Principal component analysis of breast DCE-MRI adjusted with a model-based method

Background parenchymal enhancement and uptake as breast cancer imaging biomarkers: A state-of-the-art review

Within the past decade, background parenchymal enhancement (BPE) and background parenchymal uptake (BPU) have emerged as novel imaging-derived biomarkers in the diagnosis and treatment monitoring of breast cancer. Growing evidence supports the role of breast parenchyma vascularity and metabolic activity as probable risk factors for breast cancer development. Furthermore, in the presence of a newly-diagnosed breast cancer, added clinically-relevant data was surprisingly found in the respective imaging properties of the non-affected contralateral breast. Evaluation of the contralateral BPE and BPU have been found to be especially instrumental in predicting the prognosis of a patient with breast cancer and even anticipating their response to neoadjuvant chemotherapy. Simultaneously, further research has found a link between these two biomarkers, even though they represent different physical properties. The aim of this review is to provide an up to date summary of the current clinical applications of BPE and BPU as breast cancer imaging biomarkers with the hope that it propels their further usage in clinical practice.

Image quality of the CAIPIRINHA-Dixon-TWIST-VIBE technique for ultra-fast breast DCE-MRI: Comparison with the conventional GRE technique

PURPOSE

The aim of this study was to evaluate image quality of the CAIPIRINHA-Dixon-TWIST-Volume-Interpolated Breath-hold Examination (CDT-VIBE) technique for ultra-fast breast dynamic contrast enhanced (DCE) MRI with respect to conventional Gradient-Recalled Echo (GRE) technique.

METHODS

A total of 58 patients underwent a DCE-MRI based on CDT-VIBE sequence (temporal resolution: 11.9 s), immediately followed by 1 phase of a conventional T1 weighted GRE sequence (acquisition time: 68 s). The Signal-to-Noise Ratio (SNR) on phantom images, lesion/parenchyma signal ratio (LPSR), image quality, and morphological characterization were compared between the last phase of CDT-VIBE and conventional GRE images. The image quality was assessed by visual grading analysis (VGA). Reader agreement was assessed using Kappa analysis.

RESULTS

There was no significant difference in SNR (phantom) or LPSR (patient) between CDT-VIBE and conventional GRE images (P > 0.05). Significant parallel acquisition technique (PAT) noise and mild blurriness was observed on CDT-VIBE images. Visual grading analysis (VGA) confirmed significantly worse ratings for CDT-VIBE compared to the conventional GRE sequence in terms of PAT noise, lesion's internal feature clarity, and therefore overall image quality (area under contrast curve [AUC] values: 0.578 ‒ 0.764, P < 0.05), but edge sharpness and lesion conspicuity were equivalent (P > 0.05). Kappa analysis revealed good agreement on image quality scores (к = 0.725 ‒ 0.908) and on morphologic terms (к = 0.745-1.000).

CONCLUSION

The CDT-VIBE sequence provides excellent spatial resolution and adequate image quality in ultra-fast breast DCE-MRI. Further improvement in PAT noise and internal structure blurriness may be necessary.

Decision support system for breast lesions via dynamic contrast enhanced magnetic resonance imaging

The presented study aims to design a computer-aided detection and diagnosis system for breast dynamic contrast enhanced magnetic resonance imaging. In the proposed system, the segmentation task is performed in two stages. The first stage is called breast region segmentation in which adaptive noise filtering, local adaptive thresholding, connected component analysis, integral of horizontal projection, and breast region of interest detection algorithms are applied to the breast images consecutively. The second stage of segmentation is breast lesion detection that consists of 32-class Otsu thresholding and Markov random field techniques. Histogram, gray level co-occurrence matrix and neighboring gray tone difference matrix based feature extraction, Fisher score based feature selection and, tenfold and leave-one-out cross-validation steps are carried out after segmentation to increase the reliability of the designed system while decreasing the computational time. Finally, support vector machines, k- nearest neighbor, and artificial neural network classifiers are performed to separate the breast lesions as benign and malignant. The average accuracy, sensitivity, specificity, and positive predictive values of each classifier are calculated and the best results are compared with the existing similar studies. According to the achieved results, the proposed decision support system for breast lesion segmentation distinguishes the breast lesions with 86%, 100%, 67%, and 85% accuracy, sensitivity, specificity, and positive predictive values, respectively. These results show that the proposed system can be used to support the radiologists during a breast cancer diagnosis.

