Breast density has been established as an independent risk factor associated with the development of breast cancer. It is known that an increase of mammographic density is associated with an increased cancer risk. Since a mammogram is a projection image, different body position, level of compression, and the x-ray intensity may lead to a large variability in the density measurement. Breast MRI provides strong soft tissue contrast between fibroglandular and fatty tissues, and three-dimensional coverage of the entire breast, thus making it suitable for density analysis. To develop the MRI-based method, the first task is to achieve consistency in segmentation of the breast region from the body. The method included an initial segmentation based on body landmarks of each individual woman, followed by fuzzy C-mean (FCM) classification to exclude air and lung tissue, B-spline curve fitting to exclude chest wall muscle, and dynamic searching to exclude skin. Then, within the segmented breast, the adaptive FCM was used for simultaneous bias field correction and fibroglandular tissue segmentation. The intraoperator and interoperator reproducibility was evaluated using 11 selected cases covering a broad spectrum of breast densities with different parenchymal patterns. The average standard deviation for breast volume and percent density measurements was in the range of 3%-4% among three trials of one operator or among three different operators. The body position dependence was also investigated by performing scans of two healthy volunteers, each at five different positions, and found the variation in the range of 3%-4%. These initial results suggest that the technique based on three-dimensional MRI can achieve reasonable consistency to be applied in longitudinal follow-up studies to detect small changes. It may also provide a reliable method for evaluating the change of breast density for risk management of women, or for evaluating the benefits/risks when considering hormonal replacement therapy or chemoprevention.
Rationale and Objectives-To investigate the feasibility using quantitative morphology/texture features of breast lesions for diagnostic prediction; and to explore the association of computerized features with lesion phenotype appearance on MRI.Materials and Methods-43 malignant/28 benign lesions were used in this study. A systematic approach from automated lesion segmentation, quantitative feature extraction, diagnostic feature selection using artificial neural network (ANN), and lesion classification was carried out. Eight morphological parameters and 10 GLCM (gray level co-occurrence matrices) texture features were obtained from each lesion. The diagnostic performance of selected features to differentiate between malignant and benign lesions was analyzed using the ROC analysis.Results-Six features were selected by ANN using leave-one-out cross validation, including Compactness, NRL Entropy, Volume, Gray Level Entropy, Gray Level Sum Average, and Homogeneity. The area under the ROC curve was 0.86. When dividing the database into half training and half validation set, a classifier of 5 features selected in the half training set achieved AUC of 0.82 in the other half validation set. The selected morphology feature "Compactness" was associated with shape and margin in BI-RADS lexicon, round shape and smooth margin for the benign lesions and more irregular shape for the malignant lesions. The selected texture features were associated with homogeneous/heterogeneous patterns and the enhancement intensity. The malignant lesions had higher intensity and broader distribution in the enhancement histogram (more heterogeneous) compared to the benign ones.Conclusion-Quantitative analysis of morphology/texture features of breast lesions was feasible, and these features could be selected by ANN to form a classifier for differential diagnosis. Establishing the link between computer-based features and visual descriptors defined in BI-RADS lexicon will provide the foundation for the acceptance of quantitative diagnostic features in the development of computer-aided diagnosis (CAD). The CAD for mammography is by far the most mature among all medical imaging analysis systems. It detects abnormalities or suspicious regions, and marks them with different labels indicating different features with varying degrees of malignancy [7][8][9][10]. A great deal of research has also been spent on developing CAD for breast ultrasound [11][12][13]. Given the many more images acquired in MRI compared to mammogram and ultrasound, development of breast MRI CAD is far more challenging, but on the other hand will be very helpful. The currently existing commercial CAD systems for breast MRI, such as CADstream (Confirma Inc. Kirkland, WA) and fTP (CADsciences, White Plains, NY) provide display platforms to show various presentations of the enhanced lesions to assist radiologists' interpretation. The display is mainly based on the enhancement kinetic features, such as the wash-out patterns, of voxels with the percent enhancement above a pre-se...
