Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model.
Yunchao YinDerya YakarRudi A J O DierckxKim B MouridsenThomas C KweeRobbert J de HaasPublished in: European radiology (2021)
• Deep learning algorithms can stage liver fibrosis using contrast-enhanced CT images, but the algorithm is still used as a black box and lacks transparency. • Location maps produced by Gradient-weighted Class Activation Mapping can indicate the focus of the liver fibrosis staging network. • Deep learning methods use CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage.
Keyphrases
- liver fibrosis
- deep learning
- contrast enhanced
- diffusion weighted
- magnetic resonance imaging
- computed tomography
- magnetic resonance
- convolutional neural network
- artificial intelligence
- machine learning
- dual energy
- lymph node
- diffusion weighted imaging
- pet ct
- healthcare
- positron emission tomography
- health information
- image quality
- high resolution
- social media
- mass spectrometry