Fully Automated Convolutional Neural Network Method for Quantification of Breast MRI Fibroglandular Tissue and Background Parenchymal Enhancement

The aim of this study is to develop a fully automated convolutional neural network (CNN) method for quantification of breast MRI fibroglandular tissue (FGT) and background parenchymal enhancement (BPE). An institutional review board-approved retrospective study evaluated 1114 breast volumes in 137 patients using T1 precontrast, T1 postcontrast, and T1 subtraction images. First, using our previously published method of quantification, we manually segmented and calculated the amount of FGT and BPE to establish ground truth parameters. Then, a novel 3D CNN modified from the standard 2D U-Net architecture was developed and implemented for voxel-wise prediction whole breast and FGT margins. In the collapsing arm of the network, a series of 3D convolutional filters of size 3 × 3 × 3 are applied for standard CNN hierarchical feature extraction. To reduce feature map dimensionality, a 3 × 3 × 3 convolutional filter with stride 2 in all directions is applied; a total of 4 such operations are used. In the expanding arm of the network, a series of convolutional transpose filters of size 3 × 3 × 3 are used to up-sample each intermediate layer. To synthesize features at multiple resolutions, connections are introduced between the collapsing and expanding arms of the network. L2 regularization was implemented to prevent over-fitting. Cases were separated into training (80%) and test sets (20%). Fivefold cross-validation was performed. Software code was written in Python using the TensorFlow module on a Linux workstation with NVIDIA GTX Titan X GPU. In the test set, the fully automated CNN method for quantifying the amount of FGT yielded accuracy of 0.813 (cross-validation Dice score coefficient) and Pearson correlation of 0.975. For quantifying the amount of BPE, the CNN method yielded accuracy of 0.829 and Pearson correlation of 0.955. Our CNN network was able to quantify FGT and BPE within an average of 0.42 s per MRI case. A fully automated CNN method can be utilized to quantify MRI FGT and BPE. Larger dataset will likely improve our model.

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.

Automated Detection and Segmentation of Nonmass-Enhancing Breast Tumors with Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Nonmass-enhancing (NME) lesions constitute a diagnostic challenge in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast. Computer-aided diagnosis (CAD) systems provide physicians with advanced tools for analysis, assessment, and evaluation that have a significant impact on the diagnostic performance. Here, we propose a new approach to address the challenge of NME lesion detection and segmentation, taking advantage of independent component analysis (ICA) to extract data-driven dynamic lesion characterizations. A set of independent sources was obtained from the DCE-MRI dataset of breast cancer patients, and the dynamic behavior of the different tissues was described by multiple dynamic curves, together with a set of eigenimages describing the scores for each voxel. A new test image is projected onto the independent source space using the unmixing matrix, and each voxel is classified by a support vector machine (SVM) that has already been trained with manually delineated data. A solution to the high false-positive rate problem is proposed by controlling the SVM hyperplane location, outperforming previously published approaches.

Texture features and pharmacokinetic parameters in differentiating benign and malignant breast lesions by dynamic contrast enhanced magnetic resonance imaging

Dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) has become a powerful tool for the diagnosis of breast cancer in the clinical setting due to its high sensitivity and specificity. Pharmacokinetic parameters, including Ktrans and area under the curve (AUC), and texture features derived from DCE-MRI have been used to specify the characteristics inside tumors. In the present study, 56 patients (average age 45.3±11.1; range 25-69 years) with histopathologically proved breast tumors were analyzed using the pharmacokinetic parameters and texture features. Malignant tumors displayed higher Ktrans and AUC values than the benign, Ktrans exhibited a significantly difference between the malignant and benign tumors (P=0.001) compared with the AUC values (P=0.029); texture features from DCE-MRI images and pharmacokinetic parameter maps also showed a good diagnostic ability. Alongside the routine method, principal components analysis (PCA) and Fisher discriminant analysis (FDA) were employed on these texture features to differentiate the breast lesions automatically. The Factor-1 scores of PCA were used to divide the patients into two groups, and the diagnosing accuracies of the FDA method on the texture features from DCE-MRI images, Ktrans maps, AUC maps were 93, 98 and 98%, with a cross validation accuracies of 82, 77 and 77%, respectively. To conclude, pharmacokinetic parameters, texture features and the combined computer-assisted classification method were discussed. All method involved in this study may be a potential assisted tool for radiological analysis on breast.

Perspectives: MRI of angiogenesis

Angiogenesis, the expansion of the vascular bed, is an important component in remodeling of tissues and organs. Such remodeling is essential for coping with substantial and sustained increase in the demands for supply of oxygen and nutrients and the timely removal of waste products. The vasculature, and its effectiveness in systemic delivery to all parts of the body, regulates the distribution of immune cells and the delivery of therapeutics as well as the dissemination of disease. Therefore, the vascular bed is possibly one of the key organs involved in homeostasis, in health and disease. The critical role of the vasculature in health, and the accessibility to non invasive probing by MRI, renders MRI as a modality of choice for monitoring the vasculature and its adaption to challenges.

