Development of a quantitative method for analysis of breast density based on three-dimensional breast MRI

Predicting mammographic density with linear ultrasound transducers

BACKGROUND

High mammographic density (MD) is a risk factor for the development of breast cancer (BC). Changes in MD are influenced by multiple factors such as age, BMI, number of full-term pregnancies and lactating periods. To learn more about MD, it is important to establish non-radiation-based, alternative examination methods to mammography such as ultrasound assessments.

METHODS

We analyzed data from 168 patients who underwent standard-of-care mammography and performed additional ultrasound assessment of the breast using a high-frequency (12 MHz) linear probe of the VOLUSON® 730 Expert system (GE Medical Systems Kretztechnik GmbH & Co OHG, Austria). Gray level bins were calculated from ultrasound images to characterize mammographic density. Percentage mammographic density (PMD) was predicted by gray level bins using various regression models.

RESULTS

Gray level bins and PMD correlated to a certain extent. Spearman's ρ ranged from - 0.18 to 0.32. The random forest model turned out to be the most accurate prediction model (cross-validated R2, 0.255). Overall, ultrasound images from the VOLUSON® 730 Expert device in this study showed limited predictive power for PMD when correlated with the corresponding mammograms.

CONCLUSIONS

In our present work, no reliable prediction of PMD using ultrasound imaging could be observed. As previous studies showed a reasonable correlation, predictive power seems to be highly dependent on the device used. Identifying feasible non-radiation imaging methods of the breast and their predictive power remains an important topic and warrants further evaluation. Trial registration 325-19 B (Ethics Committee of the medical faculty at Friedrich Alexander University of Erlangen-Nuremberg, Erlangen, Germany).

Improvement of semantic segmentation through transfer learning of multi-class regions with convolutional neural networks on supine and prone breast MRI images

Semantic segmentation of breast and surrounding tissues in supine and prone breast magnetic resonance imaging (MRI) is required for various kinds of computer-assisted diagnoses for surgical applications. Variability of breast shape in supine and prone poses along with various MRI artifacts makes it difficult to determine robust breast and surrounding tissue segmentation. Therefore, we evaluated semantic segmentation with transfer learning of convolutional neural networks to create robust breast segmentation in supine breast MRI without considering supine or prone positions. Total 29 patients with T1-weighted contrast-enhanced images were collected at Asan Medical Center and two types of breast MRI were performed in the prone position and the supine position. The four classes, including lungs and heart, muscles and bones, parenchyma with cancer, and skin and fat, were manually drawn by an expert. Semantic segmentation on breast MRI scans with supine, prone, transferred from prone to supine, and pooled supine and prone MRI were trained and compared using 2D U-Net, 3D U-Net, 2D nnU-Net and 3D nnU-Net. The best performance was 2D models with transfer learning. Our results showed excellent performance and could be used for clinical purposes such as breast registration and computer-aided diagnosis.

Portable NMR for quantification of breast density in vivo: Proof-of-concept measurements and comparison with quantitative MRI

Mammographic Density (MD) is the degree of radio-opacity of the breast in an X-ray mammogram. It is determined by the Fibroglandular: Adipose tissue ratio. MD has major implications in breast cancer risk and breast cancer chemoprevention. This study aimed to investigate the feasibility of accurate, low-cost quantification of MD in vivo without ionising radiation. We used single-sided portable nuclear magnetic resonance ("Portable NMR") due to its low cost and the absence of radiation-related safety concerns. Fifteen (N = 15) healthy female volunteers were selected for the study and underwent an imaging routine consisting of 2D X-ray mammography, quantitative breast 3T MRI (Dixon and T₁-based 3D compositional breast imaging), and 1D compositional depth profiling of the right breast using Portable NMR. For each participant, all the measurements were made within 3-4 h of each other. MRI-determined tissue water content was used as the MD-equivalent quantity. Portable NMR depth profiles of tissue water were compared with the equivalent depth profiles reconstructed from Dixon and T₁-based MR images, which were used as the MD-equivalent reference standard. The agreement between the depth profiles acquired using Portable NMR and the reconstructed reference-standard profiles was variable but overall encouraging. The agreement was somewhat inferior to that seen in breast tissue explant measurements conducted in vitro, where quantitative micro-CT was used as the reference standard. The lower agreement in vivo can be attributed to an uncertainty in the positioning of the Portable NMR sensor on the breast surface and breast compression in Portable NMR measurements. The degree of agreement between Portable NMR and quantitative MRI is encouraging. While the results call for further development of quantitative Portable NMR, they demonstrate the in-principle feasibility of Portable NMR-based quantitative compositional imaging in vivo and show promise for the development of safe and low-cost protocols for quantification of MD suitable for clinical applications.

Can we predict the neutral breast position using the gravity-loaded breast position, age, anthropometrics and breast composition data?

BACKGROUND

This study aimed to identify the predictor variables which account for neutral breast position variance using a full independent variable dataset (the gravity-loaded breast position, age and anthropometrics, and magnetic resonance imaging breast composition data), and a simplified independent variable dataset (magnetic resonance imaging breast composition data excluded).

METHODS

Breast position (three-dimensional neutral and static gravity-loaded), age, anthropometrics and magnetic resonance imaging breast composition data were collected for 80 females (bra size 32A to 38D). Correlations between the neutral breast position and the gravity-loaded breast position, age, anthropometrics, and magnetic resonance imaging breast composition data were assessed. Multiple linear and multivariate multiple regression models were utilised to predict neutral breast positions, with mean absolute differences and root mean square error comparing observed and predicted neutral breast positions.

FINDINGS

Breast volume was the only breast composition variable to contribute as a predictor of the neutral breast position. While ≥69% of the variance in the anteroposterior and mediolateral neutral breast positions were accounted for utilising the gravity-loaded breast position, multivariate multiple regression modelling resulted in mean absolute differences >5 mm.

INTERPRETATION

Due to the marginal contribution of breast composition data, a full independent variable dataset may be unnecessary for this application. Additionally, the gravity-loaded breast position, age, anthropometrics, and breast composition data do not successfully predict the neutral breast position. Incorporation of the neutral breast position into breast support garments may enhance bra development. However, further identification of variables which predict the neutral breast position is required.

Proton density water fraction as a reproducible MR-based measurement of breast density

PURPOSE

To introduce proton density water fraction (PDWF) as a confounder-corrected (CC) MR-based biomarker of mammographic breast density, a known risk factor for breast cancer.

METHODS

Chemical shift encoded (CSE) MR images were acquired using a low flip angle to provide proton density contrast from multiple echo times. Fat and water images, corrected for known biases, were produced by a six-echo CC CSE-MRI algorithm. Fibroglandular tissue (FGT) volume was calculated from whole-breast segmented PDWF maps at 1.5T and 3T. The method was evaluated in (1) a physical fat-water phantom and (2) normal volunteers. Results from two- and three-echo CSE-MRI methods were included for comparison.

RESULTS

Six-echo CC-CSE-MRI produced unbiased estimates of the total water volume in the phantom (mean bias 3.3%) and was reproducible across protocol changes (repeatability coefficient [RC] = 14.8 cm³ and 13.97 cm³ at 1.5T and 3.0T, respectively) and field strengths (RC = 51.7 cm³ ) in volunteers, while the two- and three-echo CSE-MRI approaches produced biased results in phantoms (mean bias 30.7% and 10.4%) that was less reproducible across field strengths in volunteers (RC = 82.3 cm³ and 126.3 cm³ ). Significant differences in measured FGT volume were found between the six-echo CC-CSE-MRI and the two- and three-echo CSE-MRI approaches (p = 0.002 and p = 0.001, respectively).

CONCLUSION

The use of six-echo CC-CSE-MRI to create unbiased PDWF maps that reproducibly quantify FGT in the breast is demonstrated. Further studies are needed to correlate this quantitative MR biomarker for breast density with mammography and overall risk for breast cancer.

Segmentation of whole breast and fibroglandular tissue using nnU-Net in dynamic contrast enhanced MR images

PURPOSE

Segmentation of the whole breast and fibroglandular tissue (FGT) is important for quantitatively analyzing the breast cancer risk in the dynamic contrast-enhanced magnetic resonance (DCE-MR) images. The purpose of this study is to improve the accuracy and efficiency of the segmentation of the whole breast and FGT in 3-D fat-suppressed DCE-MR images with a versatile deep learning (DL) framework.

METHODS

We randomly collected 100 breast DCE-MR scans from Shanghai Cancer Hospital of Fudan University. The MR scans in the dataset were different in both the spatial resolution and the MR scanners employed. Furthermore, four breast density categories were assessed by radiologists based on Breast Imaging Reporting and Data System (BI-RADS) of American College of Radiology. The dataset was separated into the training and the testing sets, while keeping a balanced distribution of scans with different imaging parameters and density categories. The nnU-Net has been recently proposed to automatically adapt preprocessing strategies and network architectures for a given medical image dataset, thus showing a great potential in the systematic adaptation of DL methods to different datasets. In this study, we applied the nnU-Net to segment the whole breast and FGT in 3-D fat-suppressed DCE-MR images. Five-fold cross validation was employed to train and validate the segmentation method.

