Brad M. Keller

Parenchymal texture analysis in digital mammography: A fully automated pipeline for breast cancer risk assessment.

PURPOSE Mammographic percent density (PD%) is known to be a strong risk factor for breast cancer. Recent studies also suggest that parenchymal texture features, which are more granular descriptors of the parenchymal pattern, can provide additional information about breast cancer risk. To date, most studies have measured mammographic texture within selected regions of interest (ROIs) in the breast, which cannot adequately capture the complexity of the parenchymal pattern throughout the whole breast. To better characterize patterns of the parenchymal tissue, the authors have developed a fully automated software pipeline based on a novel lattice-based strategy to extract a range of parenchymal texture features from the entire breast region. METHODS Digital mammograms from 106 cases with 318 age-matched controls were retrospectively analyzed. The lattice-based approach is based on a regular grid virtually overlaid on each mammographic image. Texture features are computed from the intersection (i.e., lattice) points of the grid lines within the breast, using a local window centered at each lattice point. Using this strategy, a range of statistical (gray-level histogram, co-occurrence, and run-length) and structural (edge-enhancing, local binary pattern, and fractal dimension) features are extracted. To cover the entire breast, the size of the local window for feature extraction is set equal to the lattice grid spacing and optimized experimentally by evaluating different windows sizes. The association between their lattice-based texture features and breast cancer was evaluated using logistic regression with leave-one-out cross validation and further compared to that of breast PD% and commonly used single-ROI texture features extracted from the retroareolar or the central breast region. Classification performance was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC). DeLongs test was used to compare the different ROCs in terms of AUC performance. RESULTS The average univariate performance of the lattice-based features is higher when extracted from smaller than larger window sizes. While not every individual texture feature is superior to breast PD% (AUC: 0.59, STD: 0.03), their combination in multivariate analysis has significantly better performance (AUC: 0.85, STD: 0.02, p < 0.001). The lattice-based texture features also outperform the single-ROI texture features when extracted from the retroareolar or the central breast region (AUC: 0.60-0.74, STD: 0.03). Adding breast PD% does not make a significant performance improvement to the lattice-based texture features or the single-ROI features (p > 0.05). CONCLUSIONS The proposed lattice-based strategy for mammographic texture analysis enables to characterize the parenchymal pattern over the entire breast. As such, these features provide richer information compared to currently used descriptors and may ultimately improve breast cancer risk assessment. Larger studies are warranted to validate these findings and also compare to standard demographic and reproductive risk factors.

Preliminary evaluation of the publicly available Laboratory for Breast Radiodensity Assessment (LIBRA) software tool: comparison of fully automated area and volumetric density measures in a case-control study with digital mammography.

IntroductionBreast density, commonly quantified as the percentage of mammographically dense tissue area, is a strong breast cancer risk factor. We investigated associations between breast cancer and fully automated measures of breast density made by a new publicly available software tool, the Laboratory for Individualized Breast Radiodensity Assessment (LIBRA).MethodsDigital mammograms from 106 invasive breast cancer cases and 318 age-matched controls were retrospectively analyzed. Density estimates acquired by LIBRA were compared with commercially available software and standard Breast Imaging-Reporting and Data System (BI-RADS) density estimates. Associations between the different density measures and breast cancer were evaluated by using logistic regression after adjustment for Gail risk factors and body mass index (BMI). Area under the curve (AUC) of the receiver operating characteristic (ROC) was used to assess discriminatory capacity, and odds ratios (ORs) for each density measure are provided.ResultsAll automated density measures had a significant association with breast cancer (OR = 1.47–2.23, AUC = 0.59–0.71, P < 0.01) which was strengthened after adjustment for Gail risk factors and BMI (OR = 1.96–2.64, AUC = 0.82–0.85, P < 0.001). In multivariable analysis, absolute dense area (OR = 1.84, P < 0.001) and absolute dense volume (OR = 1.67, P = 0.003) were jointly associated with breast cancer (AUC = 0.77, P < 0.01), having a larger discriminatory capacity than models considering the Gail risk factors alone (AUC = 0.64, P < 0.001) or the Gail risk factors plus standard area percent density (AUC = 0.68, P = 0.01). After BMI was further adjusted for, absolute dense area retained significance (OR = 2.18, P < 0.001) and volume percent density approached significance (OR = 1.47, P = 0.06). This combined area-volume density model also had a significantly (P < 0.001) improved discriminatory capacity (AUC = 0.86) relative to a model considering the Gail risk factors plus BMI (AUC = 0.80).ConclusionsOur study suggests that new automated density measures may ultimately augment the current standard breast cancer risk factors. In addition, the ability to fully automate density estimation with digital mammography, particularly through the use of publically available breast density estimation software, could accelerate the translation of density reporting in routine breast cancer screening and surveillance protocols and facilitate broader research into the use of breast density as a risk factor for breast cancer.

