Registration is open - make plans to attend
Get pricing and details
>
Conference 12033 > Paper 12033-120
Paper 12033-120

Cardiovascular disease and all-cause mortality risk prediction from abdominal CT using deep learning

In person: 23 February 2022 • 5:30 PM - 7:00 PM PST

Abstract

In this work we explore utilizing a convolutional neural network (CNN) to predict all-cause mortality and cardiovascular risk over a 5 year horizon from abdominal CT scans taken for routine CT colonography in otherwise healthy patients aged 50-65. We find that adding a variational autoencoder (VAE) to the CNN classifier improves its accuracy for five year survival prediction (AUC 0.792 vs 0.775). Our VAE based method performs significantly better than the Framingham Risk Score and slightly better than the method demonstrated in Pickhardt et al. (2020) which utilized a combination of five CT derived biomarkers.

Presenter

National Institutes of Health (United States)
Dan completed a PhD in physics in 2016 and then worked as a postdoc at the University of Maryland, College Park, where he got his initial experience with machine learning. From Jan 2019 to July 2021 he worked as a Staff Scientist at the National Institutes of Health Clinical Center for Dr. Ronald Summers. While there he worked on deep learning for segmentation, automated body composition analysis codes (bone mineral density, visceral/subcutaneous fat, muscle, liver fat, pancreas fat), MRI dataset curation, and mortality/ cardiovascular risk prediction using deep learning. He recently started as a Data Scientist at the Center for Clinical Data Science at Massachusetts General Hospital in Boston.
Presenter/Author
National Institutes of Health (United States)
Author
National Institutes of Health (United States)
Author
Perry J. Pickhardt
Univ. of Wisconsin School of Medicine and Public Health (United States)
Author
National Institutes of Health (United States)