Quantification of abdominal fat from computed tomography using deep learning and its association with electronic health records in an academic biobank.
Matthew T MacLeanQasim JehangirMarijana VujkovicYi-An KoHarold LittArijitt BorthakurHersh SagreiyaMark RosenDavid A MankoffMitchell D SchnallHaochang ShouJulio ChirinosScott M DamrauerDrew A TorigianRotonya CarrDaniel J RaderWalter R WitscheyPublished in: Journal of the American Medical Informatics Association : JAMIA (2021)
This work presents a fully automated and highly accurate method for the quantification of abdominal fat that can be applied to routine clinical imaging studies to fuel translational scientific discovery.
Keyphrases
- electronic health record
- deep learning
- computed tomography
- adipose tissue
- high resolution
- high throughput
- machine learning
- clinical decision support
- small molecule
- artificial intelligence
- fatty acid
- positron emission tomography
- convolutional neural network
- adverse drug
- magnetic resonance imaging
- clinical practice
- case control
- mass spectrometry
- single cell