Search

Purpose: We compared the metabolic profiles and the association between LDH-A expression and lactate production in two isogenic murine breast cancer cell lines and tumors (67NR and 4T1). These cell lines were derived from a single mammary tumor and have different growth and metabolic phenotypes.Experimental Design: LDH-A expression, lactate concentration, glucose utilization, and oxygen consumption were measured in cells, and the potential relationship between tumor lactate levels [measured by magnetic resonance spectroscopic imaging (MRSI)] and tumor glucose utilization [measured by [18F]2-deoxy-2-fluoro-d-glucose positron emission tomography ([18F]FDG-PET)] was assessed in orthotopic breast tumors derived from these cell lines.Results: We show a substantial difference in LDH-A expression between 67NR and 4T1 cells under normoxia and hypoxia. We also show that small orthotopic 4T1 tumors generate 10-fold more lactate than corresponding 67NR tumors. The high lactate levels in small primary 4T1 tumors are associated with intense pimonidazole staining (a hypoxia indicator). Less-intense hypoxia staining was observed in the larger 67NR tumors and is consistent with the gradual increase and plateau of lactate concentration in enlarging 67NR tumors.Conclusions: Lactate-MRSI has a greater dynamic range than [18F]FDG-PET and may be a more sensitive measure with which to evaluate the aggressive and metastatic potential of primary breast tumors. Clin Cancer Res; 17(19); 6250–61. ©2011 AACR.

PDF file - 790K

PDF file - 1.05MB

PDF file - 442K

PDF file - 326K

PDF file - 192K

ObjectivesTo assess DWI for tumor visibility and breast cancer detection by the addition of different synthetic b-values.MethodsEighty-four consecutive women who underwent a breast-multiparametric-MRI (mpMRI) with enhancing lesions on DCE-MRI (BI-RADS 2–5) were included in this IRB-approved retrospective study from September 2018 to March 2019. Three readers evaluated DW acquired b-800 and synthetic b-1000, b-1200, b-1500, and b-1800 s/mm2images for lesion visibility and preferred b-value based on lesion conspicuity. Image quality (1–3 scores) and breast composition (BI-RADS) were also recorded. Diagnostic parameters for DWI were determined using a 1–5 malignancy score based on qualitative imaging parameters (acquired + preferred synthetic b-values) and ADC values. BI-RADS classification was used for DCE-MRI and quantitative ADC values + BI-RADS were used for mpMRI.ResultsSixty-four malignant (average = 23 mm) and 39 benign (average = 8 mm) lesions were found in 80 women. Although b-800 achieved the best image quality score, synthetic b-values 1200–1500 s/mm2were preferred for lesion conspicuity, especially in dense breast. b-800 and synthetic b-1000/b-1200 s/mm2values allowed the visualization of 84–90% of cancers visible with DCE-MRI performing better than b-1500/b-1800 s/mm2. DWI was more specific (86.3% vs 65.7%,p< 0.001) but less sensitive (62.8% vs 90%,p< 0.001) and accurate (71% vs 80.7%,p= 0.003) than DCE-MRI for breast cancer detection, where mpMRI was the most accurate modality accounting for less false positive cases.ConclusionThe addition of synthetic b-values enhances tumor conspicuity and could potentially improve tumor visualization particularly in dense breast. However, its supportive role for DWI breast cancer detection is still not definite.Key Points•The addition of synthetic b-values (1200–1500 s/mm2) to acquired DWI afforded a better lesion conspicuity without increasing acquisition time and was particularly useful in dense breasts.•Despite the use of synthetic b-values, DWI was less sensitive and accurate than DCE-MRI for breast cancer detection.•A multiparametric MRI modality still remains the best approach having the highest accuracy for breast cancer detection and thus reducing the number of unnecessary biopsies.

Objectives To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. Methods In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. Results Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). Conclusions Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. Key Points • Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.

This multicenter retrospective study compared the performance of radiomics analysis coupled with machine learning (ML) with that of radiologists for the classification of breast tumors. A total of 93 consecutive women (mean age: 49 ± 12 years) with 104 histopathologically verified enhancing lesions (mean size: 22.8 ± 15.1 mm), classified as suspicious on multiparametric breast MRIs were included. Two experienced breast radiologists assessed all of the lesions, assigning a Breast Imaging Reporting and Database System (BI-RADS) suspicion category, providing a diffusion-weighted imaging (DWI) score based on lesion signal intensity, and determining the apparent diffusion coefficient (ADC). Ten predictive models for breast lesion discrimination were generated using radiomic features extracted from the multiparametric MRI. The area under the receiver operating curve (AUC) and the accuracy were compared using McNemar’s test. Multiparametric radiomics with DWI score and BI-RADS (accuracy = 88.5%; AUC = 0.93) and multiparametric radiomics with ADC values and BI-RADS (accuracy= 88.5%; AUC = 0.96) models showed significant improvements in diagnostic accuracy compared to the multiparametric radiomics (DWI + DCE data) model (p = 0.01 and p = 0.02, respectively), but performed similarly compared to the multiparametric assessment by radiologists (accuracy = 85.6%; AUC = 0.03; p = 0.39). In conclusion, radiomics analysis coupled with the ML of multiparametric MRI could assist in breast lesion discrimination, especially for less experienced readers of breast MRIs.

Simple Summary To our knowledge, this is the first study assessing radiomics coupled with machine learning from MRI-derived features to predict PD-L1 expression status in biopsy-proven triple negative breast cancers and comparing the performance of this approach with the performance of qualitative assessment by two radiologists. This pilot study shows that radiomics analysis coupled with machine learning of DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment. This technique could also be used to monitor PD-L1 expression, as it can vary over time and between different regions of the tumor, thus avoiding repeated biopsies. Abstract The purpose of this retrospective study was to assess whether radiomics analysis coupled with machine learning (ML) based on standard-of-care dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict PD-L1 expression status in patients with triple negative breast cancer, and to compare the performance of this approach with radiologist review. Patients with biopsy-proven triple negative breast cancer who underwent pre-treatment breast MRI and whose PD-L1 status was available were included. Following 3D tumor segmentation and extraction of radiomic features, radiomic features with significant differences between PD-L1+ and PD-L1− patients were determined, and a final predictive model to predict PD-L1 status was developed using a coarse decision tree and five-fold cross-validation. Separately, all lesions were qualitatively assessed by two radiologists independently according to the BI-RADS lexicon. Of 62 women (mean age 47, range 31–81), 27 had PD-L1− tumors and 35 had PD-L1+ tumors. The final radiomics model to predict PD-L1 status utilized three MRI parameters, i.e., variance (FO), run length variance (RLM), and large zone low grey level emphasis (LZLGLE), for a sensitivity of 90.7%, specificity of 85.1%, and diagnostic accuracy of 88.2%. There were no significant associations between qualitative assessed DCE-MRI imaging features and PD-L1 status. Thus, radiomics analysis coupled with ML based on standard-of-care DCE-MRI is a promising approach to derive prognostic and predictive information and to select patients who could benefit from anti-PD-1/PD-L1 treatment.