RESULTS

The segmentation performance was evaluated with the volume and surface agreement metrics between the DL-based automatic and the manually delineated masks, as quantified with the following measures: the average Dice volume overlap (0.968 ± 0.017 and 0.877 ± 0.081), the average surface distances (0.201 ± 0.080 mm and 0.310 ± 0.043 mm), and the Pearson correlation coefficient of masks (0.995 and 0.972) between the automatic and the manually delineated masks, as calculated for the whole breast and the FGT segmentation, respectively. The correlation coefficient between the breast densities obtained with the DL-based segmentation and the manual delineation was 0.981. There was a positive bias of 0.8% (DL-based relative to manual) in breast density measurement with the Bland-Altman plot. The execution time of the DL-based segmentation was approximately 20 s for the whole breast segmentation and 15 s for the FGT segmentation.

CONCLUSIONS

Our DL-based segmentation framework using nnU-Net could robustly achieve high accuracy and efficiency across variable MR imaging settings without extra pre- or post-processing procedures. It would be useful for developing DCE-MR-based CAD systems to quantify breast cancer risk and to be integrated into the clinical workflow.

Automated whole breast segmentation for hand-held ultrasound with position information: Application to breast density estimation

BACKGROUND AND OBJECTIVE

Women with higher breast densities have a relatively higher risk to be diagnosed with breast cancer. Hand-held ultrasound (HHUS) can provide precise screening results and detect masses in dense breasts. However, its lack of position information and automatic extraction of breast area hinder the implementation of density estimation. To facilitate reliable breast density evaluation, this study proposed an upgraded version of our whole-breast ultrasound (WBUS) system, which not only can provide precise position information, but also can extract precise breast area automatically based on deep learning method.

METHODS

WBUS images with probe position information were collected from 117 women. For each case, an automatic breast region segmentation by DeepResUnet was conducted, then fibroglandular tissues were extracted from breast region using fuzzy c-mean (FCM) classifier. Finally, the percentage of breast density and breast area of the DeepResUnet predicted region and the breast region of the ground truth were calculated and compared.

RESULTS

The average and standard deviation of each breast case for DeepResUnet predicted breast region of 10-fold in Accuracy (ACC) was 0.963±0.054. Sensitivity (SENS) was 0.928±0.11. Specificity (SPEC) was 0.967±0.054. Dice coefficient (Dice) was 0.916±0.98. Region intersection over union (IoU) was 0.856±0.134. Significant and very high correlations of breast density, fibroglandular tissue area and breast area (R = 0.843, R= 0.822 and R = 0.984, all p values < 0.001) were found between the ground truth and the result of the proposed method for ultrasound images.

CONCLUSIONS

Breast density, fibroglandular tissue, and breast volume evaluated based on the proposed method and WBUS system have significant correlations with ground truth, indicating that the proposed method and WBUS system has the potential to be an alternative modality for breast screening and density estimation in clinical use.

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

BACKGROUND

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

PURPOSE

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

STUDY TYPE

Retrospective.

POPULATION

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

FIELD STRENGTH/SEQUENCE

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

ASSESSMENT

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

STATISTICAL TESTS

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

RESULTS

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

DATA CONCLUSION

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

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Volumetric breast density estimation on MRI using explainable deep learning regression

To purpose of this paper was to assess the feasibility of volumetric breast density estimations on MRI without segmentations accompanied with an explainability step. A total of 615 patients with breast cancer were included for volumetric breast density estimation. A 3-dimensional regression convolutional neural network (CNN) was used to estimate the volumetric breast density. Patients were split in training (N = 400), validation (N = 50), and hold-out test set (N = 165). Hyperparameters were optimized using Neural Network Intelligence and augmentations consisted of translations and rotations. The estimated densities were evaluated to the ground truth using Spearman’s correlation and Bland–Altman plots. The output of the CNN was visually analyzed using SHapley Additive exPlanations (SHAP). Spearman’s correlation between estimated and ground truth density was ρ = 0.81 (N = 165, P < 0.001) in the hold-out test set. The estimated density had a median bias of 0.70% (95% limits of agreement = − 6.8% to 5.0%) to the ground truth. SHAP showed that in correct density estimations, the algorithm based its decision on fibroglandular and fatty tissue. In incorrect estimations, other structures such as the pectoral muscle or the heart were included. To conclude, it is feasible to automatically estimate volumetric breast density on MRI without segmentations, and to provide accompanying explanations.

MRI background parenchymal enhancement, fibroglandular tissue, and mammographic breast density in patients with invasive lobular breast cancer on adjuvant endocrine hormonal treatment: associations with survival

BACKGROUND

To investigate if baseline and/or changes in contralateral background parenchymal enhancement (BPE) and fibroglandular tissue (FGT) measured on magnetic resonance imaging (MRI) and mammographic breast density (MD) can be used as imaging biomarkers for overall and recurrence-free survival in patients with invasive lobular carcinomas (ILCs) undergoing adjuvant endocrine treatment.

METHODS

Women who fulfilled the following inclusion criteria were included in this retrospective HIPAA-compliant IRB-approved study: unilateral ILC, pre-treatment breast MRI and/or mammography from 2000 to 2010, adjuvant endocrine treatment, follow-up MRI, and/or mammography 1-2 years after treatment onset. BPE, FGT, and mammographic MD of the contralateral breast were independently graded by four dedicated breast radiologists according to BI-RADS. Associations between the baseline levels and change in levels of BPE, FGT, and MD with overall survival and recurrence-free survival were assessed using Kaplan-Meier survival curves and Cox regression analysis.

RESULTS

Two hundred ninety-eight patients (average age = 54.1 years, range = 31-79) fulfilled the inclusion criteria. The average follow-up duration was 11.8 years (range = 2-19). Baseline and change in levels of BPE, FGT, and MD were not significantly associated with recurrence-free or overall survival. Recurrence-free and overall survival were affected by histological subtype (p < 0.0001), number of metastatic axillary lymph nodes (p < 0.0001), age (p = 0.01), and adjuvant endocrine treatment duration (p < 0.001).

CONCLUSIONS

Qualitative evaluation of BPE, FGT, and mammographic MD changes cannot predict which patients are more likely to benefit from adjuvant endocrine treatment.

Automated fibroglandular tissue segmentation in breast MRI using generative adversarial networks

Fibroglandular tissue (FGT) segmentation is a crucial step for quantitative analysis of background parenchymal enhancement (BPE) in magnetic resonance imaging (MRI), which is useful for breast cancer risk assessment. In this study, we develop an automated deep learning method based on a generative adversarial network (GAN) to identify the FGT region in MRI volumes and evaluate its impact on a specific clinical application. The GAN consists of an improved U-Net as a generator to generate FGT candidate areas and a patch deep convolutional neural network (DCNN) as a discriminator to evaluate the authenticity of the synthetic FGT region. The proposed method has two improvements compared to the classical U-Net: (1) the improved U-Net is designed to extract more features of the FGT region for a more accurate description of the FGT region; (2) a patch DCNN is designed for discriminating the authenticity of the FGT region generated by the improved U-Net, which makes the segmentation result more stable and accurate. A dataset of 100 three-dimensional (3D) bilateral breast MRI scans from 100 patients (aged 22-78 years) was used in this study with Institutional Review Board (IRB) approval. 3D hand-segmented FGT areas for all breasts were provided as a reference standard. Five-fold cross-validation was used in training and testing of the models. The Dice similarity coefficient (DSC) and Jaccard index (JI) values were evaluated to measure the segmentation accuracy. The previous method using classical U-Net was used as a baseline in this study. In the five partitions of the cross-validation set, the GAN achieved DSC and JI values of 87.0 ± 7.0% and 77.6 ± 10.1%, respectively, while the corresponding values obtained through by the baseline method were 81.1 ± 8.7% and 69.0 ± 11.3%, respectively. The proposed method is significantly superior to the previous method using U-Net. The FGT segmentation impacted the BPE quantification application in the following manner: the correlation coefficients between the quantified BPE value and BI-RADS BPE categories provided by the radiologist were 0.46 ± 0.15 (best: 0.63) based on GAN segmented FGT areas, while the corresponding correlation coefficients were 0.41 ± 0.16 (best: 0.60) based on baseline U-Net segmented FGT areas. BPE can be quantified better using the FGT areas segmented by the proposed GAN model than using the FGT areas segmented by the baseline U-Net.

An automated approach for the optimised estimation of breast density with Dixon methods

OBJECTIVE

To present and evaluate an automated method to correct scaling between Dixon water/fat images used in breast density (BD) assessments.

