Validation of a method for measuring the volumetric breast density from digital mammograms

Breast Density: Current Knowledge, Assessment Methods, and Clinical Implications

Breast density is an accepted independent risk factor for the future development of breast cancer, and greater breast density has the potential to mask malignancies on mammography, thus lowering the sensitivity of screening mammography. The risk associated with dense breast tissue has been shown to be modifiable with changes in breast density. Numerous studies have sought to identify factors that influence breast density, including age, genetic, racial/ethnic, prepubertal, adolescent, lifestyle, environmental, hormonal, and reproductive history factors. Qualitative, semiquantitative, and quantitative methods of breast density assessment have been developed, but to date there is no consensus assessment method or reference standard for breast density. Breast density has been incorporated into breast cancer risk models, and there is growing consciousness of the clinical implications of dense breast tissue in both the medical community and public arena. Efforts to improve breast cancer screening sensitivity for women with dense breasts have led to increased attention to supplemental screening methods in recent years, prompting the American College of Radiology to publish Appropriateness Criteria for supplemental screening based on breast density.

Algorithms and methods for computerized analysis of mammography images in breast cancer risk assessment

BACKGROUND AND OBJECTIVES

The computerized analysis of mammograms for the development of quantitative biomarkers is a growing field with applications in breast cancer risk assessment. Computerized image analysis offers the possibility of using different methods and algorithms to extract additional information from screening and diagnosis images to aid in the assessment of breast cancer risk. In this work, we review the algorithms and methods for the automated, computerized analysis of mammography images for the task mentioned, and discuss the main challenges that the development and improvement of these methods face today.

METHODS

We review the recent progress in two main branches of mammography-based risk assessment: parenchymal analysis and breast density estimation, including performance indicators of most of the studies considered. Parenchymal analysis methods are divided into feature-based methods and deep learning-based methods; breast density methods are grouped into area-based, volume-based, and breast categorization methods. Additionally, we identify the challenges that these study fields currently face.

RESULTS

Parenchymal analysis using deep learning algorithms are on the rise, with some studies showing high-performance indicators, such as an area under the receiver operating characteristic curve of up to 90. Methods for risk assessment using breast density report a wider variety of performance indicators; however, we can also identify that the approaches using deep learning methods yield high performance in each of the subdivisions considered.

CONCLUSIONS

Both breast density estimation and parenchymal analysis are promising tools for the task of breast cancer risk assessment; deep learning methods have shown performance comparable or superior to the other considered methods. All methods considered face challenges such as the lack of objective comparison between them and the lack of access to datasets from different populations.

Deformable Mapping Method to Relate Lesions in Dedicated Breast CT Images to Those in Automated Breast Ultrasound and Digital Breast Tomosynthesis Images

This work demonstrates the potential for using a deformable mapping method to register lesions between dedicated breast computed tomography (bCT) and both automated breast ultrasound (ABUS) and digital breast tomosynthesis (DBT) images (craniocaudal [CC] and mediolateral oblique [MLO] views). Two multi-modality breast phantoms with external fiducial markers attached were imaged by the three modalities. The DBT MLO view was excluded for the second phantom. The automated deformable mapping algorithm uses biomechanical modeling to determine corresponding lesions based on distances between their centers of mass (d_COM) in the deformed bCT model and the reference model (DBT or ABUS). For bCT to ABUS, the mean d_COM was 5.2 ± 2.6 mm. For bCT to DBT (CC), the mean d_COM was 5.1 ± 2.4 mm. For bCT to DBT (MLO), the mean d_COM was 4.7 ± 2.5 mm. This application could help improve a radiologist's efficiency and accuracy in breast lesion characterization, using multiple imaging modalities.

Artificial intelligence in cancer imaging: Clinical challenges and applications

Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.

Multimodal Breast Parenchymal Patterns Correlation Using a Patient-Specific Biomechanical Model

In this paper, we aim to produce a realistic 2-D projection of the breast parenchymal distribution from a 3-D breast magnetic resonance image (MRI). To evaluate the accuracy of our simulation, we compare our results with the local breast density (i.e., density map) obtained from the complementary full-field digital mammogram. To achieve this goal, we have developed a fully automatic framework, which registers MRI volumes to X-ray mammograms using a subject-specific biomechanical model of the breast. The optimization step modifies the position, orientation, and elastic parameters of the breast model to perform the alignment between the images. When the model reaches an optimal solution, the MRI glandular tissue is projected and compared with the one obtained from the corresponding mammograms. To reduce the loss of information during the ray-casting, we introduce a new approach that avoids resampling the MRI volume. In the results, we focus our efforts on evaluating the agreement of the distributions of glandular tissue, the degree of structural similarity, and the correlation between the real and synthetic density maps. Our approach obtained a high-structural agreement regardless the glandularity of the breast, whilst the similarity of the glandular tissue distributions and correlation between both images increase in denser breasts. Furthermore, the synthetic images show continuity with respect to large structures in the density maps.

