Examination of fully automated mammographic density measures using LIBRA and breast cancer risk in a cohort of 21,000 non-Hispanic white women.

BACKGROUND: Breast density is strongly associated with breast cancer risk. Fully automated quantitative density assessment methods have recently been developed that could facilitate large-scale studies, although data on associations with long-term breast cancer risk are limited. We examined LIBRA assessments and breast cancer risk and compared results to prior assessments using Cumulus, an established computer-assisted method requiring manual thresholding. METHODS: We conducted a cohort study among 21,150 non-Hispanic white female participants of the Research Program in Genes, Environment and Health of Kaiser Permanente Northern California who were 40-74 years at enrollment, followed for up to 10 years, and had archived processed screening mammograms acquired on Hologic or General Electric full-field digital mammography (FFDM) machines and prior Cumulus density assessments available for analysis. Dense area (DA), non-dense area (NDA), and percent density (PD) were assessed using LIBRA software. Cox regression was used to estimate hazard ratios (HRs) for breast cancer associated with DA, NDA and PD modeled continuously in standard deviation (SD) increments, adjusting for age, mammogram year, body mass index, parity, first-degree family history of breast cancer, and menopausal hormone use. We also examined differences by machine type and breast view. RESULTS: The adjusted HRs for breast cancer associated with each SD increment of DA, NDA and PD were 1.36 (95% confidence interval, 1.18-1.57), 0.85 (0.77-0.93) and 1.44 (1.26-1.66) for LIBRA and 1.44 (1.33-1.55), 0.81 (0.74-0.89) and 1.54 (1.34-1.77) for Cumulus, respectively. LIBRA results were generally similar by machine type and breast view, although associations were strongest for Hologic machines and mediolateral oblique views. Results were also similar during the first 2 years, 2-5 years and 5-10 years after the baseline mammogram. CONCLUSION: Associations with breast cancer risk were generally similar for LIBRA and Cumulus density measures and were sustained for up to 10 years. These findings support the suitability of fully automated LIBRA assessments on processed FFDM images for large-scale research on breast density and cancer risk.

Comparison of Mammography AI Algorithms with a Clinical Risk Model for 5-year Breast Cancer Risk Prediction: An Observational Study.

Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted P < .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted P < .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023 Supplemental material is available for this article.

CT Use Reduction In Ostensive Ureteral Stone (CURIOUS).

INTRODUCTION: Computed tomography (CT) is performed in over 90% of patients diagnosed with ureteral stones, but only 10% of patients presenting to the emergency department (ED) with acute flank pain are hospitalized for a clinically important stone or non-stone diagnosis. Hydronephrosis can be accurately detected using point-of-care ultrasound and is a key predictor of ureteral stone and risk of subsequent complications. The absence of hydronephrosis is insufficient to exclude a stone. We created a sensitive clinical decision rule to predict clinically important ureteral stones. We hypothesized that this rule could identify patients at low risk for this outcome. METHODS: We conducted a retrospective cohort study in a random sample of 4000 adults who presented to one of 21 Kaiser Permanente Northern California EDs and underwent a CT for suspected ureteral stone from 1/1/2016 to 12/31/2020. The primary outcome was clinically important stone, defined as stone resulting in hospitalization or urologic procedure within 60 days. We used recursive partition analysis to generate a clinical decision rule predicting the outcome. We estimated the C-statistic (area under the curve), plotted the receiver operating characteristic (ROC) curve for the model, and calculated sensitivity, specificity, and predictive values of the model based on a risk threshold of 2%. RESULTS: Among 4000 patients, 354 (8.9%) had a clinically important stone. Our partition model resulted in four terminal nodes with risks ranging from 0.4% to 21.8%. The area under the ROC curve was 0.81 (95% CI 0.80, 0.83). Using a 2% risk cut point, a clinical decision tree including hydronephrosis, hematuria, and a history of prior stones predicted complicated stones with sensitivity 95.5% (95% CI 92.8%-97.4%), specificity 59.9% (95% CI 58.3%-61.5%), positive predictive value 18.8% (95% CI 18.1%-19.5%), and negative predictive value 99.3% (95% CI 98.8%-99.6%). CONCLUSIONS: Application of this clinical decision rule to imaging decisions would have led to 63% fewer CT scans with a miss rate of 0.4%. A limitation was the application of our decision rule only to patients who underwent CT for suspected ureteral stone. Thus, this rule would not apply to patients who were thought to have ureteral colic but did not receive a CT because ultrasound or history were sufficient for diagnosis. These results could inform future prospective validation studies.