METHODS

Dixon images were acquired in 14 subjects with different T₁ weightings (flip angles, FA, 4°/16°). Our method corrects intensity differences between water (W) and fat (F) images via the application of a uniform scaling factor (SF), determined subject-by-subject. Based on the postulation that optimal SFs yield relatively featureless summed fat/scaled-water (F+WSF) images, each SF was chosen as that which generated the lowest 95th-percentile in the absolute spatial-gradient image-volume of F+WSF . Water-fraction maps were calculated for data acquired with low/high FAs, and BD (%) was the total percentage water within each breast volume.

RESULTS

Corrected/uncorrected BD ranged from, respectively, 10.9-71.8%/8.9-66.7% for low-FA data to 8.1-74.3%/5.6-54.3% for high-FA data. Corrected metrics had an average absolute increase in BD of 6.4% for low-FA data and 18.4% for high-FA data. BD values estimated from low- and high-FA data were closer following SF-correction.

CONCLUSION

Our results demonstrate need for scaling in such BD assessments, where our method brought high-FA and low-FA data into closer agreement.

ADVANCES IN KNOWLEDGE

We demonstrated a feasible method to address a main source of inaccuracy in Dixon-based BD measurements.

Automatic Breast and Fibroglandular Tissue Segmentation in Breast MRI Using Deep Learning by a Fully-Convolutional Residual Neural Network U-Net

RATIONALE AND OBJECTIVES

Breast segmentation using the U-net architecture was implemented and tested in independent validation datasets to quantify fibroglandular tissue volume in breast MRI.

MATERIALS AND METHODS

Two datasets were used. The training set was MRI of 286 patients with unilateral breast cancer. The segmentation was done on the contralateral normal breasts. The ground truth for the breast and fibroglandular tissue (FGT) was obtained by using a template-based segmentation method. The U-net deep learning algorithm was implemented to analyze the training set, and the final model was obtained using 10-fold cross-validation. The independent validation set was MRI of 28 normal volunteers acquired using four different MR scanners. Dice Similarity Coefficient (DSC), voxel-based accuracy, and Pearson's correlation were used to evaluate the performance.

RESULTS

For the 10-fold cross-validation in the initial training set of 286 patients, the DSC range was 0.83-0.98 (mean 0.95 ± 0.02) for breast and 0.73-0.97 (mean 0.91 ± 0.03) for FGT; and the accuracy range was 0.92-0.99 (mean 0.98 ± 0.01) for breast and 0.87-0.99 (mean 0.97 ± 0.01) for FGT. For the entire 224 testing breasts of the 28 normal volunteers in the validation datasets, the mean DSC was 0.86 ± 0.05 for breast, 0.83 ± 0.06 for FGT; and the mean accuracy was 0.94 ± 0.03 for breast and 0.93 ± 0.04 for FGT. The testing results for MRI acquired using four different scanners were comparable.

CONCLUSION

Deep learning based on the U-net algorithm can achieve accurate segmentation results for the breast and FGT on MRI. It may provide a reliable and efficient method to process large number of MR images for quantitative analysis of breast density.

Quantitative Volumetric K-Means Cluster Segmentation of Fibroglandular Tissue and Skin in Breast MRI

Mammographic breast density (MBD) is the most commonly used method to assess the volume of fibroglandular tissue (FGT). However, MRI could provide a clinically feasible and more accurate alternative. There were three aims in this study: (1) to evaluate a clinically feasible method to quantify FGT with MRI, (2) to assess the inter-rater agreement of MRI-based volumetric measurements and (3) to compare them to measurements acquired using digital mammography and 3D tomosynthesis. This retrospective study examined 72 women (mean age 52.4 ± 12.3 years) with 105 disease-free breasts undergoing diagnostic 3.0-T breast MRI and either digital mammography or tomosynthesis. Two observers analyzed MRI images for breast and FGT volumes and FGT-% from T1-weighted images (0.7-, 2.0-, and 4.0-mm-thick slices) using K-means clustering, data from histogram, and active contour algorithms. Reference values were obtained with Quantra software. Inter-rater agreement for MRI measurements made with 2-mm-thick slices was excellent: for FGT-%, r = 0.994 (95% CI 0.990-0.997); for breast volume, r = 0.985 (95% CI 0.934-0.994); and for FGT volume, r = 0.979 (95% CI 0.958-0.989). MRI-based FGT-% correlated strongly with MBD in mammography (r = 0.819-0.904, P < 0.001) and moderately to high with MBD in tomosynthesis (r = 0.630-0.738, P < 0.001). K-means clustering-based assessments of the proportion of the fibroglandular tissue in the breast at MRI are highly reproducible. In the future, quantitative assessment of FGT-% to complement visual estimation of FGT should be performed on a more regular basis as it provides a component which can be incorporated into the individual's breast cancer risk stratification.

Evaluation of breast stiffness measured by ultrasound and breast density measured by MRI using a prone-supine deformation model

Background

This study evaluated breast tissue stiffness measured by ultrasound elastography and the percent breast density measured by magnetic resonance imaging to understand their relationship.

Methods

Magnetic resonance imaging and whole breast ultrasound were performed in 20 patients with suspicious lesions. Only the contralateral normal breasts were analyzed. Breast tissue stiffness was measured from the echogenic homogeneous fibroglandular tissues in the central breast area underneath the nipple. An automatic, computer algorithm-based, segmentation method was used to segment the whole breast and fibroglandular tissues on three dimensional magnetic resonanceimaging. A finite element model was applied to deform the prone magnetic resonance imaging to match the supine ultrasound images, by using the inversed gravity loaded transformation. After deformation, the tissue level used in ultrasound elastography measurement could be estimated on the deformed supine magnetic resonance imaging to measure the breast density in the corresponding tissue region.

Results

The mean breast tissue stiffness was 2.3 ± 0.8 m/s. The stiffness was not correlated with age (r = 0.29). Overall, there was no positive correlation between breast stiffness and breast volume (r = - 0.14), or the whole breast percent density (r = - 0.09). There was also no correlation between breast stiffness and the local percent density measured from the corresponding region (r = - 0.12).

Conclusions

The lack of correlation between breast stiffness measured by ultrasound and the whole breast or local percent density measured by magnetic resonance imaging suggests that breast stiffness is not solely related to the amount of fibroglandular tissue. Further studies are needed to investigate whether they are dependent or independent cancer risk factors.

NCTN Assessment on Current Applications of Radiomics in Oncology

Radiomics is a fast-growing research area based on converting standard-of-care imaging into quantitative minable data and building subsequent predictive models to personalize treatment. Radiomics has been proposed as a study objective in clinical trial concepts and a potential biomarker for stratifying patients across interventional treatment arms. In recognizing the growing importance of radiomics in oncology, a group of medical physicists and clinicians from NRG Oncology reviewed the current status of the field and identified critical issues, providing a general assessment and early recommendations for incorporation in oncology studies.

A complementary scheme for automated detection of high-uptake regions on dedicated breast PET and whole-body PET/CT

In this study, we aimed to develop a hybrid method for automated detection of high-uptake regions in the breast and axilla using dedicated breast positron-emission tomography (db PET) and whole-body PET/computed tomography (CT) images. In our proposed method, high-uptake regions in the breast and axilla were detected using db PET images and whole-body PET/CT images. In db PET images, high-uptake regions in the breast were detected using adaptive thresholding technique based on the noise characteristics. In whole-body PET/CT images, the region of the breast that includes the axilla was first extracted using CT images. Next, high-uptake regions in the extracted breast region were detected on the PET images. By integration of the results of the two types of PET images, a final candidate region was obtained. In the experiments, the accuracy of extracting the region of the breast and detection ability was evaluated using clinical data. As a result, all breast regions were extracted correctly. The sensitivity of detection was 0.765, and the number of false positive cases were 1.8, which was 30% better than those on whole-body PET/CT alone. These results suggested that the proposed method, combining the two types of PET images is effective for improving detection performance.

Transverse relaxation-based assessment of mammographic density and breast tissue composition by single-sided portable NMR

PURPOSE

Elevated mammographic density (MD) is an independent risk factor for breast cancer (BC) as well as a source of masking in X-ray mammography. High-frequency longitudinal monitoring of MD could also be beneficial in hormonal BC prevention, where early MD changes herald the treatment's success. We present a novel approach to quantification of MD in breast tissue using single-sided portable NMR. Its development was motivated by the low cost of portable-NMR instrumentation, the suitability for measurements in vivo, and the absence of ionizing radiation.

METHODS

Five breast slices were obtained from three patients undergoing prophylactic mastectomy or breast reduction surgery. Carr-Purcell-Meiboom-Gill (CPMG) relaxation curves were measured from (1) regions of high and low MD (HMD and LMD, respectively) in the full breast slices; (2) the same regions excised from the full slices; and (3) excised samples after H₂ O-D₂ O replacement. T₂ distributions were reconstructed from the CPMG decays using inverse Laplace transform.