BACKGROUND: Median survival from DIPG is less than one year. In a phase 1 dose escalation study (clinicaltrials.gov NCT01502917) 124I-omburtamab targeting B7-H3 was administered intratumorally using CED. METHODS: CED was performed between 4-14 weeks post radiation therapy. Using a 3 + 3 design, 124I-omburtamab was escalated from 0.25-10.0 mCi and infusion volumes (Vi) from 250-10,000 µl with serial 124I PET/CT performed up to ~1 week post-administration. Toxicities were assessed for 30 days. Dose escalation safety was evaluated. Survival was calculated using Kaplan-Meier statistics. RESULTS: 46 children were treated and evaluable for toxicity and survival;4 patients received partial doses and were evaluable for toxicity only. Three patients experienced dose limiting toxicities. Eleven patients had transient treatment related grade 3 toxicities with no grade 4 or 5 toxicities. Grade 3 nervous system toxicities included: muscular weakness(n=8), dysarthria(n=4), ataxia(n=3), dysphagia(n=3), and gait disturbance(n=1). Lesion absorbed doses ranged from 1,000-1,500cGy/mCi, with lesion-to-whole body radiation absorbed-dose ratios of ~900. A dose of 8mCi and infusion volume of 8,000 µl is safe and may provide a distribution volume up to 20cm3. Median survival was 15.3 months (n =46, 95% CI 12.7, 17.3). Survival rate estimates (95% CI) at 1, 2, 3 and 5 years were 0.67 (0.55;0.82); 0.18 (0.09;0.35); 0.10 (0.04;0.26); and 0.05 (0.01;0.20). Four patients survived >3 years; two remain alive (61+ and 106+ months);two have died (44 and 53 month) with distant CNS disease and one with extra-CNS metastasis. CONCLUSION: Administration of escalating doses and volumes of 124I-omburtamab via CED was a viable option for this patient subgroup. The median overall survival was increased 3-4 months compared to historical controls. Anecdotal long-term survival if validated with a planned phase 2 trial would support the concept of whole neuroaxis treatment in combination with CED in a subset of DIPG patients.

To develop a multiparametric [18F]FDG positron emission tomography/magnetic resonance imaging (PET/MRI) model for breast cancer diagnosis incorporating imaging biomarkers of breast tumors and contralateral healthy breast tissue. In this prospective study and retrospective data analysis, 141 patients (mean 57 years) with an imaging abnormality detected on mammography and/or ultrasound (BI-RADS 4/5) underwent combined multiparametric [18F]FDG PET/MRI with PET/computed tomography and multiparametric MRI of the breast at 3 T. Images were evaluated and the following were recorded: for the tumor, BI-RADS descriptors on dynamic contrast-enhanced (DCE)-MRI, mean apparent diffusion co-efficient (ADCmean) on diffusion-weighted imaging (DWI), and maximum standard uptake value (SUVmax) on [18F]FDG-PET; and for the contralateral healthy breast, background parenchymal enhancement (BPE) and amount of fibroglandular tissue (FGT) on DCE-MRI, ADCmean on DWI, and SUVmax. Histopathology served as standard of reference. Uni-, bi-, and multivariate logistic regression analyses were performed to assess the relationships between malignancy and imaging features. Predictive discrimination of benign and malignant breast lesions was examined using area under the receiver operating characteristic curve (AUC). There were 100 malignant and 41 benign lesions (size: median 1.9, range 0.5–10 cm). The multivariate regression model incorporating significant univariate predictors identified tumor enhancement kinetics (P = 0.0003), tumor ADCmean (P

Our study aimed to evaluate if breast‐conserving surgery and adjuvant treatment could affect the morphological features of axillary and intramammary lymph nodes on magnetic resonance imaging (MRI) in patients with invasive breast cancer and clinically negative axilla. In this single‐center study, we retrospectively evaluated 50 patients who had (a) breast‐conserving surgery, (b) clinically negative axilla, (c) preoperative MRI within 3 months before surgery, and (d) postoperative MRI within 12 months after surgery. Axillary and intramammary lymph nodes on postoperative MRI were identified and then compared with preoperative MRI by two breast radiologists with regards to the following: enlargement, cortical thickening, presence of fatty hilum, irregularity, heterogeneity, matting, and axillary lymph node asymmetry. Three hundred and two axillary and eight intramammary lymph nodes were evaluated. Enlargement and cortical thickening were seen in 5/50 (10%) patients in three axillary and two intramammary lymph nodes. None of the lymph nodes on postoperative MRI demonstrated occurrence of lack of fatty hilum, irregularity, heterogeneity, matting or axillary lymph node asymmetry. No evidence of recurrence was observed on 2‐year follow‐up. Lymph node enlargement and cortical thickening may be observed in a few patients in the postoperative period. Nevertheless, in patients with clinically negative axilla, these changes in morphology are often related to treatment rather than malignancy and favor short‐term follow‐up as an alternative to lymph node biopsy.

