18F-FDG Dedicated Breast PET Complementary to Breast MRI for Evaluating Early Response to Neoadjuvant Chemotherapy.

Purpose To compare quantitative measures of tumor metabolism and perfusion using fluorine 18 (18F) fluorodeoxyglucose (FDG) dedicated breast PET (dbPET) and breast dynamic contrast-enhanced (DCE) MRI during early treatment with neoadjuvant chemotherapy (NAC). Materials and Methods Prospectively collected DCE MRI and 18F-FDG dbPET examinations were analyzed at baseline (T0) and after 3 weeks (T1) of NAC in 20 participants with 22 invasive breast cancers. FDG dbPET-derived standardized uptake value (SUV), metabolic tumor volume, and total lesion glycolysis (TLG) and MRI-derived percent enhancement (PE), signal enhancement ratio (SER), and functional tumor volume (FTV) were calculated at both time points. Differences between FDG dbPET and MRI parameters were evaluated after stratifying by receptor status, Ki-67 index, and residual cancer burden. Parameters were compared using Wilcoxon signed rank and Mann-Whitney U tests. Results High Ki-67 tumors had higher baseline SUVmean (difference, 5.1; P = .01) and SUVpeak (difference, 5.5; P = .04). At T1, decreases were observed in FDG dbPET measures (pseudo-median difference T0 minus T1 value [95% CI]) of SUVmax (-6.2 [-10.2, -2.6]; P < .001), SUVmean (-2.6 [-4.9, -1.3]; P < .001), SUVpeak (-4.2 [-6.9, -2.3]; P < .001), and TLG (-29.1 mL3 [-71.4, -6.8]; P = .005) and MRI measures of SERpeak (-1.0 [-1.3, -0.2]; P = .02) and FTV (-11.6 mL3 [-22.2, -1.7]; P = .009). Relative to nonresponsive tumors, responsive tumors showed a difference (95% CI) in percent change in SUVmax of -34.3% (-55.9%, 1.5%; P = .06) and in PEpeak of -42.4% (95% CI: -110.5%, 8.5%; P = .08). Conclusion 18F-FDG dbPET was sensitive to early changes during NAC and provided complementary information to DCE MRI that may be useful for treatment response evaluation. Keywords: Breast, PET, Dynamic Contrast-enhanced MRI Clinical trial registration no. NCT01042379 Supplemental material is available for this article. © RSNA, 2024.

Cell-free DNA concentration as a biomarker of response and recurrence in HER2-negative breast cancer receiving neoadjuvant chemotherapy.

PURPOSE: We previously demonstrated the clinical significance of circulating tumor DNA (ctDNA) in patients with HER2-negative breast cancer receiving neoadjuvant chemotherapy (NAC). Here, we compared its predictive and prognostic value with cell-free DNA (cfDNA) concentration measured in the same samples from the same patients. EXPERIMENTAL DESIGN: 145 hormone receptor (HR)-positive/HER2-negative and 138 triple-negative breast cancer (TNBC) patients with ctDNA data from a previous study were included in the analysis. Associations of serial cfDNA concentration with residual cancer burden (RCB) and distant recurrence-free survival (DRFS) were examined. RESULTS: In TNBC, we observed a modest negative correlation between cfDNA concentration 3 weeks after treatment initiation and RCB, but none of the other timepoints showed significant correlation. In contrast, ctDNA was significantly positively correlated with RCB at all timepoints (all R>0.3 and p<0.05). In the HR-positive/HER2-negative group, cfDNA concentration did not associate with response to NAC, but survival analysis showed that high cfDNA-shedders at pretreatment had a significantly worse DRFS than low shedders (hazard ratio 2.12, p=0.037). In TNBC, the difference in survival between high vs. low cfDNA-shedders at all timepoints was not statistically significant. In contrast, as previously reported, ctDNA at all timepoints was significantly correlated with DRFS in both subtypes. CONCLUSIONS: In TNBC, cfDNA concentrations during therapy were not strongly correlated with response or prognosis. In the HR-positive/HER2-negative group, pretreatment cfDNA concentration was prognostic for DRFS. Overall, the predictive and prognostic value of cfDNA concentration was more limited than that of ctDNA.

