Log In Sign Up

Deep Learning Predicts Cardiovascular Disease Risks from Lung Cancer Screening Low Dose Computed Tomography

by   Hanqing Chao, et al.

The high risk population of cardiovascular disease (CVD) is simultaneously at high risk of lung cancer. Given the dominance of low dose computed tomography (LDCT) for lung cancer screening, the feasibility of extracting information on CVD from the same LDCT scan would add major value to patients at no additional radiation dose. However, with strong noise in LDCT images and without electrocardiogram (ECG) gating, CVD risk analysis from LDCT is highly challenging. Here we present an innovative deep learning model to address this challenge. Our deep model was trained with 30,286 LDCT volumes and achieved the state-of-the-art performance (area under the curve (AUC) of 0.869) on 2,085 National Lung Cancer Screening Trial (NLST) subjects, and effectively identified patients with high CVD mortality risks (AUC of 0.768). Our deep model was further calibrated against the clinical gold standard CVD risk scores from ECG-gated dedicated cardiac CT, including coronary artery calcification (CAC) score, CAD-RADS score and MESA 10-year CHD risk score from an independent dataset of 106 subjects. In this validation study, our model achieved AUC of 0.942, 0.809 and 0.817 for CAC, CAD-RADS and MESA scores, respectively. Our deep learning model has the potential to convert LDCT for lung cancer screening into dual-screening quantitative tool for CVD risk estimation.


page 1

page 3

page 16

page 17

page 19


Enhancing Cancer Prediction in Challenging Screen-Detected Incident Lung Nodules Using Time-Series Deep Learning

Lung cancer is the leading cause of cancer-related mortality worldwide. ...

LNDb: A Lung Nodule Database on Computed Tomography

Lung cancer is the deadliest type of cancer worldwide and late detection...

Clinically verified pre-screening for cancer using web search queries: Initial results

Search engine queries have been demonstrated to be a useful signal for s...

Disease Detection in Weakly Annotated Volumetric Medical Images using a Convolutional LSTM Network

We explore a solution for learning disease signatures from weakly, yet e...

Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging

Annual low dose computed tomography (CT) lung screening is currently adv...

Opportunistic hip fracture risk prediction in Men from X-ray: Findings from the Osteoporosis in Men (MrOS) Study

Osteoporosis is a common disease that increases fracture risk. Hip fract...

Development and Characterization of a Chest CT Atlas

A major goal of lung cancer screening is to identify individuals with pa...