Feature | Artificial Intelligence | December 02, 2020

AI Measured Abdominal Fat Accurately Predicts Heart Attack and Stroke Risk

Study of 12,128 patients over 5 years showed automated AI measurement of visceral fat area on abdominal CT images predicts future heart attack or stroke risk better than overall weight or BMI

An example of a body composition analysis of an abdominal CT slice with the subcutaneous fat in green, skeletal muscle red and visceral fat in yellow. This was automatically identified and analyzed via a deep learning algorithm to assess the risk for heart attack and stroke in more than 12,000 patients. #RSNA2020 #RSNA20 #RSNA

An example of a body composition analysis of an abdominal CT slice with the subcutaneous fat in green, skeletal muscle red and visceral fat in yellow. This was automatically identified and analyzed via a deep learning algorithm to assess the risk for heart attack and stroke in more than 12,000 patients.

December 2, 2020 – Automated deep learning analysis of abdominal computed tomography (CT) images produces a more precise measurement of body composition and predicts major cardiovascular events, such as heart attack and stroke, better than overall weight or body mass index (BMI), according to a study presented today at the 2020 Radiological Society of North America (RSNA) virtual meeting.

“Established cardiovascular risk models rely on factors like weight and BMI that are crude surrogates of body composition,” said Kirti Magudia, M.D., Ph.D., an abdominal imaging and ultrasound fellow at the University of California San Francisco. “It’s well established that people with the same BMI can have markedly different proportions of muscle and fat. These differences are important for a variety of health outcomes.”

Unlike BMI, which is based on height and weight, a single axial CT slice of the abdomen visualizes the volume of subcutaneous fat area, visceral fat area and skeletal muscle area. However, manually measuring these individual areas is time intensive and costly.

As a radiology resident at Brigham and Women’s Hospital in Boston, Magudia was part of a multidisciplinary team of researchers, including radiologists, a data scientist and biostatistician, who developed a fully automated method using deep learning — a type of artificial intelligence (AI) — to determine body composition metrics from abdominal CT images.

“Abdominal CT scans that are routinely performed provide a more granular way of looking at body composition, but we’re not currently taking advantage of it,” Magudia said.

The study cohort was derived from the 33,182 abdominal CT outpatient exams performed on 23,136 patients at Partners Healthcare in Boston in 2012. The researchers identified 12,128 patients who were free of major cardiovascular and cancer diagnoses at the time of imaging. Mean age of the patients was 52 years, and 57% of patients were women.

The researchers selected the L3 CT slice (from the third lumbar spine vertebra) and calculated body composition areas for each patient. Patients were then divided into four quartiles based on the normalized values of subcutaneous fat area, visceral fat area and skeletal muscle area.

In this retrospective study, it was determined which of these 12,128 patients had a myocardial infarction (heart attack) or stroke within five years after their index abdominal CT scan. The researchers found 1,560 myocardial infarctions and 938 strokes occurred in this study group.

Statistical analysis demonstrated that visceral fat area was independently associated with future heart attack and stroke. BMI was not associated with heart attack or stroke.

“The group of patients with the highest proportion of visceral fat area were more likely to have a heart attack, even when adjusted for known cardiovascular risk factors,” Magudia said. “The group of patients with the lowest amount of visceral fat area were protected against stroke in the years following the abdominal CT exam.”

“These results demonstrate that precise measures of body muscle and fat compartments achieved through CT outperform traditional biomarkers for predicting risk for cardiovascular outcomes,” she added.

According to Magudia, this work demonstrates that fully automated and normalized body composition analysis could now be applied to large-scale research projects.

“This work shows the promise of AI systems to add value to clinical care by extracting new information from existing imaging data,” Magudia said. “The deployment of AI systems would allow radiologists, cardiologists and primary care doctors to provide better care to patients at minimal incremental cost to the health care system.”

This paper is the recipient of an RSNA 2020 Trainee Research Prize.

Co-authors are Christopher P. Bridge, D.Phil., Camden P. Bay, Ph.D., Florian J. Fintelmann, M.D., Ana Babic, Ph.D., Katherine P. Andriole, Ph.D., Brian M. Wolpin, M.D., and Michael H. Rosenthal, M.D., Ph.D.

