Mediolateral Oblique Mammograms Research Articles

Inter- and intra-observer variability of qualitative visual breast-composition assessment in mammography among Japanese physicians: a first multi-institutional observer performance study in Japan.

Visual assessment of mammographic breast composition remains the most common worldwide, although subjective variability limits its reproducibility. This study aimed to investigate the inter- and intra-observer variability in qualitative visual assessment of mammographic breast composition through a multi-institutional observer performance study for the first time in Japan. This study enrolled 10 Japanese physicians from five different institutions. They used the new Japanese breast-composition classification system 4th edition to subjectively evaluate the breast composition in 200 pairs of right and left normal mediolateral oblique mammograms (number determined using precise sample size calculations) twice, with a 1-month interval (median patient age: 59years [range 40-69years]). The primary endpoint of this study was the inter-observer variability using kappa (κ) value. Inter-observer variability for the four and two classes of breast-composition assessment revealed moderate agreement (Fleiss' κ: first and second reading = 0.553 and 0.587, respectively) and substantial agreement (Fleiss' κ: first and second reading = 0.689 and 0.70, respectively). Intra-observer variability for the four and two classes of breast-composition assessment demonstrated substantial agreement (Cohen's κ, median = 0.758) and almost perfect agreement (Cohen's κ, median = 0.813). Assessments of consensus between the 10 physicians and the automated software Volpara® revealed slight agreement (Cohen's κ; first and second reading: 0.104 and 0.075, respectively). Qualitative visual assessment of mammographic breast composition using the new Japanese classification revealed excellent intra-observer reproducibility. However, persistent inter-observer variability, presenting a challenge in establishing it as the gold standard in Japan.

Pectoral muscle removal in mammogram images: A novel approach for improved accuracy and efficiency

PurposeAccurate pectoral muscle removal is critical in mammographic breast density estimation and many other computer-aided algorithms. We propose a novel approach to remove pectoral muscles form mediolateral oblique (MLO) view mammograms and compare accuracy and computational efficiency with existing method (Libra).MethodsA pectoral muscle identification pipeline was developed. The image is first binarized to enhance contrast and then the Canny algorithm was applied for edge detection. Robust interpolation is used to smooth out the pectoral muscle region. Accuracy and computational speed of pectoral muscle identification was assessed using 951 women (1,902 MLO mammograms) from the Joanne Knight Breast Health Cohort at Washington University School of Medicine.ResultsOur proposed algorithm exhibits lower mean error of 12.22% in comparison to Libra’s estimated error of 20.44%. This 40% gain in accuracy was statistically significant (p < 0.001). The computational time for the proposed algorithm is 5.4 times faster when compared to Libra (5.1 s for proposed vs. 27.7 s for Libra per mammogram).ConclusionWe present a novel approach for pectoral muscle removal in mammogram images that demonstrates significant improvement in accuracy and efficiency compared to existing method. Our findings have important implications for the development of computer-aided systems and other automated tools in this field.

Deep Learning-Based Multi-Label Tissue Segmentation and Density Assessment from Mammograms