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.

Temporal Feature Extraction from DCE-MRI to Identify Poorly Perfused Subvolumes of Tumors Related to Outcomes of Radiation Therapy in Head and Neck Cancer

This study aimed to develop an automated model to extract temporal features from DCE-MRI in head-and-neck (HN) cancers to localize significant tumor subvolumes having low blood volume (LBV) for predicting local and regional failure after chemoradiation therapy. Temporal features were extracted from time-intensity curves to build classification model for differentiating voxels with LBV from those with high BV. Support vector machine (SVM) classification was trained on the extracted features for voxel classification. Subvolumes with LBV were then assembled from the classified voxels with LBV. The model was trained and validated on independent datasets created from 456 873 DCE curves. The resultant subvolumes were compared to ones derived by a 2-step method via pharmacokinetic modeling of blood volume, and evaluated for classification accuracy and volumetric similarity by DSC. The proposed model achieved an average voxel-level classification accuracy and DSC of 82% and 0.72, respectively. Also, the model showed tolerance on different acquisition parameters of DCE-MRI. The model could be directly used for outcome prediction and therapy assessment in radiation therapy of HN cancers, or even supporting boost target definition in adaptive clinical trials with further validation. The model is fully automatable, extendable, and scalable to extract temporal features of DCE-MRI in other tumors.

Assessment of Background Parenchymal Enhancement and Lesion Kinetics in Breast MRI of BRCA 1/2 Mutation Carriers Compared to Matched Controls Using Quantitative Kinetic Analysis

RATIONALE AND OBJECTIVES

To investigate whether quantitative kinetic analysis of lesions and background parenchyma in breast magnetic resonance imaging can elucidate differences between BRCA carriers and sporadic controls with high risk for breast cancer.

MATERIALS AND METHODS

Fifty-nine BRCA and 59 control cases (49 benign, 10 malignant) were examined in this study. Principal component analysis was applied for quantitative analysis of dynamic signal in background parenchyma (B) and lesion (L) in terms of initial enhancement ratio (IER) and delayed enhancement ratio (DER).

RESULTS

Control B-IER, B-DER, L-IER, and L-DER were higher than BRCA cases in all women and in women with benign lesions; statistically significant differences in B-IER and B-DER (all women: P = 0.02 and P = 0.02, respectively; benign only: P = 0.005 and P = 0.005, respectively). In the control cohort, B-IER and B-DER were higher in the premenopausal women than in the postmenopausal women (P = 0.013 and 0.003, respectively), but not in the BRCA cohort; this led to significant differences in B-IER and B-DER between the control and the BRCA groups in the premenopausal women (P = 0.01 and 0.01, respectively) but not in the postmenopausal women.

CONCLUSION

Results suggest possible differences in the vascular properties of background parenchyma between BRCA carriers and noncarriers and its association with menopausal status.

Three-Dimensional Quantitative Validation of Breast Magnetic Resonance Imaging Background Parenchymal Enhancement Assessments

The magnetic resonance imaging (MRI) background parenchymal enhancement (BPE) and its clinical significance as a biomarker of breast cancer risk has been proposed based on qualitative studies. Previous BPE quantification studies lack appropriate correlation with BPE qualitative assessments. The purpose of this study is to validate our three-dimensional BPE quantification method with standardized BPE qualitative cases. An Institutional Review Board-approved study reviewed 500 consecutive magnetic resonance imaging cases (from January 2013-December 2014) using a strict inclusion criteria and 120 cases that best represented each of the BPE qualitative categories (minimal or mild or moderate or marked) were selected. Blinded to the qualitative data, fibroglandular tissue contours of precontrast and postcontrast images were delineated using an in-house, proprietary segmentation algorithm. Metrics of BPE were calculated including %BPE ([ratio of BPE volume to fibroglandular tissue volume] × 100) at multiple threshold levels to determine the optimal cutoff point for BPE quantification that best correlated with the reference BPE qualitative cases. The highest positive correlation was present at ×1.5 precontrast average signal intensity threshold level (r = 0.84, P < 0.001). At this level, the BPE qualitative assessment of minimal, mild, moderate, and marked correlated with the mean quantitative %BPE of 14.1% (95% CI: 10.9-17.2), 26.1% (95% CI: 22.8-29.3), 45.9% (95% CI: 40.2-51.7), and 74.0% (95% CI: 68.6-79.5), respectively. A one-way analysis of variance with post-hoc analysis showed that at ×1.5 precontrast average signal intensity level, the quantitative %BPE measurements best differentiated the four reference BPE qualitative groups (F [3,117] = 106.8, P < 0.001). Our three-dimensional BPE quantification methodology was validated using the reference BPE qualitative cases and could become an invaluable clinical tool to more accurately assess breast cancer risk and to test chemoprevention strategies.

