1.1.

Clinical Background

Breast density is an important topic in breast cancer screening because of two aspects. First, a high amount of dense (fibroglandular) breast tissue is considered to be an independent risk factor for developing breast cancer, and second, sensitivity of mammography is lower in dense breasts due to the masking effect.¹ Supplemental imaging for dense breasts [e.g., breast ultrasound, breast magnetic resonance imaging (MRI)] can thus be useful to increase cancer detection rates in breast cancer screening.² Nowadays, the majority of the US states require that women are informed if they have dense breast tissue and they will receive information about supplemental imaging options.^3,4

Radiologists typically estimate breast density during interpretation of the mammograms. However, visual breast density assessment is known to have considerable intra- and inter-reader variability.⁵ Automated breast density assessment by computer software is increasingly used to assist radiologists in reporting breast density more objectively and consistently.

The time when breast density is assessed has a considerable impact on a personalized screening work flow. When breast density is assessed by radiologists, the woman usually has already left the screening center. Supplemental imaging requires the woman to be called back for an extra assessment.

If, however, automated breast density assessment is provided during the screening appointment, then the work flow might be sped up considerably. If supplemental imaging is recommended, it could be initiated before the woman leaves the screening center (Fig. 1). The women could get the result of the recommended supplemental imaging test on the day of screening, which would reduce psychological distress. This procedure, though, would require an organizational change in scheduling, a problem that should be solvable after having gained experience and after a transition to routine.

Fig. 1

Screening workflow with breast density assessment at the time of examination allowing to initiate supplemental imaging before the woman leaves the screening center.

1.2.

Automated Breast Density Assessment

Several techniques for automated breast density measurement from mammographic x-ray images have been proposed.^6,7 These techniques either calculate the projected two-dimensional (2-D) area (in ${\mathrm{cm}}^2$) of dense tissue in the x-ray image or quantify the three-dimensional (3-D) volume (in ${\mathrm{cm}}^3$) of the dense tissue in the breast. The calculation of the projected 2-D area of dense tissue requires a segmentation of the dense tissue areas in the image.⁸ For quantification of the 3-D volume of the dense tissue, the physics of the image acquisition process is modeled and it can involve either a precalibration of the system,⁹ a calibration object in the acquired image,¹⁰ or an image-based self-calibration step.¹¹

A breast density (percentage) value can be computed by dividing the area or volume of dense tissue with the total area or volume of the breast. Because areal and volumetric breast density (VBD) values are computed from different quantities, they have different value ranges and they cannot be compared directly.¹²

Breast density classification has a high clinical relevance. A breast density category can be determined from a measured breast density value by using cut points. Furthermore, machine learning–based algorithms exist that assign a breast density category directly based on extracted image features, such as parenchymal texture or histogram information.⁷ Recently, also, deep machine learning techniques have been applied for breast density classification.¹³

For using an automated breast density assessment software for clinical decision support, it should be validated comprehensively. Ng and Lau⁷ have identified six requirements (denoted in their paper as “sanity checks”) that should be fulfilled by an automated breast density measurement software:

Some studies exist that validate existing software applications for automated breast density assessment.^14–19 Typical aspects assessed by these studies are accuracy (comparing measured breast density to an objective ground truth), reproducibility (see Ng and Lau’s requirements 1 to 5), consistency (see Ng and Lau’s requirement 6), and agreement with visual assessment (comparing classified breast density to a subjective reference).

Recently, an automated breast density measurement software (Insight BD, Siemens Healthcare GmbH) has been integrated into the acquisition work station of a mammography system (MAMMOMAT Revelation, Siemens Healthcare GmbH; Insight BD and MAMMOMAT Revelation are not commercially available in all countries. Due to regulatory reasons, the future availability cannot be guaranteed). This allows objective evaluation of breast density directly after the mammographic exam. In this work, we evaluate performance of the software Insight BD to measure VBD. In particular, we evaluate whether the software satisfies the six requirements identified by Ng and Lau. This paper is a substantially expanded version of a previously published conference paper.²⁰

2.1.