Breast Multiparametric MRI for Prediction of Neoadjuvant Chemotherapy Response in Breast Cancer: The BMMR2 Challenge.

Purpose To describe the design, conduct, and results of the Breast Multiparametric MRI for prediction of neoadjuvant chemotherapy Response (BMMR2) challenge. Materials and Methods The BMMR2 computational challenge opened on May 28, 2021, and closed on December 21, 2021. The goal of the challenge was to identify image-based markers derived from multiparametric breast MRI, including diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI, along with clinical data for predicting pathologic complete response (pCR) following neoadjuvant treatment. Data included 573 breast MRI studies from 191 women (mean age [±SD], 48.9 years ± 10.56) in the I-SPY 2/American College of Radiology Imaging Network (ACRIN) 6698 trial (ClinicalTrials.gov: NCT01042379). The challenge cohort was split into training (60%) and test (40%) sets, with teams blinded to test set pCR outcomes. Prediction performance was evaluated by area under the receiver operating characteristic curve (AUC) and compared with the benchmark established from the ACRIN 6698 primary analysis. Results Eight teams submitted final predictions. Entries from three teams had point estimators of AUC that were higher than the benchmark performance (AUC, 0.782 [95% CI: 0.670, 0.893], with AUCs of 0.803 [95% CI: 0.702, 0.904], 0.838 [95% CI: 0.748, 0.928], and 0.840 [95% CI: 0.748, 0.932]). A variety of approaches were used, ranging from extraction of individual features to deep learning and artificial intelligence methods, incorporating DCE and DWI alone or in combination. Conclusion The BMMR2 challenge identified several models with high predictive performance, which may further expand the value of multiparametric breast MRI as an early marker of treatment response. Clinical trial registration no. NCT01042379 Keywords: MRI, Breast, Tumor Response Supplemental material is available for this article. © RSNA, 2024.

Neoadjuvant Trebananib plus Paclitaxel-based Chemotherapy for Stage II/III Breast Cancer in the Adaptively Randomized I-SPY2 Trial-Efficacy and Biomarker Discovery.

PURPOSE: The neutralizing peptibody trebananib prevents angiopoietin-1 and angiopoietin-2 from binding with Tie2 receptors, inhibiting angiogenesis and proliferation. Trebananib was combined with paclitaxel±trastuzumab in the I-SPY2 breast cancer trial. PATIENTS AND METHODS: I-SPY2, a phase II neoadjuvant trial, adaptively randomizes patients with high-risk, early-stage breast cancer to one of several experimental therapies or control based on receptor subtypes as defined by hormone receptor (HR) and HER2 status and MammaPrint risk (MP1, MP2). The primary endpoint is pathologic complete response (pCR). A therapy "graduates" if/when it achieves 85% Bayesian probability of success in a phase III trial within a given subtype. Patients received weekly paclitaxel (plus trastuzumab if HER2-positive) without (control) or with weekly intravenous trebananib, followed by doxorubicin/cyclophosphamide and surgery. Pathway-specific biomarkers were assessed for response prediction. RESULTS: There were 134 participants randomized to trebananib and 133 to control. Although trebananib did not graduate in any signature [phase III probabilities: Hazard ratio (HR)-negative (78%), HR-negative/HER2-positive (74%), HR-negative/HER2-negative (77%), and MP2 (79%)], it demonstrated high probability of superior pCR rates over control (92%-99%) among these subtypes. Trebananib improved 3-year event-free survival (HR 0.67), with no significant increase in adverse events. Activation levels of the Tie2 receptor and downstream signaling partners predicted trebananib response in HER2-positive disease; high expression of a CD8 T-cell gene signature predicted response in HR-negative/HER2-negative disease. CONCLUSIONS: The angiopoietin (Ang)/Tie2 axis inhibitor trebananib combined with standard neoadjuvant therapy increased estimated pCR rates across HR-negative and MP2 subtypes, with probabilities of superiority >90%. Further study of Ang/Tie2 receptor axis inhibitors in validated, biomarker-predicted sensitive subtypes is warranted.