RESULTS

Two major peaks, identified as fat and water, were consistently observed in the T₂ distributions of HMD regions. The LMD T₂ distributions were dominated by the fat peak. The relative areas of the two peaks exhibited statistically significant (P < .005) differences between HMD and LMD regions, enabling their classification as HMD or LMD. The relative-area distributions exhibited no statistically significant differences between full slices and excised samples.

CONCLUSION

T₂ -based portable-NMR analysis is a novel approach to MD quantification. The ability to quantify tissue composition, combined with the low cost of instrumentation, make this approach promising for clinical applications.

Background parenchymal enhancement on breast MRI: A comprehensive review

The degree of normal fibroglandular tissue that enhances on breast MRI, known as background parenchymal enhancement (BPE), was initially described as an incidental finding that could affect interpretation performance. While BPE is now established to be a physiologic phenomenon that is affected by both endogenous and exogenous hormone levels, evidence supporting the notion that BPE frequently masks breast cancers is limited. However, compelling data have emerged to suggest BPE is an independent marker of breast cancer risk and breast cancer treatment outcomes. Specifically, multiple studies have shown that elevated BPE levels, measured qualitatively or quantitatively, are associated with a greater risk of developing breast cancer. Evidence also suggests that BPE could be a predictor of neoadjuvant breast cancer treatment response and overall breast cancer treatment outcomes. These discoveries come at a time when breast cancer screening and treatment have moved toward an increased emphasis on targeted and individualized approaches, of which the identification of imaging features that can predict cancer diagnosis and treatment response is an increasingly recognized component. Historically, researchers have primarily studied quantitative tumor imaging features in pursuit of clinically useful biomarkers. However, the need to segment less well-defined areas of normal tissue for quantitative BPE measurements presents its own unique challenges. Furthermore, there is no consensus on the optimal timing on dynamic contrast-enhanced MRI for BPE quantitation. This article comprehensively reviews BPE with a particular focus on its potential to increase precision approaches to breast cancer risk assessment, diagnosis, and treatment. It also describes areas of needed future research, such as the applicability of BPE to women at average risk, the biological underpinnings of BPE, and the standardization of BPE characterization. Level of Evidence: 3 Technical Efficacy Stage: 5 J. Magn. Reson. Imaging 2020;51:43-61.

An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U-nets

PURPOSE

Accurate segmentation of the breast is required for breast density estimation and the assessment of background parenchymal enhancement, both of which have been shown to be related to breast cancer risk. The MRI breast segmentation task is challenging, and recent work has demonstrated that convolutional neural networks perform well for this task. In this study, we have investigated the performance of several two-dimensional (2D) U-Net and three-dimensional (3D) U-Net configurations using both fat-suppressed and nonfat-suppressed images. We have also assessed the effect of changing the number and quality of the ground truth segmentations.

MATERIALS AND METHODS

We designed eight studies to investigate the effect of input types and the dimensionality of the U-Net operations for the breast MRI segmentation. Our training data contained 70 whole breast volumes of T1-weighted sequences without fat suppression (WOFS) and with fat suppression (FS). For each subject, we registered the WOFS and FS volumes together before manually segmenting the breast to generate ground truth. We compared four different input types to the U-nets: WOFS, FS, MIXED (WOFS and FS images treated as separate samples), and MULTI (WOFS and FS images combined into a single multichannel image). We trained 2D U-Nets and 3D U-Nets with these data, which resulted in our eight studies (2D-WOFS, 3D-WOFS, 2D-FS, 3D-FS, 2D-MIXED, 3D-MIXED, 2D-MULTI, and 3D-MULT). For each of these studies, we performed a systematic grid search to tune the hyperparameters of the U-Nets. A separate validation set with 15 whole breast volumes was used for hyperparameter tuning. We performed Kruskal-Walis test on the results of our hyperparameter tuning and did not find a statistically significant difference in the ten top models of each study. For this reason, we chose the best model as the model with the highest mean dice similarity coefficient (DSC) value on the validation set. The reported test results are the results of the top model of each study on our test set which contained 19 whole breast volumes annotated by three readers fused with the STAPLE algorithm. We also investigated the effect of the quality of the training annotations and the number of training samples for this task.

RESULTS

The study with the highest average DSC result was 3D-MULTI with 0.96 ± 0.02. The second highest average is 2D WOFS (0.96 ± 0.03), and the third is 2D MULTI (0.96 ± 0.03). We performed the Kruskal-Wallis one-way ANOVA test with Dunn's multiple comparison tests using Bonferroni P-value correction on the results of the selected model of each study and found that 3D-MULTI, 2D-MULTI, 3D-WOFS, 2D-WOFS, 2D-FS, and 3D-FS were not statistically different in their distributions, which indicates that comparable results could be obtained in fat-suppressed and nonfat-suppressed volumes and that there is no significant difference between the 3D and 2D approach. Our results also suggested that the networks trained on single sequence images or multiple sequence images organized in multichannel images perform better than the models trained on a mixture of volumes from different sequences. Our investigation of the size of the training set revealed that training a U-Net in this domain only requires a modest amount of training data and results obtained with 49 and 70 training datasets were not significantly different.

CONCLUSIONS

To summarize, we investigated the use of 2D U-Nets and 3D U-Nets for breast volume segmentation in T1 fat-suppressed and without fat-suppressed volumes. Although our highest score was obtained in the 3D MULTI study, when we took advantage of information in both fat-suppressed and nonfat-suppressed volumes and their 3D structure, all of the methods we explored gave accurate segmentations with an average DSC on >94% demonstrating that the U-Net is a robust segmentation method for breast MRI volumes.

Multimodality Imaging of Breast Parenchymal Density and Correlation with Risk Assessment

Purpose of Review

Breast density, or the amount of fibroglandular tissue in the breast, has become a recognized and independent marker for breast cancer risk. Public awareness of breast density as a possible risk factor for breast cancer has resulted in legislation for risk stratification purposes in many US states. This review will provide a comprehensive overview of the currently available imaging modalities for qualitative and quantitative breast density assessment and the current evidence on breast density and breast cancer risk assessment.

Recent Findings

To date, breast density assessment is mainly performed with mammography and to some extent with magnetic resonance imaging. Data indicate that computerized, quantitative techniques in comparison with subjective visual estimations are characterized by higher reproducibility and robustness.

Summary

Breast density reduces the sensitivity of mammography due to a masking effect and is also a recognized independent risk factor for breast cancer. Standardized breast density assessment using automated volumetric quantitative methods has the potential to be used for risk prediction and stratification and in determining the best screening plan for each woman.

Radiomic analysis of imaging heterogeneity in tumours and the surrounding parenchyma based on unsupervised decomposition of DCE-MRI for predicting molecular subtypes of breast cancer

OBJECTIVES

This study aimed to predict the molecular subtypes of breast cancer via intratumoural and peritumoural radiomic analysis with subregion identification based on the decomposition of contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHODS

The study included 211 women with histopathologically confirmed breast cancer. We utilised a completely unsupervised convex analysis of mixtures (CAM) method by unmixing dynamic imaging series from heterogeneous tissues. Each tumour and the surrounding parenchyma were thus decomposed into multiple subregions, representing different vascular characterisations, from which radiomic features were extracted. A random forest model was trained and tested using a leave-one-out cross-validation (LOOCV) method to predict breast cancer subtypes. The predictive models from tumoural and peritumoural subregions were fused for classification.

RESULTS

Tumour and peritumour DCE-MR images were decomposed into three compartments, representing plasma input, fast-flow kinetics, and slow-flow kinetics. The tumour subregion related to fast-flow kinetics showed the best performance among the subregions for differentiating between patients with four molecular subtypes (area under the receiver operating characteristic curve (AUC) = 0.832), exhibiting an AUC value significantly (p < 0.0001) higher than that obtained with the entire tumour (AUC = 0.719). When the tumour- and parenchyma-based predictive models were fused, the performance, measured as the AUC, increased to 0.897; this value was significantly higher than that obtained with other tumour partition methods.

CONCLUSIONS

Radiomic analysis of intratumoural and peritumoural heterogeneity based on the decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features and serve as a valuable clinical marker to enhance the prediction of breast cancer subtypes.

KEY POINTS

• Decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features. • Fusion of intratumoural- and peritumoural-based predictive models improves the prediction of breast cancer subtypes.

Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis

Over the years, MR systems have evolved from imaging modalities to advanced computational systems producing a variety of numerical parameters that can be used for the noninvasive preoperative assessment of breast pathology. Furthermore, the combination with state-of-the-art image analysis methods provides a plethora of quantifiable imaging features, termed radiomics that increases diagnostic accuracy towards individualized therapy planning. More importantly, radiomics can now be complemented by the emerging deep learning techniques for further process automation and correlation with other clinical data which facilitate the monitoring of treatment response, as well as the prediction of patient's outcome, by means of unravelling of the complex underlying pathophysiological mechanisms which are reflected in tissue phenotype. The scope of this review is to provide applications and limitations of radiomics towards the development of clinical decision support systems for breast cancer diagnosis and prognosis.