Heterogeneity in intratumoral regions with rapid gadolinium washout correlates with estrogen receptor status and nodal metastasis

PURPOSE

To evaluate heterogeneity within tumor subregions or "habitats" via textural kinetic analysis on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for the classification of two clinical prognostic features; 1) estrogen receptor (ER)-positive from ER-negative tumors, and 2) tumors with four or more viable lymph node metastases after neoadjuvant chemotherapy from tumors without nodal metastases.

MATERIALS AND METHODS

Two separate volumetric DCE-MRI datasets were obtained at 1.5T, comprised of bilateral axial dynamic 3D T1 -weighted fat suppressed gradient recalled echo-pulse sequences obtained before and after gadolinium-based contrast administration. Representative image slices of breast tumors from 38 and 34 patients were used for ER status and lymph node classification, respectively. Four tumor habitats were defined based on their kinetic contrast enhancement characteristics. The heterogeneity within each habitat was quantified using textural kinetic features, which were evaluated using two feature selectors and three classifiers.

RESULTS

Textural kinetic features from the habitat with rapid delayed washout yielded classification accuracies of 84.44% (area under the curve [AUC] 0.83) for ER and 88.89% (AUC 0.88) for lymph node status. The texture feature, information measure of correlation, most often chosen in cross-validations, measures heterogeneity and provides accuracy approximately the same as with the best feature set.

CONCLUSION

Heterogeneity within habitats with rapid washout is highly predictive of molecular tumor characteristics and clinical behavior.

DCE-MRI defined subvolumes of a brain metastatic lesion by principle component analysis and fuzzy-c-means clustering for response assessment of radiation therapy

PURPOSE

To develop a pharmacokinetic modelfree framework to analyze the dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) data for assessment of response of brain metastases to radiation therapy.

METHODS

Twenty patients with 45 analyzable brain metastases had MRI scans prior to whole brain radiation therapy (WBRT) and at the end of the 2-week therapy. The volumetric DCE images covering the whole brain were acquired on a 3T scanner with approximately 5 s temporal resolution and a total scan time of about 3 min. DCE curves from all voxels of the 45 brain metastases were normalized and then temporally aligned. A DCE matrix that is constructed from the aligned DCE curves of all voxels of the 45 lesions obtained prior to WBRT is processed by principal component analysis to generate the principal components (PCs). Then, the projection coefficient maps prior to and at the end of WBRT are created for each lesion. Next, a pattern recognition technique, based upon fuzzy-c-means clustering, is used to delineate the tumor subvolumes relating to the value of the significant projection coefficients. The relationship between changes in different tumor subvolumes and treatment response was evaluated to differentiate responsive from stable and progressive tumors. Performance of the PC-defined tumor subvolume was also evaluated by receiver operating characteristic (ROC) analysis in prediction of nonresponsive lesions and compared with physiological-defined tumor subvolumes.

RESULTS

The projection coefficient maps of the first three PCs contain almost all response-related information in DCE curves of brain metastases. The first projection coefficient, related to the area under DCE curves, is the major component to determine response while the third one has a complimentary role. In ROC analysis, the area under curve of 0.88 ± 0.05 and 0.86 ± 0.06 were achieved for the PC-defined and physiological-defined tumor subvolume in response assessment.

CONCLUSIONS

The PC-defined subvolume of a brain metastasis could predict tumor response to therapy similar to the physiological-defined one, while the former is determined more rapidly for clinical decision-making support.

