose To evaluate the association between the glandular tissue component (GTC) at screening breast US and the risk of future breast cancer in women with dense breasts and the association between the GTC and lobular involution. Materials and Methods Screening breast US examinations performed in women with no prior history of breast cancer and with dense breasts with negative findings from mammography from January 2012 to December 2015 were retrospectively identified. The GTC was reported as being minimal, mild, moderate, or marked at the time of the US examination. In women who had benign breast biopsy results, the degree of lobular involution in normal background tissue was categorized as not present, mild, moderate, or complete. The GTC-related breast cancer risk in women with a cancer diagnosis or follow-up after 6 months was estimated by using Cox proportional hazards regression. Cumulative logistic regression was used to evaluate the association between the GTC and lobular involution. Results Among 8483 women (mean age, 49 years ± 8 [standard deviation]), 137 developed breast cancer over a median follow-up time of 5.3 years. Compared with a minimal or mild GTC, a moderate or marked GTC was associated with an increased cancer risk (hazard ratio, 1.5; 95% CI: 1.05, 2.1; P = .03) after adjusting for age and breast density. The GTC had an inverse association with lobular involution; women with no, mild, or moderate involution had greater odds (odds ratios of 4.9 [95% CI: 1.5, 16.6], 2.6 [95% CI: 0.95, 7.2], and 1.8 [95% CI: 0.7, 4.6], respectively) of a moderate or marked GTC than those with complete involution (P = .004). Conclusion The glandular tissue component was independently associated with the future breast cancer risk in women with dense breasts and reflects the lobular involution. It should be considered for risk stratification during screening breast US. © RSNA, 2021 Online supplemental material is available for this article.

Combined Use of Texture Features and Morphological Classification Based on Dynamic Contrast-enhanced MR Imaging: Differentiating Benign and Malignant Breast Masses with High Negative Predictive Value

Purpose: We evaluated the diagnostic performance of the texture features of dynamic contrast-enhanced (DCE) MRI for breast cancer diagnosis in which the discriminator was optimized, so that the specificity was maximized via the restriction of the negative predictive value (NPV) to greater than 98%.

Methods: Histologically proven benign and malignant mass lesions of DCE MRI were enrolled retrospectively. Training and testing sets consist of 166 masses (49 benign, 117 malignant) and 50 masses (15 benign, 35 malignant), respectively. Lesions were classified via MRI review by a radiologist into 4 shape types: smooth (S-type, 34 masses in training set and 8 masses in testing set), irregular without rim-enhancement (I-type, 60 in training and 14 in testing), irregular with rim-enhancement (R-type, 56 in training and 22 in testing), and spicula (16 in training and 6 in testing). Spicula were immediately classified as malignant. For the remaining masses, 298 texture features were calculated using a parametric map of DCE MRI in 3D mass regions. Masses were classified into malignant or benign using two thresholds on a feature pair. On the training set, several feature pairs and their thresholds were selected and optimized for each mass shape type to maximize specificity with the restriction of NPV > 98%. NPV and specificity were computed using the testing set by comparison with histopathologic results and averaged on the selected feature pairs.

Results: In the training set, 27, 12, and 15 texture feature pairs are selected for S-type, I-type, and R-type masses, respectively, and thresholds are determined. In the testing set, average NPV and specificity using the selected texture features were 99.0% and 45.2%, respectively, compared to the NPV (85.7%) and specificity (40.0%) in visually assessed MRI category-based diagnosis.

Conclusion: We, therefore, suggest that the NPV of our texture-based features method described performs similarly to or greater than the NPV of the MRI category-based diagnosis.

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.

Effects of gadobutrol on background parenchymal enhancement and differential diagnosis between benign and malignant lesions in dynamic magnetic resonance imaging of the breast

BACKGROUND

The high concentration of gadolinium in gadobutrol, which is widely used in Japan, helps visualize signal enhancement of neoplastic lesions, however, there was concern that high T1 relaxivity could decrease the contrast between the lesion and the background mammary gland. We evaluate the effect of gadobutrol on background parenchymal enhancement (BPE) and differential diagnosis between benign and malignant lesions in dynamic MRI of the breast.