Quantitative analysis of peri-tumor fat in different molecular subtypes of breast cancer

BACKGROUND AND PURPOSES

The aim of this study was to develop morphological analytic methods to analyze the tumor-fat interface and in different peritumoral shells away from the tumor, and to compare the results among three molecular subtypes of breast cancer.

MATERIALS AND METHODS

A total of 102 women (mean age 48.5 y/o) with solitary well-defined breast cancers were analyzed, including 46 human epidermal growth factor receptor 2 (HER2) (+), 46 HER2(-) hormonal receptor (HR) (+), and 10 triple negative (TN) breast cancers. The tumor lesion, the breast, the fibroglandular and fatty tissue were segmented using well-established methods. The whole breast fat percentage and the peri-tumor interface fat percentage were measured. Three shells (SH1, SH2, SH3) surrounding the convex hall of the three dimensional (3D) tumor were defined and in each shell the volumetric percentage of fat was calculated. The peri-tumor interface fat percentage and the volumetric percentage of fat in the three peri-tumoral shells were compared among different subtypes.

RESULTS

In the TN group, the fat percentage on the tumor boundary was 43 ± 20% and 78 ± 12% for two dimensional (2D) and 3D measurement, respectively, which were the highest among the three subtypes but not significantly different. The fat percentage in SH2 and SH3 in the TN group was 82 ± 7% and 85 ± 7%, which was significantly higher compared to the two other two subtypes. The results remained after controlling for the whole breast fat percentage.

CONCLUSIONS

This study provided a feasible method for quantitative analysis of peri-tumoral tissue characteristics. Because of small patient number, the finding that TN tumors had the highest peri-tumor fat content among the three subtypes needs to be further verified with a large cohort study.

Reproducible automated breast density measure with no ionizing radiation using fat-water decomposition MRI

BACKGROUND

Increased breast density is a significant independent risk factor for breast cancer, and recent studies show that this risk is modifiable. Hence, breast density measures sensitive to small changes are desired.

PURPOSE

Utilizing fat-water decomposition MRI, we propose an automated, reproducible breast density measurement, which is nonionizing and directly comparable to mammographic density (MD).

STUDY TYPE

Retrospective study.

POPULATION

The study included two sample sets of breast cancer patients enrolled in a clinical trial, for concordance analysis with MD (40 patients) and reproducibility analysis (10 patients).

FIELD STRENGTH/SEQUENCE

The majority of MRI scans (59 scans) were performed with a 1.5T GE Signa scanner using radial IDEAL-GRASE sequence, while the remaining (seven scans) were performed with a 3T Siemens Skyra using 3D Cartesian 6-echo GRE sequence with a similar fat-water separation technique.

ASSESSMENT

After automated breast segmentation, breast density was calculated using FraGW, a new measure developed to reliably reflect the amount of fibroglandular tissue and total water content in the entire breast. Based on its concordance with MD, FraGW was calibrated to MR-based breast density (MRD) to be comparable to MD. A previous breast density measurement, Fra80-the ratio of breast voxels with <80% fat fraction-was also calculated for comparison with FraGW.

STATISTICAL TESTS

Pearson correlation was performed between MD (reference standard) and FraGW (and Fra80). Test-retest reproducibility of MRD was evaluated using the difference between test-retest measures (Δ_1-2 ) and intraclass correlation coefficient (ICC).

RESULTS

Both FraGW and Fra80 were strongly correlated with MD (Pearson ρ: 0.96 vs. 0.90, both P < 0.0001). MRD converted from FraGW showed higher test-retest reproducibility (Δ_1-2 variation: 1.1% ± 1.2%; ICC: 0.99) compared to MD itself (literature intrareader ICC ≤0.96) and Fra80.

DATA CONCLUSION

The proposed MRD is directly comparable with MD and highly reproducible, which enables the early detection of small breast density changes and treatment response.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;48:971-981.

Quantitative breast density analysis using tomosynthesis and comparison with MRI and digital mammography

BACKGROUND AND OBJECTIVE

Breast density at mammography has been used as markers of breast cancer risk. However, newly introduced tomosynthesis and computer-aided quantitative method could provide more reliable breast density evaluation.

METHODS

In the experiment, 98 tomosynthesis image volumes were obtained from 98 women. For each case, an automatic skin removal was used and followed by a fuzzy c-mean (FCM) classifier which separated the fibroglandular tissues from other tissues in breast area. Finally, percent of breast density and breast volume were calculated and the results were compared with MRI. In addition, the percent of breast density and breast area of digital mammography calculated using the software Cumulus (University of Toronto, Toronto, ON, Canada.) were also compared with 3-D modalities.

RESULTS

Percent of breast density and breast volume, which were computed from tomosynthesis, MRI and digital mammography were 17.37% ± 4.39% and 607.12 cm³ ± 323.01 cm³, 20.3% ± 8.6% and 537.59 cm³ ± 287.74 cm³, and 12.03% ± 4.08%, respectively. There were significant correlations on breast density as well as volume between tomosynthesis and MRI (R = 0.482 and R = 0.805), tomosynthesis and breast density with breast area of digital mammography (R = 0.789 and R = 0.877), and MRI and breast density with breast area of digital mammography (R = 0.482 and R = 0.857) (all P values < .001).

CONCLUSIONS

Breast density and breast volume evaluated from tomosynthesis, MRI and breast density and breast area of digital mammographic images have significant correlations and indicate that tomosynthesis could provide useful 3-D information on breast density through proposed method.

Automatic outer and inner breast tissue segmentation using multi-parametric MRI images of breast tumor patients

The objectives of the study were to develop a framework for automatic outer and inner breast tissue segmentation using multi-parametric MRI images of the breast tumor patients; and to perform breast density and tumor tissue analysis. MRI of the breast was performed on 30 patients at 3T-MRI. T₁, T₂ and PD-weighted(W) images, with and without fat saturation(WWFS), and dynamic-contrast-enhanced(DCE)-MRI data were acquired. The proposed automatic segmentation approach was performed in two steps. In step-1, outer segmentation of breast tissue from rest of body parts was performed on structural images (T₂-W/T₁-W/PD-W without fat saturation images) using automatic landmarks detection technique based on operations like profile screening, Otsu thresholding, morphological operations and empirical observation. In step-2, inner segmentation of breast tissue into fibro-glandular(FG), fatty and tumor tissue was performed. For validation of breast tissue segmentation, manual segmentation was carried out by two radiologists and similarity coefficients(Dice and Jaccard) were computed for outer as well as inner tissues. FG density and tumor volume were also computed and analyzed. The proposed outer and inner segmentation approach worked well for all the subjects and was validated by two radiologists. The average Dice and Jaccard coefficients value for outer segmentation using T₂-W images, obtained by two radiologists, were 0.977 and 0.951 respectively. These coefficient values for FG tissue were 0.915 and 0.875 respectively whereas for tumor tissue, values were 0.968 and 0.95 respectively. The volume of segmented tumor ranged over 2.1 cm3–7.08 cm³. The proposed approach provided automatic outer and inner breast tissue segmentation, which enables automatic calculations of breast tissue density and tumor volume. This is a complete framework for outer and inner breast segmentation method for all structural images.

Breast density: why all the fuss?

The term "breast density" or mammographic density (MD) denotes those components of breast parenchyma visualised at mammography that are denser than adipose tissue. MD is composed of a mixture of epithelial and stromal components, notably collagen, in variable proportions. MD is most commonly assessed in clinical practice with the time-honoured method of visual estimation of area-based percent density (PMD) on a mammogram, with categorisation into quartiles. The computerised semi-automated thresholding method, Cumulus, also yielding area-based percent density, is widely used for research purposes; however, the advent of fully automated volumetric methods developed as a consequence of the widespread use of digital mammography (DM) and yielding both absolute and percent dense volumes, has resulted in an explosion of interest in MD recently. Broadly, the importance of MD is twofold: firstly, the presence of marked MD significantly reduces mammographic sensitivity for breast cancer, even with state-of-the-art DM. Recognition of this led to the formation of a powerful lobby group ('Are You Dense') in the US, as a consequence of which 32 states have legislated for mandatory disclosure of MD to women undergoing mammography. Secondly, it is now widely accepted that MD is in itself a risk factor for breast cancer, with a four-to sixfold increased relative risk in women with PMD in the highest quintile compared to those with PMD in the lowest quintile. Consequently, major research efforts are underway to assess whether use of MD could provide a major step forward towards risk-adapted, personalised breast cancer prevention, imaging, and treatment.

Breast MRI segmentation for density estimation: Do different methods give the same results and how much do differences matter?

PURPOSE

To compare two methods of automatic breast segmentation with each other and with manual segmentation in a large subject cohort. To discuss the factors involved in selecting the most appropriate algorithm for automatic segmentation and, in particular, to investigate the appropriateness of overlap measures (e.g., Dice and Jaccard coefficients) as the primary determinant in algorithm selection.

