Faculty Bibliography

We present a deep convolutional neural network for breast cancer screening exam classification, trained and evaluated on over 200,000 exams (over 1,000,000 images). Our network achieves an AUC of 0.895 in predicting the presence of cancer in the breast, when tested on the screening population. We attribute the high accuracy to a few technical advances. (i) Our network's novel two-stage architecture and training procedure, which allows us to use a high-capacity patch-level network to learn from pixel-level labels alongside a network learning from macroscopic breast-level labels. (ii) A custom ResNet-based network used as a building block of our model, whose balance of depth and width is optimized for high-resolution medical images. (iii) Pretraining the network on screening BI-RADS classification, a related task with more noisy labels. (iv) Combining multiple input views in an optimal way among a number of possible choices. To validate our model, we conducted a reader study with 14 readers, each reading 720 screening mammogram exams, and show that our model is as accurate as experienced radiologists when presented with the same data. We also show that a hybrid model, averaging the probability of malignancy predicted by a radiologist with a prediction of our neural network, is more accurate than either of the two separately. To further understand our results, we conduct a thorough analysis of our network's performance on different subpopulations of the screening population, the model's design, training procedure, errors, and properties of its internal representations. Our best models are publicly available at https://github.com/nyukat/breastcancerclassifier.

PURPOSE/OBJECTIVE:To evaluate the relationship between mammographic density, background parenchymal enhancement and fibroglandular tissue on MRI in women with triple negative breast cancer (TNBC) compared to women with non-triple negative breast cancer (non-TNBC). METHODS:The institutional Breast Cancer Database was queried to identify the clinicopathologic and imaging characteristics among women who underwent mammography and breast MRI between 2010-2018. Statistical analyses included Pearson's Chi Square, Wilcoxon Rank-Sum and logistic regression. RESULTS:Of 2995 women, 225 (7.5 %) had TNBC with a median age of 60 years (23-96) and median follow-up of 5.69 years. Compared to women with non-TNBC, TNBC was associated with African-American race 36/225 (16 %), BRCA1,2 positivity 34/225 (15.1 %), previous history of breast cancer 35/225 (15.6 %), presenting on breast exam 126/225 (56 %) or MRI 13/225 (5.8 %), palpability 133/225 (59.1 %), more invasive ductal carcinoma (IDC) 208/225 (92.4 %), higher stage (stage III) 37/225 (16.5 %), higher grade (grade 3) 186/225 (82.7 %) (all p < 0.001), lower mammographic breast density (MBD) 18/225 (8 %) (p = 0.04), lower fibroglandular tissue (FGT) 17/225 (7.6 %) (p = 0.01), and lower background parenchymal enhancement (BPE) 89/225 (39.8 %) (p = 0.02). Nine of 225 (4 %) women with TNBC experienced recurrence with no significant association with MBD, FGT, or BPE. There was no significant difference in median age of our TNBC and non-TNBC cohorts. CONCLUSIONS:The higher proportion of women with lower MBD, FGT and BPE in women with TNBC suggests that MBD, amount of FGT and degree of BPE may be associated with breast cancer risk in women with TNBC.

The degree of normal fibroglandular tissue that enhances on breast MRI, known as background parenchymal enhancement (BPE), was initially described as an incidental finding that could affect interpretation performance. While BPE is now established to be a physiologic phenomenon that is affected by both endogenous and exogenous hormone levels, evidence supporting the notion that BPE frequently masks breast cancers is limited. However, compelling data have emerged to suggest BPE is an independent marker of breast cancer risk and breast cancer treatment outcomes. Specifically, multiple studies have shown that elevated BPE levels, measured qualitatively or quantitatively, are associated with a greater risk of developing breast cancer. Evidence also suggests that BPE could be a predictor of neoadjuvant breast cancer treatment response and overall breast cancer treatment outcomes. These discoveries come at a time when breast cancer screening and treatment have moved toward an increased emphasis on targeted and individualized approaches, of which the identification of imaging features that can predict cancer diagnosis and treatment response is an increasingly recognized component. Historically, researchers have primarily studied quantitative tumor imaging features in pursuit of clinically useful biomarkers. However, the need to segment less well-defined areas of normal tissue for quantitative BPE measurements presents its own unique challenges. Furthermore, there is no consensus on the optimal timing on dynamic contrast-enhanced MRI for BPE quantitation. This article comprehensively reviews BPE with a particular focus on its potential to increase precision approaches to breast cancer risk assessment, diagnosis, and treatment. It also describes areas of needed future research, such as the applicability of BPE to women at average risk, the biological underpinnings of BPE, and the standardization of BPE characterization. Level of Evidence: 3 Technical Efficacy Stage: 5.

Architectural distortion on digital breast tomosynthesis (