Objectives: Breast cancer is the most commonly diagnosed type of cancer among women and a common cause of cancer-related deaths. Early diagnosis and treatment of breast cancer is critical in disease prognosis. Breast density is known to have a correlation with breast cancer. In recent years, there has been an increasing interest in the investigation of computer-aided methods for early diagnosis of breast cancer. In this study, a new fully-automated deep learning-based cascaded model was proposed for breast density assessment. In the first stage, the segmentation of adipose, fibroglandular, and pectoral muscle tissues from the digitized film mammograms of the Digital Database for Screening Mammography (DDSM) was investigated using various types of U-nets. Features extracted from the breast tissue segmentation predictions were then used to assess breast density in the second stage. Material and methods: 66 and 296 mediolateral oblique mammograms were selected from DDSM dataset for segmentation and breast density assessment systems, respectively. Different U-nets with varying number of layers and filters were implemented and the model having the highest performance was determined. U-net performance was investigated using categorical cross-entropy, Dice, Tversky, Focal Tversky, and logarithmic cosine-hyperbolic Dice loss functions. The performances of U-nets having different types of connections were investigated. The performances of U-nets having pre-trained weights from VGG16, VGG19, and ResNet50 networks in the encoding path were also investigated. Segmentation results were improved by using an image processing pipeline based on morphological operators. Segmentation performance was presented in terms of accuracy, balanced accuracy, intersection over union, and Dice's similarity coefficient (DSC) metrics. The segmentation system predictions were then used to estimate mammographic density using a machine learning pipeline by extracting features related to the fibroglandular tissue percentage. Results: Using ResNet50-U-net on the test data, average DSC scores of 82.71%, 73.39%, and 95.30% were obtained for adipose, fibroglandular, and pectoral muscle tissue segmentation, respectively. The mammogram segmentation results are 3%-12% better than the current state-of-the-art DSC in the literature when considering all of the foreground tissues concurrently. A breast density classification accuracy of 76.01% was achieved on a separate mammogram dataset, which is comparable to the recent studies in the literature. Conclusion: The proposed system can be used for automatic segmentation of mammogram into adipose, fibroglandular, and pectoral muscle tissues. The segmentation model enables the estimation of the fibroglandular-adipose tissue interface, which is recently found to be an important region for breast cancer investigations. The proposed fully-automatic breast density assessment system has a comparable performance to the ones in the literature.

Standardised or individualised X-ray tube angle for mediolateral oblique projection in digital mammography?

IntroductionWe aimed to investigate whether there were any differences in positioning criteria related to the presentation of the pectoralis major muscle (pectoral muscle) for women of different heights using a standardized 60° X-ray tube angle for mammograms in mediolateral oblique (MLO) projection. MethodsData from MLO mammograms of right breasts of 45,193 women screened in BreastScreen Norway 2016–2019 were used. The positioning criteria were related to the pectoral muscle length (measure A and measure B), width and shape and considered adequate or inadequate depending on the degree of fulfilling the criteria. Data associated with the pectoral muscle were extracted from Volpara, an automated software for breast density assessment. Information on height was obtained from a self-reported questionnaire received by the women together with the invitation to attend the screening program. Women were divided into three groups based on the height percentiles (P) in the Norwegian growth curves: < 25th percentile (<P25th: ≤163 cm), 25th-75th percentile (P25–P75th: 164–170 cm), and >75th percentile (>P75th: >170 cm). Logistic regression was used to analyse the odds of adequate pectoral muscle length A and B, and shape, adjusting each model for screening technique and equipment model. Results were presented with odds ratios (OR) and 95% confidence intervals (CI). ResultsMean age of the screened women was 61.5 (SD = 4.8) years. The adequate measure for the pectoral muscle length A was obtained for 25.9% (11,724/45,193), length B for 76.3% (34,489/45,193), width for 75.0% (33,894/45,193) and shape for 97.6% (44,118/45,193) of the mammograms. Adjusted odds of an adequate pectoral muscle length A were lower for women of <P25th (OR = 0.90, 95% CI: 0.86–0.95) compared to women of P25-75th. Odds of an adequate pectoral muscle length B were lower for women of <P25th (OR = 0.88, 95% CI 0.84–0.93) and higher for women of >P75th (OR = 1.08, 95% CI 1.02–1.14) compared to women of P25-75. Odds of an adequate pectoral muscle shape were higher for women of <P25th (OR = 1.14, 95%CI 1.08–1.19) and lower for women of >P75th (OR = 0.92, 95% CI 0.87–0.97) compared to women of P25-75th. ConclusionThe 60° X-ray tube angle might suit most of the female population offered mammographic screening in Norway, but women of a relatively low height (163 cm or lower) might benefit from an X-ray tube angle less than 60-degrees. Implications for practiceUsing 60° X-ray tube angle for the MLO mammograms in BreastScreen Norway fit the majority of the participating women. More research is needed to change the protocol associated with the tube angle for women shorter than 163 cm.