METHODS

Two methods of breast segmentation were applied to the task of calculating MRI breast density in 200 subjects drawn from the Avon Longitudinal Study of Parents and Children, a large cohort study with an MRI component. A semiautomated, bias-corrected, fuzzy C-means (BC-FCM) method was combined with morphological operations to segment the overall breast volume from in-phase Dixon images. The method makes use of novel, problem-specific insights. The resulting segmentation mask was then applied to the corresponding Dixon water and fat images, which were combined to give Dixon MRI density values. Contemporaneously acquired T1 - and T2 -weighted image datasets were analyzed using a novel and fully automated algorithm involving image filtering, landmark identification, and explicit location of the pectoral muscle boundary. Within the region found, fat-water discrimination was performed using an Expectation Maximization-Markov Random Field technique, yielding a second independent estimate of MRI density.

RESULTS

Images are presented for two individual women, demonstrating how the difficulty of the problem is highly subject-specific. Dice and Jaccard coefficients comparing the semiautomated BC-FCM method, operating on Dixon source data, with expert manual segmentation are presented. The corresponding results for the method based on T1 - and T2 -weighted data are slightly lower in the individual cases shown, but scatter plots and interclass correlations for the cohort as a whole show that both methods do an excellent job in segmenting and classifying breast tissue.

CONCLUSIONS

Epidemiological results demonstrate that both methods of automated segmentation are suitable for the chosen application and that it is important to consider a range of factors when choosing a segmentation algorithm, rather than focus narrowly on a single metric such as the Dice coefficient.

3D MRI for Quantitative Analysis of Quadrant Percent Breast Density: Correlation with Quadrant Location of Breast Cancer

RATIONALE AND OBJECTIVES

Breast cancer occurs more frequently in the upper outer (UO) quadrant, but whether this higher cancer incidence is related to the greater amount of dense tissue is not known. Magnetic resonance imaging acquires three-dimensional volumetric images and is the most suitable among all breast imaging modalities for regional quantification of density. This study applied a magnetic resonance imaging-based method to measure quadrant percent density (QPD), and evaluated its association with the quadrant location of the developed breast cancer.

MATERIALS AND METHODS

A total of 126 cases with pathologically confirmed breast cancer were reviewed. Only women who had unilateral breast cancer located in a clear quadrant were selected for analysis. A total of 84 women, including 47 Asian women and 37 western women, were included. An established computer-aided method was used to segment the diseased breast and the contralateral normal breast, and to separate the dense and fatty tissues. Then, a breast was further separated into four quadrants using the nipple and the centroid as anatomic landmarks. The tumor was segmented using a computer-aided method to determine its quadrant location. The distribution of cancer quadrant location, the quadrant with the highest QPD, and the proportion of cancers occurring in the highest QPD were analyzed.

RESULTS

The highest incidence of cancer occurred in the UO quadrant (36 out of 84, 42.9%). The highest QPD was also noted most frequently in the UO quadrant (31 out of 84, 36.9%). When correlating the highest QPD with the quadrant location of breast cancer, only 17 women out of 84 (20.2%) had breast cancer occurring in the quadrant with the highest QPD.

CONCLUSIONS

The results showed that the development of breast cancer in a specific quadrant could not be explained by the density in that quadrant, and further studies are needed to find the biological reasons accounting for the higher breast cancer incidence in the UO quadrant.

Does breast MRI background parenchymal enhancement indicate metabolic activity? Qualitative and 3D quantitative computer imaging analysis

PURPOSE

To investigate whether the degree of breast magnetic resonance imaging (MRI) background parenchymal enhancement (BPE) is associated with the amount of breast metabolic activity measured by breast parenchymal uptake (BPU) of 18F-FDG on positron emission tomography / computed tomography (PET/CT).

MATERIALS AND METHODS

An Institutional Review Board (IRB)-approved retrospective study was performed. Of 327 patients who underwent preoperative breast MRI from 1/1/12 to 12/31/15, 73 patients had 18F-FDG PET/CT evaluation performed within 1 week of breast MRI and no suspicious findings in the contralateral breast. MRI was performed on a 1.5T or 3.0T system. The imaging sequence included a triplane localizing sequence followed by sagittal fat-suppressed T₂ -weighted sequence, and a bilateral sagittal T₁ -weighted fat-suppressed fast spoiled gradient-echo sequence, which was performed before and three times after a rapid bolus injection (gadobenate dimeglumine, Multihance; Bracco Imaging; 0.1 mmol/kg) delivered through an IV catheter. The unaffected contralateral breast in these 73 patients underwent BPE and BPU assessments. For PET/CT BPU calculation, a 3D region of interest (ROI) was drawn around the glandular breast tissue and the maximum standardized uptake value (SUV_max ) was determined. Qualitative MRI BPE assessments were performed on a 4-point scale, in accordance with BI-RADS categories. Additional 3D quantitative MRI BPE analysis was performed using a previously published in-house technique. Spearman's correlation test and linear regression analysis was performed (SPSS, v. 24).

RESULT

The median time interval between breast MRI and 18F-FDG PET/CT evaluation was 3 days (range, 0-6 days). BPU SUV_max mean value was 1.6 (SD, 0.53). Minimum and maximum BPU SUV_max values were 0.71 and 4.0. The BPU SUV_max values significantly correlated with both the qualitative and quantitative measurements of BPE, respectively (r(71) = 0.59, P < 0.001 and r(71) = 0.54, P < 0.001). Qualitatively assessed high BPE group (BI-RADS 3/4) had significantly higher BPU SUV_max of 1.9 (SD = 0.44) compared to low BPE group (BI-RADS 1/2) with an average BPU SUV_max of 1.17 (SD = 0.32) (P < 0.001). On linear regression analysis, BPU SUV_max significantly predicted qualitative and quantitative measurements of BPE (β = 1.29, t(71) = 3.88, P < 0.001 and β = 19.52, t(71) = 3.88, P < 0.001).

CONCLUSION

There is a significant association between breast BPU and BPE, measured both qualitatively and quantitatively. Increased breast cancer risk in patients with high MRI BPE could be due to elevated basal metabolic activity of the normal breast tissue, which may provide a susceptible environment for tumor growth.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:753-759.

Sample size and power determination when limited preliminary information is available

Background

We describe a novel strategy for power and sample size determination developed for studies utilizing investigational technologies with limited available preliminary data, specifically of imaging biomarkers. We evaluated diffuse optical spectroscopic imaging (DOSI), an experimental noninvasive imaging technique that may be capable of assessing changes in mammographic density. Because there is significant evidence that tamoxifen treatment is more effective at reducing breast cancer risk when accompanied by a reduction of breast density, we designed a study to assess the changes from baseline in DOSI imaging biomarkers that may reflect fluctuations in breast density in premenopausal women receiving tamoxifen.

Method

While preliminary data demonstrate that DOSI is sensitive to mammographic density in women about to receive neoadjuvant chemotherapy for breast cancer, there is no information on DOSI in tamoxifen treatment. Since the relationship between magnetic resonance imaging (MRI) and DOSI has been established in previous studies, we developed a statistical simulation approach utilizing information from an investigation of MRI assessment of breast density in 16 women before and after treatment with tamoxifen to estimate the changes in DOSI biomarkers due to tamoxifen.

Results

Three sets of 10,000 pairs of MRI breast density data with correlation coefficients of 0.5, 0.8 and 0.9 were simulated and generated and were used to simulate and generate a corresponding 5,000,000 pairs of DOSI values representing water, ctHHB, and lipid. Minimum sample sizes needed per group for specified clinically-relevant effect sizes were obtained.

Conclusion

The simulation techniques we describe can be applied in studies of other experimental technologies to obtain the important preliminary data to inform the power and sample size calculations.

Electronic supplementary material

The online version of this article (doi:10.1186/s12874-017-0329-1) contains supplementary material, which is available to authorized users.

Generation of anatomically realistic numerical phantoms for photoacoustic and ultrasonic breast imaging

Photoacoustic computed tomography (PACT) and ultrasound computed tomography (USCT) are emerging modalities for breast imaging. As in all emerging imaging technologies, computer-simulation studies play a critically important role in developing and optimizing the designs of hardware and image reconstruction methods for PACT and USCT. Using computer-simulations, the parameters of an imaging system can be systematically and comprehensively explored in a way that is generally not possible through experimentation. When conducting such studies, numerical phantoms are employed to represent the physical properties of the patient or object to-be-imaged that influence the measured image data. It is highly desirable to utilize numerical phantoms that are realistic, especially when task-based measures of image quality are to be utilized to guide system design. However, most reported computer-simulation studies of PACT and USCT breast imaging employ simple numerical phantoms that oversimplify the complex anatomical structures in the human female breast. We develop and implement a methodology for generating anatomically realistic numerical breast phantoms from clinical contrast-enhanced magnetic resonance imaging data. The phantoms will depict vascular structures and the volumetric distribution of different tissue types in the breast. By assigning optical and acoustic parameters to different tissue structures, both optical and acoustic breast phantoms will be established for use in PACT and USCT studies.