Protein signaling and drug target activation signatures to guide therapy prioritization: Therapeutic resistance and sensitivity in the I-SPY 2 Trial.

Molecular subtyping of breast cancer is based mostly on HR/HER2 and gene expression-based immune, DNA repair deficiency, and luminal signatures. We extend this description via functional protein pathway activation mapping using pre-treatment, quantitative expression data from 139 proteins/phosphoproteins from 736 patients across 8 treatment arms of the I-SPY 2 Trial (ClinicalTrials.gov: NCT01042379). We identify predictive fit-for-purpose, mechanism-of-action-based signatures and individual predictive protein biomarker candidates by evaluating associations with pathologic complete response. Elevated levels of cyclin D1, estrogen receptor alpha, and androgen receptor S650 associate with non-response and are biomarkers for global resistance. We uncover protein/phosphoprotein-based signatures that can be utilized both for molecularly rationalized therapeutic selection and for response prediction. We introduce a dichotomous HER2 activation response predictive signature for stratifying triple-negative breast cancer patients to either HER2 or immune checkpoint therapy response as a model for how protein activation signatures provide a different lens to view the molecular landscape of breast cancer and synergize with transcriptomic-defined signatures.

Effect of Longitudinal Variation in Tumor Volume Estimation for MRI-guided Personalization of Breast Cancer Neoadjuvant Treatment.

Purpose To investigate the impact of longitudinal variation in functional tumor volume (FTV) underestimation and overestimation in predicting pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC). Materials and Methods Women with breast cancer who were enrolled in the prospective I-SPY 2 TRIAL (Investigation of Serial Studies to Predict Your Therapeutic Response with Imaging and Molecular Analysis 2) from May 2010 to November 2016 were eligible for this retrospective analysis. Participants underwent four MRI examinations during NAC treatment. FTV was calculated based on automated segmentation. Baseline FTV before treatment (FTV0) and the percentage of FTV change at early treatment and inter-regimen time points relative to baseline (∆FTV1 and ∆FTV2, respectively) were classified into high-standard or standard groups based on visual assessment of FTV under- and overestimation. Logistic regression models predicting pCR using single predictors (FTV0, ∆FTV1, and ∆FTV2) and multiple predictors (all three) were developed using bootstrap resampling with out-of-sample data evaluation with the area under the receiver operating characteristic curve (AUC) independently in each group. Results This study included 432 women (mean age, 49.0 years ± 10.6 [SD]). In the FTV0 model, the high-standard and standard groups showed similar AUCs (0.61 vs 0.62). The high-standard group had a higher estimated AUC compared with the standard group in the ∆FTV1 (0.74 vs 0.63), ∆FTV2 (0.79 vs 0.62), and multiple predictor models (0.85 vs 0.64), with a statistically significant difference for the latter two models (P = .03 and P = .01, respectively). Conclusion The findings in this study suggest that longitudinal variation in FTV estimation needs to be considered when using early FTV change as an MRI-based criterion for breast cancer treatment personalization. Keywords: Breast, Cancer, Dynamic Contrast-enhanced, MRI, Tumor Response ClinicalTrials.gov registration no. NCT01042379 Supplemental material is available for this article. © RSNA, 2023 See also the commentary by Ram in this issue.

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.

Computational drug repositioning for the identification of new agents to sensitize drug-resistant breast tumors across treatments and receptor subtypes.