A New Imaging Workup of The Male Breast: Single-View Mammography and Ultrasonography

Background: There is no generally accepted standard radiological approach to male breast diseases. Ultrasonography and mammography are the most preferred methods for imaging. The purpose of this study is to investigate the diagnostic performances of only single-view (mediolateral oblique) mammography and routine two-view mammography in the male breast diseases and also to evaluate the contribution of ultrasonography to the diagnosis and the management of the disease.Methods: Three hundred-twenty male patients’ breast imaging findings were evaluated retrospectively. Only mediolateral oblique and routine two-view mammograms were re-evaluated four months apart by two breast radiologists. The kappa value was calculated to measure consistency between two groups. The sensitivity, specificity, positive and negative predictive value, and detection accuracy of malignancy were calculated for both mammographic examinations and ultrasonography.Results: The accuracy of detection of malignant breast masses according to mediolateral oblique and two-view mammograms, and ultrasonography were 96.3 %, 97.5 %, and 99.5 %, respectively. Consistency between single-view and two-view mammograms was excellent (? = 0.967) and statistically significant (p=0.000). Two-view mammograms did not make any contribution to single-view mammograms.Conclusion: Only mediolateral oblique mammogram is sufficient in terms of characterization, spread and localization of the lesion, as long as mastectomy is preferred and the findings are supported by ultrasonography. Since there is no diagnostic performance difference, only mediolateral oblique view would protect from the potential adverse effects of extra radiation exposure and this is an important advantage.

On Segmentation of Pectoral Muscle in Digital Mammograms by Means of Deep Learning

Computer-aided diagnosis (CAD) has long become an integral part of radiological management of breast disease, facilitating a number of important clinical applications, including quantitative assessment of breast density and early detection of malignancies based on X-ray mammography. Common to such applications is the need to automatically discriminate between breast tissue and adjacent anatomy, with the latter being predominantly represented by pectoralis major (or pectoral muscle). Especially in the case of mammograms acquired in the mediolateral oblique (MLO) view, the muscle is easily confusable with some elements of breast anatomy due to their morphological and photometric similarity. As a result, the problem of automatic detection and segmentation of pectoral muscle in MLO mammograms remains a challenging task, innovative approaches to which are still required and constantly searched for. To address this problem, the present paper introduces a two-step segmentation strategy based on a combined use of data-driven prediction (deep learning) and graph-based image processing. In particular, the proposed method employs a convolutional neural network (CNN) which is designed to predict the location of breast-pectoral boundary at different levels of spatial resolution. Subsequently, the predictions are used by the second stage of the algorithm, in which the desired boundary is recovered as a solution to the shortest path problem on a specially designed graph. The proposed algorithm has been tested on three different datasets (i.e., MIAS, CBIS-DDSm, and InBreast) using a range of quantitative metrics. The results of comparative analysis show considerable improvement over state-of-the-art, while offering the possibility of model-free and fully automatic processing. The average values of dice similarity coefficient (DSC) and accuracy (ACC) on the mentioned three datasets are 97.22 ± 1.96% and 99.64±.27%, respectively.