Purpose To compare annotation segmentation approaches and to assess the value of radiomics analysis applied to diffusion-weighted imaging (DWI) for evaluation of breast cancer receptor status and molecular subtyping. Procedures In this IRB-approved HIPAA-compliant retrospective study, 91 patients with treatment-naïve breast malignancies proven by image-guided breast biopsy, (luminal A, n = 49; luminal B, n = 8; human epidermal growth factor receptor 2 [HER2]-enriched, n = 11; triple negative [TN], n = 23) underwent multiparametric magnetic resonance imaging (MRI) of the breast at 3 T with dynamic contrast-enhanced MRI, T2-weighted and DW imaging. Lesions were manually segmented on high b-value DW images and segmentation ROIS were propagated to apparent diffusion coefficient (ADC) maps. In addition in a subgroup (n = 79) where lesions were discernable on ADC maps alone, these were also directly segmented there. To derive radiomics signatures, the following features were extracted and analyzed: first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient, autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation, and mutual information coefficients were used for feature selection. Linear discriminant analysis followed by k-nearest neighbor classification with leave-one-out cross-validation was applied for pairwise differentiation of receptor status and molecular subtyping. Histopathologic results were considered the gold standard. Results For lesion that were segmented on DWI and segmentation ROIs were propagated to ADC maps the following classification accuracies > 90% were obtained: luminal B vs. HER2-enriched, 94.7 % (based on COM features); luminal B vs. others, 92.3 % (COM, HIS); and HER2-enriched vs. others, 90.1 % (RLM, COM). For lesions that were segmented directly on ADC maps, better results were achieved yielding the following classification accuracies: luminal B vs. HER2-enriched, 100 % (COM, WAV); luminal A vs. luminal B, 91.5 % (COM, WAV); and luminal B vs. others, 91.1 % (WAV, ARM, COM). Conclusions Radiomic signatures from DWI with ADC mapping allows evaluation of breast cancer receptor status and molecular subtyping with high diagnostic accuracy. Better classification accuracies were obtained when breast tumor segmentations could be performed on ADC maps.

The purpose of this multicenter retrospective study was to evaluate radiomics analysis coupled with machine learning (ML) of dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI) radiomics models separately and combined as multiparametric MRI for improved breast cancer detection. Consecutive patients (Memorial Sloan Kettering Cancer Center, January 2018–March 2020; Medical University Vienna, from January 2011–August 2014) with a suspicious enhancing breast tumor on breast MRI categorized as BI-RADS 4 and who subsequently underwent image-guided biopsy were included. In 93 patients (mean age: 49 years ± 12 years; 100% women), there were 104 lesions (mean size: 22.8 mm; range: 7–99 mm), 46 malignant and 58 benign. Radiomics features were calculated. Subsequently, the five most significant features were fitted into multivariable modeling to produce a robust ML model for discriminating between benign and malignant lesions. A medium Gaussian support vector machine (SVM) model with five-fold cross validation was developed for each modality. A model based on DWI-extracted features achieved an AUC of 0.79 (95% CI: 0.70–0.88), whereas a model based on DCE-extracted features yielded an AUC of 0.83 (95% CI: 0.75–0.91). A multiparametric radiomics model combining DCE- and DWI-extracted features showed the best AUC (0.85; 95% CI: 0.77–0.92) and diagnostic accuracy (81.7%; 95% CI: 73.0–88.6). In conclusion, radiomics analysis coupled with ML of multiparametric MRI allows an improved evaluation of suspicious enhancing breast tumors recommended for biopsy on clinical breast MRI, facilitating accurate breast cancer diagnosis while reducing unnecessary benign breast biopsies.

Diffusion-weighted imaging is a non-invasive functional imaging modality for breast tumor characterization through apparent diffusion coefficients. Yet, it has so far been unable to intuitively inform on tissue microstructure. In this IRB-approved prospective study, we applied novel multidimensional diffusion (MDD) encoding across 16 patients with suspected breast cancer to evaluate its potential for tissue characterization in the clinical setting. Data acquired via custom MDD sequences was processed using an algorithm estimating non-parametric diffusion tensor distributions. The statistical descriptors of these distributions allow us to quantify tissue composition in terms of metrics informing on cell densities, shapes, and orientations. Additionally, signal fractions from specific cell types, such as elongated cells (bin1), isotropic cells (bin2), and free water (bin3), were teased apart. Histogram analysis in cancers and healthy breast tissue showed that cancers exhibited lower mean values of “size” (1.43 ± 0.54 × 10−3 mm2/s) and higher mean values of “shape” (0.47 ± 0.15) corresponding to bin1, while FGT (fibroglandular breast tissue) presented higher mean values of “size” (2.33 ± 0.22 × 10−3 mm2/s) and lower mean values of “shape” (0.27 ± 0.11) corresponding to bin3 (p &lt, 0.001). Invasive carcinomas showed significant differences in mean signal fractions from bin1 (0.64 ± 0.13 vs. 0.4 ± 0.25) and bin3 (0.18 ± 0.08 vs. 0.42 ± 0.21) compared to ductal carcinomas in situ (DCIS) and invasive carcinomas with associated DCIS (p = 0.03). MDD enabled qualitative and quantitative evaluation of the composition of breast cancers and healthy glands.

Altered metabolism including lipids is an emerging hallmark of breast cancer. The purpose of this study was to investigate if breast cancers exhibit different magnetic resonance spectroscopy (MRS)-based lipid composition than normal fibroglandular tissue (FGT). MRS spectra, using the stimulated echo acquisition mode sequence, were collected with a 3T scanner from patients with suspicious lesions and contralateral normal tissue. Fat peaks at 1.3 + 1.6 ppm (L13 + L16), 2.1 + 2.3 ppm (L21 + L23), 2.8 ppm (L28), 4.1 + 4.3 ppm (L41 + L43), and 5.2 + 5.3 ppm (L52 + L53) were quantified using LCModel software. The saturation index (SI), number of double bods (NBD), mono and polyunsaturated fatty acids (MUFA and PUFA), and mean chain length (MCL) were also computed. Results showed that mean concentrations of all lipid metabolites and PUFA were significantly lower in tumors compared with that of normal FGT (p ≤ 0.002 and 0.04, respectively). The measure best separating normal and tumor tissues after adjusting with multivariable analysis was L21 + L23, which yielded an area under the curve of 0.87 (95% CI: 0.75–0.98). Similar results were obtained between HER2 positive versus HER2 negative tumors. Hence, MRS-based lipid measurements may serve as independent variables in a multivariate approach to increase the specificity of breast cancer characterization.

The purpose of this study was to investigate whether ultra-high-field dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast at 7T using quantitative pharmacokinetic (PK) analysis can differentiate between benign and malignant breast tumors for improved breast cancer diagnosis and to predict molecular subtypes, histologic grade, and proliferation rate in breast cancer. In this prospective study, 37 patients with 43 lesions suspicious on mammography or ultrasound underwent bilateral DCE-MRI of the breast at 7T. PK parameters (KTrans, kep, Ve) were evaluated with two region of interest (ROI) approaches (2D whole-tumor ROI or 2D 10 mm standardized ROI) manually drawn by two readers (senior reader, R1, and R2) independently. Histopathology served as the reference standard. PK parameters differentiated benign and malignant lesions (n = 16, 27, respectively) with good accuracy (AUCs = 0.655&ndash, 0.762). The addition of quantitative PK analysis to subjective BI-RADS classification improved breast cancer detection from 88.4% to 97.7% for R1 and 86.04% to 97.67% for R2. Different ROI approaches did not influence diagnostic accuracy for both readers. Except for KTrans for whole-tumor ROI for R2, none of the PK parameters were valuable to predict molecular subtypes, histologic grade, or proliferation rate in breast cancer. In conclusion, PK-enhanced BI-RADS is promising for the noninvasive differentiation of benign and malignant breast tumors.