A data-driven approach to prostate cancer detection from dynamic contrast enhanced MRI

Magnetic resonance imaging (MRI), particularly dynamic contrast enhanced (DCE) imaging, has shown great potential in prostate cancer diagnosis and staging. In the current practice of DCE-MRI, diagnosis is based on quantitative parameters extracted from the series of T1-weighted images acquired after the injection of a contrast agent. To calculate these parameters, a pharmacokinetic model is fitted to the T1-weighted intensities. Most models make simplistic assumptions about the perfusion process. Moreover, these models require accurate estimation of the arterial input function, which is challenging. In this work we propose a data-driven approach to characterization of the prostate tissue that uses the time series of DCE T1-weighted images without pharmacokinetic modeling. This approach uses a number of model-free empirical parameters and also the principal component analysis (PCA) of the normalized T1-weighted intensities, as features for cancer detection from DCE MRI. The optimal set of principal components is extracted with sparse regularized regression through least absolute shrinkage and selection operator (LASSO). A support vector machine classifier was used with leave-one-patient-out cross validation to determine the ability of this set of features in cancer detection. Our data is obtained from patients prior to radical prostatectomy and the results are validated based on histological evaluation of the extracted specimens. Our results, obtained on 449 tissue regions from 16 patients, show that the proposed data-driven features outperform the traditional pharmacokinetic parameters with an area under ROC of 0.86 for LASSO-isolated PCA parameters, compared to 0.78 for pharmacokinetic parameters. This shows that our novel approach to the analysis of DCE data has the potential to improve the multiparametric MRI protocol for prostate cancer detection.

Automatic segmentation of invasive breast carcinomas from dynamic contrast-enhanced MRI using time series analysis

PURPOSE

To accurately segment invasive ductal carcinomas (IDCs) from dynamic contrast-enhanced MRI (DCE-MRI) using time series analysis based on linear dynamic system (LDS) modeling.

MATERIALS AND METHODS

Quantitative segmentation methods based on black-box modeling and pharmacokinetic modeling are highly dependent on imaging pulse sequence, timing of bolus injection, arterial input function, imaging noise, and fitting algorithms. We modeled the underlying dynamics of the tumor by an LDS and used the system parameters to segment the carcinoma on the DCE-MRI. Twenty-four patients with biopsy-proven IDCs were analyzed. The lesions segmented by the algorithm were compared with an expert radiologist's segmentation and the output of a commercial software, CADstream. The results are quantified in terms of the accuracy and sensitivity of detecting the lesion and the amount of overlap, measured in terms of the Dice similarity coefficient (DSC).

RESULTS

The segmentation algorithm detected the tumor with 90% accuracy and 100% sensitivity when compared with the radiologist's segmentation and 82.1% accuracy and 100% sensitivity when compared with the CADstream output. The overlap of the algorithm output with the radiologist's segmentation and CADstream output, computed in terms of the DSC was 0.77 and 0.72, respectively. The algorithm also shows robust stability to imaging noise. Simulated imaging noise with zero mean and standard deviation equal to 25% of the base signal intensity was added to the DCE-MRI series. The amount of overlap between the tumor maps generated by the LDS-based algorithm from the noisy and original DCE-MRI was DSC = 0.95.

CONCLUSION

The time-series analysis based segmentation algorithm provides high accuracy and sensitivity in delineating the regions of enhanced perfusion corresponding to tumor from DCE-MRI.

Spectral embedding based active contour (SEAC) for lesion segmentation on breast dynamic contrast enhanced magnetic resonance imaging

PURPOSE

Segmentation of breast lesions on dynamic contrast enhanced (DCE) magnetic resonance imaging (MRI) is the first step in lesion diagnosis in a computer-aided diagnosis framework. Because manual segmentation of such lesions is both time consuming and highly susceptible to human error and issues of reproducibility, an automated lesion segmentation method is highly desirable. Traditional automated image segmentation methods such as boundary-based active contour (AC) models require a strong gradient at the lesion boundary. Even when region-based terms are introduced to an AC model, grayscale image intensities often do not allow for clear definition of foreground and background region statistics. Thus, there is a need to find alternative image representations that might provide (1) strong gradients at the margin of the object of interest (OOI); and (2) larger separation between intensity distributions and region statistics for the foreground and background, which are necessary to halt evolution of the AC model upon reaching the border of the OOI.

METHODS

In this paper, the authors introduce a spectral embedding (SE) based AC (SEAC) for lesion segmentation on breast DCE-MRI. SE, a nonlinear dimensionality reduction scheme, is applied to the DCE time series in a voxelwise fashion to reduce several time point images to a single parametric image where every voxel is characterized by the three dominant eigenvectors. This parametric eigenvector image (PrEIm) representation allows for better capture of image region statistics and stronger gradients for use with a hybrid AC model, which is driven by both boundary and region information. They compare SEAC to ACs that employ fuzzy c-means (FCM) and principal component analysis (PCA) as alternative image representations. Segmentation performance was evaluated by boundary and region metrics as well as comparing lesion classification using morphological features from SEAC, PCA+AC, and FCM+AC.