METHODS

Ninety-nine patients were enrolled prospectively. Measurements of the following signal intensities (SIs) were obtained: breast tissue on a pre-contrast image (SI_pre) and an early-phase image (SI_early); and the SIs of breast cancer on a pre-contrast image (SI_pre-cancer) and an early-phase image (SI_early-cancer). We calculated the BPE ratio, i.e., (SI_early - SI_pre)/SI_pre and the cancer/BPE ratio, i.e., (SI_early-cancer - SI_pre-cancer)/(SI_early on the affected side - SI_pre on the affected side). These quantitative assessments were compared with the data from the recently published multicenter study (reference study without use of gadobutrol). In addition, two radiologists reinterpreted each of the MR images, and a third radiologist set the ROIs in the lesions and performed kinetic analysis as a Reader 3.

RESULTS

While there was no significant difference in the SI of breast cancer in the premenopausal patients between the two studies, that in postmenopausal patients was significantly higher in the present study than in the reference study (p = 0.002). Although there was no significant difference in the cancer/BPE ratio in the postmenopausal patients between the two studies, the cancer/BPE ratio in the premenopausal patients was significantly higher in the reference study than in the present study (p = 0.028). For differentiation between benign and malignant masses, the mass margin was found to be the most important term (p < 0.001). According to the data of Reader 3, visual washout was observed in all 18 patients in whom the interpretation was changed from "plateau" to "washout".

CONCLUSIONS

Gadobutrol may decrease the contrast between breast cancer and background parenchyma in premenopausal patients, and it may have a characteristic that "washout" does not easily occur, leading to "plateau" in patients with breast cancer.

Fully automatic quantification of fibroglandular tissue and background parenchymal enhancement with accurate implementation for axial and sagittal breast MRI protocols

PURPOSE

To propose and evaluate a fully automated technique for quantification of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) in breast MRI.

METHODS

We propose a fully automated method, where after preprocessing, FGT is segmented in T1-weighted, nonfat-saturated MRI. Incorporating an anatomy-driven prior probability for FGT and robust texture descriptors against intensity variations, our method effectively addresses major image processing challenges, including wide variations in breast anatomy and FGT appearance among individuals. Our framework then propagates this segmentation to dynamic contrast-enhanced (DCE)-MRI to quantify BPE within the segmented FGT regions. Axial and sagittal image data from 40 cancer-unaffected women were used to evaluate our proposed method vs a manually annotated reference standard.

RESULTS

High spatial correspondence was observed between the automatic and manual FGT segmentation (mean Dice similarity coefficient 81.14%). The FGT and BPE quantifications (denoted FGT% and BPE%) indicated high correlation (Pearson's r = 0.99 for both) between automatic and manual segmentations. Furthermore, the differences between the FGT% and BPE% quantified using automatic and manual segmentations were low (mean differences: -0.66 ± 2.91% for FGT% and -0.17 ± 1.03% for BPE%). When correlated with qualitative clinical BI-RADS ratings, the correlation coefficient for FGT% was still high (Spearman's ρ = 0.92), whereas that for BPE was lower (ρ = 0.65). Our proposed approach also performed significantly better than a previously validated method for sagittal breast MRI.

CONCLUSIONS

Our method demonstrated accurate fully automated quantification of FGT and BPE in both sagittal and axial breast MRI. Our results also suggested the complexity of BPE assessment, demonstrating relatively low correlation between segmentation and clinical rating.

Fully Automatic Assessment of Background Parenchymal Enhancement on Breast MRI Using Machine-Learning Models

BACKGROUND

Automated measurement and classification models with objectivity and reproducibility are required for accurate evaluation of the breast cancer risk of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE).

PURPOSE

To develop and evaluate a machine-learning algorithm for breast FGT segmentation and BPE classification.

STUDY TYPE

Retrospective.

POPULATION

A total of 794 patients with breast cancer, 594 patients assigned to the development set, and 200 patients to the test set.

FIELD STRENGTH/SEQUENCE

3T and 1.5T; T₂ -weighted, fat-saturated T₁ -weighted (T₁ W) with dynamic contrast enhancement (DCE).