Breast pectoral muscle segmentation in mammograms using a modified holistically-nested edge detection network

This paper presents a method for automatic breast pectoral muscle segmentation in mediolateral oblique mammograms using a Convolutional Neural Network (CNN) inspired by the Holistically-nested Edge Detection (HED) network. Most of the existing methods in the literature are based on hand-crafted models such as straight-line, curve-based techniques or a combination of both. Unfortunately, such models are insufficient when dealing with complex shape variations of the pectoral muscle boundary and when the boundary is unclear due to overlapping breast tissue. To compensate for these issues, we propose a neural network framework that incorporates multi-scale and multi-level learning, capable of learning complex hierarchical features to resolve spatial ambiguity in estimating the pectoral muscle boundary. For this purpose, we modified the HED network architecture to specifically find 'contour-like' objects in mammograms. The proposed framework produced a probability map that can be used to estimate the initial pectoral muscle boundary. Subsequently, we process these maps by extracting morphological properties to find the actual pectoral muscle boundary. Finally, we developed two different post-processing steps to find the actual pectoral muscle boundary. Quantitative evaluation results show that the proposed method is comparable with alternative state-of-the-art methods producing on average values of 94.8 ± 8.5% and 97.5 ± 6.3% for the Jaccard and Dice similarity metrics, respectively, across four different databases.

Global parenchymal texture features based on histograms of oriented gradients improve cancer development risk estimation from healthy breasts

BackgroundThe breast dense tissue percentage on digital mammograms is one of the most commonly used markers for breast cancer risk estimation. Geometric features of dense tissue over the breast and the presence of texture structures contained in sliding windows that scan the mammograms may improve the predictive ability when combined with the breast dense tissue percentage. MethodsA case/control study nested within a screening program covering 1563 women with craniocaudal and mediolateral-oblique mammograms (755 controls and the contralateral breast mammograms at the closest screening visit before cancer diagnostic for 808 cases) aging 45 to 70 from Comunitat Valenciana (Spain) was used to extract geometric and texture features. The dense tissue segmentation was performed using DMScan and validated by two experienced radiologists. A model based on Random Forests was trained several times varying the set of variables. A training dataset of 1172 patients was evaluated with a 10-stratified-fold cross-validation scheme. The area under the Receiver Operating Characteristic curve (AUC) was the metric for the predictive ability. The results were assessed by only considering the output after applying the model to the test set, which was composed of the remaining 391 patients. ResultsThe AUC score obtained by the dense tissue percentage (0.55) was compared to a machine learning-based classifier results. The classifier, apart from the percentage of dense tissue of both views, firstly included global geometric features such as the distance of dense tissue to the pectoral muscle, dense tissue eccentricity or the dense tissue perimeter, obtaining an accuracy of 0.56. By the inclusion of a global feature based on local histograms of oriented gradients, the accuracy of the classifier was significantly improved (0.61). The number of well-classified patients was improved up to 236 when it was 208. ConclusionRelative geometric features of dense tissue over the breast and histograms of standardized local texture features based on sliding windows scanning the whole breast improve risk prediction beyond the dense tissue percentage adjusted by geometrical variables. Other classifiers could improve the results obtained by the conventional Random Forests used in this study.

Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set.

Purpose To investigate the combination of mammography radiomics and quantitative three-compartment breast (3CB) image analysis of dual-energy mammography to limit unnecessary benign breast biopsies. Materials and Methods For this prospective study, dual-energy craniocaudal and mediolateral oblique mammograms were obtained immediately before biopsy in 109 women (mean age, 51 years; range, 31-85 years) with Breast Imaging Reporting and Data System category 4 or 5 breast masses (35 invasive cancers, 74 benign) from 2013 through 2017. The three quantitative compartments of water, lipid, and protein thickness at each pixel were calculated from the attenuation at high and low energy by using a within-image phantom. Masses were automatically segmented and features were extracted from the low-energy mammograms and the quantitative compartment images. Tenfold cross-validations using a linear discriminant classifier with predefined feature signatures helped differentiate between malignant and benign masses by means of (a) water-lipid-protein composition images alone, (b) mammography radiomics alone, and (c) a combined image analysis of both. Positive predictive value of biopsy performed (PPV3) at maximum sensitivity was the primary performance metric, and results were compared with those for conventional diagnostic digital mammography. Results The PPV3 for conventional diagnostic digital mammography in our data set was 32.1% (35 of 109; 95% confidence interval [CI]: 23.9%, 41.3%), with a sensitivity of 100%. In comparison, combined mammography radiomics plus quantitative 3CB image analysis had PPV3 of 49% (34 of 70; 95% CI: 36.5%, 58.9%; P < .001), with a sensitivity of 97% (34 of 35; 95% CI: 90.3%, 100%; P < .001) and 35.8% (39 of 109) fewer total biopsies (P < .001). Conclusion Quantitative three-compartment breast image analysis of breast masses combined with mammography radiomics has the potential to reduce unnecessary breast biopsies. © RSNA, 2018 Online supplemental material is available for this article.