RESULTS

On a cohort of 50 breast DCE-MRI studies, PrEIm yielded overall better region and boundary-based statistics compared to the original DCE-MR image, FCM, and PCA based image representations. Additionally, SEAC outperformed a hybrid AC applied to both PCA and FCM image representations. Mean dice similarity coefficient (DSC) for SEAC was significantly better (DSC = 0.74 ± 0.21) than FCM+AC (DSC = 0.50 ± 0.32) and similar to PCA+AC (DSC = 0.73 ± 0.22). Boundary-based metrics of mean absolute difference and Hausdorff distance followed the same trends. Of the automated segmentation methods, breast lesion classification based on morphologic features derived from SEAC segmentation using a support vector machine classifier also performed better (AUC = 0.67 ± 0.05; p < 0.05) than FCM+AC (AUC = 0.50 ± 0.07), and PCA+AC (AUC = 0.49 ± 0.07).

CONCLUSIONS

In this work, we presented SEAC, an accurate, general purpose AC segmentation tool that could be applied to any imaging domain that employs time series data. SE allows for projection of time series data into a PrEIm representation so that every voxel is characterized by the dominant eigenvectors, capturing the global and local time-intensity curve similarities in the data. This PrEIm allows for the calculation of strong tensor gradients and better region statistics than the original image intensities or alternative image representations such as PCA and FCM. The PrEIm also allows for building a more accurate hybrid AC scheme.

Standardization of radiological evaluation of dynamic contrast enhanced MRI: application in breast cancer diagnosis

Dynamic contrast enhanced MRI is applied as an adjuvant tool for breast cancer detection, diagnosis, and follow-up of therapy. Despite improvements through the years in achieving higher spatial and temporal resolution, it still suffers from lack of scanning and processing standardization, and consequently, high variability in the radiological evaluation, particularly differentiating malignant from benign lesions. We describe here a hybrid method for achieving standardization of the radiological evaluation of breast dynamic contrast enhanced (DCE)-magnetic resonance imaging (MRI) protocols, based on integrating the model based three time point (3TP) method with principal component analysis (PCA). The scanning and image processing procedures consisted of three main steps: 1. 3TP standardization of the MRI acquisition parameters according to a kinetic model, 2. Applying PCA to test cases and constructing an eigenvectors' base related to the contrast-enhancement kinetics and 3. Projecting all new cases on the eigenvectors' base and evaluating the clinical outcome. Datasets of overall 96 malignant and 26 benign breast lesions were recorded on 1.5T and 3T scanners, using three different MRI acquisition parameters optimized by the 3TP method. The final radiological evaluation showed similar detection and diagnostic ability for the three different MRI acquisition parameters. The area under the curve of receiver operating characteristic analysis yielded a value of 0.88 ± 0.034 for differentiating malignant from benign lesions. This 3TP + PCA hybrid method is fast and can be readily applied as a computer aided diagnostic tool of breast cancer. The underlying principles of this method can be extended to standardize the evaluation of malignancies in other organs.

Characterization of estrogen-receptor-targeted contrast agents in solution, breast cancer cells, and tumors in vivo

The estrogen receptor (ER) is a major prognostic biomarker of breast cancer, currently determined in surgical specimens by immunohistochemistry. Two new ER-targeted probes, pyridine-tetra-acetate-Gd chelate (PTA-Gd) conjugated either to 17β-estradiol (EPTA-Gd) or to tamoxifen (TPTA-Gd), were explored as contrast agents for molecular imaging of ER. In solution, both probes exhibited a micromolar ER binding affinity, fast water exchange rate (∼10(7) s(-1)), and water proton-relaxivity of 4.7-6.8 mM(-1) s(-1). In human breast cancer cells, both probes acted as estrogen agonists and enhanced the water protons T1 relaxation rate and relaxivity in ER-positive as compared to ER-negative cells, with EPTA-Gd showing a higher ER-specific relaxivity than TPTA-Gd. In studies of breast cancer tumors in vivo, EPTA-Gd induced the highest enhancement in ER-positive tumors as compared to ER-negative tumors and muscle tissue, enabling in vivo detection of ER. TPTA-Gd demonstrated the highest enhancement in muscle tissue indicating nonspecific interaction of this agent with muscle components. The extracellular contrast agents, PTA-Gd and GdDTPA, showed no difference in the perfusion capacity of ER-positive and -negative tumors confirming the specific interaction of EPTA-Gd with ER. These findings lay a basis for the molecular imaging of the ER using EPTA-Gd as a template for further developments.

