Related Experiment Video
Updated: Jan 1, 2026
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Comparison of a Deep Learning Risk Score and Standard Mammographic Density Score for Breast Cancer Risk Prediction
Karin Dembrower1, Yue Liu1, Hossein Azizpour1
1From the Department of Physiology and Pharmacology, Karolinska Institutet, Solnavägen 9 (Biomedicum), 171 65 Stockholm, Sweden (K.D.); Department of Radiology, Division of Breast Radiology, Capio Sankt Görans Hospital, Stockholm, Sweden (K.D.); School of Electrical Engineering and Computer, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden (Y.L.); School of Electrical Engineering and Computer, Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Stockholm, Sweden (H.A.); Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden (M.E.); School of Electrical Engineering and Computer, Science for Life Laboratory, KTH Royal Institute of Technology, Stockholm, Sweden (K.S.); Department of Physiology and Pharmacology, Karolinska Institutet, Stockholm, Sweden (P.L.); Department of Thoracic Radiology, Imaging and Physiology, Karolinska University Hospital, Stockholm, Sweden (P.L.); and Department of Pathology and Oncology, Division of Breast Radiology, Karolinska University Hospital, Stockholm, Sweden (F.S.).
Abstract:
Background Most risk prediction models for breast cancer are based on questionnaires and mammographic density assessments. By training a deep neural network, further information in the mammographic images can be considered. Purpose To develop a risk score that is associated with future breast cancer and compare it with density-based models. Materials and Methods In this retrospective study, all women aged 40-74 years within the Karolinska University Hospital uptake area in whom breast cancer was diagnosed in 2013-2014 were included along with healthy control subjects. Network development was based on cases diagnosed from 2008 to 2012. The deep learning (DL) risk score, dense area, and percentage density were calculated for the earliest available digital mammographic examination for each woman. Logistic regression models were fitted to determine the association with subsequent breast cancer. False-negative rates were obtained for the DL risk score, age-adjusted dense area, and age-adjusted percentage density. Results A total of 2283 women, 278 of whom were later diagnosed with breast cancer, were evaluated. The age at mammography (mean, 55.7 years vs 54.6 years; P < .001), the dense area (mean, 38.2 cm2 vs 34.2 cm2; P < .001), and the percentage density (mean, 25.6% vs 24.0%; P < .001) were higher among women diagnosed with breast cancer than in those without a breast cancer diagnosis. The odds ratios and areas under the receiver operating characteristic curve (AUCs) were higher for age-adjusted DL risk score than for dense area and percentage density: 1.56 (95% confidence interval [CI]: 1.48, 1.64; AUC, 0.65), 1.31 (95% CI: 1.24, 1.38; AUC, 0.60), and 1.18 (95% CI: 1.11, 1.25; AUC, 0.57), respectively (P < .001 for AUC). The false-negative rate was lower: 31% (95% CI: 29%, 34%), 36% (95% CI: 33%, 39%; P = .006), and 39% (95% CI: 37%, 42%; P < .001); this difference was most pronounced for more aggressive cancers. Conclusion Compared with density-based models, a deep neural network can more accurately predict which women are at risk for future breast cancer, with a lower false-negative rate for more aggressive cancers. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Bahl in this issue.
