CT-derived pectoralis composition and incident pneumonia hospitalization using fully automated deep-learning algorithm: multi-ethnic study of atherosclerosis.
Hamza A IbadQuincy A HathawayDavid A BluemkeArta KasaeianJoshua G KleinMatthew J BudoffR Graham BarrMatthew AllisonWendy S PostJoão A C LimaShadpour DemehriPublished in: European radiology (2023)
•Identification of independent and modifiable risk factors of pneumonia can have important clinical impact on patients with chronic obstructive pulmonary disease. •Opportunistic CT measures of adipose tissue within pectoralis muscles using deep-learning algorithms can be quickly obtainable at zero additional cost or radiation exposure. •Deep learning-derived pectoralis muscle measurements of intermuscular fat and its subcomponents are independently associated with subsequent incident pneumonia hospitalization.
Keyphrases
- deep learning
- adipose tissue
- cardiovascular disease
- artificial intelligence
- machine learning
- risk factors
- convolutional neural network
- image quality
- computed tomography
- dual energy
- contrast enhanced
- respiratory failure
- community acquired pneumonia
- insulin resistance
- high fat diet
- magnetic resonance imaging
- skeletal muscle
- positron emission tomography
- intensive care unit
- metabolic syndrome
- high throughput
- acute respiratory distress syndrome
- bioinformatics analysis