Introduction: Drug resistance is a major obstacle in cancer treatment and can involve a variety of different factors. Identifying effective therapies for drug resistant tumors is integral for improving patient outcomes. Methods: In this study, we applied a computational drug repositioning approach to identify potential agents to sensitize primary drug resistant breast cancers. We extracted drug resistance profiles from the I-SPY 2 TRIAL, a neoadjuvant trial for early stage breast cancer, by comparing gene expression profiles of responder and non-responder patients stratified into treatments within HR/HER2 receptor subtypes, yielding 17 treatment-subtype pairs. We then used a rank-based pattern-matching strategy to identify compounds in the Connectivity Map, a database of cell line derived drug perturbation profiles, that can reverse these signatures in a breast cancer cell line. We hypothesize that reversing these drug resistance signatures will sensitize tumors to treatment and prolong survival. Results: We found that few individual genes are shared among the drug resistance profiles of different agents. At the pathway level, however, we found enrichment of immune pathways in the responders in 8 treatments within the HR+HER2+, HR+HER2-, and HR-HER2- receptor subtypes. We also found enrichment of estrogen response pathways in the non-responders in 10 treatments primarily within the hormone receptor positive subtypes. Although most of our drug predictions are unique to treatment arms and receptor subtypes, our drug repositioning pipeline identified the estrogen receptor antagonist fulvestrant as a compound that can potentially reverse resistance across 13/17 of the treatments and receptor subtypes including HR+ and triple negative. While fulvestrant showed limited efficacy when tested in a panel of 5 paclitaxel resistant breast cancer cell lines, it did increase drug response in combination with paclitaxel in HCC-1937, a triple negative breast cancer cell line. Conclusion: We applied a computational drug repurposing approach to identify potential agents to sensitize drug resistant breast cancers in the I-SPY 2 TRIAL. We identified fulvestrant as a potential drug hit and showed that it increased response in a paclitaxel-resistant triple negative breast cancer cell line, HCC-1937, when treated in combination with paclitaxel.

Clinical significance and biology of circulating tumor DNA in high-risk early-stage HER2-negative breast cancer receiving neoadjuvant chemotherapy.

Circulating tumor DNA (ctDNA) analysis may improve early-stage breast cancer treatment via non-invasive tumor burden assessment. To investigate subtype-specific differences in the clinical significance and biology of ctDNA shedding, we perform serial personalized ctDNA analysis in hormone receptor (HR)-positive/HER2-negative breast cancer and triple-negative breast cancer (TNBC) patients receiving neoadjuvant chemotherapy (NAC) in the I-SPY2 trial. ctDNA positivity rates before, during, and after NAC are higher in TNBC than in HR-positive/HER2-negative breast cancer patients. Early clearance of ctDNA 3 weeks after treatment initiation predicts a favorable response to NAC in TNBC only. Whereas ctDNA positivity associates with reduced distant recurrence-free survival in both subtypes. Conversely, ctDNA negativity after NAC correlates with improved outcomes, even in patients with extensive residual cancer. Pretreatment tumor mRNA profiling reveals associations between ctDNA shedding and cell cycle and immune-associated signaling. On the basis of these findings, the I-SPY2 trial will prospectively test ctDNA for utility in redirecting therapy to improve response and prognosis.

Radiomic tumor phenotypes augment molecular profiling in predicting recurrence free survival after breast neoadjuvant chemotherapy.

BACKGROUND: Early changes in breast intratumor heterogeneity during neoadjuvant chemotherapy may reflect the tumor's ability to adapt and evade treatment. We investigated the combination of precision medicine predictors of genomic and MRI data towards improved prediction of recurrence free survival (RFS). METHODS: A total of 100 women from the ACRIN 6657/I-SPY 1 trial were retrospectively analyzed. We estimated MammaPrint, PAM50 ROR-S, and p53 mutation scores from publicly available gene expression data and generated four, voxel-wise 3-D radiomic kinetic maps from DCE-MR images at both pre- and early-treatment time points. Within the primary lesion from each kinetic map, features of change in radiomic heterogeneity were summarized into 6 principal components. RESULTS: We identify two imaging phenotypes of change in intratumor heterogeneity (p < 0.01) demonstrating significant Kaplan-Meier curve separation (p < 0.001). Adding phenotypes to established prognostic factors, functional tumor volume (FTV), MammaPrint, PAM50, and p53 scores in a Cox regression model improves the concordance statistic for predicting RFS from 0.73 to 0.79 (p = 0.002). CONCLUSIONS: These results demonstrate an important step in combining personalized molecular signatures and longitudinal imaging data towards improved prognosis.