Automated mammographic breast density estimation using a fully convolutional network

PURPOSE

The purpose of this study was to develop a fully automated algorithm for mammographic breast density estimation using deep learning.

METHOD

Our algorithm used a fully convolutional network, which is a deep learning framework for image segmentation, to segment both the breast and the dense fibroglandular areas on mammographic images. Using the segmented breast and dense areas, our algorithm computed the breast percent density (PD), which is the faction of dense area in a breast. Our dataset included full-field digital screening mammograms of 604 women, which included 1208 mediolateral oblique (MLO) and 1208 craniocaudal (CC) views. We allocated 455, 58, and 91 of 604 women and their exams into training, testing, and validation datasets, respectively. We established ground truth for the breast and the dense fibroglandular areas via manual segmentation and segmentation using a simple thresholding based on BI-RADS density assessments by radiologists, respectively. Using the mammograms and ground truth, we fine-tuned a pretrained deep learning network to train the network to segment both the breast and the fibroglandular areas. Using the validation dataset, we evaluated the performance of the proposed algorithm against radiologists' BI-RADS density assessments. Specifically, we conducted a correlation analysis between a BI-RADS density assessment of a given breast and its corresponding PD estimate by the proposed algorithm. In addition, we evaluated our algorithm in terms of its ability to classify the BI-RADS density using PD estimates, and its ability to provide consistent PD estimates for the left and the right breast and the MLO and CC views of the same women. To show the effectiveness of our algorithm, we compared the performance of our algorithm against a state of the art algorithm, laboratory for individualized breast radiodensity assessment (LIBRA).

RESULT

The PD estimated by our algorithm correlated well with BI-RADS density ratings by radiologists. Pearson's rho values of our algorithm for CC view, MLO view, and CC-MLO-averaged were 0.81, 0.79, and 0.85, respectively, while those of LIBRA were 0.58, 0.71, and 0.69, respectively. For CC view and CC-MLO averaged cases, the difference in rho values between the proposed algorithm and LIBRA showed statistical significance (P < 0.006). In addition, our algorithm provided reliable PD estimates for the left and the right breast (Pearson's ρ > 0.87) and for the MLO and CC views (Pearson's ρ = 0.76). However, LIBRA showed a lower Pearson's rho value (0.66) for both the left and right breasts for the CC view. In addition, our algorithm showed an excellent ability to separate each sub BI-RADS breast density class (statistically significant, p-values = 0.0001 or less); only one comparison pair, density 1 and density 2 in the CC view, was not statistically significant (P = 0.54). However, LIBRA failed to separate breasts in density 1 and 2 for both the CC and MLO views (P > 0.64).

CONCLUSION

We have developed a new deep learning based algorithm for breast density segmentation and estimation. We showed that the proposed algorithm correlated well with BI-RADS density assessments by radiologists and outperformed an existing state of the art algorithm.

Machine Learning in Medical Imaging

Advances in both imaging and computers have synergistically led to a rapid rise in the potential use of artificial intelligence in various radiological imaging tasks, such as risk assessment, detection, diagnosis, prognosis, and therapy response, as well as in multi-omics disease discovery. A brief overview of the field is given here, allowing the reader to recognize the terminology, the various subfields, and components of machine learning, as well as the clinical potential. Radiomics, an expansion of computer-aided diagnosis, has been defined as the conversion of images to minable data. The ultimate benefit of quantitative radiomics is to (1) yield predictive image-based phenotypes of disease for precision medicine or (2) yield quantitative image-based phenotypes for data mining with other -omics for discovery (ie, imaging genomics). For deep learning in radiology to succeed, note that well-annotated large data sets are needed since deep networks are complex, computer software and hardware are evolving constantly, and subtle differences in disease states are more difficult to perceive than differences in everyday objects. In the future, machine learning in radiology is expected to have a substantial clinical impact with imaging examinations being routinely obtained in clinical practice, providing an opportunity to improve decision support in medical image interpretation. The term of note is decision support, indicating that computers will augment human decision making, making it more effective and efficient. The clinical impact of having computers in the routine clinical practice may allow radiologists to further integrate their knowledge with their clinical colleagues in other medical specialties and allow for precision medicine.

