Automatic Deep-Learning Segmentation of Epicardial Adipose Tissue from Low-Dose Chest CT and Prognosis Impact on COVID-19.
Axel BartoliJoris FournelLéa Ait-YahiaFarah CadourFarouk TradiBadih GhattasSébastien CortaredonaMatthieu MillionAdèle LasbleizAnne DutourBénédicte GaboritAlexis JacquierPublished in: Cells (2022)
A DL algorithm was developed and evaluated to obtain reproducible and precise EAT segmentation on LDCT. EAT extent in association with lung lesion extent was associated with adverse clinical outcomes with an AUC = 0.805.
Keyphrases
- deep learning
- low dose
- adipose tissue
- convolutional neural network
- coronavirus disease
- artificial intelligence
- sars cov
- machine learning
- computed tomography
- high dose
- image quality
- insulin resistance
- high fat diet
- dual energy
- contrast enhanced
- magnetic resonance imaging
- magnetic resonance
- emergency department
- type diabetes
- positron emission tomography
- respiratory syndrome coronavirus