Using deep learning to segment breast and fibroglandular tissue in MRI volumes

PURPOSE

Automated segmentation of breast and fibroglandular tissue (FGT) is required for various computer-aided applications of breast MRI. Traditional image analysis and computer vision techniques, such atlas, template matching, or, edge and surface detection, have been applied to solve this task. However, applicability of these methods is usually limited by the characteristics of the images used in the study datasets, while breast MRI varies with respect to the different MRI protocols used, in addition to the variability in breast shapes. All this variability, in addition to various MRI artifacts, makes it a challenging task to develop a robust breast and FGT segmentation method using traditional approaches. Therefore, in this study, we investigated the use of a deep-learning approach known as "U-net."

MATERIALS AND METHODS

We used a dataset of 66 breast MRI's randomly selected from our scientific archive, which includes five different MRI acquisition protocols and breasts from four breast density categories in a balanced distribution. To prepare reference segmentations, we manually segmented breast and FGT for all images using an in-house developed workstation. We experimented with the application of U-net in two different ways for breast and FGT segmentation. In the first method, following the same pipeline used in traditional approaches, we trained two consecutive (2C) U-nets: first for segmenting the breast in the whole MRI volume and the second for segmenting FGT inside the segmented breast. In the second method, we used a single 3-class (3C) U-net, which performs both tasks simultaneously by segmenting the volume into three regions: nonbreast, fat inside the breast, and FGT inside the breast. For comparison, we applied two existing and published methods to our dataset: an atlas-based method and a sheetness-based method. We used Dice Similarity Coefficient (DSC) to measure the performances of the automated methods, with respect to the manual segmentations. Additionally, we computed Pearson's correlation between the breast density values computed based on manual and automated segmentations.

RESULTS

The average DSC values for breast segmentation were 0.933, 0.944, 0.863, and 0.848 obtained from 3C U-net, 2C U-nets, atlas-based method, and sheetness-based method, respectively. The average DSC values for FGT segmentation obtained from 3C U-net, 2C U-nets, and atlas-based methods were 0.850, 0.811, and 0.671, respectively. The correlation between breast density values based on 3C U-net and manual segmentations was 0.974. This value was significantly higher than 0.957 as obtained from 2C U-nets (P < 0.0001, Steiger's Z-test with Bonferoni correction) and 0.938 as obtained from atlas-based method (P = 0.0016).

CONCLUSIONS

In conclusion, we applied a deep-learning method, U-net, for segmenting breast and FGT in MRI in a dataset that includes a variety of MRI protocols and breast densities. Our results showed that U-net-based methods significantly outperformed the existing algorithms and resulted in significantly more accurate breast density computation.

Impact of Different Analytic Approaches on the Analysis of the Breast Fibroglandular Tissue Using Diffusion Weighted Imaging

Purpose. This study investigated the impact of the different region of interest (ROI) approaches on measurement of apparent diffusion coefficient (ADC) values in the breast firbroglandular tissue (FT). Methods. Breast MR images of 38 women diagnosed with unilateral breast cancer were studied. Percent density (PD) and ADC were measured from the contralateral normal breast. Four different ROIs were used for ADC measurement. The measured PD and ADC were correlated. Results. Among the four ROIs, the manually placed small ROI on FT gave the highest mean ADC (ADC = 1839 ± 343 [×10⁻⁶ mm²/s]), while measurement from the whole breast gave the lowest mean ADC (ADC = 933 ± 383 [×10⁻⁶ mm²/s]). The ADC measured from the whole breast was highly correlated with PD with r = 0.95. In slice-to-slice comparison, the central slices with more FT had higher ADC values than the peripheral slices did, presumably due to less partial volume effect from fat. Conclusions. Our results indicated that the measured ADC heavily depends on the composition of breast tissue contained in the ROI used for the ADC measurements. Women with low breast density showing lower ADC values were most likely due to the partial volume effect of fatty tissues.

Localized-atlas-based segmentation of breast MRI in a decision-making framework

Breast-region segmentation is an important step for density estimation and Computer-Aided Diagnosis (CAD) systems in Magnetic Resonance Imaging (MRI). Detection of breast-chest wall boundary is often a difficult task due to similarity between gray-level values of fibroglandular tissue and pectoral muscle. This paper proposes a robust breast-region segmentation method which is applicable for both complex cases with fibroglandular tissue connected to the pectoral muscle, and simple cases with high contrast boundaries. We present a decision-making framework based on geometric features and support vector machine (SVM) to classify breasts in two main groups, complex and simple. For complex cases, breast segmentation is done using a combination of intensity-based and atlas-based techniques; however, only intensity-based operation is employed for simple cases. A novel atlas-based method, that is called localized-atlas, accomplishes the processes of atlas construction and registration based on the region of interest (ROI). Atlas-based segmentation is performed by relying on the chest wall template. Our approach is validated using a dataset of 210 cases. Based on similarity between automatic and manual segmentation results, the proposed method achieves Dice similarity coefficient, Jaccard coefficient, total overlap, false negative, and false positive values of 96.3, 92.9, 97.4, 2.61 and 4.77%, respectively. The localization error of the breast-chest wall boundary is 1.97 mm, in terms of averaged deviation distance. The achieved results prove that the suggested framework performs the breast segmentation with negligible errors and efficient computational time for different breasts from the viewpoints of size, shape, and density pattern.

Breast density estimation from high spectral and spatial resolution MRI

A three-dimensional breast density estimation method is presented for high spectral and spatial resolution (HiSS) MR imaging. Twenty-two patients were recruited (under an Institutional Review Board--approved Health Insurance Portability and Accountability Act-compliant protocol) for high-risk breast cancer screening. Each patient received standard-of-care clinical digital x-ray mammograms and MR scans, as well as HiSS scans. The algorithm for breast density estimation includes breast mask generating, breast skin removal, and breast percentage density calculation. The inter- and intra-user variabilities of the HiSS-based density estimation were determined using correlation analysis and limits of agreement. Correlation analysis was also performed between the HiSS-based density estimation and radiologists' breast imaging-reporting and data system (BI-RADS) density ratings. A correlation coefficient of 0.91 ([Formula: see text]) was obtained between left and right breast density estimations. An interclass correlation coefficient of 0.99 ([Formula: see text]) indicated high reliability for the inter-user variability of the HiSS-based breast density estimations. A moderate correlation coefficient of 0.55 ([Formula: see text]) was observed between HiSS-based breast density estimations and radiologists' BI-RADS. In summary, an objective density estimation method using HiSS spectral data from breast MRI was developed. The high reproducibility with low inter- and low intra-user variabilities shown in this preliminary study suggest that such a HiSS-based density metric may be potentially beneficial in programs requiring breast density such as in breast cancer risk assessment and monitoring effects of therapy.

A computerized volumetric segmentation method applicable to multi-centre MRI data to support computer-aided breast tissue analysis, density assessment and lesion localization

Density assessment and lesion localization in breast MRI require accurate segmentation of breast tissues. A fast, computerized algorithm for volumetric breast segmentation, suitable for multi-centre data, has been developed, employing 3D bias-corrected fuzzy c-means clustering and morphological operations. The full breast extent is determined on T1-weighted images without prior information concerning breast anatomy. Left and right breasts are identified separately using automatic detection of the midsternum. Statistical analysis of breast volumes from eighty-two women scanned in a UK multi-centre study of MRI screening shows that the segmentation algorithm performs well when compared with manually corrected segmentation, with high relative overlap (RO), high true-positive volume fraction (TPVF) and low false-positive volume fraction (FPVF), and has an overall performance of RO 0.94 ± 0.05, TPVF 0.97 ± 0.03 and FPVF 0.04 ± 0.06, respectively (training: 0.93 ± 0.05, 0.97 ± 0.03 and 0.04 ± 0.06; test: 0.94 ± 0.05, 0.98 ± 0.02 and 0.05 ± 0.07).

Opportunistic Breast Density Assessment in Women Receiving Low-dose Chest Computed Tomography Screening

RATIONALE AND OBJECTIVES

Low-dose chest computed tomography (LDCT), increasingly being used for screening of lung cancer, may also be used to measure breast density, which is proven as a risk factor for breast cancer. In this study, we developed a segmentation method to measure quantitative breast density on CT images and correlated with magnetic resonance density.

MATERIALS AND METHODS

Forty healthy women receiving both LDCT and breast magnetic resonance imaging (MRI) were studied. A semiautomatic method was applied to quantify the breast density on LDCT images. The intra- and interoperator reproducibility was evaluated. The volumetric density on MRI was obtained by using a well-established automatic template-based segmentation method. The breast volume (BV), fibroglandular tissue volume (FV), and percent breast density (PD) measured on LDCT and MRI were compared.