PurposeTo investigate methods developed for the characterisation of the morphology and enhancement kinetic features of both mass and non-mass lesions, and to determine their diagnostic performance to differentiate between malignant and benign lesions that present as mass versus non-mass types. MethodsQuantitative analysis of morphological features and enhancement kinetic parameters of breast lesions were used to differentiate among four groups of lesions: 88 malignant (43 mass, 45 non-mass) and 28 benign (19 mass, 9 non-mass). The enhancement kinetics was measured and analysed to obtain transfer constant (Ktrans) and rate constant (kep). For each mass eight shape/margin parameters and 10 enhancement texture features were obtained. For the lesions presenting as nonmass-like enhancement, only the texture parameters were obtained. An artificial neural network (ANN) was used to build the diagnostic model.ResultsFor lesions presenting as mass, the four selected morphological features could reach an area under the ROC curve (AUC) of 0.87 in differentiating between malignant and benign lesions. The kinetic parameter (kep) analysed from the hot spot of the tumour reached a comparable AUC of 0.88. The combined morphological and kinetic features improved the AUC to 0.93, with a sensitivity of 0.97 and a specificity of 0.80. For lesions presenting as non-mass-like enhancement, four texture features were selected by the ANN and achieved an AUC of 0.76. The kinetic parameter kep from the hot spot only achieved an AUC of 0.59, with a low added diagnostic value. ConclusionThe results suggest that the quantitative diagnostic features can be used for developing automated breast CAD (computer-aided diagnosis) for mass lesions to achieve a high diagnostic performance, but more advanced algorithms are needed for diagnosis of lesions presenting as non-mass-like enhancement.
The automatic chest template-based breast MRI segmentation method worked well for cases with different body and breast shapes and different density patterns. Compared to the radiologist-established truth, the mean difference in segmented breast volume was approximately 1%, and the total error by considering the additive inclusion and exclusion errors was approximately 3%. This method may provide a reliable tool for MRI-based segmentation of breast density.
Purpose:To investigate the application of MR spectroscopy using chemical-shift imaging (CSI) for characterizing human breast lesions at 1.5T, and to evaluate the diagnostic performance using ROC (receiver operating characteristics) analysis. Materials and Methods:Thirty-six patients (35-73 years old, mean 52), with 27 malignant and 9 benign lesions, underwent anatomical imaging, dynamic contrast-enhanced MR imaging, and CSI. The ROC analysis was performed and the cutoff point yielding the highest accuracy was found to be a choline (Cho) signal-to-noise ratio (SNR) Ͼ3.2. Results:The mean Cho SNR was 2.8 Ϯ 0.8 (range, 1.8 -4.3) for the benign group and 5.9 Ϯ 3.4 (2.1-17.5) for the malignant group (P ϭ 0.01). Based on the criterion of Cho SNR Ͼ3.2 as malignant, CSI correctly diagnosed 22 of 27 malignant lesions and 7 of 9 benign lesions, resulting in a sensitivity of 81%, specificity of 78%, and overall accuracy of 81%. If the criterion was set higher at Cho SNR Ͼ4.0 the specificity improved to 89% but sensitivity was lowered to 67%. Conclusion:The ROC analysis presented in this work could be used to set an objective diagnostic criterion depending on preferred emphasis on sensitivity or specificity.