Triple-negative and non-triple-negative breast cancer prediction by mammographic radiomics features

Objective To develop and validate a radiomics predictive model based on mammogram for preoperative predicting triple-negative breast cancer (TNBC) or non-triple-negative breast cancer (NTNBC). Methods We retrospectively analyzed 459 Chinese women who were diagnosed with invasive breast cancer (confirmed by pathology) during August 2015 to November 2015. Our cohort included 34 TNBC and random selected 102 NTNBC cases. Regions of interest (ROIs) were manually selected from craniocaudal and mediolateral oblique mammograms by radiologists through manual lesion segmentation, and 43 radiomics features were evaluated. Craniocaudal (CC) single-view, mediolateral oblique (MLO) single-view and CC and MLO double-view classification model were constructed respectively. Classification performance was evaluated by the area under receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity. Kruskal-Walls U test and t test were used to compare the radiomics features between TNBC and UTNBC. Results The model that used the combination of both the CC and MLO view images achieved the overall best performance than using either of the two views alone, yielding an AUC of 0.791, accuracy of 0.798, sensitivity of 0.776 and specificity of 0.806 for TNBC comparing with NTNBC. Three features were selected by the model (gray scale span and inverse different moment for CC, roundness for MLO) showed a statistical significance (P 0.6 in the subtype classification. Conclusion This research constructed model based on mammograms classification model can effectively distinguish between TNBC and NTNBC. This model has potential value for breast cancer molecular subtype classification and clinical treatment. Key words: Breast neoplasms; Triple-negative breast cancer; Molecular subtypes; Radiomics; Machine learning; Mammogram

A robust method for segmenting pectoral muscle in mediolateral oblique (MLO) mammograms.

Accurately detecting and removing pectoral muscle areas depicting on mediolateral oblique (MLO) view mammograms are an important step to develop a computer-aided detection scheme to assess global mammographic density or tissue patterns. This study aims to develop and test a new fully automated, accurate and robust method for segmenting pectoral muscle in MLO mammograms. The new method includes the following steps. First, a small rectangular region in the top-left corner of the MLO mammogram which may contain pectoral muscle is captured and enhanced by the fractional differential method. Next, an improved iterative threshold method is applied to segment a rough binary boundary of the pectoral muscle in the small region. Then, a rough contour is fitted with the least squares method on the basis of points of the rough boundary. Last, the fitting contour is subjected to local active contour evolution to obtain the final pectoral muscle segmentation line. The method has been tested on 720 MLO mammograms. The segmentation results generated using the new scheme were evaluated by two expert mammographic radiologists using a 5-scale rating system. More than 65% were rated above scale 3. When assessing the segmentation results generated using Hough transform, morphologic thresholding methods and Unet-based model, less than 20%, 35% and 47% of segmentation results were rated above scale 3 by two radiologists, respectively. Quantitative data analysis results show that the Dice coefficient of 0.986 ± 0.005 is obtained. In addition, the mean rate of errors and Hausdorff distance between the contours detected by automated and manual segmentation are FP = 1.71 ± 3.82%, FN = 5.20 ± 3.94% and 2.75 ± 1.39mm separately. The proposed method can be used to segment the pectoral muscle in MLO mammograms with higher accuracy and robustness.

Geometry-Based Pectoral Muscle Segmentation From MLO Mammogram Views.

Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972±0.003 and 0.985±0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.Computer-aided diagnosis systems (CADx) play a major role in the early diagnosis of breast cancer. Extracting the breast region precisely from a mammogram is an essential component of CADx for mammography. The appearance of the pectoral muscle on medio-lateral oblique (MLO) views increases the false positive rate in CADx. Therefore, the pectoral muscle should be identified and removed from the breast region in an MLO image before further analysis. None of the previous pectoral muscle segmentation methods address all breast types based on the breast imaging-reporting and data system tissue density classes. In this paper, we deal with this deficiency by introducing a new simple yet effective method that combines geometric rules with a region growing algorithm to support the segmentation of all types of pectoral muscles (normal, convex, concave, and combinatorial). Experimental segmentation accuracy results were reported for four tissue density classes on 872 MLO images from three publicly available datasets. An average Jaccard index and Dice similarity coefficient of 0.972±0.003 and 0.985±0.001 were obtained, respectively. The mean Hausdorff distance between the contours detected by our method and the ground truth is below 5mm for all datasets. An average acceptable segmentation rate of ∼95% was achieved outperforming several state-of-the-art competing methods. Excellent results were obtained even for the most challenging class of extremely dense breasts.

Improvements of an objective model of compressed breasts undergoing mammography: Generation and characterization of breast shapes.

To develop a set of accurate 2D models of compressed breasts undergoing mammography or breast tomosynthesis, based on objective analysis, to accurately characterize mammograms with few linearly independent parameters, and to generate novel clinically realistic paired cranio-caudal (CC) and medio-lateral oblique (MLO) views of the breast. We seek to improve on an existing model of compressed breasts by overcoming detector size bias, removing the nipple and non-mammary tissue, pairing the CC and MLO views from a single breast, and incorporating the pectoralis major muscle contour into the model. The outer breast shapes in 931 paired CC and MLO mammograms were automatically detected with an in-house developed segmentation algorithm. From these shapes three generic models (CC-only, MLO-only, and joint CC/MLO) with linearly independent components were constructed via principal component analysis (PCA). The ability of the models to represent mammograms not used for PCA was tested via leave-one-out cross-validation, by measuring the average distance error (ADE). The individual models based on six components were found to depict breast shapes with accuracy (mean ADE-CC=0.81mm, ADE-MLO=1.64mm, ADE-Pectoralis=1.61mm), outperforming the joint CC/MLO model (P≤0.001). The joint model based on 12 principal components contains 99.5% of the total variance of the data, and can be used to generate new clinically realistic paired CC and MLO breast shapes. This is achieved by generating random sets of 12 principal components, following the Gaussian distributions of the histograms of each component, which were obtained from the component values determined from the images in the mammography database used. Our joint CC/MLO model can successfully generate paired CC and MLO view shapes of the same simulated breast, while the individual models can be used to represent with high accuracy clinical acquired mammograms with a small set of parameters. This is the first step toward objective 3D compressed breast models, useful for dosimetry and scatter correction research, among other applications.

Identification and segmentation of obscure pectoral muscle in mediolateral oblique mammograms.

X-ray mammography is a widely used and reliable method for detecting pre-symptomatic breast cancer. One of the difficulties in automatically computerized mammogram analysis is the presence of pectoral muscles in mediolateral oblique mammograms because the pectoral muscle does not belong to the scope of the breast. The objective of this study is to identify the boundary of obscure pectoral muscle in mediolateral oblique mammograms. Two tentative boundary curves are individually created to be the potential boundaries. To find the first tentative boundary, this study finds local extrema, prunes weak extrema and then determines an appropriate threshold for identifying the brighter tissue, whose edge is considered the first tentative boundary. The second tentative boundary is found by partitioning the breast into several regions, where each local threshold is tuned based on the local intensity. Subsequently, both of these tentative boundaries are used as the reference to create a refined boundary by Hough transform. Then, the refined boundary is partitioned into quadrilateral regions, in which the edge of this boundary is detected. Finally, these reliable edge points are collected to generate the genuine boundary by curve fitting. The proposed method achieves the least mean square error 4.88 ± 2.47 (mean ± standard deviation) and the least misclassification error rate (MER) with 0.00466 ± 0.00191 in terms of MER. The experimental results indicate that this method performs best and stably in boundary identification of the pectoral muscle. The proposed method can identify the boundary from obscure pectoral muscle, which has not been solved by the previous studies.