ASSESSMENT

Manual segmentation was performed for the whole breast and FGT regions in the contralateral breast. The BPE region was determined by thresholding using the subtraction of the pre- and postcontrast T₁ W images and the segmented FGT mask. Two radiologists independently assessed the categories of FGT and BPE. A deep-learning-based algorithm was designed to segment and measure the volume of whole breast and FGT and classify the grade of BPE.

STATISTICAL TESTS

Dice similarity coefficients (DSC) and Spearman correlation analysis were used to compare the volumes from the manual and deep-learning-based segmentations. Kappa statistics were used for agreement analysis. Comparison of area under the receiver operating characteristic (ROC) curves (AUC) and F1 scores were calculated to evaluate the performance of BPE classification.

RESULTS

The mean (±SD) DSC for manual and deep-learning segmentations was 0.85 ± 0.11. The correlation coefficient for FGT volume from manual- and deep-learning-based segmentations was 0.93. Overall accuracy of manual segmentation and deep-learning segmentation in BPE classification task was 66% and 67%, respectively. For binary categorization of BPE grade (minimal/mild vs. moderate/marked), overall accuracy increased to 91.5% in manual segmentation and 90.5% in deep-learning segmentation; the AUC was 0.93 in both methods.

DATA CONCLUSION

This deep-learning-based algorithm can provide reliable segmentation and classification results for BPE.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Harmonization of Quantitative Parenchymal Enhancement in T1 -Weighted Breast MRI

BACKGROUND

Differences in imaging parameters influence computer-extracted parenchymal enhancement measures from breast MRI.

PURPOSE

To investigate the effect of differences in dynamic contrast-enhanced MRI acquisition parameter settings on quantitative parenchymal enhancement of the breast, and to evaluate harmonization of contrast-enhancement values with respect to flip angle and repetition time.

STUDY TYPE

Retrospective.

PHANTOM/POPULATIONS

We modeled parenchymal enhancement using simulations, a phantom, and two cohorts (N = 398 and N = 302) from independent cancer centers.

SEQUENCE FIELD/STRENGTH

1.5T dynamic contrast-enhanced T1 -weighted spoiled gradient echo MRI. Vendors: Philips, Siemens, General Electric Medical Systems.

ASSESSMENT

We assessed harmonization of parenchymal enhancement in simulations and phantom by varying the MR parameters that influence the amount of T1 -weighting: flip angle (8°-25°) and repetition time (4-12 msec). We calculated the median and interquartile range (IQR) of the enhancement values before and after harmonization. In vivo, we assessed overlap of quantitative parenchymal enhancement in the cohorts before and after harmonization using kernel density estimations. Cohort 1 was scanned with flip angle 20° and repetition time 8 msec; cohort 2 with flip angle 10° and repetition time 6 msec.

STATISTICAL TESTS

Paired Wilcoxon signed-rank-test of bootstrapped kernel density estimations.

RESULTS

Before harmonization, simulated enhancement values had a median (IQR) of 0.46 (0.34-0.49). After harmonization, the IQR was reduced: median (IQR): 0.44 (0.44-0.45). In the phantom, the IQR also decreased, median (IQR): 0.96 (0.59-1.22) before harmonization, 0.96 (0.91-1.02) after harmonization. Harmonization yielded significantly (P < 0.001) better overlap in parenchymal enhancement between the cohorts: median (IQR) was 0.46 (0.37-0.58) for cohort 1 vs. 0.37 (0.30-0.44) for cohort 2 before harmonization (57% overlap); and 0.35 (0.28-0.43) vs. .0.37 (0.30-0.44) after harmonization (85% overlap).

DATA CONCLUSION

The proposed practical harmonization method enables an accurate comparison between patients scanned with differences in imaging parameters.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 4.

[Kaiser score for diagnosis of breast lesions presenting as non-mass enhancement on MRI]

OBJECTIVE

To evaluate the diagnostic efficacy of Kaiser score for breast lesions presenting as non-mass enhancement.

METHODS

We collected data from patients with breast lesions presenting as non-mass enhancement on preoperative DCE-MRI between January, 2014 and June, 2019. All the cases were confirmed by surgical pathology or puncture biopsy. With pathology results as the gold standard, we evaluated the diagnostic efficacy of Kaiser score and MRI BI-RADS classification and the consistency between the diagnostic results by the two methods and the pathological results.