Watch the RSNA presentation of this study in the VIDEO: Deep Learning Analysis of Abdominal Fat to Assess Heart Attack and Stroke Risk.
 

 

Find more cardiology related RSNA news

Find radiology related RSNA News

Related Content

More complex, longer interventional procedures such as structural heart interventions or this revascularization of a coronary chronic total occlusion (CTO) at Henry Ford Hospital in Detroit, requires angiography imaging systems that have improved image detail and lower radiation dose. However, purchase of new systems was put on hold by many hospitals in 2020 due to the sudden drop in elective procedures and diversion of resources due to the COVID-19. Photo by Dave Fornell.

More complex, longer interventional procedures such as structural heart interventions or this revascularization of a coronary chronic total occlusion (CTO) at Henry Ford Hospital in Detroit, requires angiography imaging systems that have improved image detail and lower radiation dose. However, purchase of new systems was put on hold by many hospitals in 2020 due to the sudden drop in elective procedures and diversion of resources due to the COVID-19. Photo by Dave Fornell.

Feature | Angiography | January 19, 2021 | By Bhvita Jani
January 19, 2021 – With the postponement of non-essential elective surgeries and medical procedures in 2020 to conser
AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient care, announced today that the U.S. Food and Drug Administration (FDA) has granted 510(k) clearance for the company’s flagship image analysis platform.
News | Artificial Intelligence | January 18, 2021
January 18, 2021 — AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient ca
Coronary CT angiography images courtesy of Canon Medical Systems.

Coronary CT angiography images courtesy of Canon Medical Systems.

News | Computed Tomography (CT) | January 18, 2021
MRI of Nonferromagnetic Ballistics Suspended in Gelatin. 

MRI of Nonferromagnetic Ballistics Suspended in Gelatin. Scout (A), T1-weighted spin-echo (SE) (B), T2-weighted SE (C), T2-weighted gradient-recalled echo (GRE) (TR/TE, 500/10; D), and T2-weighted GRE (TR/TE, 700/30; E) MR images show jacket hollow point .45 automatic Colt pistol bullet (Corbon) (1), solid lead .45 Long Colt bullet (Winchester) (2), full metal jacket (FMJ) automatic Colt pistol bullet (Winchester) (3), 5.56-mm FMJ bullet (Federal Ammunition) (4), #7 lead shotgun pellet (Winchester) (5), and 5-mm lead air gun pellet (Sheridan) (6). On all sequences, metallic artifact is minimal. Although metallic artifact increases or blooms with increased TR/TE in GRE images (D and E), amount of surrounding distortion is still minimal.

News | Magnetic Resonance Imaging (MRI) | January 15, 2021
January 15, 2021 — 
Novel Coronavirus SARS-CoV-2 Transmission electron micrograph of SARS-CoV-2 virus particles, isolated from a patient. Image captured and color-enhanced at the NIAID Integrated Research Facility (IRF) in Fort Detrick, Maryland. Credit: National Institute of Allergy and Infectious Diseases, NIH

Novel Coronavirus SARS-CoV-2 Transmission electron micrograph of SARS-CoV-2 virus particles, isolated from a patient. Image captured and color-enhanced at the NIAID Integrated Research Facility (IRF) in Fort Detrick, Maryland. Image courtesy of  National Institute of Allergy and Infectious Diseases (NIH)

News | Coronavirus (COVID-19) | January 15, 2021
January 15, 2021 — In one of the first studies to examine the impact of the...
This cutting-edge technology assists radiologists in the interpretation of screening mammograms and allows them to diagnose breast cancer earlier and more accurately
News | Mammography | January 12, 2021
January 12, 2021 — Therapixel announced that...
The U.S. Food and Drug Administration released the agency's first Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan. This action plan describes a multi-pronged approach to advance the Agency's oversight of AI/ML-based medical software.
News | Artificial Intelligence | January 12, 2021
January 12, 2021 — The U.S.