A Comparative Study of the Inter-reader Variability of Breast Percent Density Estimation in Digital Mammography: Potential Effect of Reader’s Training and Clinical Experience. In: Martí J, Oliver A, Freixenet J, Martí R, editors. Digital Mammography. Berlin: Springer Berlin Heidelberg; 2010. pp. 114-20. [DOI: 10.1007/978-3-642-13666-5_16]

Reliability of Computer-Assisted Breast Density Estimation: Comparison of Interactive Thresholding, Semiautomated, and Fully Automated Methods

OBJECTIVE

The purpose of this study was to investigate the reliability of computer-assisted methods of estimating breast density.

MATERIALS AND METHODS

Craniocaudal mammograms of 100 healthy subjects were collected from a screening mammography database. Three expert readers independently assessed mammographic breast density twice in a 1-month period using interactive thresholding and semiautomated methods. In addition, fully automated breast density estimation software was used to generate objective breast density estimates. The reliability of the computer-assisted breast density estimation was assessed in terms of concordance correlation coefficients, limits of agreement, systematic difference, and reader variability.

RESULTS

Statistically significant systematic bias (paired t test, p < 0.01) and variability (4.75-10.91) were found within and between readers for both the interactive thresholding and the semiautomated methods. Using the semiautomated method significantly reduced the within-reader bias of one reader (p < 0.02) and the between-reader variability of all three readers (p < 0.05). The breast density estimates obtained with the fully automated method had excellent agreement with those of the reference standard (concordance correlation coefficient, 0.93) without a significant systematic difference.

CONCLUSION

Reader-dependent variability and systematic bias exist in breast density estimates obtained with the interactive thresholding method, but they may be reduced in part by use of the semiautomated method. Assessing reader performance may be necessary for more reliable breast density estimation, especially for surveillance of breast density over time. The fully automated method has the potential to provide reliable breast density estimates nearly free from reader-dependent systematic bias and reader variability.

Mammographic breast density: comparison of methods for quantitative evaluation

PURPOSE

To evaluate the results from two software tools for measurement of mammographic breast density and compare them with observer-based scores in a large cohort of women.

MATERIALS AND METHODS

Following written informed consent, a data set of 36 281 mammograms from 8867 women were collected from six United Kingdom centers in an ethically approved trial. Breast density was assessed by one of 26 readers on a visual analog scale and with two automated density tools. Mean differences were calculated as the mean of all the individual percentage differences between each measurement for each case (woman). Agreement in total breast volume, fibroglandular volume, and percentage density was assessed with the Bland-Altman method. Association with observer's scores was calculated by using the Pearson correlation coefficient (r).

RESULTS

Correlation between the Quantra and Volpara outputs for total breast volume was r = 0.97 (P < .001), with a mean difference of 43.5 cm(3) for all cases representing 5.0% of the mean total breast volume. Correlation of the two measures was lower for fibroglandular volume (r = 0.86, P < .001). The mean difference was 30.3 cm(3) for all cases representing 21.2% of the mean fibroglandular tissue volume result. Quantra gave the larger value and the difference tended to increase with volume. For the two measures of percentage volume density, the mean difference was 1.61 percentage points (r = 0.78, P < .001). Comparison of observer's scores with the area-based density given by Quantra yielded a low correlation (r = 0.55, P < .001). Correlations of observer's scores with the volumetric density results gave r values of 0.60 (P < .001) and 0.63 (P < .001) for Quantra and Volpara, respectively.

CONCLUSION

Automated techniques for measuring breast density show good correlation, but these are poorly correlated with observer's scores. However automated techniques do give different results that should be considered when informing patient personalized imaging. (©) RSNA, 2015 Clinical trial registration no. ISRCTN 73467396.

The TOMMY trial: a comparison of TOMosynthesis with digital MammographY in the UK NHS Breast Screening Programme--a multicentre retrospective reading study comparing the diagnostic performance of digital breast tomosynthesis and digital mammography with digital mammography alone

BACKGROUND

Digital breast tomosynthesis (DBT) is a three-dimensional mammography technique with the potential to improve accuracy by improving differentiation between malignant and non-malignant lesions.

OBJECTIVES

The objectives of the study were to compare the diagnostic accuracy of DBT in conjunction with two-dimensional (2D) mammography or synthetic 2D mammography, against standard 2D mammography and to determine if DBT improves the accuracy of detection of different types of lesions.

STUDY POPULATION

Women (aged 47-73 years) recalled for further assessment after routine breast screening and women (aged 40-49 years) with moderate/high of risk of developing breast cancer attending annual mammography screening were recruited after giving written informed consent.

INTERVENTION

All participants underwent a two-view 2D mammography of both breasts and two-view DBT imaging. Image-processing software generated a synthetic 2D mammogram from the DBT data sets.

RETROSPECTIVE READING STUDY

In an independent blinded retrospective study, readers reviewed (1) 2D or (2) 2D + DBT or (3) synthetic 2D + DBT images for each case without access to original screening mammograms or prior examinations. Sensitivities and specificities were calculated for each reading arm and by subgroup analyses.