We evaluated the performance of radiomics and artificial intelligence (AI) from multiparametric magnetic resonance imaging (MRI) for the assessment of breast cancer molecular subtypes. Ninety-one breast cancer patients who underwent 3T dynamic contrast-enhanced (DCE) MRI and diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) mapping were included retrospectively. Radiomic features were extracted from manually drawn regions of interest (n = 704 features per lesion) on initial DCE-MRI and ADC maps. The ten best features for subtype separation were selected using probability of error and average correlation coefficients. For pairwise comparisons with &gt, 20 patients in each group, a multi-layer perceptron feed-forward artificial neural network (MLP-ANN) was used (70% of cases for training, 30%, for validation, five times each). For all other separations, linear discriminant analysis (LDA) and leave-one-out cross-validation were applied. Histopathology served as the reference standard. MLP-ANN yielded an overall median area under the receiver-operating-characteristic curve (AUC) of 0.86 (0.77&ndash, 0.92) for the separation of triple negative (TN) from other cancers. The separation of luminal A and TN cancers yielded an overall median AUC of 0.8 (0.75&ndash, 0.83). Radiomics and AI from multiparametric MRI may aid in the non-invasive differentiation of TN and luminal A breast cancers from other subtypes.

This chapter offers a comprehensive summary of applications of advanced diffusion encoding methods in MRI within a narrowly defined area of in vivo human measurements with imaging read-out and voxel-by-voxel data analysis. The list of methods comprises tensor-valued encoding to investigate cell densities, shapes, and orientations in heterogeneous tissues, time/frequency-dependent encoding for estimating structural length scales, adjustable velocity-encoding to monitor flow in the microcapillary network, double encoding with varying mixing times to assess diffusional exchange between distinct tissue microenvironments and across cell membranes, and relaxation-diffusion correlation to resolve and separately characterize tissue microenvironments in terms of their local chemical composition and microstructure. The shown examples include proof-of-concept measurements on healthy volunteers, pilot investigations of pathologies, and clinical research involving 10-100 subjects. Studied organs include brain, breast, prostate, liver, kidney, placenta, muscle, and peripheral nerve, with examples of pathologies from tumors, schizophrenia, multiple sclerosis, stroke, neurocysticercosis, pre-eclampsia, and chronic exertional compartment syndrome. (Less)

Background The MRI Breast Imaging-Reporting and Data System (BI-RADS) lexicon recommends that a breast MRI protocol contain T2 -weighted and dynamic contrast-enhanced (DCE) MRI sequences. The addition of diffusion-weighted imaging (DWI) significantly improves diagnostic accuracy. This study aims to clarify which descriptors from DCE-MRI, DWI, and T2 -weighted imaging are most strongly associated with a breast cancer diagnosis. Purpose/hypothesis To develop a multiparametric MRI (mpMRI) model for breast cancer diagnosis incorporating American College of Radiology (ACR) BI-RADS recommended descriptors for breast MRI with DCE, T2 -weighted imaging, and DWI with apparent diffusion coefficient (ADC) mapping. Study type Retrospective. Subjects In all, 188 patients (mean 51.6 years) with 210 breast tumors (136 malignant and 74 benign) who underwent mpMRI from December 2010 to September 2014. Field strength/sequence IR inversion recovert DCE-MRI dynamic contrast-enhanced magnetic resonance imaging VIBE Volume-Interpolated-Breathhold-Examination FLASH turbo fast-low-angle-shot TWIST Time-resolved angiography with stochastic Trajectories. Assessment Two radiologists in consensus and another radiologist independently evaluated the mpMRI data. Characteristics for mass (n = 182) and nonmass (n = 28) lesions were recorded on DCE and T2 -weighted imaging according to BI-RADS, as well as DWI descriptors. Two separate models were analyzed, using DCE-MRI BI-RADS descriptors, T2 -weighted imagines, and ADCmean as either a continuous or binary form using a previously published ADC cutoff value of ≤1.25 × 10-3 mm2 /sec for differentiation between benign and malignant lesions. Histopathology was the standard of reference. Statistical tests χ2 test, Fisher's exact test, Kruskal-Wallis test, Pearson correlation coefficient, multivariate logistic regression analysis, Hosmer-Lemeshow test of goodness-of-fit, receiver operating characteristics analysis. Results In Model 1, ADCmean (P = 0.0031), mass margins with DCE (P = 0.0016), and delayed enhancement with DCE (P = 0.0016) were significantly and independently associated with breast cancer diagnosis; Model 2 identified ADCmean (P = 0.0031), mass margins with DCE (P = 0.0012), initial enhancement (P = 0.0422), and delayed enhancement with DCE (P = 0.0065) to be significantly independently associated with breast cancer diagnosis. T2 -weighted imaging variables were not included in the final models. DATA CONCLUSION: mpMRI with DCE-MRI and DWI with ADC mapping enables accurate breast cancer diagnosis. A model using quantitative and qualitative descriptors from DCE-MRI and DWI identifies breast cancer with a high diagnostic accuracy. T2 -weighted imaging does not significantly contribute to breast cancer diagnosis. Level of evidence 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:864-874.

Magnetic resonance imaging (MRI) is a well-established method in breast imaging, with manifold clinical applications, including the non-invasive differentiation between benign and malignant breast lesions, preoperative staging, detection of scar versus recurrence, implant assessment, and the evaluation of high-risk patients. At present, dynamic contrast-enhanced MRI is the most sensitive imaging technique for breast cancer diagnosis, and provides excellent morphological and to some extent also functional information. To compensate for the limited functional information, and to increase the specificity of MRI while preserving its sensitivity, additional functional parameters such as diffusion-weighted imaging and apparent diffusion coefficient mapping, and MR spectroscopic imaging have been investigated and implemented into the clinical routine. Several additional MRI parameters to capture breast cancer biology are still under investigation. MRI at high and ultra-high field strength and advances in hard- and software may also further improve this imaging technique. This article will review the current clinical role of breast MRI, including multiparametric MRI and abbreviated protocols, and provide an outlook on the future of this technique. In addition, the predictive and prognostic value of MRI as well as the evolving field of radiogenomics will be discussed.