Care in the time of COVID-19: impact on the diagnosis and treatment of breast cancer in a large, integrated health care system.

PURPOSES: To delineate operational changes in Kaiser Permanente Northern California breast care and evaluate the impact of these changes during the initial COVID-19 Shelter-in-Place period (SiP, 3/17/20-5/17/20). METHODS: By extracting data from institutional databases and reviewing electronic medical charts, we compared clinical and treatment characteristics of breast cancer patients diagnosed 3/17/20-5/17/20 to those diagnosed 3/17/19-5/17/2019. Outcomes included time from biopsy to consultation and treatment. Comparisons were made using Chi-square or Wilcoxon rank-sum tests. RESULTS: Fewer new breast cancers were diagnosed in 2020 during the SiP period than during a similar period in 2019 (n = 247 vs n = 703). A higher percentage presented with symptomatic disease in 2020 than 2019 (78% vs 37%, p < 0.001). Higher percentages of 2020 patients presented with grade 3 (37% vs 25%, p = 0.004) and triple-negative tumors (16% vs 10%, p = 0.04). A smaller percentage underwent surgery first in 2020 (71% vs 83%, p < 0.001) and a larger percentage had neoadjuvant chemotherapy (16% vs 11%, p < 0.001). Telehealth utilization increased from 0.8% in 2019 to 70.0% in 2020. Times to surgery and neoadjuvant chemotherapy were shorter in 2020 than 2019 (19 vs 26 days, p < 0.001, and 23 vs 28 days, p = 0.03, respectively). CONCLUSIONS: During SiP, fewer breast cancers were diagnosed than during a similar period in 2019, and a higher proportion presented with symptomatic disease. Early-stage breast cancer diagnoses decreased, while metastatic cancer diagnoses remained similar. Telehealth increased significantly, and times to treatment were shorter in 2020 than 2019. Our system continued to provide timely breast cancer treatment despite significant pandemic-driven disruption.

Implementation of Intraoperative Ultrasound Localization for Breast-Conserving Surgery in a Large, Integrated Health Care System is Feasible and Effective.

BACKGROUND: Intraoperative ultrasound (IUS) localization for breast cancer is a noninvasive localization technique. In 2015, an IUS program for breast-conserving surgery (BCS) was initiated in a large, integrated health care system. This study evaluated the clinical results of IUS implementation. METHODS: The study identified breast cancer patients with BCS from 1 January to 31 October 2015 and from 1 January to 31 October 2019. Clinicopathologic characteristics were collected, and localization types were categorized. Clinical outcomes were analyzed, including localization use, surgeon adoption of IUS, day-of-surgery intervals, and re-excision rates. Multivariate logistic regression analysis was performed to evaluate predictors of re-excision. RESULTS: The number of BCS procedures increased 23%, from 1815 procedures in 2015 to 2226 procedures in 2019. The IUS rate increased from 4% of lumpectomies (n = 79) in 2015 to 28% of lumpectomies (n = 632) in 2019 (p < 0.001). Surgeons using IUS increased from 6% (5 of 88 surgeons) in 2015 to 70% (42 of 60 surgeons) in 2019. In 2019, 76% of IUS surgeons performed at least 25% of lumpectomies with IUS. The mean time from admission to incision was shorter with IUS or seed localization than with wire localization (202 min with IUS, 201 with seed localization, 262 with wire localization in 2019; p < 0.001). The IUS re-excision rates were lower than for other localization techniques (13.6%, vs 19.6% for seed localization and 24.7% for wire localization in 2019; p = 0.006), and IUS predicted lower re-excision rates in a multivariable model (odds ratio [OR], 0.59). CONCLUSIONS: In a high-volume integrated health system, IUS was adopted for BCS by a majority of surgeons. The use of IUS decreased the time from admission to incision compared with wire localization, and decreased re-excision rates compared with other localization techniques.