Early changes in tumor properties during treatment may tell us whether or not a patient's tumor is responding to treatment. Such changes may be seen on imaging. Here, changes in breast cancer properties are identified on imaging and are used in combination with gene markers to investigate whether response to treatment can be predicted using mathematical models. We demonstrate that tumor properties seen on imaging early on in treatment can help to predict patient outcomes. Our approach may allow clinicians to better inform patients about their prognosis and choose appropriate and effective therapies.

Deep Learning to Simulate Contrast-enhanced Breast MRI of Invasive Breast Cancer.

Background There is increasing interest in noncontrast breast MRI alternatives for tumor visualization to increase the accessibility of breast MRI. Purpose To evaluate the feasibility and accuracy of generating simulated contrast-enhanced T1-weighted breast MRI scans from precontrast MRI sequences in biopsy-proven invasive breast cancer with use of deep learning. Materials and Methods Women with invasive breast cancer and a contrast-enhanced breast MRI examination that was performed for initial evaluation of the extent of disease between January 2015 and December 2019 at a single academic institution were retrospectively identified. A three-dimensional, fully convolutional deep neural network simulated contrast-enhanced T1-weighted breast MRI scans from five precontrast sequences (T1-weighted non-fat-suppressed [FS], T1-weighted FS, T2-weighted FS, apparent diffusion coefficient, and diffusion-weighted imaging). For qualitative assessment, four breast radiologists (with 3-15 years of experience) blinded to whether the method of contrast was real or simulated assessed image quality (excellent, acceptable, good, poor, or unacceptable), presence of tumor enhancement, and maximum index mass size by using 22 pairs of real and simulated contrast-enhanced MRI scans. Quantitative comparison was performed using whole-breast similarity and error metrics and Dice coefficient analysis of enhancing tumor overlap. Results Ninety-six MRI examinations in 96 women (mean age, 52 years ± 12 [SD]) were evaluated. The readers assessed all simulated MRI scans as having the appearance of a real MRI scan with tumor enhancement. Index mass sizes on real and simulated MRI scans demonstrated good to excellent agreement (intraclass correlation coefficient, 0.73-0.86; P < .001) without significant differences (mean differences, -0.8 to 0.8 mm; P = .36-.80). Almost all simulated MRI scans (84 of 88 [95%]) were considered of diagnostic quality (ratings of excellent, acceptable, or good). Quantitative analysis demonstrated strong similarity (structural similarity index, 0.88 ± 0.05), low voxel-wise error (symmetric mean absolute percent error, 3.26%), and Dice coefficient of enhancing tumor overlap of 0.75 ± 0.25. Conclusion It is feasible to generate simulated contrast-enhanced breast MRI scans with use of deep learning. Simulated and real contrast-enhanced MRI scans demonstrated comparable tumor sizes, areas of tumor enhancement, and image quality without significant qualitative or quantitative differences. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Slanetz in this issue. An earlier incorrect version appeared online. This article was corrected on January 17, 2023.

Safety and efficacy of HSP90 inhibitor ganetespib for neoadjuvant treatment of stage II/III breast cancer.