Automated Volumetric Mammographic Breast Density Measurements May Underestimate Percent Breast Density for High-density Breasts

RATIONALE AND OBJECTIVES

The purpose of this study was to evaluate discrepancy in breast composition measurements obtained from mammograms using two commercially available software methods for systematic trends in overestimation or underestimation compared to magnetic resonance-derived measurements.

MATERIALS AND METHODS

An institutional review board-approved, Health Insurance Portability and Accountability Act-compliant retrospective study was performed to calculate percent breast density (PBD) by quantifying fibroglandular volume and total breast volume derived from magnetic resonance imaging (MRI) segmentation and mammograms using two commercially available software programs (Volpara and Quantra). Consecutive screening MRI exams from a 6-month period with negative or benign findings were used. The most recent mammogram within 9 months was used to derive mean density values from "for processing" images at the per breast level. Bland-Altman statistical analyses were performed to determine the mean discrepancy and the limits of agreement.

RESULTS

A total of 110 women with 220 breasts met the study criteria. Overall, PBD was not different between MRI (mean 10%, range 1%-41%) and Volpara (mean 10%, range 3%-29%); a small but significant difference was present in the discrepancy between MRI and Quantra (4.0%, 95% CI: 2.9 to 5.0, P < 0.001). Discrepancy was highest at higher breast densities, with Volpara slightly underestimating and Quantra slightly overestimating PBD compared to MRI. The mean discrepancy for both Volpara and Quantra for total breast volume was not significantly different from MRI (p = 0.89, 0.35, respectively). Volpara tended to underestimate, whereas Quantra tended to overestimate fibroglandular volume, with the highest discrepancy at higher breast volumes.

CONCLUSIONS

Both Volpara and Quantra tend to underestimate PBD, which is most pronounced at higher densities. PBD can be accurately measured using automated volumetric software programs, but values should not be used interchangeably between vendors.

Qualitative Versus Quantitative Mammographic Breast Density Assessment: Applications for the US and Abroad

Mammographic breast density (MBD) has been proven to be an important risk factor for breast cancer and an important determinant of mammographic screening performance. The measurement of density has changed dramatically since its inception. Initial qualitative measurement methods have been found to have limited consistency between readers, and in regards to breast cancer risk. Following the introduction of full-field digital mammography, more sophisticated measurement methodology is now possible. Automated computer-based density measurements can provide consistent, reproducible, and objective results. In this review paper, we describe various methods currently available to assess MBD, and provide a discussion on the clinical utility of such methods for breast cancer screening.

Local breast density assessment using reacquired mammographic images

PURPOSE

The aim of this paper is to evaluate the spatial glandular volumetric tissue distribution as well as the density measures provided by Volpara™ using a dataset composed of repeated pairs of mammograms, where each pair was acquired in a short time frame and in a slightly changed position of the breast.

MATERIALS AND METHODS

We conducted a retrospective analysis of 99 pairs of repeatedly acquired full-field digital mammograms from 99 different patients. The commercial software Volpara™ Density Maps (Volpara Solutions, Wellington, New Zealand) is used to estimate both the global and the local glandular tissue distribution in each image. The global measures provided by Volpara™, such as breast volume, volume of glandular tissue, and volumetric breast density are compared between the two acquisitions. The evaluation of the local glandular information is performed using histogram similarity metrics, such as intersection and correlation, and local measures, such as statistics from the difference image and local gradient correlation measures.

RESULTS

Global measures showed a high correlation (breast volume R=0.99, volume of glandular tissue R=0.94, and volumetric breast density R=0.96) regardless the anode/filter material. Similarly, histogram intersection and correlation metric showed that, for each pair, the images share a high degree of information. Regarding the local distribution of glandular tissue, small changes in the angle of view do not yield significant differences in the glandular pattern, whilst changes in the breast thickness between both acquisition affect the spatial parenchymal distribution.

CONCLUSIONS

This study indicates that Volpara™ Density Maps is reliable in estimating the local glandular tissue distribution and can be used for its assessment and follow-up. Volpara™ Density Maps is robust to small variations of the acquisition angle and to the beam energy, although divergences arise due to different breast compression conditions.

Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132

Image registration and fusion algorithms exist in almost every software system that creates or uses images in radiotherapy. Most treatment planning systems support some form of image registration and fusion to allow the use of multimodality and time-series image data and even anatomical atlases to assist in target volume and normal tissue delineation. Treatment delivery systems perform registration and fusion between the planning images and the in-room images acquired during the treatment to assist patient positioning. Advanced applications are beginning to support daily dose assessment and enable adaptive radiotherapy using image registration and fusion to propagate contours and accumulate dose between image data taken over the course of therapy to provide up-to-date estimates of anatomical changes and delivered dose. This information aids in the detection of anatomical and functional changes that might elicit changes in the treatment plan or prescription. As the output of the image registration process is always used as the input of another process for planning or delivery, it is important to understand and communicate the uncertainty associated with the software in general and the result of a specific registration. Unfortunately, there is no standard mathematical formalism to perform this for real-world situations where noise, distortion, and complex anatomical variations can occur. Validation of the software systems performance is also complicated by the lack of documentation available from commercial systems leading to use of these systems in undesirable 'black-box' fashion. In view of this situation and the central role that image registration and fusion play in treatment planning and delivery, the Therapy Physics Committee of the American Association of Physicists in Medicine commissioned Task Group 132 to review current approaches and solutions for image registration (both rigid and deformable) in radiotherapy and to provide recommendations for quality assurance and quality control of these clinical processes.

A review of biomechanically informed breast image registration

Breast radiology encompasses the full range of imaging modalities from routine imaging via x-ray mammography, magnetic resonance imaging and ultrasound (both two- and three-dimensional), to more recent technologies such as digital breast tomosynthesis, and dedicated breast imaging systems for positron emission mammography and ultrasound tomography. In addition new and experimental modalities, such as Photoacoustics, Near Infrared Spectroscopy and Electrical Impedance Tomography etc, are emerging. The breast is a highly deformable structure however, and this greatly complicates visual comparison of imaging modalities for the purposes of breast screening, cancer diagnosis (including image guided biopsy), tumour staging, treatment monitoring, surgical planning and simulation of the effects of surgery and wound healing etc. Due primarily to the challenges posed by these gross, non-rigid deformations, development of automated methods which enable registration, and hence fusion, of information within and across breast imaging modalities, and between the images and the physical space of the breast during interventions, remains an active research field which has yet to translate suitable methods into clinical practice. This review describes current research in the field of breast biomechanical modelling and identifies relevant publications where the resulting models have been incorporated into breast image registration and simulation algorithms. Despite these developments there remain a number of issues that limit clinical application of biomechanical modelling. These include the accuracy of constitutive modelling, implementation of representative boundary conditions, failure to meet clinically acceptable levels of computational cost, challenges associated with automating patient-specific model generation (i.e. robust image segmentation and mesh generation) and the complexity of applying biomechanical modelling methods in routine clinical practice.

Fully Automated Quantitative Estimation of Volumetric Breast Density from Digital Breast Tomosynthesis Images: Preliminary Results and Comparison with Digital Mammography and MR Imaging

PURPOSE

To assess a fully automated method for volumetric breast density (VBD) estimation in digital breast tomosynthesis (DBT) and to compare the findings with those of full-field digital mammography (FFDM) and magnetic resonance (MR) imaging.

MATERIALS AND METHODS

Bilateral DBT images, FFDM images, and sagittal breast MR images were retrospectively collected from 68 women who underwent breast cancer screening from October 2011 to September 2012 with institutional review board-approved, HIPAA-compliant protocols. A fully automated computer algorithm was developed for quantitative estimation of VBD from DBT images. FFDM images were processed with U.S. Food and Drug Administration-cleared software, and the MR images were processed with a previously validated automated algorithm to obtain corresponding VBD estimates. Pearson correlation and analysis of variance with Tukey-Kramer post hoc correction were used to compare the multimodality VBD estimates.