RESULTS

A total of 90 lesions were detected in 88 patients, including 28 benign lesions (31.1%) and 62 malignant lesions (68.9%). For diagnosis of the lesions, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of Kaiser Score were 100%, 75%, 89.9%, 100% and 92%, as compared with 93.5%, 46.4%, 79.5%, 76.5% and 78.9% of MRI BI-RADS, respectively. The diagnostic specificity of Kaiser score was significantly higher than that of BI-RADS classification (P=0.021).

CONCLUSIONS

The Kaiser score system provides a diagnostic strategy for BI-RADS classification of breast lesions with non-mass enhancement and has a better diagnostic efficacy than BI-RADS classification alone. The use of Kaiser score can significantly improve the diagnostic specificity of such breast lesions for inexperienced radiologists.

A Survey of Deep-Learning Applications in Ultrasound: Artificial Intelligence-Powered Ultrasound for Improving Clinical Workflow

Ultrasound is the most commonly used imaging modality in clinical practice because it is a nonionizing, low-cost, and portable point-of-care imaging tool that provides real-time images. Artificial intelligence (AI)-powered ultrasound is becoming more mature and getting closer to routine clinical applications in recent times because of an increased need for efficient and objective acquisition and evaluation of ultrasound images. Because ultrasound images involve operator-, patient-, and scanner-dependent variations, the adaptation of classical machine learning methods to clinical applications becomes challenging. With their self-learning ability, deep-learning (DL) methods are able to harness exponentially growing graphics processing unit computing power to identify abstract and complex imaging features. This has given rise to tremendous opportunities such as providing robust and generalizable AI models for improving image acquisition, real-time assessment of image quality, objective diagnosis and detection of diseases, and optimizing ultrasound clinical workflow. In this report, the authors review current DL approaches and research directions in rapidly advancing ultrasound technology and present their outlook on future directions and trends for DL techniques to further improve diagnosis, reduce health care cost, and optimize ultrasound clinical workflow.

Predictive Value of Breast MRI Background Parenchymal Enhancement for Neoadjuvant Treatment Response among HER2- Patients

OBJECTIVE

Women with advanced HER2- breast cancer have limited treatment options. Breast MRI functional tumor volume (FTV) is used to predict pathologic complete response (pCR) to improve treatment efficacy. In addition to FTV, background parenchymal enhancement (BPE) may predict response and was explored for HER2- patients in the I-SPY-2 TRIAL.

METHODS

Women with HER2- stage II or III breast cancer underwent prospective serial breast MRIs during four neoadjuvant chemotherapy timepoints. BPE was quantitatively calculated using whole-breast manual segmentation. Logistic regression models were systematically explored using pre-specified and optimized predictor selection based on BPE or combined with FTV.

RESULTS

A total of 352 MRI examinations in 88 patients (29 with pCR, 59 non-pCR) were evaluated. Women with hormone receptor (HR)+HER2- cancers who achieved pCR demonstrated a significantly greater decrease in BPE from baseline to pre-surgery compared to non-pCR patients (odds ratio 0.64, 95% confidence interval (CI): 0.39-0.92, P = 0.04). The associated BPE area under the curve (AUC) was 0.77 (95% CI: 0.56-0.98), comparable to the range of FTV AUC estimates. Among multi-predictor models, the highest cross-validated AUC of 0.81 (95% CI: 0.73-0.90) was achieved with combined FTV+HR predictors, while adding BPE to FTV+HR models had an estimated AUC of 0.82 (95% CI: 0.74-0.92).

CONCLUSION

Among women with HER2- cancer, BPE alone demonstrated association with pCR in women with HR+HER2- breast cancer, with similar diagnostic performance to FTV. BPE predictors remained significant in multivariate FTV models, but without added discrimination for pCR prediction. This may be due to small sample size limiting ability to create subtype-specific multivariate models.