HSP90 inhibitors destabilize oncoproteins associated with cell cycle, angiogenesis, RAS-MAPK activity, histone modification, kinases and growth factors. We evaluated the HSP90-inhibitor ganetespib in combination with standard chemotherapy in patients with high-risk early-stage breast cancer. I-SPY2 is a multicenter, phase II adaptively randomized neoadjuvant (NAC) clinical trial enrolling patients with stage II-III breast cancer with tumors 2.5 cm or larger on the basis of hormone receptors (HR), HER2 and Mammaprint status. Multiple novel investigational agents plus standard chemotherapy are evaluated in parallel for the primary endpoint of pathologic complete response (pCR). Patients with HER2-negative breast cancer were eligible for randomization to ganetespib from October 2014 to October 2015. Of 233 women included in the final analysis, 140 were randomized to the standard NAC control; 93 were randomized to receive 150 mg/m2 ganetespib every 3 weeks with weekly paclitaxel over 12 weeks, followed by AC. Arms were balanced for hormone receptor status (51-52% HR-positive). Ganetespib did not graduate in any of the biomarker signatures studied before reaching maximum enrollment. Final estimated pCR rates were 26% vs. 18% HER2-negative, 38% vs. 22% HR-negative/HER2-negative, and 15% vs. 14% HR-positive/HER2-negative for ganetespib vs control, respectively. The predicted probability of success in phase 3 testing was 47% HER2-negative, 72% HR-negative/HER2-negative, and 19% HR-positive/HER2-negative. Ganetespib added to standard therapy is unlikely to yield substantially higher pCR rates in HER2-negative breast cancer compared to standard NAC, and neither HSP90 pathway nor replicative stress expression markers predicted response. HSP90 inhibitors remain of limited clinical interest in breast cancer, potentially in other clinical settings such as HER2-positive disease or in combination with anti-PD1 neoadjuvant chemotherapy in triple negative breast cancer.Trial registration: www.clinicaltrials.gov/ct2/show/NCT01042379.

Diffusion-Weighted MRI for Predicting Pathologic Complete Response in Neoadjuvant Immunotherapy.

This study tested the hypothesis that a change in the apparent diffusion coefficient (ADC) measured in diffusion-weighted MRI (DWI) is an independent imaging marker, and ADC performs better than functional tumor volume (FTV) for assessing treatment response in patients with locally advanced breast cancer receiving neoadjuvant immunotherapy. A total of 249 patients were randomized to standard neoadjuvant chemotherapy with pembrolizumab (pembro) or without pembrolizumab (control). DCE-MRI and DWI, performed prior to and 3 weeks after the start of treatment, were analyzed. Percent changes of tumor ADC metrics (mean, 5th to 95th percentiles of ADC histogram) and FTV were evaluated for the prediction of pathologic complete response (pCR) using a logistic regression model. The area under the ROC curve (AUC) estimated for the percent change in mean ADC was higher in the pembro cohort (0.73, 95% confidence interval [CI]: 0.52 to 0.93) than in the control cohort (0.63, 95% CI: 0.43 to 0.83). In the control cohort, the percent change of the 95th percentile ADC achieved the highest AUC, 0.69 (95% CI: 0.52 to 0.85). In the pembro cohort, the percent change of the 25th percentile ADC achieved the highest AUC, 0.75 (95% CI: 0.55 to 0.95). AUCs estimated for percent change of FTV were 0.61 (95% CI: 0.39 to 0.83) and 0.66 (95% CI: 0.47 to 0.85) for the pembro and control cohorts, respectively. Tumor ADC may perform better than FTV to predict pCR at an early treatment time-point during neoadjuvant immunotherapy.

Expert tumor annotations and radiomics for locally advanced breast cancer in DCE-MRI for ACRIN 6657/I-SPY1.

Breast cancer is one of the most pervasive forms of cancer and its inherent intra- and inter-tumor heterogeneity contributes towards its poor prognosis. Multiple studies have reported results from either private institutional data or publicly available datasets. However, current public datasets are limited in terms of having consistency in: a) data quality, b) quality of expert annotation of pathology, and c) availability of baseline results from computational algorithms. To address these limitations, here we propose the enhancement of the I-SPY1 data collection, with uniformly curated data, tumor annotations, and quantitative imaging features. Specifically, the proposed dataset includes a) uniformly processed scans that are harmonized to match intensity and spatial characteristics, facilitating immediate use in computational studies, b) computationally-generated and manually-revised expert annotations of tumor regions, as well as c) a comprehensive set of quantitative imaging (also known as radiomic) features corresponding to the tumor regions. This collection describes our contribution towards repeatable, reproducible, and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments.

Effect of Inter-Reader Variability on Diffusion-Weighted MRI Apparent Diffusion Coefficient Measurements and Prediction of Pathologic Complete Response for Breast Cancer.