Adaptive multi-cluster fuzzy C-means segmentation of breast parenchymal tissue in digital mammography

The relative fibroglandular tissue content in the breast, commonly referred to as breast density, has been shown to be the most significant risk factor for breast cancer after age. Currently, the most common approaches to quantify density are based on either semi-automated methods or visual assessment, both of which are highly subjective. This work presents a novel multi-class fuzzy c-means (FCM) algorithm for fully-automated identification and quantification of breast density, optimized for the imaging characteristics of digital mammography. The proposed algorithm involves adaptive FCM clustering based on an optimal number of clusters derived by the tissue properties of the specific mammogram, followed by generation of a final segmentation through cluster agglomeration using linear discriminant analysis. When evaluated on 80 bilateral screening digital mammograms, a strong correlation was observed between algorithm-estimated PD% and radiological ground-truth of r=0.83 (p<0.001) and an average Jaccard spatial similarity coefficient of 0.62. These results show promise for the clinical application of the algorithm in quantifying breast density in a repeatable manner.

Emphysema Predicts Hospitalisation and Incident Airflow Obstruction among Older Smokers: A Prospective Cohort Study

Background Emphysema on CT is common in older smokers. We hypothesised that emphysema on CT predicts acute episodes of care for chronic lower respiratory disease among older smokers. Materials and Methods Participants in a lung cancer screening study age ≥60 years were recruited into a prospective cohort study in 2001–02. Two radiologists independently visually assessed the severity of emphysema as absent, mild, moderate or severe. Percent emphysema was defined as the proportion of voxels ≤ −910 Hounsfield Units. Participants completed a median of 5 visits over a median of 6 years of follow-up. The primary outcome was hospitalization, emergency room or urgent office visit for chronic lower respiratory disease. Spirometry was performed following ATS/ERS guidelines. Airflow obstruction was defined as FEV1/FVC ratio <0.70 and FEV1<80% predicted. Results Of 521 participants, 4% had moderate or severe emphysema, which was associated with acute episodes of care (rate ratio 1.89; 95% CI: 1.01–3.52) adjusting for age, sex and race/ethnicity, as was percent emphysema, with similar associations for hospitalisation. Emphysema on visual assessment also predicted incident airflow obstruction (HR 5.14; 95% CI 2.19–21.1). Conclusion Visually assessed emphysema and percent emphysema on CT predicted acute episodes of care for chronic lower respiratory disease, with the former predicting incident airflow obstruction among older smokers.