RESULTS

Estimates of VBD from DBT were significantly correlated with FFDM-based and MR imaging-based estimates with r = 0.83 (95% confidence interval [CI]: 0.74, 0.90) and r = 0.88 (95% CI: 0.82, 0.93), respectively (P < .001). The corresponding correlation between FFDM and MR imaging was r = 0.84 (95% CI: 0.76, 0.90). However, statistically significant differences after post hoc correction (α = 0.05) were found among VBD estimates from FFDM (mean ± standard deviation, 11.1% ± 7.0) relative to MR imaging (16.6% ± 11.2) and DBT (19.8% ± 16.2). Differences between VDB estimates from DBT and MR imaging were not significant (P = .26).

CONCLUSION

Fully automated VBD estimates from DBT, FFDM, and MR imaging are strongly correlated but show statistically significant differences. Therefore, absolute differences in VBD between FFDM, DBT, and MR imaging should be considered in breast cancer risk assessment.

A Review on Automatic Mammographic Density and Parenchymal Segmentation

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models.

Reliability of automated breast density measurements

PURPOSE

To estimate the reliability of a reference standard two-dimensional area-based method and three automated volumetric breast density measurements by using repeated measures.

MATERIALS AND METHODS

Thirty women undergoing screening mammography consented to undergo a repeated left craniocaudal examination performed by a second technologist in this prospective institutional review board-approved HIPAA-compliant study. Breast density was measured by using an area-based method (Cumulus ABD) and three automated volumetric methods (CumulusV [University of Toronto], Volpara [version 1.4.5; Volpara Solutions, Wellington, New Zealand), and Quantra [version 2.0; Hologic, Danbury, Conn]). Discrepancy between the first and second breast density measurements (Δ1-2) was obtained for each algorithm by subtracting the second measurement from the first. The Δ1-2 values of each algorithm were then analyzed with a random-effects model to derive Bland-Altman-type limits of measurement agreement.

RESULTS

Variability was higher for Cumulus ABD and CumulusV than for Volpara or Quantra. The within-breast density measurement standard deviations were 3.32% (95% confidence interval [CI]: 2.65, 4.44), 3.59% (95% CI: 2.86, 4.48), 0.99% (95% CI: 0.79, 1.33), and 1.64% (95% CI: 1.31, 1.39) for Cumulus ABD, CumulusV, Volpara, and Quantra, respectively. Although the mean discrepancy between repeat breast density measurements was not significantly different from zero for any of the algorithms, larger absolute breast density discrepancy (Δ1-2) values were associated with larger breast density values for Cumulus ABD and CumulusV but not for Volpara and Quantra.

CONCLUSION

Variability in a repeated measurement of breast density is lowest for Volpara and Quantra; these algorithms may be more suited to incorporation into a risk model.

Breast cancer risk analysis based on a novel segmentation framework for digital mammograms

The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value < 0.0001). We demonstrate the capability of our methods to discriminate between women with and without cancer by analyzing the contralateral mammograms of 50 women with unilateral breast cancer, and 50 controls. Using MD we obtained an area under the ROC curve (AUC) of 0.61; however our texture-based measure of mammographic pattern significantly outperforms the MD discrimination with an AUC of 0.70.

Measurement of breast density with digital breast tomosynthesis--a systematic review

Digital breast tomosynthesis (DBT) has gained acceptance as an adjunct to digital mammography in screening. Now that breast density reporting is mandated in several states in the USA, it is increasingly important that the methods of breast density measurement be robust, reliable and consistent. Breast density assessment with DBT needs some consideration since quantitative methods are modelled for two-dimensional (2D) mammography. A review of methods used for breast density assessment with DBT was performed. Existing evidence shows Cumulus has better reproducibility than that of the breast imaging reporting and data system (BI-RADS®) but still suffers from subjective variability; MedDensity is limited by image noise, whilst Volpara and Quantra are robust and consistent. The reported BI-RADs inter-reader breast density agreement (k) ranged from 0.65 to 0.91, with inter-reader correlation (r) ranging from 0.70 to 0.93. The correlation (r) between BI-RADS and Cumulus ranged from 0.54-0.94, whilst that of BI-RADs and MedDensity ranged from 0.48-0.78. The reported agreement (k) between BI-RADs and Volpara is 0.953. Breast density correlation between DBT and 2D mammography ranged from 0.73 to 0.97, with agreement (k) ranging from 0.56 to 0.96. To avoid variability and provide more reliable breast density information for clinicians, automated volumetric methods are preferred.