This study evaluated the inter-reader agreement of tumor apparent diffusion coefficient (ADC) measurements performed on breast diffusion-weighted imaging (DWI) for assessing treatment response in a multi-center clinical trial of neoadjuvant chemotherapy (NAC) for breast cancer. DWIs from 103 breast cancer patients (mean age: 46 ± 11 years) acquired at baseline and after 3 weeks of treatment were evaluated independently by two readers. Three types of tumor regions of interests (ROIs) were delineated: multiple-slice restricted, single-slice restricted and single-slice tumor ROIs. Compared to tumor ROIs, restricted ROIs were limited to low ADC areas of enhancing tumor only. We found excellent agreement (intraclass correlation coefficient [ICC] ranged from 0.94 to 0.98) for mean ADC. Higher ICCs were observed in multiple-slice restricted ROIs (range: 0.97 to 0.98) than in other two ROI types (both in the range of 0.94 to 0.98). Among the three ROI types, the highest area under the receiver operating characteristic curves (AUCs) were observed for mean ADC of multiple-slice restricted ROIs (0.65, 95% confidence interval [CI]: 0.52-0.79 and 0.67, 95% CI: 0.53-0.81 for Reader 1 and Reader 2, respectively). In conclusion, mean ADC values of multiple-slice restricted ROI showed excellent agreement and similar predictive performance for pathologic complete response between the two readers.

Redefining breast cancer subtypes to guide treatment prioritization and maximize response: Predictive biomarkers across 10 cancer therapies.

Using pre-treatment gene expression, protein/phosphoprotein, and clinical data from the I-SPY2 neoadjuvant platform trial (NCT01042379), we create alternative breast cancer subtypes incorporating tumor biology beyond clinical hormone receptor (HR) and human epidermal growth factor receptor-2 (HER2) status to better predict drug responses. We assess the predictive performance of mechanism-of-action biomarkers from ∼990 patients treated with 10 regimens targeting diverse biology. We explore >11 subtyping schemas and identify treatment-subtype pairs maximizing the pathologic complete response (pCR) rate over the population. The best performing schemas incorporate Immune, DNA repair, and HER2/Luminal phenotypes. Subsequent treatment allocation increases the overall pCR rate to 63% from 51% using HR/HER2-based treatment selection. pCR gains from reclassification and improved patient selection are highest in HR+ subsets (>15%). As new treatments are introduced, the subtyping schema determines the minimum response needed to show efficacy. This data platform provides an unprecedented resource and supports the usage of response-based subtypes to guide future treatment prioritization.

Post-Processing Bias Field Inhomogeneity Correction for Assessing Background Parenchymal Enhancement on Breast MRI as a Quantitative Marker of Treatment Response.

Background parenchymal enhancement (BPE) of breast fibroglandular tissue (FGT) in dynamic contrast-enhanced breast magnetic resonance imaging (MRI) has shown an association with response to neoadjuvant chemotherapy (NAC) in patients with breast cancer. Fully automated segmentation of FGT for BPE calculation is a challenge when image artifacts are present. Low spatial frequency intensity nonuniformity due to coil sensitivity variations is known as bias or inhomogeneity and can affect FGT segmentation and subsequent BPE measurement. In this study, we utilized the N4ITK algorithm for bias correction over a restricted bilateral breast volume and compared the contralateral FGT segmentations based on uncorrected and bias-corrected images in three MRI examinations at pre-treatment, early treatment and inter-regimen timepoints during NAC. A retrospective analysis of 2 cohorts was performed: one with 735 patients enrolled in the multi-center I-SPY 2 TRIAL and the sub-cohort of 340 patients meeting a high-quality benchmark for segmentation. Bias correction substantially increased the FGT segmentation quality for 6.3-8.0% of examinations, while it substantially decreased the quality for no examination. Our results showed improvement in segmentation quality and a small but statistically significant increase in the resulting BPE measurement after bias correction at all timepoints in both cohorts. Continuing studies are examining the effects on pCR prediction.