RESULTS

Data were available for 7060 subjects comprising 6020 (1158 cancers) assessment cases and 1040 (two cancers) family history screening cases. Overall sensitivity was 87% [95% confidence interval (CI) 85% to 89%] for 2D only, 89% (95% CI 87% to 91%) for 2D + DBT and 88% (95% CI 86% to 90%) for synthetic 2D + DBT. The difference in sensitivity between 2D and 2D + DBT was of borderline significance (p = 0.07) and for synthetic 2D + DBT there was no significant difference (p = 0.6). Specificity was 58% (95% CI 56% to 60%) for 2D, 69% (95% CI 67% to 71%) for 2D + DBT and 71% (95% CI 69% to 73%) for synthetic 2D + DBT. Specificity was significantly higher in both DBT reading arms for all subgroups of age, density and dominant radiological feature (p < 0.001 all cases). In all reading arms, specificity tended to be lower for microcalcifications and higher for distortion/asymmetry. Comparing 2D + DBT to 2D alone, sensitivity was significantly higher: 93% versus 86% (p < 0.001) for invasive tumours of size 11-20 mm. Similarly, for breast density 50% or more, sensitivities were 93% versus 86% (p = 0.03); for grade 2 invasive tumours, sensitivities were 91% versus 87% (p = 0.01); where the dominant radiological feature was a mass, sensitivities were 92% and 89% (p = 0.04) For synthetic 2D + DBT, there was significantly (p = 0.006) higher sensitivity than 2D alone in invasive cancers of size 11-20 mm, with a sensitivity of 91%.

CONCLUSIONS

The specificity of DBT and 2D was better than 2D alone but there was only marginal improvement in sensitivity. The performance of synthetic 2D appeared to be comparable to standard 2D. If these results were observed with screening cases, DBT and 2D mammography could benefit to the screening programme by reducing the number of women recalled unnecessarily, especially if a synthetic 2D mammogram were used to minimise radiation exposure. Further research is required into the feasibility of implementing DBT in a screening setting, prognostic modelling on outcomes and mortality, and comparison of 2D and synthetic 2D for different lesion types.

STUDY REGISTRATION

Current Controlled Trials ISRCTN73467396.

FUNDING

This project was funded by the NIHR Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol. 19, No. 4. See the HTA programme website for further project information.

Reader variability in breast density estimation from full-field digital mammograms: the effect of image postprocessing on relative and absolute measures

RATIONALE AND OBJECTIVES

Mammographic breast density, a strong risk factor for breast cancer, may be measured as either a relative percentage of dense (ie, radiopaque) breast tissue or as an absolute area from either raw (ie, "for processing") or vendor postprocessed (ie, "for presentation") digital mammograms. Given the increasing interest in the incorporation of mammographic density in breast cancer risk assessment, the purpose of this study is to determine the inherent reader variability in breast density assessment from raw and vendor-processed digital mammograms, because inconsistent estimates could to lead to misclassification of an individual woman's risk for breast cancer.

MATERIALS AND METHODS

Bilateral, mediolateral-oblique view, raw, and processed digital mammograms of 81 women were retrospectively collected for this study (N = 324 images). Mammographic percent density and absolute dense tissue area estimates for each image were obtained from two radiologists using a validated, interactive software tool.

RESULTS

The variability of interreader agreement was not found to be affected by the image presentation style (ie, raw or processed, F-test: P > .5). Interreader estimates of relative and absolute breast density are strongly correlated (Pearson r > 0.84, P < .001) but systematically different (t-test, P < .001) between the two readers.

CONCLUSION

Our results show that mammographic density may be assessed with equal reliability from either raw or vendor postprocessed images. Furthermore, our results suggest that the primary source of density variability comes from the subjectivity of the individual reader in assessing the absolute amount of dense tissue present in the breast, indicating the need to use standardized tools to mitigate this effect.

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.

Analysis of parenchymal texture with digital breast tomosynthesis: comparison with digital mammography and implications for cancer risk assessment

PURPOSE

To correlate the parenchymal texture features at digital breast tomosynthesis (DBT) and digital mammography with breast percent density (PD), an established breast cancer risk factor, in a screening population of women.

MATERIALS AND METHODS

This HIPAA-compliant study was approved by the institutional review board. Bilateral DBT images and digital mammograms from 71 women (mean age, 54 years; age range, 34-75 years) with negative or benign findings at screening mammography were retrospectively collected from a separate institutional review board-approved DBT screening trial (performed from July 2007 to March 2008) in which all women had given written informed consent. Parenchymal texture features of skewness, coarseness, contrast, energy, homogeneity, and fractal dimension were computed from the retroareolar region. Principal component analysis (PCA) was applied to obtain orthogonal texture components. Mammographic PD was estimated with software. Correlation analysis and multiple linear regression with generalized estimating equations were performed to determine the association between texture features and breast PD. Regression was adjusted for age to determine the independent association of texture to breast PD when age was also considered as a predictor variable.

RESULTS

Texture feature correlations to breast PD were stronger with DBT than with digital mammography. Statistically significant correlations (P < .001) were observed for contrast (r = 0.48), energy (r = -0.47), and homogeneity (r = -0.56) at DBT and for contrast (r = 0.26), energy (r = -0.26), and homogeneity (r = -0.33) at digital mammography. Multiple linear regression analysis of PCA texture components as predictors of PD also demonstrated significantly stronger associations with DBT. The association was strongest when age was also considered as a predictor of PD (R² = 0.41 for DBT and 0.28 for digital mammography; P < .001).

CONCLUSION

Parenchymal texture features are more strongly correlated to breast PD in DBT than in digital mammography. The authors' long-term hypothesis is that parenchymal texture analysis with DBT will result in quantitative imaging biomarkers that can improve the estimation of breast cancer risk.