Comparison of volumetric breast density estimations from mammography and thorax CT

Breast density has become an important issue in current breast cancer screening, both as a recognized risk factor for breast cancer and by decreasing screening efficiency by the masking effect. Different qualitative and quantitative methods have been proposed to evaluate area-based breast density and volumetric breast density (VBD). We propose a validation method comparing the computation of VBD obtained from digital mammographic images (VBDMX) with the computation of VBD from thorax CT images (VBDCT). We computed VBDMX by applying a conversion function to the pixel values in the mammographic images, based on models determined from images of breast equivalent material. VBDCT is computed from the average Hounsfield Unit (HU) over the manually delineated breast volume in the CT images. This average HU is then compared to the HU of adipose and fibroglandular tissues from patient images. The VBDMX method was applied to 663 mammographic patient images taken on two Siemens Inspiration (hospL) and one GE Senographe Essential (hospJ). For the comparison study, we collected images from patients who had a thorax CT and a mammography screening exam within the same year. In total, thorax CT images corresponding to 40 breasts (hospL) and 47 breasts (hospJ) were retrieved. Averaged over the 663 mammographic images the median VBDMX was 14.7% . The density distribution and the inverse correlation between VBDMX and breast thickness were found as expected. The average difference between VBDMX and VBDCT is smaller for hospJ (4%) than for hospL (10%). This study shows the possibility to compare VBDMX with the VBD from thorax CT exams, without additional examinations. In spite of the limitations caused by poorly defined breast limits, the calibration of mammographic images to local VBD provides opportunities for further quantitative evaluations.

Research in digital mammography and tomosynthesis at the University of Toronto

There have been major advances in the field of breast cancer imaging since the early 1970s, both in technological improvements and in the use of the methods of medical physics and image analysis to optimize image quality. The introduction of digital mammography in 2000 provided a marked improvement in imaging of dense breasts. In addition, it became possible to produce tomographic and functional images on modified digital mammography systems. Digital imaging also greatly facilitated the extraction of quantitative information from images. My laboratory has been fortunate in being able to participate in some of these exciting developments. I will highlight some of the areas of our research interest which include modeling of the image formation process, development of high-resolution X-ray detectors for digital mammography and investigating new methods for analyzing image quality. I will also describe our more recent work on developing new applications of digital mammography including tomosynthesis, contrast-enhanced mammography, and measurement of breast density. Finally, I will point to a new area for our research--the application of the techniques of medical imaging to making pathology more quantitative to contribute to use of biomarkers for better characterizing breast cancer and directing therapeutic decisions.

Mammographic density estimation with automated volumetric breast density measurement

OBJECTIVE

To compare automated volumetric breast density measurement (VBDM) with radiologists' evaluations based on the Breast Imaging Reporting and Data System (BI-RADS), and to identify the factors associated with technical failure of VBDM.

MATERIALS AND METHODS

In this study, 1129 women aged 19-82 years who underwent mammography from December 2011 to January 2012 were included. Breast density evaluations by radiologists based on BI-RADS and by VBDM (Volpara Version 1.5.1) were compared. The agreement in interpreting breast density between radiologists and VBDM was determined based on four density grades (D1, D2, D3, and D4) and a binary classification of fatty (D1-2) vs. dense (D3-4) breast using kappa statistics. The association between technical failure of VBDM and patient age, total breast volume, fibroglandular tissue volume, history of partial mastectomy, the frequency of mass > 3 cm, and breast density was analyzed.

RESULTS

The agreement between breast density evaluations by radiologists and VBDM was fair (k value = 0.26) when the four density grades (D1/D2/D3/D4) were used and moderate (k value = 0.47) for the binary classification (D1-2/D3-4). Twenty-seven women (2.4%) showed failure of VBDM. Small total breast volume, history of partial mastectomy, and high breast density were significantly associated with technical failure of VBDM (p = 0.001 to 0.015).

CONCLUSION

There is fair or moderate agreement in breast density evaluation between radiologists and VBDM. Technical failure of VBDM may be related to small total breast volume, a history of partial mastectomy, and high breast density.