Purpose To measure the apparent diffusion coefficient (ADC) values in estrogen receptor-positive (ER+) and axillary lymph node-negative (LN–) invasive breast cancer and investigate the correlation of ADC with Oncotype Dx test recurrence scores (ODxRS). Materials and Methods This was a Health Insurance Portability and Accountability Act (HIPAA)-compliant single-site retrospective study. Patients underwent preoperative 3.0T MRI scans with additional diffusion-weighted imaging sequential scans (b = 0, 600 and b = 0, 1000 s/mm2) from January 2011 to 2013. The study population included 31 ER+/LN– invasive breast cancers, which underwent ODxRS genomic testing. ADC600 and ADC1000 parametric maps were generated, and ADC values were calculated from a user-drawn region of interest. ODxRS predicts 10-year recurrence risk in individual patients: low (RS 30). All breast lesions, including subgroups of invasive ductal carcinoma (IDC) lesions and mass-only lesions were dichotomized by RS scores, low-risk versus intermediate/high-risk, and statistical analysis was performed using Mann–Whitney's test (statistical significance at P < 0.05) and receiver operating characteristic (ROC) curves. Multivariate analysis was also performed. Results Invasive breast cancers, when scored as low-risk by ODxRS, had significantly higher ADC values compared with intermediate/high-risk lesions for both ADC600 (P = 0.007) and ADC1000 (P = 0.008) mean values. This was true both when analyzing only mass-lesions (P = 0.03 and 0.01) or only IDCs (P = 0.001 and 0.009). Conclusion Preliminary findings suggest that lesion ADC values correlate with recurrence risk likelihood stratified using ODxRS. Hence, ADC is a potential surrogate biomarker for tumor aggressiveness. Level of Evidence: 3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2017.

Objective. To investigate if histogram analysis and visually assessed heterogeneity of diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) mapping can predict molecular subtypes of invasive breast cancers. Materials and Methods. In this retrospective study, 91 patients with invasive breast carcinoma who underwent preoperative magnetic resonance imaging (MRI) with DWI at our institution were included. Two radiologists delineated a 2-D region of interest (ROI) on ADC maps in consensus. Tumors were also independently classified into low and high heterogeneity based on visual assessment of DWI. First-order statistics extracted through histogram analysis within the ROI of the ADC maps (mean, 10th percentile, 50th percentile, 90th percentile, standard deviation, kurtosis, and skewness) and visually assessed heterogeneity were evaluated for associations with tumor receptor status (ER, PR, and HER2 status) as well as molecular subtype. Results. HER2-positive lesions demonstrated significantly higher mean (p=0.034), Perc50 (p=0.046), and Perc90 (p=0.040), with AUCs of 0.605, 0.592, and 0.652, respectively, than HER2-negative lesions. No significant differences were found in the histogram values for ER and PR statuses. Neither quantitative histogram analysis based on ADC maps nor qualitative visual heterogeneity assessment of DWI images was able to significantly differentiate between molecular subtypes, i.e., luminal A versus all other subtypes (luminal B, HER2-enriched, and triple negative) combined, luminal A and B combined versus HER2-enriched and triple negative combined, and triple negative versus all other types combined. Conclusion. Histogram analysis and visual heterogeneity assessment cannot be used to differentiate molecular subtypes of invasive breast cancer.

BACKGROUND Ivosidenib (AG-120, IVO) is a first-in-class oral inhibitor of mutant isocitrate dehydrogenase 1 (mIDH1), and vorasidenib (AG-881, VOR) is an oral, potent, brain-penetrant inhibitor of mIDH1/2. Both have been evaluated in glioma patients in ongoing phase 1 studies. In orthotopic glioma models, IVO and VOR reduced 2-hydroxyglutarate (2-HG) levels by 85% and 98%, respectively, despite different brain-to-plasma ratios (< 0.04 vs 1.33). METHODS Patients with recurrent, nonenhancing, WHO-2016 grade 2/3, mIDH1-R132H oligodendroglioma or astrocytoma undergoing craniotomy were randomized 2:2:1 to IVO 500mg QD, VOR 50mg QD, or no treatment (cohort 1), or 1:1 to IVO 250mg BID or VOR 10mg QD (cohort 2), for 4 weeks preoperatively. Postoperatively, patients continued receiving IVO or VOR (control patients were randomized 1:1 to IVO or VOR). Tumors were assessed for mIDH1 status, cellularity, and 2-HG and drug concentrations. Treated subjects were compared with controls and mIDH1/wild-type banked reference samples. Primary endpoint: tumor 2-HG concentration following IVO or VOR. RESULTS As of March 1, 2019, 27 patients (18 men; 25/2 grade 2/3) were randomized preoperatively in cohort 1 (IVO 10, VOR 12, untreated 5): 27 received drug (IVO 13, VOR 14); 1 discontinued VOR postoperatively due to disease progression. Of 26 tumors analyzed, 22 were evaluable. Mean brain-to-plasma ratios: 0.13 IVO, 1.59 VOR. Relative to untreated samples, IVO and VOR reduced tumor 2-HG by 92.0% (95% CI 73.2, 97.4) and 92.5% (95% CI 78.1, 97.7), respectively. Common (≥ 4 patients) TEAEs (all cohort 1 patients, all grades): diarrhea (37.0%), constipation, hypocalcemia, and nausea (each 18.5%), anemia, hyperglycemia, pruritus, headache, and fatigue (each 14.8%). Cohort 2 has completed accrual, with analyses ongoing. CONCLUSIONS In cohort 1 of this phase 1 perioperative study, IVO and VOR demonstrated brain penetrance and lowered 2-HG compared with controls. Updated data from both cohorts will be presented.