Denoising and Multiple Tissue Compartment Visualization of Multi-b-Valued Breast Diffusion MRI.

BACKGROUND: Multi-b-valued/multi-shell diffusion provides potentially valuable metrics in breast MRI but suffers from low signal-to-noise ratio and has potentially long scan times. PURPOSE: To investigate the effects of model-based denoising with no loss of spatial resolution on multi-shell breast diffusion MRI; to determine the effects of downsampling on multi-shell diffusion; and to quantify these effects in multi-b-valued (three directions per b-value) acquisitions. STUDY TYPE: Prospective ("fully-sampled" multi-shell) and retrospective longitudinal (multi-b). SUBJECTS: One normal subject (multi-shell) and 10 breast cancer subjects imaging at four timepoints (multi-b). FIELD STRENGTH/SEQUENCE: 3T multi-shell acquisition and 1.5T multi-b acquisition. ASSESSMENT: The "fully-sampled" multi-shell acquisition was retrospectively downsampled to determine the bias and error from downsampling. Mean, axial/parallel, radial diffusivity, and fractional anisotropy (FA) were analyzed. Denoising was applied retrospectively to the multi-b-valued breast cancer subject dataset and assessed subjectively for image noise level and tumor conspicuity. STATISTICAL TESTS: Parametric paired t-test (P < 0.05 considered statistically significant) on mean and coefficient of variation of each metric-the apparent diffusion coefficient (ADC) from all b-values, fast ADC, slow ADC, and perfusion fraction. Paired and two-sample t-tests for each metric comparing normal and tumor tissue. RESULTS: In the multi-shell data, denoising effectively suppressed FA (-45% to -78%), with small biases in mean diffusivity (-5% in normal, +23% in tumor, and -4% in vascular compartments). In the multi-b data, denoising resulted in small biases to the ADC metrics in tumor and normal contralateral tissue (by -3% to +11%), but greatly reduced the coefficient of variation for every metric (by -1% to -24%). Denoising improved differentiation of tumor and normal tissue regions in most metrics and timepoints; subjectively, image noise level and tumor conspicuity were improved in the fast ADC maps. DATA CONCLUSION: Model-based denoising effectively suppressed erroneously high FA and improved the accuracy of diffusivity metrics. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY STAGE: 1.

Effect of Background Parenchymal Enhancement on Breast MR Imaging Interpretive Performance in Community-based Practices.

Purpose To evaluate the effect of background parenchymal enhancement (BPE) on breast magnetic resonance (MR) imaging interpretive performance in a large multi-institutional cohort with independent analysis of screening and diagnostic MR studies. Materials and Methods Analysis of 3770 breast MR studies was conducted. Examinations were performed in 2958 women at six participating facilities in the San Francisco Bay Area from January 2010 to October 2012. Findings were recorded prospectively in the San Francisco Mammography Registry. Performance measures were compared between studies with low BPE (mild or minimal) and those with high BPE (moderate or marked) by using binomial tests of proportions. Results Of 1726 MR imaging studies in the screening group, 1301 were classified as having low BPE and 425 were classified as having high BPE (75% vs 25%, respectively; P < .001). Of 2044 MR imaging studies in the diagnostic group, 1443 were classified as having low BPE and 601 were classified as having high BPE (71% vs 29%, respectively; P < .001). For low versus high BPE groups at screening, abnormal interpretation rate was 157 of 1301 versus 111 of 424 (12% vs 26%, P < .001); biopsy recommendation rate was 85 of 1301 versus 54 of 424 (7% vs 13%, P < .001); and specificity was 89% (95% confidence interval [CI]: 87, 91) versus 75% (95% CI: 71, 80) (P = .01). For the low versus high BPE groups at diagnostic MR imaging, biopsy recommendation rate was 325 of 1443 versus 195 of 601 (23% vs 32%, P < .001); and specificity was 86% (95% CI: 84, 88) versus 75% (95% CI: 74, 82) (P < .001). There were no significant differences between studies with low versus high BPE in sensitivity for screening (76% [95% CI: 55, 91] vs 83% [95% CI: 52, 98]; P = .94) or diagnostic (93% [95% CI: 87, 97] vs 96% [95% CI: 87, 99]; P = .69) MR imaging, nor were there significant differences in cancer detection rate per 1000 patients between the low BPE versus high BPE groups for screening (15 per 1000 vs 24 per 1000, P = .30) or diagnostic (78 per 1000 vs 85 per 1000, P = .64) MR imaging. Conclusion Relative to MR studies with minimal or mild BPE, those with moderate or marked BPE were associated with higher abnormal interpretation and biopsy rates and lower specificity, with no difference in cancer detection rate. © RSNA, 2017 Online supplemental material is available for this article.