Fully automatic classification of breast MRI background parenchymal enhancement using a transfer learning approach

Marked enhancement of the fibroglandular tissue on contrast-enhanced breast magnetic resonance imaging (MRI) may affect lesion detection and classification and is suggested to be associated with higher risk of developing breast cancer. The background parenchymal enhancement (BPE) is qualitatively classified according to the BI-RADS atlas into the categories "minimal," "mild," "moderate," and "marked." The purpose of this study was to train a deep convolutional neural network (dCNN) for standardized and automatic classification of BPE categories.This IRB-approved retrospective study included 11,769 single MR images from 149 patients. The MR images were derived from the subtraction between the first post-contrast volume and the native T1-weighted images. A hierarchic approach was implemented relying on 2 dCNN models for detection of MR-slices imaging breast tissue and for BPE classification, respectively. Data annotation was performed by 2 board-certified radiologists. The consensus of the 2 radiologists was chosen as reference for BPE classification. The clinical performances of the single readers and of the dCNN were statistically compared using the quadratic Cohen's kappa.Slices depicting the breast were classified with training, validation, and real-world (test) accuracies of 98%, 96%, and 97%, respectively. Over the 4 classes, the BPE classification was reached with mean accuracies of 74% for training, 75% for the validation, and 75% for the real word dataset. As compared to the reference, the inter-reader reliabilities for the radiologists were 0.780 (reader 1) and 0.679 (reader 2). On the other hand, the reliability for the dCNN model was 0.815.Automatic classification of BPE can be performed with high accuracy and support the standardization of tissue classification in MRI.

Interobserver Agreement for the Computed Tomography Severity Grading Scales for Acute Traumatic Brain Injury

The purpose of this study was to determine the interobserver variability among providers of different specialties and levels of experience across five established computed tomography (CT) scoring systems for acute traumatic brain injury (TBI). One hundred cases were selected at random from a retrospective population of adult patients transported to our emergency department and subjected to a non-contrast head CT due to suspicion of TBI. Eight neuroradiologists and neurosurgeons in trainee (residents and fellows) and attending roles independently scored each non-contrast head CT scan on the Marshall, Rotterdam, Helsinki, Stockholm, and NeuroImaging Radiological Interpretation System (NIRIS) head CT scales. Interobserver variability of scale scores-overall and by specialty and level of training-was quantified using the intraclass correlation coefficient (ICC), and agreement with respect to National Institutes of Health Common Data Elements (NIH CDEs) was assessed using Cohen's kappa. All CT severity scoring systems showed high interobserver agreement as evidenced by high ICCs, ranging from 0.75-0.89. For all scoring systems, neuroradiologists (ICC range from 0.81-0.94) tended to have higher interobserver agreement than neurosurgeons (ICC range from 0.63-0.76). For all scoring systems, attendings (ICC range from 0.76-0.89) had similar interobserver agreement to trainees (ICC range from 0.73-0.89). Agreement with respect to NIH CDEs was high for ascertaining presence/absence of hemorrhage, skull fracture, and mass effect, with estimated kappa statistics of least 0.89. Acute TBI CT scoring systems demonstrate high interobserver agreement. These results provide scientific rigor for future use of these systems for the classification of acute TBI.

Inter- and Intrareader Agreement of NI-RADS in the Interpretation of Surveillance Contrast-Enhanced CT after Treatment of Oral Cavity and Oropharyngeal Squamous Cell Carcinoma

BACKGROUND AND PURPOSE

The Neck Imaging Reporting and Data System was introduced to assess the probability of recurrence in surveillance imaging after treatment of head and neck cancer. This study investigated inter- and intrareader agreement in interpreting contrast-enhanced CT after treatment of oral cavity and oropharyngeal squamous cell carcinoma.

MATERIALS AND METHODS

This retrospective study analyzed CT datasets of 101 patients. Four radiologists provided the Neck Imaging Reporting and Data System reports for the primary site and neck (cervical lymph nodes). The Kendall's coefficient of concordance (W), Fleiss κ (κ_F), the Kendall's rank correlation coefficient (τ_B), and weighted κ statistics (κ_w) were calculated to assess inter- and intrareader agreement.

RESULTS

Overall, interreader agreement was strong or moderate for both the primary site (W = 0.74, κ_F = 0.48) and the neck (W = 0.80, κ_F = 0.50), depending on the statistics applied. Interreader agreement was higher in patients with proved recurrence at the primary site (W = 0.96 versus 0.56, κ_F = 0.65 versus 0.30) or in the neck (W = 0.78 versus 0.56, κ_F = 0.41 versus 0.29). Intrareader agreement was moderate to strong or almost perfect at the primary site (range τ_B = 0.67-0.82, κ_w = 0.85-0.96) and strong or almost perfect in the neck (range τ_B = 0.76-0.86, κ_w = 0.89-0.95).

