AI-based abdominal CT measurements of orthotopic and ectopic fat predict mortality and cardiometabolic disease risk in adults

Matthew H Lee ¹, Ryan Zea ², John W Garrett ²

⁰Departments of Radiology and Medical Physics, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA. mlee5@uwhealth.org.

European Radiology +

|

July 12, 2024

View abstract on PubMed

Summary

Fully automated CT scans can predict mortality and cardiometabolic disease risk in asymptomatic adults. These abdominal fat measures significantly outperform traditional anthropometric measures like BMI for risk assessment.

Area Of Science

Radiology
Medical Imaging
Artificial Intelligence in Medicine

Background

Cardiometabolic diseases and mortality risk are significant public health concerns.
Traditional anthropometric measures like Body Mass Index (BMI) have limitations in predicting these risks.
Abdominal adipose tissue distribution is increasingly recognized as a crucial factor in metabolic health.

Purpose Of The Study

To evaluate the predictive utility of CT-derived abdominal fat measures for mortality and cardiometabolic disease risk.
To compare the performance of AI-quantified fat measures against traditional anthropometric measures.
To assess the association of visceral adipose tissue (VAT), subcutaneous adipose tissue (SAT), and liver/muscle attenuation with health outcomes.

Main Methods

Utilized fully automated AI tools to quantify L3 level visceral (VAT) and subcutaneous (SAT) fat area, visceral-to-subcutaneous fat ratio (VSR), VAT attenuation, muscle attenuation, and liver attenuation from non-contrast CT scans.
Applied these measures to asymptomatic adults undergoing CT colonography (CTC).
Conducted longitudinal follow-up for deaths, cardiovascular events, and diabetes, using ROC and time-to-event analyses to determine predictive accuracy (AUCs) and hazard ratios (HRs).

Main Results

CT-based fat measures, particularly muscle attenuation and VSR, demonstrated superior 5-year AUCs for mortality prediction compared to BMI.
Higher visceral fat (VAT area, VSR), muscle attenuation, and liver attenuation were significantly associated with increased mortality risk.
Elevated VAT area and VSR predicted higher risk of cardiovascular events and diabetes.
A U-shaped association between SAT and mortality risk was observed, indicating increased risk at both very low and very high levels.

Conclusions

Fully automated CT-based abdominal fat quantification provides robust prediction of mortality and cardiometabolic disease risk in asymptomatic adults.
These AI-driven imaging biomarkers offer superior risk stratification compared to conventional anthropometric measures.
CT-derived body composition analysis reveals critical insights into metabolic dysregulation and associated health risks not captured by BMI.

Keywords:

Abdominal fat Artificial intelligence Body composition CT Ectopic fat

Related Concept Videos

Imaging Studies for Cardiovascular System III: X-Ray

The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...