Parenchymal texture analysis in digital mammography: robust texture feature identification and equivalence across devices

Abstract. An analytical framework is presented for evaluating the equivalence of parenchymal texture features across different full-field digital mammography (FFDM) systems using a physical breast phantom. Phantom images (FOR PROCESSING) are acquired from three FFDM systems using their automated exposure control setting. A panel of texture features, including gray-level histogram, co-occurrence, run length, and structural descriptors, are extracted. To identify features that are robust across imaging systems, a series of equivalence tests are performed on the feature distributions, in which the extent of their intersystem variation is compared to their intrasystem variation via the Hodges–Lehmann test statistic. Overall, histogram and structural features tend to be most robust across all systems, and certain features, such as edge enhancement, tend to be more robust to intergenerational differences between detectors of a single vendor than to intervendor differences. Texture features extracted from larger regions of interest (i.e., >63  pixels2) and with a larger offset length (i.e., >7  pixels), when applicable, also appear to be more robust across imaging systems. This framework and observations from our experiments may benefit applications utilizing mammographic texture analysis on images acquired in multivendor settings, such as in multicenter studies of computer-aided detection and breast cancer risk assessment.

Fully-automated fibroglandular tissue segmentation in breast MRI

We propose an automated segmentation method for estimating the fibroglandular (i.e., dense) tissue in breast MRI. The first step of our method is to segment the breast as an organ from other imaged parts through an integrated edge extraction and voting algorithm. Then, we apply the nonparametric non-uniform intensity normalization (N3) algorithm to the segmented breast to correct bias field which is common in breast MRI. After that, fuzzy C-means clustering is performed to categorize the breast tissue into two clusters, i.e., fibroglandular tissue and fat. The automated segmentation results are compared to manual segmentations, verified by an experienced breast imaging radiologist, to assess the accuracy of the algorithm, where the Dices Similarity Coefficient (DSC) shows a 0.73 agreement in our experiments. The benefit of the bias correction step is also shown through the comparison with the results obtained by excluding the bias correction step.

Multivariate Compensation of Quantitative Pulmonary Emphysema Metric Variation From Low-Dose, Whole-Lung CT Scans

OBJECTIVE Emphysema is a disease of the lung characterized by the destruction of the alveolar sac walls. Several quantitative densitometric measures of emphysema from wholelung CT have been proposed for evaluating disease severity and progression. However, a concern with these quantitative measures has been the large interscan variability observed during longitudinal studies of emphysema. To account for and reduce inherent measure variability, this work implements and evaluates the use of a multivariate random-effects model for correcting longitudinal variation in densitometric scores of emphysema due to inspiration. MATERIALS AND METHODS The method of multivariate compensation was validated on three of the most commonly reported densitometric measures of emphysema: the emphysema index, histogram percentile, and fractal dimension. Two short-interval, zero-change datasets, one for model development (n = 105) and one for validation (n = 106), were retrospectively identified and used to ensure that all variation was caused by inherent measure variability. RESULTS A statistically significant (F test, p < 0.001) reduction of 42.40% in measurement limits of agreement could be obtained after model application, with compensated emphysema metric differences showing 31-33% of the variance compared with uncompensated metric variance. CONCLUSION Compensation was still effective when the trained model was applied to the second validation dataset. Multivariate compensation was found to be useful in reducing interscan measurement variability and should be applied to future longitudinal studies of emphysema.

Associations between breast density and a panel of single nucleotide polymorphisms linked to breast cancer risk: a cohort study with digital mammography

BackgroundBreast density and single-nucleotide polymorphisms (SNPs) have both been associated with breast cancer risk. To determine the extent to which these two breast cancer risk factors are associated, we investigate the association between a panel of validated SNPs related to breast cancer and quantitative measures of mammographic density in a cohort of Caucasian and African-American women.MethodsIn this IRB-approved, HIPAA-compliant study, we analyzed a screening population of 639 women (250 African American and 389 Caucasian) who were tested with a validated panel assay of 12 SNPs previously associated to breast cancer risk. Each woman underwent digital mammography as part of routine screening and all were interpreted as negative. Both absolute and percent estimates of area and volumetric density were quantified on a per-woman basis using validated software. Associations between the number of risk alleles in each SNP and the density measures were assessed through a race-stratified linear regression analysis, adjusted for age, BMI, and Gail lifetime risk.ResultsThe majority of SNPs were not found to be associated with any measure of breast density. SNP rs3817198 (in LSP1) was significantly associated with both absolute area (p = 0.004) and volumetric (p = 0.019) breast density in Caucasian women. In African-American women, SNPs rs3803662 (in TNRC9/TOX3) and rs4973768 (in NEK10) were significantly associated with absolute (p = 0.042) and percent (p = 0.028) volume density respectively.ConclusionsThe majority of SNPs investigated in our study were not found to be significantly associated with breast density, even when accounting for age, BMI, and Gail risk, suggesting that these two different risk factors contain potentially independent information regarding a woman’s risk to develop breast cancer. Additionally, the few statistically significant associations between breast density and SNPs were different for Caucasian versus African American women. Larger prospective studies are warranted to validate our findings and determine potential implications for breast cancer risk assessment.