CONCLUSIONS

The Neck Imaging Reporting and Data System used for surveillance contrast-enhanced CT after treatment of oral cavity and oropharyngeal squamous cell carcinoma provides acceptable score reproducibility with limitations in patients with posttherapeutic changes but no cancer recurrence.

Automated volumetric radiomic analysis of breast cancer vascularization improves survival prediction in primary breast cancer

To investigate whether automated volumetric radiomic analysis of breast cancer vascularization (VAV) can improve survival prediction in primary breast cancer. 314 consecutive patients with primary invasive breast cancer received standard clinical MRI before the initiation of treatment according to international recommendations. Diagnostic work-up, treatment, and follow-up was done at one tertiary care, academic breast-center (outcome: disease specific survival/DSS vs. disease specific death/DSD). The Nottingham Prognostic Index (NPI) was used as the reference method with which to predict survival of breast cancer. Based on the MRI scans, VAV was accomplished by commercially available, FDA-cleared software. DSD served as endpoint. Integration of VAV into the NPI gave NPI_VAV. Prediction of DSD by NPI_VAV compared to standard NPI alone was investigated (Cox regression, likelihood-test, predictive accuracy: Harrell's C, Kaplan Meier statistics and corresponding hazard ratios/HR, confidence intervals/CI). DSD occurred in 35 and DSS in 279 patients. Prognostication of the survival outcome by NPI (Harrell's C = 75.3%) was enhanced by VAV (NPI_VAV: Harrell's C = 81.0%). Most of all, the NPI_VAV identified patients with unfavourable outcome more reliably than NPI alone (hazard ratio/HR = 4.5; confidence interval/CI = 2.14-9.58; P = 0.0001). Automated volumetric radiomic analysis of breast cancer vascularization improved survival prediction in primary breast cancer. Most of all, it optimized the identification of patients at higher risk of an unfavorable outcome. Future studies should integrate MRI as a "gate keeper" in the management of breast cancer patients. Such a "gate keeper" could assist in selecting patients benefitting from more advanced diagnostic procedures (genetic profiling etc.) in order to decide whether are a more aggressive therapy (chemotherapy) is warranted.

Combination of an ultrafast TWIST-VIBE Dixon sequence protocol and diffusion-weighted imaging into an accurate easily applicable classification tool for masses in breast MRI

OBJECTIVES

This study aimed to develop a tool for the classification of masses in breast MRI, based on ultrafast TWIST-VIBE Dixon (TVD) dynamic sequences combined with DWI. TVD sequences allow to abbreviate breast MRI protocols, but provide kinetic information only on the contrast wash-in, and because of the lack of the wash-out kinetics, their diagnostic value might be hampered. A special focus of this study was thus to maintain high diagnostic accuracy in lesion classification.

MATERIALS AND METHODS

Sixty-one patients who received breast MRI between 02/2014 and 04/2015 were included, with 83 reported lesions (60 malignant). Our institute's standard breast MRI protocol was complemented by an ultrafast TVD sequence. ADC and peak enhancement of the TVD sequences were integrated into a generalised linear model (GLM) for malignancy prediction. For comparison, a second GLM was calculated using ADC and conventional DCE curve type. The resulting GLMs were evaluated for standard diagnostic parameters. For easy application of the GLMs, nomograms were created.

RESULTS

The GLM based on peak enhancement of the TVD and ADC was as equally accurate as the GLM based on conventional DCE and ADC, with no significant differences (sensitivity, 93.3%/93.3%; specificity, 91.3%/87.0%; PPV, 96.6%/94.9%; NPV, 84.0%/83.3%; all, p ≥ 0.315).

CONCLUSIONS

This study presents a method to integrate ultrafast TVD sequences into a breast MRI protocol, allowing a reduction of the examination time while maintaining diagnostic accuracy. A GLM based on the combination of TVD-derived peak enhancement and ADC provides high diagnostic accuracy, and can be easily applied using a nomogram.