Breast density quantification with cone-beam CT: a post-mortem study

Forty post-mortem breasts were imaged with a flat-panel based cone-beam x-ray CT system at 50 kVp. The feasibility of breast density quantification has been investigated using standard histogram thresholding and an automatic segmentation method based on the fuzzy c-means algorithm (FCM). The breasts were chemically decomposed into water, lipid, and protein immediately after image acquisition was completed. The per cent fibroglandular volume (%FGV) from chemical analysis was used as the gold standard for breast density comparison. Both image-based segmentation techniques showed good precision in breast density quantification with high linear coefficients between the right and left breast of each pair. When comparing with the gold standard using %FGV from chemical analysis, Pearson's r-values were estimated to be 0.983 and 0.968 for the FCM clustering and the histogram thresholding techniques, respectively. The standard error of the estimate was also reduced from 3.92% to 2.45% by applying the automatic clustering technique. The results of the postmortem study suggested that breast tissue can be characterized in terms of water, lipid and protein contents with high accuracy by using chemical analysis, which offers a gold standard for breast density studies comparing different techniques. In the investigated image segmentation techniques, the FCM algorithm had high precision and accuracy in breast density quantification. In comparison to conventional histogram thresholding, it was more efficient and reduced inter-observer variation.

High mammographic density in women of Ashkenazi Jewish descent

Introduction

Percent mammographic density (PMD) adjusted for age and body mass index is one of the strongest risk factors for breast cancer and is known to be approximately 60% heritable. Here we report a finding of an association between genetic ancestry and adjusted PMD.

Methods

We selected self-identified Caucasian women in the California Pacific Medical Center Research Institute Cohort whose screening mammograms placed them in the top or bottom quintiles of age-adjusted and body mass index-adjusted PMD. Our final dataset included 474 women with the highest adjusted PMD and 469 with the lowest genotyped on the Illumina 1 M platform. Principal component analysis (PCA) and identity-by-descent analyses allowed us to infer the women's genetic ancestry and correlate it with adjusted PMD.

Results

Women of Ashkenazi Jewish ancestry, as defined by the first principal component of PCA and identity-by-descent analyses, represented approximately 15% of the sample. Ashkenazi Jewish ancestry, defined by the first principal component of PCA, was associated with higher adjusted PMD (P = 0.004). Using multivariate regression to adjust for epidemiologic factors associated with PMD, including age at parity and use of postmenopausal hormone therapy, did not attenuate the association.

Conclusions

Women of Ashkenazi Jewish ancestry, based on genetic analysis, are more likely to have high age-adjusted and body mass index-adjusted PMD. Ashkenazi Jews may have a unique set of genetic variants or environmental risk factors that increase mammographic density.

Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer

The role of breast image analysis in radiologists' interpretation tasks in cancer risk assessment, detection, diagnosis, and treatment continues to expand. Breast image analysis methods include segmentation, feature extraction techniques, classifier design, biomechanical modeling, image registration, motion correction, and rigorous methods of evaluation. We present a review of the current status of these task-based image analysis methods, which are being developed for the various image acquisition modalities of mammography, tomosynthesis, computed tomography, ultrasound, and magnetic resonance imaging. Depending on the task, image-based biomarkers from such quantitative image analysis may include morphological, textural, and kinetic characteristics and may depend on accurate modeling and registration of the breast images. We conclude with a discussion of future directions.

Statistical evaluation of a fully automated mammographic breast density algorithm

Visual assessments of mammographic breast density by radiologists are used in clinical practice; however, these assessments have shown weaker associations with breast cancer risk than area-based, quantitative methods. The purpose of this study is to present a statistical evaluation of a fully automated, area-based mammographic density measurement algorithm. Five radiologists estimated density in 5% increments for 138 “For Presentation” single MLO views; the median of the radiologists' estimates was used as the reference standard. Agreement amongst radiologists was excellent, ICC = 0.884, 95% CI (0.854, 0.910). Similarly, the agreement between the algorithm and the reference standard was excellent, ICC = 0.862, falling within the 95% CI of the radiologists' estimates. The Bland-Altman plot showed that the reference standard was slightly positively biased (+1.86%) compared to the algorithm-generated densities. A scatter plot showed that the algorithm moderately overestimated low densities and underestimated high densities. A box plot showed that 95% of the algorithm-generated assessments fell within one BI-RADS category of the reference standard. This study demonstrates the effective use of several statistical techniques that collectively produce a comprehensive evaluation of the algorithm and its potential to provide mammographic density measures that can be used to inform clinical practice.

Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c-means clustering and support vector machine segmentation

PURPOSE

The amount of fibroglandular tissue content in the breast as estimated mammographically, commonly referred to as breast percent density (PD%), is one of the most significant risk factors for developing breast cancer. Approaches to quantify breast density commonly focus on either semiautomated methods or visual assessment, both of which are highly subjective. Furthermore, most studies published to date investigating computer-aided assessment of breast PD% have been performed using digitized screen-film mammograms, while digital mammography is increasingly replacing screen-film mammography in breast cancer screening protocols. Digital mammography imaging generates two types of images for analysis, raw (i.e., "FOR PROCESSING") and vendor postprocessed (i.e., "FOR PRESENTATION"), of which postprocessed images are commonly used in clinical practice. Development of an algorithm which effectively estimates breast PD% in both raw and postprocessed digital mammography images would be beneficial in terms of direct clinical application and retrospective analysis.

METHODS

This work proposes a new algorithm for fully automated quantification of breast PD% based on adaptive multiclass fuzzy c-means (FCM) clustering and support vector machine (SVM) classification, optimized for the imaging characteristics of both raw and processed digital mammography images as well as for individual patient and image characteristics. Our algorithm first delineates the breast region within the mammogram via an automated thresholding scheme to identify background air followed by a straight line Hough transform to extract the pectoral muscle region. The algorithm then applies adaptive FCM clustering based on an optimal number of clusters derived from image properties of the specific mammogram to subdivide the breast into regions of similar gray-level intensity. Finally, a SVM classifier is trained to identify which clusters within the breast tissue are likely fibroglandular, which are then aggregated into a final dense tissue segmentation that is used to compute breast PD%. Our method is validated on a group of 81 women for whom bilateral, mediolateral oblique, raw and processed screening digital mammograms were available, and agreement is assessed with both continuous and categorical density estimates made by a trained breast-imaging radiologist.

RESULTS

Strong association between algorithm-estimated and radiologist-provided breast PD% was detected for both raw (r = 0.82, p < 0.001) and processed (r = 0.85, p < 0.001) digital mammograms on a per-breast basis. Stronger agreement was found when overall breast density was assessed on a per-woman basis for both raw (r = 0.85, p < 0.001) and processed (0.89, p < 0.001) mammograms. Strong agreement between categorical density estimates was also seen (weighted Cohen's κ ≥ 0.79). Repeated measures analysis of variance demonstrated no statistically significant differences between the PD% estimates (p > 0.1) due to either presentation of the image (raw vs processed) or method of PD% assessment (radiologist vs algorithm).

CONCLUSIONS

The proposed fully automated algorithm was successful in estimating breast percent density from both raw and processed digital mammographic images. Accurate assessment of a woman's breast density is critical in order for the estimate to be incorporated into risk assessment models. These results show promise for the clinical application of the algorithm in quantifying breast density in a repeatable manner, both at time of imaging as well as in retrospective studies.

An analysis of the mechanical parameters used for finite element compression of a high-resolution 3D breast phantom

PURPOSE

The authors previously introduced a methodology to generate a realistic three-dimensional (3D), high-resolution, computer-simulated breast phantom based on empirical data. One of the key components of such a phantom is that it provides a means to produce a realistic simulation of clinical breast compression. In the current study, they have evaluated a finite element (FE) model of compression and have demonstrated the effect of a variety of mechanical properties on the model using a dense mesh generated from empirical breast data. While several groups have demonstrated an effective compression simulation with lower density finite element meshes, the presented study offers a mesh density that is able to model the morphology of the inner breast structures more realistically than lower density meshes. This approach may prove beneficial for multimodality breast imaging research, since it provides a high level of anatomical detail throughout the simulation study.

METHODS

In this paper, the authors describe methods to improve the high-resolution performance of a FE compression model. In order to create the compressible breast phantom, dedicated breast CT data was segmented and a mesh was generated with 4-noded tetrahedral elements. Using an explicit FE solver to simulate breast compression, several properties were analyzed to evaluate their effect on the compression model including: mesh density, element type, density, and stiffness of various tissue types, friction between the skin and the compression plates, and breast density. Following compression, a simulated projection was generated to demonstrate the ability of the compressible breast phantom to produce realistic simulated mammographic images.

RESULTS

Small alterations in the properties of the breast model can change the final distribution of the tissue under compression by more than 1 cm; which ultimately results in different representations of the breast model in the simulated images. The model properties that impact displacement the most are mesh density, friction between the skin and the plates, and the relative stiffness of the different tissue types.

CONCLUSIONS

The authors have developed a 3D, FE breast model that can yield high spatial resolution breast deformations under uniaxial compression for imaging research purposes and demonstrated that small changes in the mechanical properties can affect images generated using the phantom.