Volumetric Breast Density Measurement

Insight BD measures VBD based on a physics model of the image acquisition process and an image-based self-calibration.^11,21 This model appears to be the basis of most commercial software implementations to assess breast density.⁷ The model assumes that the breast consists of two types of tissue, fibroglandular and fatty tissue, with known energy-dependent x-ray attenuation values.

The algorithm receives an unprocessed full-field digital mammogram (FFDM) or an unprocessed central digital breast tomosynthesis (DBT) projection image as input along with the image acquisition parameters such as compressed breast thickness and peak tube voltage. For each detector pixel location, the amount of fibroglandular tissue (measured in mm) located above the pixel is calculated and a 2-D breast density map is created. The total amount of fibroglandular tissue ($V_{\mathrm{fg}}$, measured in ${\mathrm{cm}}^3$) is determined from the map by numerical integration over the projected breast area. The volume of the breast, $V_{\text{breast}}$, is determined using the known compressed thickness of the breast, its projected surface area, and a 3-D shape model. For determining $V_{\mathrm{fg}}$ and $V_{\text{breast}}$, the pectoral muscle region is excluded.

The VBD is calculated by dividing $V_{\mathrm{fg}}$ by the total breast volume ($V_{\mathrm{breast}}$, measured in ${\mathrm{cm}}^3$):

Breast density categories (a, b, c, and d) correlating with those from ACR BI-RADS fifth ed. atlas²² are assigned by using VBD cut points. To aid classification between categories “b” and “c,” considered to be a nondense and dense breast, respectively, the distribution of dense tissue is also taken into account as described by Fieselmann et al.²¹

The software framework used in this work consists of a core module for the VBD measurement and a wrapper around this module allowing for batch processing of many image files at once. The core module is the same as the one implemented in the Insight BD application of the MAMMOMAT Revelation mammography system.

2.2.

Evaluation of Accuracy

Accuracy of breast density measurement is evaluated using phantoms with physical characteristics similar to that of breast tissue (phototimer compensation plates; CIRS Inc., Norfolk, Virginia).

Plates simulating 100% fatty breast tissue and plates simulating fibroglandular breast tissue are placed on the left and right sides, respectively, of the breast support table (Fig. 2). Different glandularities (right side only: 30%, 50%, and 70%) and plate heights (left and right sides: 30 mm, 50 mm, and 70 mm) lead to nine different combinations for evaluation. Images are acquired with a MAMMOMAT Inspiration mammography system (Siemens Healthcare GmbH) using W/Rh anode/filter combination, antiscatter grid in place and automatic exposure control enabled. The tube voltages are chosen automatically depending on the compression paddle height.

Fig. 2

Setup for phantom-based accuracy evaluation of VBD measurement: (a) photograph, (b) breast density map with measurement regions indicated by red squares.

The average VBD is measured in two square regions of interest (side length 27.54 mm, Fig. 2) in the 2-D breast density map, one placed in the fatty tissue region and one placed in the fibroglandular tissue region. To measure the accuracy, two quantities are computed. The mean absolute deviation [MAD, measured in percentage points (pp)] is defined as

The mean absolute percentage error (MAPE, measured in %) is calculated as

In the above equations, $x_i$ and $y_i$ ($i=1,\dots ,N$) denote the known ground truth values and the measured values, respectively. $N$ denotes the number of samples.

2.3.

Evaluation of Reproducibility

2.4.

Evaluation of Consistency

The calculated breast density in a large population is analyzed with respect to the women’s age. With postmenopausal alteration of fibroglandular breast tissue, it is expected that the density of a woman’s breast will decrease with increasing age.²⁶

The images from data set 1 (Table 1) are used for this analysis. Breast density is calculated from all 8150 four-view exams on a per breast basis (averaging results from CC and MLO views) giving 16,300 separate values for VBD and breast density category, respectively. Mean and standard deviation of VBD as well as frequency of breast density categories are calculated depending on a woman’s age.

2.5.