RESULTS

The measurements of BV, FV, and PD on LDCT images yield highly consistent results, with the intraclass correlation coefficient of 0.999 for BV, 0.977 for FV, and 0.966 for PD for intraoperator reproducibility, and intraclass correlation coefficient of 0.953 for BV, 0.974 for FV, and 0.973 for PD for interoperator reproducibility. The BV, FV, and PD measured on LDCT and MRI were well correlated (all r ≥ 0.90). Bland-Altman plots showed that a larger BV and FV were measured on LDCT than on MRI.

CONCLUSIONS

The preliminary results showed that quantitative breast density can be measured from LDCT, and that our segmentation method could yield a high reproducibility on the measured volume and PD. The results measured on LDCT and MRI were highly correlated. Our results showed that LDCT may provide valuable information about breast density for evaluating breast cancer risk.

Breast Density Analysis with Automated Whole-Breast Ultrasound: Comparison with 3-D Magnetic Resonance Imaging

In this study, a semi-automatic breast segmentation method was proposed on the basis of the rib shadow to extract breast regions from 3-D automated whole-breast ultrasound (ABUS) images. The density results were correlated with breast density values acquired with 3-D magnetic resonance imaging (MRI). MRI images of 46 breasts were collected from 23 women without a history of breast disease. Each subject also underwent ABUS. We used Otsu's thresholding method on ABUS images to obtain local rib shadow information, which was combined with the global rib shadow information (extracted from all slice projections) and integrated with the anatomy's breast tissue structure to determine the chest wall line. The fuzzy C-means classifier was used to extract the fibroglandular tissues from the acquired images. Whole-breast volume (WBV) and breast percentage density (BPD) were calculated in both modalities. Linear regression was used to compute the correlation of density results between the two modalities. The consistency of density measurement was also analyzed on the basis of intra- and inter-operator variation. There was a high correlation of density results between MRI and ABUS (R(2) = 0.798 for WBV, R(2) = 0.825 for PBD). The mean WBV from ABUS images was slightly smaller than the mean WBV from MR images (MRI: 342.24 ± 128.08 cm(3), ABUS: 325.47 ± 136.16 cm(3), p < 0.05). In addition, the BPD calculated from MR images was smaller than the BPD from ABUS images (MRI: 24.71 ± 15.16%, ABUS: 28.90 ± 17.73%, p < 0.05). The intra-operator and inter-operator variant analysis results indicated that there was no statistically significant difference in breast density measurement variation between the two modalities. Our results revealed a high correlation in WBV and BPD between MRI and ABUS. Our study suggests that ABUS provides breast density information useful in the assessment of breast health.

Inter- and intra-observer agreement of BI-RADS-based subjective visual estimation of amount of fibroglandular breast tissue with magnetic resonance imaging: comparison to automated quantitative assessment

Purpose

To evaluate the inter-/intra-observer agreement of BI-RADS-based subjective visual estimation of the amount of fibroglandular tissue (FGT) with magnetic resonance imaging (MRI), and to investigate whether FGT assessment benefits from an automated, observer-independent, quantitative MRI measurement by comparing both approaches.

Materials and methods

Eighty women with no imaging abnormalities (BI-RADS 1 and 2) were included in this institutional review board (IRB)-approved prospective study. All women underwent un-enhanced breast MRI. Four radiologists independently assessed FGT with MRI by subjective visual estimation according to BI-RADS. Automated observer-independent quantitative measurement of FGT with MRI was performed using a previously described measurement system. Inter-/intra-observer agreements of qualitative and quantitative FGT measurements were assessed using Cohen’s kappa (k).

Results

Inexperienced readers achieved moderate inter-/intra-observer agreement and experienced readers a substantial inter- and perfect intra-observer agreement for subjective visual estimation of FGT. Practice and experience reduced observer-dependency. Automated observer-independent quantitative measurement of FGT was successfully performed and revealed only fair to moderate agreement (k = 0.209–0.497) with subjective visual estimations of FGT.

Conclusion

Subjective visual estimation of FGT with MRI shows moderate intra-/inter-observer agreement, which can be improved by practice and experience. Automated observer-independent quantitative measurements of FGT are necessary to allow a standardized risk evaluation.

Key Points

• Subjective FGT estimation with MRI shows moderate intra-/inter-observer agreement in inexperienced readers.

• Inter-observer agreement can be improved by practice and experience.

• Automated observer-independent quantitative measurements can provide reliable and standardized assessment of FGT with MRI.

Does breast composition influence late adverse effects in breast radiotherapy?

BACKGROUND

Large breast size is associated with increased risk of late adverse effects after surgery and radiotherapy for early breast cancer. It is hypothesised that effects of radiotherapy on adipose tissue are responsible for some of the effects seen. In this study, the association of breast composition with late effects was investigated along with other breast features such as fibroglandular tissue distribution, seroma and scar.

METHODS

The patient dataset comprised of 18 cases with changes in breast appearance at 2 years follow-up post-radiotherapy and 36 controls with no changes, from patients entered into the FAST-Pilot and UK FAST trials at The Royal Marsden. Breast composition, fibroglandular tissue distribution, seroma and scar were assessed on planning CT scan images and compared using univariate analysis. The association of all features with late-adverse effect was tested using logistic regression (adjusting for confounding factors) and matched analysis was performed using conditional logistic regression.

RESULTS

In univariate analyses, no statistically significant differences were found between cases and controls in terms of breast features studied. A statistically significant association (p < 0.05) between amount of seroma and change in photographic breast appearance was found in unmatched and matched logistic regression analyses with odds ratio (95% CI) of 3.44 (1.28-9.21) and 2.57 (1.05-6.25), respectively.

CONCLUSIONS

A significant association was found between seroma and late-adverse effects after radiotherapy although no significant associations were noted with breast composition in this study. Therefore, the cause for large breast size as a risk factor for late effects after surgery and optimally planned radiotherapy remains unresolved.

Comparison of Dixon Sequences for Estimation of Percent Breast Fibroglandular Tissue

OBJECTIVES

To evaluate sources of error in the Magnetic Resonance Imaging (MRI) measurement of percent fibroglandular tissue (%FGT) using two-point Dixon sequences for fat-water separation.

METHODS

Ten female volunteers (median age: 31 yrs, range: 23-50 yrs) gave informed consent following Research Ethics Committee approval. Each volunteer was scanned twice following repositioning to enable an estimation of measurement repeatability from high-resolution gradient-echo (GRE) proton-density (PD)-weighted Dixon sequences. Differences in measures of %FGT attributable to resolution, T1 weighting and sequence type were assessed by comparison of this Dixon sequence with low-resolution GRE PD-weighted Dixon data, and against gradient-echo (GRE) or spin-echo (SE) based T1-weighted Dixon datasets, respectively.

RESULTS

%FGT measurement from high-resolution PD-weighted Dixon sequences had a coefficient of repeatability of ±4.3%. There was no significant difference in %FGT between high-resolution and low-resolution PD-weighted data. Values of %FGT from GRE and SE T1-weighted data were strongly correlated with that derived from PD-weighted data (r = 0.995 and 0.96, respectively). However, both sequences exhibited higher mean %FGT by 2.9% (p < 0.0001) and 12.6% (p < 0.0001), respectively, in comparison with PD-weighted data; the increase in %FGT from the SE T1-weighted sequence was significantly larger at lower breast densities.

CONCLUSION

Although measurement of %FGT at low resolution is feasible, T1 weighting and sequence type impact on the accuracy of Dixon-based %FGT measurements; Dixon MRI protocols for %FGT measurement should be carefully considered, particularly for longitudinal or multi-centre studies.

Impact of positional difference on the measurement of breast density using MRI

PURPOSE

This study investigated the impact of arms/hands and body position on the measurement of breast density using MRI.

METHODS

Noncontrast-enhanced T1-weighted images were acquired from 32 healthy women. Each subject received four MR scans using different experimental settings, including a high resolution hands-up, a low resolution hands-up, a high resolution hands-down, and finally, another high resolution hands-up after repositioning. The breast segmentation was performed using a fully automatic chest template-based method. The breast volume (BV), fibroglandular tissue volume (FV), and percent density (PD) measured from the four MR scan settings were analyzed.

RESULTS

A high correlation of BV, FV, and PD between any pair of the four MR scans was noted (r > 0.98 for all). Using the generalized estimating equation method, a statistically significant difference in mean BV among four settings was noted (left breast, score test p = 0.0056; right breast, score test p = 0.0016), adjusted for age and body mass index. Despite differences in BV, there were no statistically significant differences in the mean PDs among the four settings (p > 0.10 for left and right breasts). Using Bland-Altman plots, the smallest mean difference/bias and standard deviations for BV, FV, and PD were noted when comparing hands-up high vs low resolution when the breast positions were exactly the same.

CONCLUSIONS

The authors' study showed that BV, FV, and PD measurements from MRI of different positions were highly correlated. BV may vary with positions but the measured PD did not differ significantly between positions. The study suggested that the percent density analyzed from MRI studies acquired using different arms/hands and body positions from multiple centers can be combined for analysis.