Improving performance of computer-aided detection of masses by incorporating bilateral mammographic density asymmetry: an assessment

Abstract

Rationale and objectives: Bilateral mammographic density asymmetry is a promising indicator in assessing risk of having or developing breast cancer. This study aims to assess the performance improvement of a computer-aided detection (CAD) scheme in detecting masses by incorporating bilateral mammographic density asymmetrical information.

Materials and methods: A testing dataset containing 2400 full-field digital mammograms (FFDM) acquired from 600 examination cases was established. Among them, 300 were positive cases with verified cancer associated with malignant masses and 300 were negative cases. Two computerized schemes were applied to process images of each case. The first single-image based CAD scheme detected suspicious mass regions and the second scheme computed average and difference of mammographic tissue density depicted between the left and right breast. A fusion method based on rotation of the CAD scoring projection reference axis was then applied to combine CAD-generated mass detection scores and either the computed average or difference (asymmetry) of bilateral mammographic density scores. The CAD performance levels with and without incorporating mammographic density information were evaluated and compared using a free-response receiver operating characteristic type data analysis method.

Results: CAD achieved a case-based mass detection sensitivity of 0.74 and a region-based sensitivity of 0.56 at a false-positive rate of 0.25 per image. By fusing the CAD and bilateral mammographic density asymmetry scores, the case-based and region-based sensitivity levels of the CAD scheme were increased to 0.84 and 0.69, respectively, at the same false-positive rate. Fusion with average mammographic density only slightly increased CAD sensitivity to 0.75 (case-based) and 0.57 (region-based).

Conclusions: This study indicated that 1) bilateral mammographic density asymmetry was a stronger indicator of the case depicting suspicious masses than the average density computed from two breasts and 2) fusion between the conventional CAD scores and bilateral mammographic density asymmetry information could substantially increase CAD performance in mass detection.

Figure 1

Distribution of breast density BIRADS ratings in the testing dataset.

Figure 2

An example of applying our CAD scheme to both CC and MLO view images of a testing case in which a true-positive mass is cued on both CC and MLO view images.

Figure 3

Illustration of fusion between CAD scores and bilateral mammographic density asymmetry scores by rotating the CAD scoring projection (reference) axis. In the figure 300 true-positive mass regions (o) and 300 CAD-detected false-positive regions (Δ) are presented, which represent one region with the maximum CAD-generated detection score per case. For the cases without a detected suspicious region, a sign (Δ or o) is added in the position of CAD score = 0. The dash line represents the original CAD scoring axis and the solid line represents the rotated new CAD scoring projection axis.

Figure 4

Comparison of two histograms of normalizated average (a) and asymmetry (b) of bilateral mammographic density scores between 300 positive and 300 negative cases.

Figure 5

The trend of CAD cueing sensitivity and minimum CAD cueing score (threshold) as the increase of CAD scoring projection (reference) axis roation slopes when fusion of CAD scores and the bilateral mammographic density asymmetry scores. The false-positive rate is 0.25 per image.

Figure 6

Comparsion of two case-based FROC curves representing the original CAD perforamcne (S = 0.0) and CAD performance after incorporating the bilateral mammographic density asymmetry information with a rotation slope of S = 0.6.

Figure 7

Comparsion of two region-based FROC curves representing the original CAD perforamcne (S = 0.0) and CAD performance after incorporating the bilateral mammographic density asymmetry information with a rotation slope of S = 0.6.

Figure 8

The trend of CAD cueing sensitivity and minimum CAD cueing score (threshold) as the increase of CAD scoring projection (reference) axis roation slopes when fusion of CAD scores and the average mammographic density scores. The false-positive rate is 0.25 per image