Background To evaluate the diagnostic performance of radiomic signatures extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) for the assessment of breast cancer receptor status and molecular subtypes. Methods One hundred and forty-three patients with biopsy-proven breast cancer who underwent CE-MRI at 3 T were included in this IRB-approved HIPAA-compliant retrospective study. The training dataset comprised 91 patients (luminal A, n = 49; luminal B, n = 8; HER2-enriched, n = 11; triple negative, n = 23), while the validation dataset comprised 52 patients from a second institution (luminal A, n = 17; luminal B, n = 17; triple negative, n = 18). Radiomic analysis of manually segmented tumors included calculation of features derived from the first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient (GRA), autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry (GEO). Fisher, probability of error and average correlation (POE + ACC), and mutual information coefficients were used for feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise radiomic-based separation of receptor status and molecular subtypes. Histopathology served as the standard of reference. Results In the training dataset, radiomic signatures yielded the following accuracies > 80%: luminal B vs. luminal A, 84.2% (mainly based on COM features); luminal B vs. triple negative, 83.9% (mainly based on GEO features); luminal B vs. all others, 89% (mainly based on COM features); and HER2-enriched vs. all others, 81.3% (mainly based on COM features). Radiomic signatures were successfully validated in the separate validation dataset for luminal A vs. luminal B (79.4%) and luminal B vs. triple negative (77.1%). Conclusions In this preliminary study, radiomic signatures with CE-MRI enable the assessment of breast cancer receptor status and molecular subtypes with high diagnostic accuracy. These results need to be confirmed in future larger studies.

Breast cancer is a heterogeneous disease with different prognoses and responses to systemic treatment depending on its molecular characteristics, which makes it imperative to develop new biomarkers for an individualized diagnosis and personalized oncological treatment. Ex vivo high-resolution magic angle spinning proton magnetic resonance spectroscopy (HRMAS 1H MRS) is the most common technique for metabolic quantification in human surgical and biopsy tissue specimens. To perform a review of the current available literature on the clinical applications of HRMAS 1H MRS metabolic analysis in tissue samples of breast cancer patients. This systematic scoping review included original research papers published in the English language in peer-reviewed journals. Study selection was performed independently by two reviewers and preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines were followed. The literature search returned 159 studies and 26 papers were included as part of this systematic review. There was considerable variation regarding tissue type, aims, and statistical analysis methods across the different studies. To facilitate the interpretation of the results, the included studies were grouped according to their aims or main outcomes into: feasibility and tumor diagnosis (n = 6); tumor heterogeneity (n = 2); correlation with proteomics/transcriptomics (n = 3); correlation with prognostic factors (n = 11); and response evaluation to NAC (n = 4). There is a lot of potential in including metabolic information of breast cancer tissue obtained with HRMAS 1H MRS. To date, studies show that metabolic concentrations quantified by this technique can be related to the diagnosis, prognosis, and treatment response in breast cancer patients.

Background Available data proving the value of DWI for breast cancer diagnosis is mainly for enhancing masses; DWI may be less sensitive and specific in non-mass enhancement (NME) lesions. The objective of this study was to assess the diagnostic accuracy of DWI using different ROI measurement approaches and ADC metrics in breast lesions presenting as NME lesions on dynamic contrast-enhanced (DCE) MRI. Methods In this retrospective study, 95 patients who underwent multiparametric MRI with DCE and DWI from September 2007 to July 2013 and who were diagnosed with a suspicious NME (BI-RADS 4/5) were included. Twenty-nine patients were excluded for lesion non-visibility on DWI (n = 24: 12 benign and 12 malignant) and poor DWI quality (n = 5: 1 benign and 4 malignant). Two readers independently assessed DWI and DCE-MRI findings in two separate randomized readings using different ADC metrics and ROI approaches. NME lesions were classified as either benign (> 1.3 × 10−3 mm2/s) or malignant (≤ 1.3 × 10−3 mm2/s). Histopathology was the standard of reference. ROC curves were plotted, and AUCs were determined. Concordance correlation coefficient (CCC) was measured. Results There were 39 malignant (59%) and 27 benign (41%) lesions in 66 (65 women, 1 man) patients (mean age, 51.8 years). The mean ADC value of the darkest part of the tumor (Dptu) achieved the highest diagnostic accuracy, with AUCs of up to 0.71. Inter-reader agreement was highest with Dptu ADC max (CCC 0.42) and lowest with the point tumor (Ptu) ADC min (CCC = − 0.01). Intra-reader agreement was highest with Wtu ADC mean (CCC = 0.44 for reader 1, 0.41 for reader 2), but this was not associated with the highest diagnostic accuracy. Conclusions Diagnostic accuracy of DWI with ADC mapping is limited in NME lesions. Thirty-one percent of lesions presenting as NME on DCE-MRI could not be evaluated with DWI, and therefore, DCE-MRI remains indispensable. Best results were achieved using Dptu 2D ROI measurement and ADC mean.

Background Diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) mapping is one of the most useful additional MRI parameters to improve diagnostic accuracy and is now often used in a multiparameric imaging setting for breast tumor detection and characterization. Purpose To evaluate whether different ADC metrics can also be used for prediction of receptor status, proliferation rate, and molecular subtype in invasive breast cancer. Study type Retrospective. Subjects In all, 107 patients with invasive breast cancer met the inclusion criteria (mean age 57 years, range 32-87) and underwent multiparametric breast MRI. Field strength/sequence 3 T, readout-segmented echo planar imaging (rsEPI) with IR fat suppression, dynamic contrast-enhanced (DCE) T1 -weighted imaging, T2 -weighted turbo-spin echo (TSE) with fatsat. Assessment Two readers independently drew a region of interest on ADC maps on the whole tumor (WTu), and on its darkest part (DpTu). Minimum, mean, and maximum ADC values of both WTu and DpTu were compared for receptor status, proliferation rate, and molecular subtypes. Statistical tests Wilcoxon rank sum, Mann-Whitney U-tests for associations between radiologic features and histopathology; histogram and q-q plots, Shapiro-Wilk's test to assess normality, concordance correlation coefficient for precision and accuracy; receiver operating characteristics curve analysis. Results Estrogen receptor (ER) and progesterone receptor (PR) status had significantly different ADC values for both readers. Maximum WTu (P = 0.0004 and 0.0005) and mean WTu (P = 0.0101 and 0.0136) were significantly lower for ER-positive tumors, while PR-positive tumors had significantly lower maximum WTu values (P = 0.0089 and 0.0047). Maximum WTu ADC was the only metric that was significantly different for molecular subtypes for both readers (P = 0.0100 and 0.0132) and enabled differentiation of luminal tumors from nonluminal (P = 0.0068 and 0.0069) with an area under the curve of 0.685 for both readers. Data conclusion Maximum WTu ADC values may be used to differentiate luminal from other molecular subtypes of breast cancer. Level of evidence 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:836-846.