Mammographic Parenchymal Patterns as an Imaging Marker of Endogenous Hormonal Exposure: A Preliminary Study in a High-Risk Population

RATIONALE AND OBJECTIVES Parenchymal texture patterns have been previously associated with breast cancer risk, yet their underlying biological determinants remain poorly understood. Here, we investigate the potential of mammographic parenchymal texture as a phenotypic imaging marker of endogenous hormonal exposure. MATERIALS AND METHODS A retrospective cohort study was performed. Digital mammography (DM) images in the craniocaudal (CC) view from 297 women, 154 without breast cancer and 143 with unilateral breast cancer, were analyzed. Menopause status was used as a surrogate of cumulative endogenous hormonal exposure. Parenchymal texture features were extracted and mammographic percent density (MD%) was computed using validated computerized methods. Univariate and multivariable logistic regression analysis was performed to assess the association between texture features and menopause status, after adjusting for MD% and hormonally related confounders. The receiver operating characteristic (ROC) area under the curve (AUC) of each model was estimated to evaluate the degree of association between the extracted mammographic features and menopause status. RESULTS Coarseness, gray-level correlation, and fractal dimension texture features have a significant independent association with menopause status in the cancer-affected population; skewness and fractal dimension exhibit a similar association in the cancer-free population (P < .05). The ROC AUC of the logistic regression model including all texture features was 0.70 (P < .05) for cancer-affected and 0.63 (P < .05) for cancer-free women. Texture features retained significant association with menopause status (P < .05) after adjusting for MD%, age at menarche, ethnicity, contraception use, hormone replacement therapy, parity, and age at first birth. CONCLUSION Mammographic texture patterns may reflect the effect of endogenous hormonal exposure on the breast tissue and may capture such effects beyond mammographic density. Differences in texture features between pre- and postmenopausal women are more pronounced in the cancer-affected population, which may be attributed to an increased association to breast cancer risk. Texture features could ultimately be incorporated in breast cancer risk assessment models as markers of hormonal exposure.

Breast cancer risk prediction via area and volumetric estimates of breast density

We performed a study to assess the potential value of absolute and relative measures of area and volumetric breast density in predicting breast cancer risk. A case-control study was performed. The raw mediolateral-oblique (MLO) view digital mammography (DM) images of 106 women with unilateral breast cancer and 318 age-matched controls were retrospectively analyzed. The unaffected breast of the cancer cases was used as a surrogate of higher cancer risk. For each image, area and volumetric breast density measures were estimated using fully-automated software. The performance of the density metrics to distinguish between cancer cases and controls was assessed using linear discriminant and ROC curve analysis. Absolute measures of dense tissue content had stronger discriminatory capacity (AUCs=0.65-0.67) than percent density (AUCs=0.57). Shape-location features also showed modest discriminatory power (AUC=0.56-0.65). A combined area-volumetric model was able to outperform (AUC=0.70) any single-feature model. Absolute measures of fibroglandular tissue content were seen to be more discriminative than percent density estimates, indicating that total fibroglandular tissue content may be more reflective of cancer risk than relative measures of density. Our results suggest that area and volumetric breast density measures could be complementary in breast cancer risk assessment.