An Anthropometric-Based Subject-Specific Finite Element Model of the Human Breast for Predicting Large Deformations.

The large deformation of the human breast threatens proper nodules tracking when the subject mammograms are used as pre-planning data for biopsy. However, techniques capable of accurately supporting the surgeons during biopsy are missing. Finite element (FE) models are at the basis of currently investigated methodologies to track nodules displacement. Nonetheless, the impact of breast material modeling on the mechanical response of its tissues (e.g., tumors) is not clear. This study proposes a subject-specific FE model of the breast, obtained by anthropometric measurements, to predict breast large deformation. A healthy breast subject-specific FE parametric model was developed and validated by Cranio-caudal (CC) and Medio-Lateral Oblique (MLO) mammograms. The model was successively modified, including nodules, and utilized to investigate the effect of nodules size, typology, and material modeling on nodules shift under the effect of CC, MLO, and gravity loads. Results show that a Mooney–Rivlin material model can estimate healthy breast large deformation. For a pathological breast, under CC compression, the nodules displacement is very close to zero when a linear elastic material model is used. Finally, when nodules are modeled, including tumor material properties, under CC, or MLO or gravity loads, nodules shift shows ~15% average relative difference.

Mammographic Breast Density Assessment Using Automated Volumetric Software and Breast Imaging Reporting and Data System (BIRADS) Categorization by Expert Radiologists

To investigate agreement on mammographic breast density (MD) assessment between automated volumetric software and Breast Imaging Reporting and Data System (BIRADS) categorization by expert radiologists. Forty cases of left craniocaudal and mediolateral oblique mammograms from 20 women were used. All images had their volumetric density classified using Volpara density grade (VDG) and average volumetric breast density percentage. The same images were then classified into BIRADS categories (I-IV) by 20 American Board of Radiology examiners. The results demonstrated a moderate agreement (κ = 0.537; 95% CI = 0.234-0.699) between VDG classification and radiologists' BIRADS density assessment. Interreader agreement using BIRADS also demonstrated moderate agreement (κ = 0.565; 95% CI = 0.519-0.610) ranging from 0.328 to 0.669. Radiologists' average BIRADS was lower than average VDG scores by 0.33, with their mean being 2.13, whereas the mean VDG was 2.48 (U = -3.742; P < 0.001). VDG and BIRADS showed a very strong positive correlation (ρ = 0.91; P < 0.001) as did BIRADS and average volumetric breast density percentage (ρ = 0.94; P < 0.001). Automated volumetric breast density assessment shows moderate agreement and very strong correlation with BIRADS; interreader variations still exist within BIRADS. Because of the increasing importance of MD measurement in clinical management of patients, widely accepted, reproducible, and accurate measures of MD are required.

Feasibility study of a breast density measurement within a direct photon-counting mammography scanner system.

To evaluate the clinical feasibility of breast density measurements by a new application within a direct photon-counting mammography scanner system. A retrospective study of consecutive women who underwent mammography using a direct photon-counting mammography scanner system (MicroDose mammography SI; Philips Digital Mammography Sweden AB) was performed at the authors' institution between September and December 2013. Quantitative volumetric glandularity measurements were performed automatically for each acquired mammographic image using an application (Breast Density Measurement; Philips Digital Mammography Sweden AB). The quantitative volumetric glandularity of each breast was defined as the average values for the mediolateral oblique (MLO) and craniocaudal (CC) mammogram views. Of the 44 women who underwent bilateral mammogram acquisitions, the breast density measurements were performed successfully in 40 patients (90.9%). A very good to excellent correlation in the quantitative breast density measurements acquired from the MLO and CC images was obtained in the 40 evaluable patients (R = 0.99). The calculated volumetric glandularity using this new application should correspond well with the true volumetric density of each breast.