Sonographic-MRI Correlation After Percutaneous Sampling of Targeted Breast Ultrasound Lesions: Initial Experiences With Limited-Sequence Unenhanced MRI for Postprocedural Clip Localization.

OBJECTIVE: The purpose of this study is to determine the frequency of correlation of sonographic and MRI findings after percutaneous sampling of presumed ultrasound correlates to suspicious lesions detected on breast MRI and to describe our initial experiences with limited-sequence MRI for postprocedural clip verification. MATERIALS AND METHODS: Between January 1, 2014, and March 31, 2016, a total of 1947 contrast-enhanced breast MRI examinations were performed, and 245 targeted ultrasound examinations were conducted to identify correlates to suspicious MRI findings. We retrospectively identified all lesions that underwent ultrasound-guided sampling of a presumed sonographic correlate and for which a subsequent postprocedural limited-sequence unenhanced MR image for clip localization was available. This consisted of a T1-weighted non-fat-saturated and a T2-weighted fat-saturated sequence. Frequencies of sonographic-MRI correlation were quantified. RESULTS: The study cohort consisted of 35 patients with 38 presumed correlates that underwent ultrasound-guided sampling with postprocedural MRI for clip verification. The mean time from percutaneous sampling to postprocedural MRI examination was 1 day. Ten presumed sonographic correlates (26%) were found to localize to a site distinct from the lesion originally identified on MRI. One of these discordant cases revealed malignancy on subsequent MRI-guided biopsy, whereas the presumed sonographic correlate was found to be benign. No patient or lesion characteristics were associated with significantly different frequencies of correlation. CONCLUSION: In our initial experiences with MRI performed for postprocedural clip verification, 26% of presumed correlates to suspicious lesions detected on MRI were not the actual correlate, and 10% of these discordant cases ultimately revealed malignancy. Radiologists should take caution presuming that lesions identified on ultrasound actually represent the suspicious lesions detected on MRI. MRI for clip verification may be useful if ultrasound-guided sampling is pursued.

Benefit of semiannual ipsilateral mammographic surveillance following breast conservation therapy.

PURPOSE: To compare cancer recurrence outcomes on the basis of compliant semiannual versus noncompliant annual ipsilateral mammographic surveillance following breast conservation therapy (BCT). MATERIALS AND METHODS: A HIPAA-compliant retrospective review was performed of post-BCT examinations from 1997 through 2008 by using a deidentified database. The Committee on Human Research did not require institutional review board approval for this study, which was considered quality assurance. Groups were classified according to compliance with institutional post-BCT protocol, which recommends semiannual mammographic examinations of the ipsilateral breast for 5 years. A compliant semiannual examination was defined as an examination with an interval of 0-9 months, although no examination had intervals less than 3 months. A noncompliant annual examination was defined as an examination with an interval of 9-18 months. Cancer recurrence outcomes were compared on the basis of the last examination interval leading to diagnosis. RESULTS: Initially, a total of 10 750 post-BCT examinations among 2329 asymptomatic patients were identified. Excluding initial mammographic follow-up, there were 8234 examinations. Of these, 7169 examinations were semiannual with 94 recurrences detected and 1065 examinations were annual with 15 recurrences detected. There were no differences in demographic risk factors or biopsy rates. Recurrences identified at semiannual intervals were significantly less advanced than those identified at annual intervals (stage I vs stage II, P = .04; stage 0 + stage I vs stage II, P = .03). Nonsignificant findings associated with semiannual versus annual intervals included smaller tumor size (mean, 11.7 vs 15.3 mm; P = .15) and node negativity (98% vs 91%, P = .28). CONCLUSION: Results suggest that a semiannual interval is preferable for ipsilateral mammographic surveillance, allowing detection of a significantly higher proportion of cancer recurrences at an earlier stage than noncompliant annual surveillance.