Impact of deformable registration methods for prediction of recurrence free survival response to neoadjuvant chemotherapy in breast cancer: Results from the ISPY 1/ACRIN 6657 trial.

PURPOSE: Image registration plays a vital role in spatially aligning multiple MRI scans for better longitudinal assessment of tumor morphological features. The objective was to evaluate the effect of registration accuracy of six established deformable registration methods(ANTs, DRAMMS, ART, NiftyReg, SSD-FFD, and NMI-FFD) on the predictive value of extracted radiomic features when modeling recurrence-free-survival(RFS) for women after neoadjuvant chemotherapy(NAC) for locally advanced breast cancer. METHODS: 130 women had DCE-MRI scans available from the first two visits in the ISPY1/ACRIN-6657 cohort. We calculated the transformation field from each of the different deformable registration methods, and used it to compute voxel-wise parametric-response-maps(PRM) for established four kinetic features.104-radiomic features were computed from each PRM map to characterize intra-tumor heterogeneity. We evaluated performance for RFS using Cox-regression, C-statistic, and Kaplan-Meier(KM) plots. RESULTS: A baseline model(F1:Age, Race, and Hormone-receptor-status) had a 0.54 C-statistic, and model F2(baseline + functional-tumor-volume at early treatment visit(FTV2)) had 0.63. The F2+ANTs had the highest C-statistic(0.72) with the smallest landmark differences(5.40±4.40mm) as compared to other models. The KM curve for model F2 gave p=0.004 for separation between women above and below the median hazard compared to the model F1(p=0.31). A models augmented with radiomic features, also achieved significant KM curve separation(p<0.001) except the F2+ART model. CONCLUSION: Incorporating image registration in quantifying changes in tumor heterogeneity during NAC can improve prediction of RFS. Radiomic features of PRM maps derived from warping the DCE-MRI kinetic maps using ANTs registration method further improved the early prediction of RFS as compared to other methods.

Impact of Alternate b-Value Combinations and Metrics on the Predictive Performance and Repeatability of Diffusion-Weighted MRI in Breast Cancer Treatment: Results from the ECOG-ACRIN A6698 Trial.

In diffusion-weighted MRI (DW-MRI), choice of b-value influences apparent diffusion coefficient (ADC) values by probing different aspects of the tissue microenvironment. As a secondary analysis of the multicenter ECOG-ACRIN A6698 trial, the purpose of this study was to investigate the impact of alternate b-value combinations on the performance and repeatability of tumor ADC as a predictive marker of breast cancer treatment response. The final analysis included 210 women who underwent standardized 4-b-value DW-MRI (b = 0/100/600/800 s/mm2) at multiple timepoints during neoadjuvant chemotherapy treatment and a subset (n = 71) who underwent test−retest scans. Centralized tumor ADC and perfusion fraction (fp) measures were performed using variable b-value combinations. Prediction of pathologic complete response (pCR) based on the mid-treatment/12-week percent change in each metric was estimated by area under the receiver operating characteristic curve (AUC). Repeatability was estimated by within-subject coefficient of variation (wCV). Results show that two-b-value ADC calculations provided non-inferior predictive value to four-b-value ADC calculations overall (AUCs = 0.60−0.61 versus AUC = 0.60) and for HR+/HER2− cancers where ADC was most predictive (AUCs = 0.75−0.78 versus AUC = 0.76), p < 0.05. Using two b-values (0/600 or 0/800 s/mm2) did not reduce ADC repeatability over the four-b-value calculation (wCVs = 4.9−5.2% versus 5.4%). The alternate metrics ADCfast (b ≤ 100 s/mm2), ADCslow (b ≥ 100 s/mm2), and fp did not improve predictive performance (AUCs = 0.54−0.60, p = 0.08−0.81), and ADCfast and fp demonstrated the lowest repeatability (wCVs = 6.71% and 12.4%, respectively). In conclusion, breast tumor ADC calculated using a simple two-b-value approach can provide comparable predictive value and repeatability to full four-b-value measurements as a marker of treatment response.