Statistical Learning Algorithm for in situ and invasive breast carcinoma segmentation

Dynamic Contrast Enhanced MRI (DCE-MRI) has proven to be a highly sensitive imaging modality in diagnosing breast cancers. However, analyzing the DCE-MRI is time-consuming and prone to errors due to the large volume of data. Mathematical models to quantify contrast perfusion, such as the black box methods and pharmacokinetic analysis, are inaccurate, sensitive to noise and depend on a large number of external factors such as imaging parameters, patient physiology, arterial input function, and fitting algorithms, leading to inaccurate diagnosis. In this paper, we have developed a novel Statistical Learning Algorithm for Tumor Segmentation (SLATS) based on Hidden Markov Models to auto-segment regions of angiogenesis, corresponding to tumor. The SLATS algorithm has been trained to identify voxels belonging to the tumor class using the time-intensity curve, first and second derivatives of the intensity curves ("velocity" and "acceleration" respectively) and a composite vector consisting of a concatenation of the intensity, velocity and acceleration vectors. The results of SLATS trained for the four vectors has been shown for 22 Invasive Ductal Carcinoma (IDC) and 19 Ductal Carcinoma In Situ (DCIS) cases. The SLATS trained for the velocity tuple shows the best performance in delineating the tumors when compared with the segmentation performed by an expert radiologist and the output of a commercially available software, CADstream.

Evaluation of the kinetic properties of background parenchymal enhancement throughout the phases of the menstrual cycle

PURPOSE

To develop and apply a semiautomatic method of segmenting fibroglandular tissue to quantify magnetic resonance (MR) imaging contrast material-enhancement kinetics of breast background parenchyma (BP) and lesions throughout the phases of the menstrual cycle in women with benign and malignant lesions.

MATERIALS AND METHODS

The institutional review board approved this retrospective HIPAA-compliant study, and informed consent was waived. From December 2008 to August 2011, 58 premenopausal women who had undergone contrast material-enhanced MR imaging and MR imaging-guided biopsy were identified. The longest time from the start of the last known period was 34 days. One lesion per patient (37 benign and 21 malignant) was analyzed. The patient groups were stratified according to the week of the menstrual cycle when MR imaging was performed. A method based on principal component analysis (PCA) was applied for quantitative analysis of signal enhancement in the BP and lesions by using the percentage of slope and percentage of enhancement. Linear regression and the Mann-Whitney U test were used to assess the association between the kinetic parameters and the week of the menstrual cycle.

RESULTS

In the women with benign lesions, percentages of slope and enhancement for both BP and lesions during week 2 were significantly (P < .05) lower than those in week 4. Percentage of enhancement in the lesion in week 2 was lower than that in week 3 (P < .05). The MR images of women with malignant lesions showed no significant difference between the weeks for any of the parameters. There was a strong positive correlation between lesion and BP percentage of slope (r = 0.72) and between lesion and BP percentage of enhancement (r = 0.67) in the benign group. There was also a significant (P = .03) difference in lesion percentage of slope between the benign and malignant groups at week 2.

CONCLUSION

The PCA-based method can quantify contrast enhancement kinetics of BP semiautomatically, and kinetics of BP and lesions vary according to the week of the menstrual cycle in benign but not in malignant lesions.

A feasible high spatiotemporal resolution breast DCE-MRI protocol for clinical settings

Three dimensional bilateral imaging is the standard for most clinical breast dynamic contrast-enhanced (DCE) MRI protocols. Because of high spatial resolution (sRes) requirement, the typical 1-2 min temporal resolution (tRes) afforded by a conventional full-k-space-sampling gradient echo (GRE) sequence precludes meaningful and accurate pharmacokinetic analysis of DCE time-course data. The commercially available, GRE-based, k-space undersampling and data sharing TWIST (time-resolved angiography with stochastic trajectories) sequence was used in this study to perform DCE-MRI exams on thirty one patients (with 36 suspicious breast lesions) before their biopsies. The TWIST DCE-MRI was immediately followed by a single-frame conventional GRE acquisition. Blinded from each other, three radiologist readers assessed agreements in multiple lesion morphology categories between the last set of TWIST DCE images and the conventional GRE images. Fleiss' κ test was used to evaluate inter-reader agreement. The TWIST DCE time-course data were subjected to quantitative pharmacokinetic analyses. With a four-channel phased-array breast coil, the TWIST sequence produced DCE images with 20 s or less tRes and ~ 1.0×1.0×1.4 mm(3) sRes. There were no significant differences in signal-to-noise (P=.45) and contrast-to-noise (P=.51) ratios between the TWIST and conventional GRE images. The agreements in morphology evaluations between the two image sets were excellent with the intra-reader agreement ranging from 79% for mass margin to 100% for mammographic density and the inter-reader κ value ranging from 0.54 (P<.0001) for lesion size to 1.00 (P<.0001) for background parenchymal enhancement. Quantitative analyses of the DCE time-course data provided higher breast cancer diagnostic accuracy (91% specificity at 100% sensitivity) than the current clinical practice of morphology and qualitative kinetics assessments. The TWIST sequence may be used in clinical settings to acquire high spatiotemporal resolution breast DCE-MRI images for both precise lesion morphology characterization and accurate pharmacokinetic analysis.