Qualitative assessment of enhancement in a renal mass: contribution of subtraction CT.

PURPOSE: To evaluate the impact of subtraction CT on reader confidence and diagnostic accuracy when characterizing renal masses. MATERIALS AND METHODS: In this institutional review board-approved retrospective study, 159 patients (85 men and 74 women; mean age, 62.6 years; range, 22-88 years) underwent routine unenhanced and contrast-enhanced multidetector computed tomography (MDCT) for renal lesion characterization. Subtraction images were subsequently generated on scanner console. Two readers independently reviewed the MDCT images to characterize presence of enhancement using a 6-point scale during 3 blinded review sessions of (1) only subtraction, (2) routine, and (3) combined subtraction and routine images. The standard of reference consisted of either histopathology or follow-up imaging and clinical data. RESULTS: Of the 240 lesions evaluated, 60 lesions (mean, 3.2 cm; range, 1-7.5 cm) were enhancing and 180 lesions (mean, 2.7 cm; range, 0.5-12 cm) were nonenhancing. For determination of lesion enhancement, a combined evaluation of routine MDCT and subtraction images improved reader confidence in 60% to 63% of lesions (P < 0.001). The combined evaluation also provided the highest sensitivity (97%), specificity (99%), and accuracy (98.9%). CONCLUSION: When used in combination with routine image interpretation, subtraction CT improves reader confidence and diagnostic accuracy in identifying enhancement in renal lesions.

Telehealth for Preoperative Evaluation of Patients With Breast Cancer During the COVID-19 Pandemic.

Introduction The COVID-19 pandemic drove rapid, widespread adoption of telehealth (TH). We evaluated surgical telehealth utilization and outcomes for newly diagnosed breast cancer patients during the initial pandemic period. Methods We identified patients with breast cancer diagnosed March 17, 2020 through May 17, 2020 who underwent surgery as the initial treatment. Clinicodemographic characteristics were collected. Initial consultation types (office, telephone, or video) were categorized. Outcomes included time to consultation, surgeon touchpoints, time to surgery, surgery types, and reexcision rates. Continuous variables were compared using Mann-Whitney tests or t-tests, and categorical variables were compared using χ2 or Fisher's exact tests. Results Of 158 patients, 56% had initial telehealth consultations (21% telephone, 35% video) and 42% did not have a preoperative physical examination. Age, race/ethnicity, and stage distributions were similar between initial visit types. Median time to consultation was lower in the initial telehealth group than the office group (6 days vs 9 days, p = 0.01). Other outcomes (surgeon touchpoints, time to surgery, surgery type, reconstruction) were similar between visit types. We observed higher reexcision rates in patients with initial telehealth visits (20% telehealth vs 4% office, p = 0.01), but evaluation was limited by small numbers. The reexcision rate was 13% for patients with telehealth visits and no preoperative physical exam. Discussion During the initial pandemic period, the majority of new breast cancer patients had an initial telehealth surgical consultation. Office and telehealth consultation visits had comparable numbers of postconsultation surgeon touchpoints and most outcomes. Our findings suggest that telehealth consultations may be feasible for preoperative breast cancer consultations.

Acute Kidney Injury After CT in Emergency Patients with Chronic Kidney Disease: A Propensity Score-matched Analysis.