Background Breast magnetic resonance spectroscopy (1 H-MRS) has been largely based on choline metabolites; however, other relevant metabolites can be detected and monitored. Purpose To investigate whether lipid metabolite concentrations detected with 1 H-MRS can be used for the noninvasive differentiation of benign and malignant breast tumors, differentiation among molecular breast cancer subtypes, and prediction of long-term survival outcomes. Study type Retrospective. Subjects In all, 168 women, aged ≥18 years. Field strength/sequence Dynamic contrast-enhanced MRI at 1.5 T: sagittal 3D spoiled gradient recalled sequence with fat saturation, flip angle = 10°, repetition time / echo time (TR/TE) = 7.4/4.2 msec, slice thickness = 3.0 mm, field of view (FOV) = 20 cm, and matrix size = 256 × 192. 1 H-MRS: PRESS with TR/TE = 2000/135 msec, water suppression, and 128 scan averages, in addition to 16 reference scans without water suppression. Assessment MRS quantitative analysis of lipid resonances using the LCModel was performed. Histopathology was the reference standard. Statistical tests Categorical data were described using absolute numbers and percentages. For metric data, means (plus 95% confidence interval [CI]) and standard deviations as well as median, minimum, and maximum were calculated. Due to skewed data, the latter were more adequate; unpaired Mann-Whitney U-tests were performed to compare groups without and with Bonferroni correction. ROC analyses were also performed. Results There were 111 malignant and 57 benign lesions. Mean voxel size was 4.4 ± 4.6 cm3 . Six lipid metabolite peaks were quantified: L09, L13 + L16, L21 + L23, L28, L41 + L43, and L52 + L53. Malignant lesions showed lower L09, L21 + L23, and L52 + L53 than benign lesions (P = 0.022, 0.027, and 0.0006). Similar results were observed for Luminal A or Luminal A/B vs. other molecular subtypes. At follow-up, patients were split into two groups based on median values for the six peaks; recurrence-free survival was significantly different between groups for L09, L21 + L23, and L28 (P = 0.0173, 0.0024, and 0.0045). Data conclusion Quantitative in vivo 1 H-MRS assessment of lipid metabolism may provide an additional noninvasive imaging biomarker to guide therapeutic decisions in breast cancer. Level of evidence 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:239-249.

Purpose To develop a multiparametric [18F]FDG positron emission tomography/magnetic resonance imaging (PET/MRI) model for breast cancer diagnosis incorporating imaging biomarkers of breast tumors and contralateral healthy breast tissue. Methods In this prospective study and retrospective data analysis, 141 patients (mean 57 years) with an imaging abnormality detected on mammography and/or ultrasound (BI-RADS 4/5) underwent combined multiparametric [18F]FDG PET/MRI with PET/computed tomography and multiparametric MRI of the breast at 3 T. Images were evaluated and the following were recorded: for the tumor, BI-RADS descriptors on dynamic contrast-enhanced (DCE)-MRI, mean apparent diffusion co-efficient (ADCmean) on diffusion-weighted imaging (DWI), and maximum standard uptake value (SUVmax) on [18F]FDG-PET; and for the contralateral healthy breast, background parenchymal enhancement (BPE) and amount of fibroglandular tissue (FGT) on DCE-MRI, ADCmean on DWI, and SUVmax. Histopathology served as standard of reference. Uni-, bi-, and multivariate logistic regression analyses were performed to assess the relationships between malignancy and imaging features. Predictive discrimination of benign and malignant breast lesions was examined using area under the receiver operating characteristic curve (AUC). Results There were 100 malignant and 41 benign lesions (size: median 1.9, range 0.5–10 cm). The multivariate regression model incorporating significant univariate predictors identified tumor enhancement kinetics (P = 0.0003), tumor ADCmean (P

2010 Background: The prognosis of diffuse intrinsic pontine glioma (DIPG) is dire with a median overall survival less than one-year. 124I-omburtamab is a radiolabeled monoclonal antibody that targets B7-H3 epitope. We evaluated the safety of administering escalating doses and volumes of 124I-omburtamab via convection-enhanced delivery (CED) in children with DIPG. Methods: MSKCC 11-011 trial is a standard 3+3 phase 1, open-label, dose escalation study in patients with non-progressive DIPG. CED of 124I-omburtamab was performed between 4-14 weeks post-external radiation therapy. Nine dose levels of a single injection of 124I-omburtamab (Y-mAbs Therapeutics, USA) (range 0.25 to 8.0 mCi; and volume of infusion (Vi) from 250 to 8,000 µl) have been evaluated so far. Patients were assessed weekly for 30 days. Results: 46 children were evaluable for primary and secondary endpoints. The median age at enrolment was 6.5 years (range 2-17). Two patients have experienced AEs CTCAE grade 3 that were categorized as dose limiting toxicities (DLTs), which led to inclusion of three more patients at both the 4 and 6 mCi dose levels. Eight patients have reported transient AEs of grade 3 considered related to 124I-omburtamab. The acute grade 3 AEs were generally indicative of nervous system effects due to volume intolerance or radiation injury, and included hemiparesis (n = 3), dysarthria (n = 3), ataxia (n = 3), dysphagia (n = 2), muscular weakness (n = 2) and gait disturbance (n = 1). There were no related AEs CTCAE grade 4 or 5. Estimations of distribution volumes based on T2-weighted imaging were linearly related to volume with a mean volume of distribution/volume of infusion ratio (Vd/Vi) between 3 and 3.5. The mean ratio of lesion-to-whole body absorbed dose was ̃1000. Median overall survival from diagnosis across all cohorts was 14.8 months (n = 46, 95% CI 11.5, 16.8) and the survival rate estimates (with 95% confidence intervals) at 1, 2, 3 and 5 years were 0.63 (0.46;0.76); 0.13 (0.05;0.26); 0.08 (0.02;0.19); and 0.04 (0.00;0.16), respectively. Four patients have survived > 3 years; two remain alive at 46 and 96 months and two have died at 43 and 53 months, both with CNS disease outside of the treatment field and one with extra-CNS metastases. Conclusions: 124I-omburtamab via CED into the brain stem of children with DIPG and previously irradiated provides a possibility for improved treatment of DIPG. A dose of 8mCi and an infusion volume of 8,000 µl is considered safe and may provide a distribution volume large enough to cover tumor volumes up to 20 cm3. The median overall survival of all patients included in the trial appears to be increased with 3-4 months compared to historical control data from consortia trials. A phase 2 trial aiming at investigating the efficacy of radiolabeled omburtamab administered via CED is being planned. Clinical trial information: NCT01502917.