Comparison of New and Established Full-Field Digital Mammography Systems in Diagnostic Performance

ObjectiveTo compare the diagnostic performance of new and established full-field digital mammography (FFDM) systems.Materials and MethodsDuring a 15-month period, 1038 asymptomatic women who visited for mammography were prospectively included from two institutions. For women with routine two-view mammograms from established FFDM systems, bilateral mediolateral oblique (MLO) mammograms were repeated using the new FFDM system. One of the four reviewers evaluated two-sets of bilateral MLO mammograms at 4-week intervals by using a five-point score for the probability of malignancy according to a Breast Imaging Reporting and Data System. The lesion type and breast density were determined by the consensus of two readers at each institution. The dichotomized mammographic results correlated with a final pathologic outcome and follow-up data. Receiver operating characteristic (ROC) curves, sensitivity, and specificity were compared in general and according to the lesion type and breast density.ResultsOf the 1038 cases, 193 (18.6%) had cancer. The areas under the ROC curve (AUC), sensitivity, and specificity of the established system were 0.815, 65.3%, and 90.2%, respectively. Those of the new system were 0.839, 68.4%, and 91.7%, respectively. There were no significant differences in the AUCs, sensitivities or the specificities in general between new and established systems (Ps = 0.194, 0.590, 0.322, respectively). We found no significant difference in these parameters according to lesion type or breast density.ConclusionThe new FFDM system has a comparable diagnostic performance with established systems.

A pectoral muscle segmentation algorithm for digital mammograms using Otsu thresholding and multiple regression analysis

One of the issues when interpreting a mammogram is that the density of a pectoral muscle region is similar to the tumor cells. The appearance of pectoral muscle on medio-lateral oblique (MLO) views of mammograms will increase the false positives in computer aided detection (CAD) of breast cancer. For this reason, pectoral muscle has to be identified and segmented from the breast region in a mammogram before further analysis. The main goal of this paper is to propose an accurate and efficient algorithm of pectoral muscle extraction on MLO mammograms. The proposed algorithm is based on the positional characteristic of pectoral muscle in a breast region to combine the iterative Otsu thresholding scheme and the mathematic morphological processing to find a rough border of the pectoral muscle. The multiple regression analysis (MRA) is then employed on this rough border to obtain an accurate segmentation of the pectoral muscle. The presented algorithm is tested on the digital mammograms from the Mammogram Image Analysis Society (MIAS) database. The experimental results show that the pectoral muscle extracted by the presented algorithm approximately follows that extracted by an expert radiologist.

Pectoral Muscle Segmentation for Digital Mammograms Based on Otsu Thresholding

The appearance of pectoral muscle in medio-lateral oblique (MLO) views of mammograms can increase the false positive in computer aided detection (CAD) of breast cancer detection. Pectoral muscle has to be identified and segmented from the breast region in a mammogram before further analysis. The main goal of this paper is to propose an accurate and efficient algorithm of pectoral muscle extraction on MLO mammograms. The proposed algorithm bases on the positional characteristic of pectoral muscle in a breast region to combine the iterative Otsu thresholding scheme and the mathematic morphological processing to find the rough border of the pectoral muscle. The multiple regression analysis is then employed on the rough border to obtain the accurate segmentation of the pectoral muscle. The presented algorithm is tested on the digital mammograms from the Mammogram Image Analysis Society (MIAS) database. The experimental results show that the pectoral muscle extracted by the presented algorithm approximately follows that extracted by an expert radiologist.