INTRODUCTION: Acute kidney injury (AKI) after intravenous contrast administration for computed tomography (CT) occurs infrequently, but certain patients may be susceptible. This study evaluated AKI incidence among emergency department (ED) patients with pre-existing chronic kidney disease (CKD) undergoing CT exams. METHODS: This retrospective cohort study in an integrated healthcare system included ED patients previously diagnosed with CKD stages 3-5 (estimated glomerular filtration rate <60 milliliters per minute per 1.73 meters squared over at least three months), undergoing CT exams with or without intravenous contrast, from January 1, 2013-December 31, 2017. We excluded patients with CT prior to (30 days) or following (14 days) index CT and missing serum creatinine (sCr) measurements. We applied propensity score matching, and then multivariable regression adjustment for post-CT ED disposition and ED diagnosis, to calculate adjusted risk of AKI. Secondary patient-centered outcomes included 30-day mortality, end-stage renal disease (ESRD) diagnosis, and dialysis initiation. RESULTS: Among 103,573 eligible ED patients undergoing CT, propensity score matching yielded 5,589 pairs. Adjusted risk ratio (ARR) for AKI was higher overall for contrast-enhanced CT (1.60; 95% confidence interval [CI], 1.43-1.79). However, secondary outcomes were infrequent: 19/5,589 non-contrast vs 40/5,589 contrast patients with new dialysis initiation at 30 days (adjusted risk 0.3% vs 0.7%; adjusted risk reduction 0.4%; 95% CI, 0.1%-0.7%). CONCLUSION: In ED patients with chronic kidney disease undergoing CT, intravenous contrast was associated with higher overall adjusted risk of AKI, but patient-centered secondary outcomes were rare. The clinical significance of transient kidney injury after CT is unclear, although patients with advanced chronic kidney disease appear to have elevated risk.

Comparison of Segmentation Methods in Assessing Background Parenchymal Enhancement as a Biomarker for Response to Neoadjuvant Therapy.

Breast parenchymal enhancement (BPE) has shown association with breast cancer risk and response to neoadjuvant treatment. However, BPE quantification is challenging, and there is no standardized segmentation method for measurement. We investigated the use of a fully automated breast fibroglandular tissue segmentation method to calculate BPE from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for use as a predictor of pathologic complete response (pCR) following neoadjuvant treatment in the I-SPY 2 TRIAL. In this trial, patients had DCE-MRI at baseline (T0), after 3 weeks of treatment (T1), after 12 weeks of treatment and between drug regimens (T2), and after completion of treatment (T3). A retrospective analysis of 2 cohorts was performed: one with 735 patients and another with a final cohort of 340 patients, meeting a high-quality benchmark for segmentation. We evaluated 3 subvolumes of interest segmented from bilateral T1-weighted axial breast DCE-MRI: full stack (all axial slices), half stack (center 50% of slices), and center 5 slices. The differences between methods were assessed, and a univariate logistic regression model was implemented to determine the predictive performance of each segmentation method. The results showed that the half stack method provided the best compromise between sampling error from too little tissue and inclusion of incorrectly segmented tissues from extreme superior and inferior regions. Our results indicate that BPE calculated using the half stack segmentation approach has potential as an early biomarker for response to treatment in the hormone receptor-negative and human epidermal growth factor receptor 2-positive subtype.

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.

Predicting breast cancer response to neoadjuvant treatment using multi-feature MRI: results from the I-SPY 2 TRIAL.

Dynamic contrast-enhanced (DCE) MRI provides both morphological and functional information regarding breast tumor response to neoadjuvant chemotherapy (NAC). The purpose of this retrospective study is to test if prediction models combining multiple MRI features outperform models with single features. Four features were quantitatively calculated in each MRI exam: functional tumor volume, longest diameter, sphericity, and contralateral background parenchymal enhancement. Logistic regression analysis was used to study the relationship between MRI variables and pathologic complete response (pCR). Predictive performance was estimated using the area under the receiver operating characteristic curve (AUC). The full cohort was stratified by hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) status (positive or negative). A total of 384 patients (median age: 49 y/o) were included. Results showed analysis with combined features achieved higher AUCs than analysis with any feature alone. AUCs estimated for the combined versus highest AUCs among single features were 0.81 (95% confidence interval [CI]: 0.76, 0.86) versus 0.79 (95% CI: 0.73, 0.85) in the full cohort, 0.83 (95% CI: 0.77, 0.92) versus 0.73 (95% CI: 0.61, 0.84) in HR-positive/HER2-negative, 0.88 (95% CI: 0.79, 0.97) versus 0.78 (95% CI: 0.63, 0.89) in HR-positive/HER2-positive, 0.83 (95% CI not available) versus 0.75 (95% CI: 0.46, 0.81) in HR-negative/HER2-positive, and 0.82 (95% CI: 0.74, 0.91) versus 0.75 (95% CI: 0.64, 0.83) in triple negatives. Multi-feature MRI analysis improved pCR prediction over analysis of any individual feature that we examined. Additionally, the improvements in prediction were more notable when analysis was conducted according to cancer subtype.

