Realistic High-Resolution Body Computed Tomography Image Synthesis by Using Progressive Growing Generative Adversarial Network: Visual Turing Test.
Ho Young ParkHyun Jin BaeGil-Sun HongMinjee KimJihye YunSungwon ParkWon Jung ChungNamkug KimPublished in: JMIR medical informatics (2021)
The GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; however, it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details.
Keyphrases
- deep learning
- high resolution
- computed tomography
- convolutional neural network
- optical coherence tomography
- dual energy
- positron emission tomography
- image quality
- multiple sclerosis
- magnetic resonance imaging
- contrast enhanced
- mass spectrometry
- tandem mass spectrometry
- high speed
- magnetic resonance
- liquid chromatography