IntroductionIn addition to being a risk factor for breast cancer, breast density has been hypothesized to be a surrogate biomarker for predicting response to endocrine-based chemotherapies. The purpose of this study was to evaluate whether a noninvasive bedside scanner based on diffuse optical spectroscopic imaging (DOSI) provides quantitative metrics to measure and track changes in breast tissue composition and density. To access a broad range of densities in a limited patient population, we performed optical measurements on the contralateral normal breast of patients before and during neoadjuvant chemotherapy (NAC). In this work, DOSI parameters, including tissue hemoglobin, water, and lipid concentrations, were obtained and correlated with magnetic resonance imaging (MRI)-measured fibroglandular tissue density. We evaluated how DOSI could be used to assess breast density while gaining new insight into the impact of chemotherapy on breast tissue.MethodsThis was a retrospective study of 28 volunteers undergoing NAC treatment for breast cancer. Both 3.0-T MRI and broadband DOSI (650 to 1,000 nm) were obtained from the contralateral normal breast before and during NAC. Longitudinal DOSI measurements were used to calculate breast tissue concentrations of oxygenated and deoxygenated hemoglobin, water, and lipid. These values were compared with MRI-measured fibroglandular density before and during therapy.ResultsWater (r = 0.843; P < 0.001), deoxyhemoglobin (r = 0.785; P = 0.003), and lipid (r = -0.707; P = 0.010) concentration measured with DOSI correlated strongly with MRI-measured density before therapy. Mean DOSI parameters differed significantly between pre- and postmenopausal subjects at baseline (water, P < 0.001; deoxyhemoglobin, P = 0.024; lipid, P = 0.006). During NAC treatment measured at about 90 days, significant reductions were observed in oxyhemoglobin for pre- (-20.0%; 95% confidence interval (CI), -32.7 to -7.4) and postmenopausal subjects (-20.1%; 95% CI, -31.4 to -8.8), and water concentration for premenopausal subjects (-11.9%; 95% CI, -17.1 to -6.7) compared with baseline. Lipid increased slightly in premenopausal subjects (3.8%; 95% CI, 1.1 to 6.5), and water increased slightly in postmenopausal subjects (4.4%; 95% CI, 0.1 to 8.6). Percentage change in water at the end of therapy compared with baseline correlated strongly with percentage change in MRI-measured density (r = 0.864; P = 0.012).ConclusionsDOSI functional measurements correlate with MRI fibroglandular density, both before therapy and during NAC. Although from a limited patient dataset, these results suggest that DOSI may provide new functional indices of density based on hemoglobin and water that could be used at the bedside to assess response to therapy and evaluate disease risk.
In recent years, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has altered the clinical management for women with breast cancer. In March 2007, the American Cancer Society (ACS) issued a new guideline recommending annual MRI screening for high-risk women. This guideline is expected to substantially increase the number of women each year who receive breast MRI. The diagnosis of breast MRI involves the description of morphological and enhancement kinetics features. To standardize the communication language, the Breast Imaging Reporting and Data System (BI-RADS) MRI lexicon was developed by the American College of Radiology (ACR). In this article, the authors will review various appearances of breast lesions on MRI by using the standardized terms of the ACR BI-RADS MRI lexicon. The purpose is to familiarize all medical professionals with the breast MRI lexicon because the use of this imaging modality is rapidly growing in the field of breast disease. By using this common language, a comprehensive analysis of both morphological and kinetic features used in image interpretation will help radiologists and other clinicians to communicate more clearly and consistently. This may, in turn, help physicians and patients to jointly select an appropriate management protocol for each patient's clinical situation. In March 2007, the American Cancer Society (ACS) issued a new guideline recommending annual screening for high-risk women using breast magnetic resonance imaging (MRI). MRI is recommended as an adjunct to mammography for women with a lifetime risk of 20%-25% or greater, including women with a strong family history of breast or ovarian cancer and women who had been treated for Hodgkin disease. 1 For women with a 15% to 20% lifetime risk, based on the analysis of multiple risk factors such as a personal history of breast cancer, carcinoma in situ, atypical hyperplasia, and extremely dense breasts on mammography, the ACS suggested that the screening decisions should be made on a case-by-case basis. 2 Breast MRI can alter the clinical management for a sizable fraction of women with early stage breast cancer and help in determining the optimal local treatment. [3][4][5][6] Kuhl et al concluded that MRI screening of women with a history of familial or hereditary breast cancer can achieve a significantly higher sensitivity
Choosing an appropriate bias field correction method is a very important preprocessing step to allow an accurate segmentation of fibroglandular tissues based on breast MRI for quantitative measurement of breast density. The proposed algorithm combining N3+FCM and CLIC both yield satisfactory results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.