OBJECTIVE Accurately determining diffuse intrinsic pontine glioma (DIPG) tumor volume is clinically important. The aims of the current study were to 1) measure DIPG volumes using methods that require different degrees of subjective judgment; and 2) evaluate interobserver agreement of measurements made using these methods. METHODS Eight patients from a Phase I clinical trial testing convection-enhanced delivery (CED) of a therapeutic antibody were included in the study. Pre-CED, post–radiation therapy axial T2-weighted images were analyzed using 2 methods requiring high degrees of subjective judgment (picture archiving and communication system [PACS] polygon and Volume Viewer auto-contour methods) and 1 method requiring a low degree of subjective judgment (k-means clustering segmentation) to determine tumor volumes. Lin's concordance correlation coefficients (CCCs) were calculated to assess interobserver agreement. RESULTS The CCCs of measurements made by 2 observers with the PACS polygon and the Volume Viewer auto-contour methods were 0.9465 (lower 1-sided 95% confidence limit 0.8472) and 0.7514 (lower 1-sided 95% confidence limit 0.3143), respectively. Both were considered poor agreement. The CCC of measurements made using k-means clustering segmentation was 0.9938 (lower 1-sided 95% confidence limit 0.9772), which was considered substantial strength of agreement. CONCLUSIONS The poor interobserver agreement of PACS polygon and Volume Viewer auto-contour methods highlighted the difficulty in consistently measuring DIPG tumor volumes using methods requiring high degrees of subjective judgment. k-means clustering segmentation, which requires a low degree of subjective judgment, showed better interobserver agreement and produced tumor volumes with delineated borders.

To assess the association between apparent diffusion coefficient (ADC), and histological prognostic parameters in malignant breast lesions. The ability of ADC to identify lesions with the presence of Lymphovascular invasion (LVI) in breast carcinoma was also examined.This HIPAA-compliant retrospective study consisted of 212 consecutive patients with known cancers who underwent 3.0T MRI between January 2011 and 2013. In this study, a total of 126 malignant lesions in 114 women, who had undergone DWI (b-values of 0 and 1000s/mm(2)) in addition to diagnostic MRI, were included. Patients with less than 0.8cm lesions, or those who underwent neoadjuvant chemotherapy or suboptimal DW images were excluded. Classical prognostic factors [lesion size, histopathological type and grade, lymph node (LN) status and lymphovascular invasion (LVI)], molecular prognostic markers [estrogen receptor (ER), progesterone receptor (PR) and human epidermal grow factor receptor 2 (HER2)] were reviewed and recorded. A region of interest (ROI) was drawn within the lesions to measure ADC values. Statistical analyses were performed by the Wilcoxon rank sum test (statistical significance at P0.05). Adjusted p values from multiple comparison analysis were also calculated.This study demonstrates an inverse correlation between ADC and LVI in malignant lesions and the ability of ADC to identify aggressiveness in lesions with positive LVI. Tumor size, grade, ER, PR, HER2 and lymph node status did not impact tumor ADC value. However, tumors with LVI showed significantly lower ADC values when compared to tumors without LVI, regardless of the enhancement type, histological grade, histological type, and LN status.Our study shows that ADC could be a potential clinical adjunct in the evaluation of prognostic factors related to malignant lesion aggressiveness such as LVI.

Purpose To use features extracted from magnetic resonance (MR) images and a machine-learning method to assist in differentiating breast cancer molecular subtypes. Materials and Methods This retrospective Health Insurance Portability and Accountability Act (HIPAA)-compliant study received Institutional Review Board (IRB) approval. We identified 178 breast cancer patients between 2006–2011 with: 1) ERPR + (n = 95, 53.4%), ERPR–/HER2 + (n = 35, 19.6%), or triple negative (TN, n = 48, 27.0%) invasive ductal carcinoma (IDC), and 2) preoperative breast MRI at 1.5T or 3.0T. Shape, texture, and histogram-based features were extracted from each tumor contoured on pre- and three postcontrast MR images using in-house software. Clinical and pathologic features were also collected. Machine-learning-based (support vector machines) models were used to identify significant imaging features and to build models that predict IDC subtype. Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Kruskal–Wallis test. Results Each support vector machine fit in the LOOCV process generated a model with varying features. Eleven out of the top 20 ranked features were significantly different between IDC subtypes with P < 0.05. When the top nine pathologic and imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 83.4%. The combined pathologic and imaging model's accuracy for each subtype was 89.2% (ERPR+), 63.6% (ERPR–/HER2+), and 82.5% (TN). When only the top nine imaging features were incorporated, the predictive model distinguished IDC subtypes with an overall accuracy on LOOCV of 71.2%. The combined pathologic and imaging model's accuracy for each subtype was 69.9% (ERPR+), 62.9% (ERPR–/HER2+), and 81.0% (TN). Conclusion We developed a machine-learning-based predictive model using features extracted from MRI that can distinguish IDC subtypes with significant predictive power. J. Magn. Reson. Imaging 2016;44:122–129.

Background To use clinical and MRI radiomic features coupled with machine learning to assess HER2 expression level and predict pathologic response (pCR) in HER2 overexpressing breast cancer patients receiving neoadjuvant chemotherapy (NAC). Methods This retrospective study included 311 patients. pCR was defined as no residual invasive carcinoma in the breast or axillary lymph nodes (ypT0/isN0). Radiomics/statistical analysis was performed using MATLAB and CERR software. After ROC and correlation analysis, selected radiomics parameters were advanced to machine learning modelling alongside clinical MRI-based parameters (lesion type, multifocality, size, nodal status). For predicting pCR, the data was split into a training and test set (80:20). Findings The overall pCR rate was 60.5% (188/311). The final model to predict HER2 heterogeneity utilised three MRI parameters (two clinical, one radiomic) for a sensitivity of 99.3% (277/279), specificity of 81.3% (26/32), and diagnostic accuracy of 97.4% (303/311). The final model to predict pCR included six MRI parameters (two clinical, four radiomic) for a sensitivity of 86.5% (32/37), specificity of 80.0% (20/25), and diagnostic accuracy of 83.9% (52/62) (test set); these results were independent of age and ER status, and outperformed the best model developed using clinical parameters only (p=0.029, comparison of proportion Chi-squared test). Interpretation The machine learning models, including both clinical and radiomics MRI features, can be used to assess HER2 expression level and can predict pCR after NAC in HER2 overexpressing breast cancer patients. Funding NIH/NCI (P30CA008748), Susan G. Komen Foundation, Breast Cancer Research Foundation, Spanish Foundation Alfonso Martin Escudero, European School of Radiology.