A Deep Learning Mammography-based Model for Improved Breast Cancer Risk Prediction.

By Adam Yala, C. Lehman, Tal Schuster, Tally Portnoi, Regina Barzilay. Radiology, 2019

630 citations recorded by the source corpus.

Background Mammographic density improves the accuracy of breast cancer risk models. However, the use of breast density is limited by subjective assessment, variation across radiologists, and restricted data. A mammography-based deep learning (DL) model may provide more accurate risk prediction. Purpose To develop a mammography-based DL breast cancer risk model that is more accurate than established clinical breast cancer risk models. Materials and Methods This retrospective study included 88 994 consecutive screening mammograms in 39 571 women between January 1, 2009, and December 31, 2012. For each patient, all examinations were assigned to either training, validation, or test sets, resulting in 71 689, 8554, and 8751 examinations, respectively. Cancer outcomes were obtained through linkage to a regional tumor registry. By using risk factor information from patient questionnaires and electronic medical records review, three models were developed to assess breast cancer risk within 5 years: a risk-factor-based logistic regression model (RF-LR) that used traditional risk factors, a DL model (image-only DL) that used mammograms alone, and a hybrid DL model that used both traditional risk factors and mammograms. Comparisons were made to an established breast cancer risk model that included breast density (Tyrer-Cuzick model, version 8 [TC]). Model performance was compared by using areas under the receiver operating characteristic curve (AUCs) with DeLong test (P < .05). Results The test set included 3937 women, aged 56.20 years ± 10.04. Hybrid DL and image-only DL showed AUCs of 0.70 (95% confidence interval [CI]: 0.66, 0.75) and 0.68 (95% CI: 0.64, 0.73), respectively. RF-LR and TC showed AUCs of 0.67 (95% CI: 0.62, 0.72) and 0.62 (95% CI: 0.57, 0.66), respectively. Hybrid DL showed a significantly higher AUC (0.70) than TC (0.62; P < .001) and RF-LR (0.67; P = .01). Conclusion Deep learning models that use full-field mammograms yield substantially improved risk discrimination compared with the Tyrer-Cuzick (version 8) model. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Sitek and Wolfe in this issue.

Subfields: Artificial Intelligence, Oncology, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/87466f870df7165622478e5a8834174ecb8093d2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Oncology

In Pulmonary and Respiratory Medicine

Citations in the corpus

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (2019, background): “For example, medical (Yala et al., 2019) and other high-value decision applications require some means of verifying reasons for the predicted outcomes.”
Artificial intelligence in healthcare: An essential guide for health leaders (2019, methodology): “More importantly, this AI model is specifically designed to ensure it is equally accurate for white and black women.(16) Several hospitals in Canada are using AI to predict the number of patients to the emergency department 2 or 3 days in advance, allowing the hospital to take proactive action in st”
A Game Theoretic Approach to Class-wise Selective Rationalization (2019, methodology): “The first class of method is to explicitly introduce a generator that learns to select important subsets of inputs as explanations [12, 19, 21, 30, 31], which often comes with some information-theoretic properties.”
Calibration: the Achilles heel of predictive analytics (2019, background): “Calibration is especially important when the aim is to support decision-making, even when discrimination is moderate such as for breast cancer prediction models [13].”
Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging (2023, background): “An overview of machine learning applications in oncological imaging [82,83].”
Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines (2020, background): “Spasov et al. 36 , Yala et al. 37 , and Yoo et al. 38 implemented CNNs to learn image features and fused these feature representations with clinical features before feeding them into a feed-forward neural network.”