KEY POINTS

• Ultrafast TWIST-VIBE Dixon sequence protocols in combination with diffusion-weighted imaging allow to shorten breast MRI examinations, while diagnostic accuracy is maintained. • Integrating peak enhancement from the TWIST-VIBE Dixon sequence and the apparent diffusion coefficient into a generalised linear model provides a comprehensible image evaluation approach. • This approach is further facilitated by nomograms.

Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses

We investigated whether the integration of machine learning (ML) into MRI interpretation can provide accurate decision rules for the management of suspicious breast masses. A total of 173 consecutive patients with suspicious breast masses upon complementary assessment (BI-RADS IV/V: n = 100/76) received standardized breast MRI prior to histological verification. MRI findings were independently assessed by two observers (R1/R2: 5 years of experience/no experience in breast MRI) using six (semi-)quantitative imaging parameters. Interobserver variability was studied by ICC (intraclass correlation coefficient). A polynomial kernel function support vector machine was trained to differentiate between benign and malignant lesions based on the six imaging parameters and patient age. Ten-fold cross-validation was applied to prevent overfitting. Overall diagnostic accuracy and decision rules (rule-out criteria) to accurately exclude malignancy were evaluated. Results were integrated into a web application and published online. Malignant lesions were present in 107 patients (60.8%). Imaging features showed excellent interobserver variability (ICC: 0.81–0.98) with variable diagnostic accuracy (AUC: 0.65–0.82). Overall performance of the ML algorithm was high (AUC = 90.1%; BI-RADS IV: AUC = 91.6%). The ML algorithm provided decision rules to accurately rule-out malignancy with a false negative rate <1% in 31.3% of the BI-RADS IV cases. Thus, integration of ML into MRI interpretation can provide objective and accurate decision rules for the management of suspicious breast masses, and could help to reduce the number of potentially unnecessary biopsies.

Breast Cancer Radiogenomics: Current Status and Future Directions

Radiogenomics is an area of research that aims to identify associations between imaging phenotypes ("radio-") and tumor genome ("-genomics"). Breast cancer radiogenomics research in particular has been an especially prolific area of investigation in recent years as evidenced by the wide number and variety of publications and conferences presentations. To date, research has primarily been focused on dynamic contrast enhanced pre-operative breast MRI and breast cancer molecular subtypes, but investigations have extended to all breast imaging modalities as well as multiple additional genetic markers including those that are commercially available. Furthermore, both human and computer-extracted features as well as deep learning techniques have been explored. This review will summarize the specific imaging modalities used in radiogenomics analysis, describe the methods of extracting imaging features, and present the types of genomics, molecular, and related information used for analysis. Finally, the limitations and future directions of breast cancer radiogenomics research will be discussed.

Agreement between dynamic contrast-enhanced magnetic resonance imaging and pathologic tumour size of breast cancer and analysis of the correlation with BI-RADS descriptors

Purpose

The purpose of this study was to evaluate magnetic resonance imaging (MRI)-pathology concordance of tumour size in patients with invasive breast carcinoma, with an emphasis on Breast Imaging Reporting and Data System (BI-RADS) descriptors of dynamic contrast-enhanced MRI (DCE-MRI).

Material and methods

Of patients who had preoperative DCE-MRI, 94 were enrolled. Concordance between MRI and the pathological findings was defined as a difference in tumour size of 5 mm or less. The greatest dimension was measured by two radiologists, and BI-RADS descriptives were described in accordance. The gold standard was chosen as the pathologic assessment.

Results

Tumour measurements determined by MRI and the pathological reports were not statistically different (2.64 ± 1.16 cm, Wilcaxon Z = –1.853, p = 0.064). Tumour sizes were concordant in 72/94 patients (76.6%). The mean difference between the pathological and MRI tumour sizes was –0.1 cm. MRI overestimated the size of 17/94 tumours (18.1%) and underestimated the size of 5/94 tumours (5.3%). Discordance was associated with larger tumour size. Histologic and molecular type of tumours, patient age, histologic grade, lymphovascular invasion or perineural invasion positivity, fibroglandular volume, background parenchymal enhancement, and being mass or non-mass were not associated with concordance. Irregular margin and heterogenous enhancement in DCE-MRI were associated with discordance in logistic regression analysis (p = 0.035, OR: 4.24; p = 0.021, OR: 4.96).