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.

Exploration of PET and MRI radiomic features for decoding breast cancer phenotypes and prognosis.

Radiomics is an emerging technology for imaging biomarker discovery and disease-specific personalized treatment management. This paper aims to determine the benefit of using multi-modality radiomics data from PET and MR images in the characterization breast cancer phenotype and prognosis. Eighty-four features were extracted from PET and MR images of 113 breast cancer patients. Unsupervised clustering based on PET and MRI radiomic features created three subgroups. These derived subgroups were statistically significantly associated with tumor grade (p = 2.0 × 10-6), tumor overall stage (p = 0.037), breast cancer subtypes (p = 0.0085), and disease recurrence status (p = 0.0053). The PET-derived first-order statistics and gray level co-occurrence matrix (GLCM) textural features were discriminative of breast cancer tumor grade, which was confirmed by the results of L2-regularization logistic regression (with repeated nested cross-validation) with an estimated area under the receiver operating characteristic curve (AUC) of 0.76 (95% confidence interval (CI) = [0.62, 0.83]). The results of ElasticNet logistic regression indicated that PET and MR radiomics distinguished recurrence-free survival, with a mean AUC of 0.75 (95% CI = [0.62, 0.88]) and 0.68 (95% CI = [0.58, 0.81]) for 1 and 2 years, respectively. The MRI-derived GLCM inverse difference moment normalized (IDMN) and the PET-derived GLCM cluster prominence were among the key features in the predictive models for recurrence-free survival. In conclusion, radiomic features from PET and MR images could be helpful in deciphering breast cancer phenotypes and may have potential as imaging biomarkers for prediction of breast cancer recurrence-free survival.

Inter-reader Variability in the Use of BI-RADS Descriptors for Suspicious Findings on Diagnostic Mammography: A Multi-institution Study of 10 Academic Radiologists.

RATIONALE AND OBJECTIVES: The study aimed to determine the inter-observer agreement among academic breast radiologists when using the Breast Imaging Reporting and Data System (BI-RADS) lesion descriptors for suspicious findings on diagnostic mammography. MATERIALS AND METHODS: Ten experienced academic breast radiologists across five medical centers independently reviewed 250 de-identified diagnostic mammographic cases that were previously assessed as BI-RADS 4 or 5 with subsequent pathologic diagnosis by percutaneous or surgical biopsy. Each radiologist assessed the presence of the following suspicious mammographic findings: mass, asymmetry (one view), focal asymmetry (two views), architectural distortion, and calcifications. For any identified calcifications, the radiologist also described the morphology and distribution. Inter-observer agreement was determined with Fleiss kappa statistic. Agreement was also calculated by years of experience. RESULTS: Of the 250 lesions, 156 (62%) were benign and 94 (38%) were malignant. Agreement among the 10 readers was strongest for recognizing the presence of calcifications (k = 0.82). There was substantial agreement among the readers for the identification of a mass (k = 0.67), whereas agreement was fair for the presence of a focal asymmetry (k = 0.21) or architectural distortion (k = 0.28). Agreement for asymmetries (one view) was slight (k = 0.09). Among the categories of calcification morphology and distribution, reader agreement was moderate (k = 0.51 and k = 0.60, respectively). Readers with more experience (10 or more years in clinical practice) did not demonstrate higher levels of agreement compared to those with less experience. CONCLUSIONS: Strength of agreement varies widely for different types of mammographic findings, even among dedicated academic breast radiologists. More subtle findings such as asymmetries and architectural distortion demonstrated the weakest agreement. Studies that seek to evaluate the predictive value of certain mammographic features for malignancy should take into consideration the inherent interpretive variability for these findings.