Skip to Main Content

An official website of the United States government

Deep learning for indirect and direct cardiovascular risk estimation from ungated chest CT

Principal Investigator
Name
Piotr Slomka
Degrees
PhD
Institution
Cedars-Sinai
Position Title
Professor of Medicine and Cardiology
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-981
Initial CDAS Request Approval
Nov 1, 2022
Title
Deep learning for indirect and direct cardiovascular risk estimation from ungated chest CT
Summary
Coronary artery calcification (CAC) is frequently used to estimate a patient’s risk of cardiovascular disease and to target appropriate medical therapies. While coronary artery calcification is typically acquired from dedicated, ECG-gated computed tomography (CT) scans, it is possible to get similar information from low-dose ungated chest CT. We recently developed a novel convolutional long short-term model for rapid quantification of coronavirus disease 2019 pneumonia burden from computed tomography and validated diagnostic performance on a subset of National Lung Screening Trial population. We have also demonstrated that deep learning CAC scores, using a related model, from low dose ungated chest CT can accurately predict adverse cardiovascular events using this approach in PET/CT data. However, there is an abundance of information other than CAC contained within a chest CT, such as cardiac volumes and epicardial adipose tissue, which could be used to provide risk stratification for patients. Therefore, it may be possible to further refine risk stratification from ungated chest CT beyond that possible with CAC alone. In the proposed study, we will leverage our existing deep learning models and our expertise in artificial intelligence development and validation to evaluate two different approaches to estimating cardiovascular risk from ungated low-dose chest CT. In the first approach, we will use the deep learning model to quantify known markers associated with cardiovascular risk from chest CT including coronary artery calcification, epicardial adipose tissue volume and attenuation, liver fat, skeletal muscle volume, and cardiac volumes. We will assess the accuracy of those estimates and then will determine whether these measures can be used to accurately predict cardiovascular risk. In the second approach, we will develop an explainable deep learning model to directly predict cardiovascular risk from chest CT, without the intermediate step of quantifying known predictors. This novel approach will potentially simplify the process of risk prediction, but also serves as a method to identify potentially important, but yet undiscovered, cardiovascular biomarkers.
Aims

Accurately targeting medical therapies is central to management of patients with coronary artery disease (CAD), regardless of the presence of symptoms. Coronary artery calcium (CAC) scoring from ECG-gated, non-contrast, computed tomography (CT) scans has emerged as a leading biomarker of CAD and cardiovascular risk. We have demonstrated that deep learning (DL) of CAC scores from low dose ungated chest CT from PET/CT and SPECT/CT can accurately predict adverse cardiovascular events with analysis performed in < 6 seconds per patient, making it suitable for large scale batch processing. However, there is also an abundance of information other than CAC contained within a chest CT, such as cardiac volumes and epicardial adipose tissue, which could be used to provide risk stratification for patients. Therefore, it may be possible to further refine risk stratification from ungated chest CT beyond that possible with CAC alone. It could be especially valuable to explore this in a large dataset like the National Lung Screening trial (NLST).

We propose to develop and validate state-of-the art DL for cardiovascular risk estimation from the low dose chest CT. We propose these 3 specific aims.

1) Derive standard measures of cardiovascular risk with DL. We will leverage and adapt our existing DL models to segment and quantify CAC, epicardial adipose tissue volume and attenuation, cardiac volumes, and liver to spleen attenuation ratios from low-dose chest CT. This would allow risk predictions to consider CAC information and cardiac volumes, but also other known features of importance present of chest CT.

2) We will determine whether these measures can be efficiently combined to predict cardiovascular risk. We will combine CAC and associated information such as density, number of lesions, and cardiac volumes, with non-cardiac measures such as liver attenuation, spleen attenuation, liver/ to spleen attenuation ratio,and skeletal muscle volume to provide risk stratification for all-cause mortality and cardiovascular mortality in patients from the NLST, without exclusions and specifically assessing sub-groups of patients (sex, race, previous CAD). Integration will be accomplished by extreme boosting models as in our previous work.

3) We will explore direct cardiovascular risk prediction from CT image data. This approach can allow for identification of latent DL image features (without specific segmentation of structures), which are associated with risk of cardiovascular events. Attention maps will be integrated into the model to highlight image regions associated with increased risk, allowing physicians to review the validity of the model and understand the findings as well as provide insights into novel imaging biomarkers.

The large set of chest CT data from NLST (n=22417) has already been transferred to Cedars-Sinai Medical Center under a separate project (NLST-651). The funding for this project is available under the Outstanding Investigator award R35 NIH/NHLBI grant (1R35HL161195) PI: Piotr Slomka. All the essential infrastructure is already in place in our laboratory, including necessary hardware and computing resources. Clinical oversight from physicians is also available for CAC scoring or visual CT interpretation.

Collaborators

Piotr Slomka Cedars-Sinai
Damini Dey Cedars-Sinai
Daniel Berman Cedars-Sinai

Related Publications