Evaluation of Agreement with Radiologists’ Visual Assessment

600 four-view anonymized FFDM exams had been randomly selected from the MBTST, and 32 experienced radiologists from the US and Canada provided individual breast density classifications for these exams according to the ACR BI-RADS^® fifth ed. atlas. Nine radiologists labeled the first set of 200 exams (set “1 to 200”), 10 radiologists labeled the second set of 200 exams (set “201 to 400”), and 13 radiologists labeled the third set of 200 exams (set “401 to 600”). The most frequently chosen category for a certain exam is defined to be the reference density category by the radiologists for this exam (panel majority vote).²¹

The software calculates density categories for each of the 600 FFDM exams. 512 exams have DBT raw projection images (MLO views only) available that were acquired in a different breast compression. For these DBT exams, density categories are calculated by the software as well. These categories, determined by the software using FFDM and DBT exams, respectively, are compared to the reference density categories by the radiologists. Overall percentage agreement and Cohen’s linearly weighted kappa²⁷ values are computed.

3.1.

Evaluation of Accuracy

The results for the accuracy evaluation are shown in Fig. 3. The measured VBD values are plotted against the ground truth VBD values. One sample point has a ground truth VBD value of 33% instead of 30%, which corresponds to 60-mm plate height with 30% glandularity plus 10-mm plate height with 50% glandularity. The MAD are 3.38 and 1.65 pp for the fatty tissue and dense tissue regions, respectively. MAPE is 3.84% for the dense tissue region. MAPE was not calculated for the fatty tissue region as the denominator would be zero.

Fig. 3

Results for accuracy evaluation by phantom experiments.

3.2.

Evaluation of Reproducibility

Scatter plots for the reproducibility evaluation are shown in Figs. 4 and 5 (different FFDM views; color encodes density of sample values), Figs. 6 and 7 (FFDM and DBT exams), and Fig. 8 (two FFDM acquisitions). PCC and MAD values are shown inside the plots.

Fig. 4

Results for reproducibility evaluation with data set 1 (left versus right breast).

Fig. 5

Results for reproducibility evaluation with data set 1 (CC versus MLO view).

Fig. 6

Results for reproducibility evaluation with data set 2 (FFDM versus DBT).

Fig. 7

Results for reproducibility evaluation with data set 3 (FFDM versus DBT).

Fig. 8

Results for reproducibility evaluation with data set 4 (two FFDMs, same view).

3.3.

Evaluation of Consistency

In Fig. 9, the breast density per breast depending on the age at examination is shown. It is presented as VBD value and as breast density category dichotomized as nondense (a, b) and dense (c, d) categories. A histogram of the age at examination for data set 1 is shown in Fig. 10. Proportions of calculated breast density categories for different age groups are shown in Fig. 11. For comparison, proportions for the same age groups as reported by the Breast Cancer Surveillance Consortium (BCSC) are shown as well.

Fig. 9

Breast density per breast depending on age at examination: (a) mean and standard deviation of VBD (b) dichotomous breast density classification.

Fig. 10

Histogram of the age at examination for data set 1.

Fig. 11

Proportions of calculated breast density categories depending on age group: (a) our evaluation, (b) for comparison, data from BCSC.²⁸

3.4.

Comparison with Radiologists’ Visual Assessment

Confusion matrices for the evaluation of agreement of the software density categories with radiologists’ visual assessment are shown in Table 2. The overall percentage agreement is 69.5% [Cohen’s linearly weighted kappa $({\kappa }_{\mathrm{lw}})=0.67$] for the categories based on FFDM images and 64.6% (${\kappa }_{\mathrm{lw}}=0.59$) for the categories based on DBT projections. When the results are dichotomized into nondense (a, b) and dense (c, d) categories, the agreement is 88.5% (${\kappa }_{\mathrm{lw}}=0.76$) and 83.0% (${\kappa }_{\mathrm{lw}}=0.64$), respectively.

Table 2

Confusion matrices showing agreement between density categories determined by radiologists and by the software. The software used either FFDM or DBT exam data as input data.