The effect of temporal sampling on quantitative pharmacokinetic and three-time-point analysis of breast DCE-MRI

The effects of temporal sampling on the previously published three-time-point (3TP) method are compared with those of a Tofts-Kety model using an arterial input function from the alternating minimization with model (AMM) method. Computer simulations are done to estimate the expected error in both the 3TP and Tofts-Kety models as a function of the temporal sampling rate of the data. The error in the 3TP model parameters remained essentially constant with respect to temporal sampling. The Tofts-Kety model showed a linear increase in parameter error with respect to temporal sampling. Both analysis methods were also applied to 87 clinically acquired breast scans. These scans were downsampled in time by a factor of 2 and 4, and the methods were reapplied. The spatial resolution was held constant throughout this study. At temporal resolutions less than 19.4 s, the Tofts-Kety model outperformed the 3TP model using receiver operating characteristic curve analysis (area under the ROC curve [AUC] of 0.94 compared to 0.91). As the temporal sampling rate decreased, the 3TP model outperformed the Tofts-Kety model (AUC of 0.89 versus 0.85). When the temporal sampling rate of the data was less than 20 s, the Tofts-Kety model with the AMM method had lower parameter error than the 3TP method.

In vivo magnetic resonance imaging of the estrogen receptor in an orthotopic model of human breast cancer

Histologic overexpression of the estrogen receptor α (ER) is a well-established prognostic marker in breast cancer. Noninvasive imaging techniques that could detect ER overexpression would be useful in a variety of settings where patients' biopsies are problematic to obtain. This study focused on developing, by in vivo MRI, strategies to measure the level of ER expression in an orthotopic mouse model of human breast cancer. Specifically, novel ER-targeted contrast agents based on pyridine-tetra-acetate-Gd(III) chelate (PTA-Gd) conjugated to 17β-estradiol (EPTA-Gd) or to tamoxifen (TPTA-Gd) were examined in ER-positive or ER-negative tumors. Detection of specific interactions of EPTA-Gd with ER were documented that could differentiate ER-positive and ER-negative tumors. In vivo competition experiments confirmed that the enhanced detection capability of EPTA-Gd was based specifically on ER targeting. In contrast, PTA-Gd acted as an extracellular probe that enhanced ER detection similarly in either tumor type, confirming a similar vascular perfusion efficiency in ER-positive and ER-negative tumors in the model. Finally, TPTA-Gd accumulated selectively in muscle and could not preferentially identify ER-positive tumors. Together, these results define a novel MRI probe that can permit selective noninvasive imaging of ER-positive tumors in vivo.

PCATMIP: enhancing signal intensity in diffusion-weighted magnetic resonance imaging

Diffusion-weighted MRI studies generally lose signal intensity to physiological motion, which can adversely affect quantification/diagnosis. Averaging over multiple repetitions, often used to improve image quality, does not eliminate the signal loss. In this article, PCATMIP, a combined principal component analysis and temporal maximum intensity projection approach, is developed to address this problem. Data are first acquired for a fixed number of repetitions. Assuming that physiological fluctuations of image intensities locally are likely temporally correlated unlike random noise, a local moving boxcar in the spatial domain is used to reconstruct low-noise images by considering the most relevant principal components in the temporal domain. Subsequently, a temporal maximum intensity projection yields a high signal-intensity image. Numerical and experimental studies were performed for validation and to determine optimal parameters for increasing signal intensity and minimizing noise. Subsequently, a combined principal component analysis and temporal maximum intensity projection approach was used to analyze diffusion-weighted porcine liver MRI scans. In these scans, the variability of apparent diffusion coefficient values among repeated measurements was reduced by 59% relative to averaging, and there was an increase in the signal intensity with higher intensity differences observed at higher b-values. In summary, a combined principal component analysis and temporal maximum intensity projection approach is a postprocessing approach that corrects for bulk motion-induced signal loss and improves apparent diffusion coefficient measurement reproducibility.