Temporally downsampled cerebral CT perfusion image restoration using deep residual learning.
Haichen ZhuDan TongLu ZhangShijie WangWeiwen WuHui TangYang ChenLimin LuoJian ZhuBaosheng LiPublished in: International journal of computer assisted radiology and surgery (2019)
The trained model can restore the temporally downsampled 15-pass CTP to 30 passes very well. According to the contrast test, sufficient information cannot be restored with, e.g., simple interpolation method and deep convolutional generative adversarial network, but can be restored with the proposed CNN model. This method can be an optional way to reduce radiation dose during CTP imaging.
Keyphrases
- contrast enhanced
- high resolution
- magnetic resonance
- computed tomography
- magnetic resonance imaging
- deep learning
- subarachnoid hemorrhage
- convolutional neural network
- healthcare
- resistance training
- dual energy
- image quality
- mass spectrometry
- machine learning
- body composition
- brain injury
- fluorescence imaging
- cerebral ischemia