Figure 1 - uploaded by Ti Bai
Content may be subject to copyright.
Download
View publication
The proposed spatially shift-invariant network architecture. The LDCT is first decomposed into four sub-images, which are fed into the feature extractor. Then, a feature fuser is used to combine the features. Lastly, a predictor is used to generate the results. detail how to choose the pixels in Y E and the associated complement Y C , as well as the prior distribution P (µ X E ).

The proposed spatially shift-invariant network architecture. The LDCT is first decomposed into four sub-images, which are fed into the feature extractor. Then, a feature fuser is used to combine the features. Lastly, a predictor is used to generate the results. detail how to choose the pixels in Y E and the associated complement Y C , as well as the prior distribution P (µ X E ).

Source publication
Figure 1: The proposed spatially shift-invariant network architecture....
Figure 3: Denoising performance comparison for slice 2 for a patient in...
Figure 5: Denoising performance comparison among different algorithms...
Figure 6: Denoising performance comparison among different algorithms...
Figure 7: Comparison of different algorithms regarding the lesion...
Probabilistic self-learning framework for Low-dose CT Denoising
Preprint
Full-text available
  • May 2020
Despite the indispensable role of X-ray computed tomography (CT) in diagnostic medicine field, the associated ionizing radiation is still a major concern considering that it may cause genetic and cancerous diseases. Decreasing the exposure can reduce the dose and hence the radiation-related risk, but will also induce higher quantum noise. Supervise...
Cite
Download full-text

Context in source publication

Context 1
... sub-module contains four layers and accepts only the features from the complementary sub-images. For example, if the target sub-image is the red sub-image in figure 1, the input to the red feature fuser sub-module will only accept the features from the yellow, green, and blue sub-images. ...