Mammographic risk scoring has commonly been automated by extracting a set of handcrafted features from mammograms, and relating the responses directly or indirectly to breast cancer risk. We present a method that learns a feature hierarchy from unlabeled data. When the learned features are used as the input to a simple classifier, two different tasks can be addressed: i) breast density segmentation, and ii) scoring of mammographic texture. The proposed model learns features at multiple scales. To control the models capacity a novel sparsity regularizer is introduced that incorporates both lifetime and population sparsity. We evaluated our method on three different clinical datasets. Our state-of-the-art results show that the learned breast density scores have a very strong positive relationship with manual ones, and that the learned texture scores are predictive of breast cancer. The model is easy to apply and generalizes to many other segmentation and scoring problems.

In conclusion, we applied a deep-learning method, U-net, for segmenting breast and FGT in MRI in a dataset that includes a variety of MRI protocols and breast densities. Our results showed that U-net-based methods significantly outperformed the existing algorithms and resulted in significantly more accurate breast density computation.

PurposeTo determine to what extent automatically measured volumetric mammographic density influences screening performance when using digital mammography (DM).MethodsWe collected a consecutive series of 111,898 DM examinations (2003–2011) from one screening unit of the Dutch biennial screening program (age 50–75 years). Volumetric mammographic density was automatically assessed using Volpara. We determined screening performance measures for four density categories comparable to the American College of Radiology (ACR) breast density categories.ResultsOf all the examinations, 21.6% were categorized as density category 1 (‘almost entirely fatty’) and 41.5, 28.9, and 8.0% as category 2–4 (‘extremely dense’), respectively. We identified 667 screen-detected and 234 interval cancers. Interval cancer rates were 0.7, 1.9, 2.9, and 4.4‰ and false positive rates were 11.2, 15.1, 18.2, and 23.8‰ for categories 1–4, respectively (both p-trend < 0.001). The screening sensitivity, calculated as the proportion of screen-detected among the total of screen-detected and interval tumors, was lower in higher density categories: 85.7, 77.6, 69.5, and 61.0% for categories 1–4, respectively (p-trend < 0.001).ConclusionsVolumetric mammographic density, automatically measured on digital mammograms, impacts screening performance measures along the same patterns as established with ACR breast density categories. Since measuring breast density fully automatically has much higher reproducibility than visual assessment, this automatic method could help with implementing density-based supplemental screening.

BackgroundIn mammography, breast compression is applied to reduce the thickness of the breast. While it is widely accepted that firm breast compression is needed to ensure acceptable image quality, guidelines remain vague about how much compression should be applied during mammogram acquisition. A quantitative parameter indicating the desirable amount of compression is not available. Consequently, little is known about the relationship between the amount of breast compression and breast cancer detectability. The purpose of this study is to determine the effect of breast compression pressure in mammography on breast cancer screening outcomes.MethodsWe used digital image analysis methods to determine breast volume, percent dense volume, and pressure from 132,776 examinations of 57,179 women participating in the Dutch population-based biennial breast cancer screening program. Pressure was estimated by dividing the compression force by the area of the contact surface between breast and compression paddle. The data was subdivided into quintiles of pressure and the number of screen-detected cancers, interval cancers, false positives, and true negatives were determined for each group. Generalized estimating equations were used to account for correlation between examinations of the same woman and for the effect of breast density and volume when estimating sensitivity, specificity, and other performance measures. Sensitivity was computed using interval cancers occurring between two screening rounds and using interval cancers within 12 months after screening. Pair-wise testing for significant differences was performed.ResultsPercent dense volume increased with increasing pressure, while breast volume decreased. Sensitivity in quintiles with increasing pressure was 82.0%, 77.1%, 79.8%, 71.1%, and 70.8%. Sensitivity based on interval cancers within 12 months was significantly lower in the highest pressure quintile compared to the third (84.3% vs 93.9%, p = 0.034). Specificity was lower in the lowest pressure quintile (98.0%) compared to the second, third, and fourth group (98.5%, p < 0.005). Specificity of the fifth quintile was 98.4%.ConclusionResults suggest that if too much pressure is applied during mammography this may reduce sensitivity. In contrast, if pressure is low this may decrease specificity.