Conclusions

Two BI-RADS descriptors of irregular contour and heterogeneous contrast uptake were found to be associated with tumour size discrepancy. This might be attributed to the dynamic and morphologic specialities of tumours primarily rather than tumour biology.

Population-Based Assessment of the Association Between Magnetic Resonance Imaging Background Parenchymal Enhancement and Future Primary Breast Cancer Risk

PURPOSE

To evaluate comparative associations of breast magnetic resonance imaging (MRI) background parenchymal enhancement (BPE) and mammographic breast density with subsequent breast cancer risk.

PATIENTS AND METHODS

We examined women undergoing breast MRI in the Breast Cancer Surveillance Consortium from 2005 to 2015 (with one exam in 2000) using qualitative BPE assessments of minimal, mild, moderate, or marked. Breast density was assessed on mammography performed within 5 years of MRI. Among women diagnosed with breast cancer, the first BPE assessment was included if it was more than 3 months before their first diagnosis. Breast cancer risk associated with BPE was estimated using Cox proportional hazards regression.

RESULTS

Among 4,247 women, 176 developed breast cancer (invasive, n = 129; ductal carcinoma in situ,n = 47) over a median follow-up time of 2.8 years. More women with cancer had mild, moderate, or marked BPE than women without cancer (80% v 66%, respectively). Compared with minimal BPE, increasing BPE levels were associated with significantly increased cancer risk (mild: hazard ratio [HR], 1.80; 95% CI, 1.12 to 2.87; moderate: HR, 2.42; 95% CI, 1.51 to 3.86; and marked: HR, 3.41; 95% CI, 2.05 to 5.66). Compared with women with minimal BPE and almost entirely fatty or scattered fibroglandular breast density, women with mild, moderate, or marked BPE demonstrated elevated cancer risk if they had almost entirely fatty or scattered fibroglandular breast density (HR, 2.30; 95% CI, 1.19 to 4.46) or heterogeneous or extremely dense breasts (HR, 2.61; 95% CI, 1.44 to 4.72), with no significant interaction (P = .82). Combined mild, moderate, and marked BPE demonstrated significantly increased risk of invasive cancer (HR, 2.73; 95% CI, 1.66 to 4.49) but not ductal carcinoma in situ (HR, 1.48; 95% CI, 0.72 to 3.05).

CONCLUSION

BPE is associated with future invasive breast cancer risk independent of breast density. BPE should be considered for risk prediction models for women undergoing breast MRI.

Solitary, Well-Circumscribed, T2 Hyperintense Masses on MRI Have Very Low Malignancy Rates

OBJECTIVE

The purpose of this study was to determine the malignancy rate of solitary MRI masses with benign BI-RADS descriptors.

METHODS

A retrospective review was conducted of all breast MRI reports that described a mass with a final BI-RADS assessment of 3, 4, or 5, from February 1, 2005, through February 28, 2014 (n = 1510). Studies were excluded if the mass was not solitary, did not meet formal criteria for a mass, or had classically suspicious BI-RADS features (e.g., washout kinetics, and spiculated margin). The masses were reviewed by 2 fellowship-trained breast radiologists who reported consensus BI-RADS mass margin, shape, internal-enhancement, and kinetics descriptors. The T2 signal was reported as hyperintense if equal to or greater than the signal intensity of the axillary lymph nodes. Pathology results or 2 years of imaging follow-up were recorded. Comparisons were made between mass descriptors and clinical outcomes.

RESULTS

There were 127 women with 127 masses available for analysis. There were 76 (60%) masses that underwent biopsy for an overall malignancy rate of 4% (5/127): 2 ductal carcinoma in situ (DCIS) and 3 invasive ductal carcinoma. The malignancy rate was 2% (1/59) for T2 hyperintense solitary masses. The malignancy rate was greater than 2% for all of the following BI-RADS descriptors: oval (3%, 3/88), round (5%, 2/39), circumscribed (4%, 5/127), homogeneous (4%, 3/74), and dark internal septations (4%, 2/44).

CONCLUSION

T2 hyperintense solitary masses without associated suspicious features have a low malignancy rate, and they could be considered for a BI-RADS 3 final assessment.