Does prior knowledge in the form of multiple low-dose PET images (at different dose levels) improve standard-dose PET prediction?
This work addresses quality degradation in PET imaging for medical applications, but it is incremental as it builds on existing deep learning denoising methods by incorporating additional data.
The paper tackled the problem of predicting standard-dose PET images from low-dose versions by proposing a method that uses multiple low-dose levels as prior knowledge, instead of relying on a single dose level, to improve estimation accuracy.
Reducing the injected dose would result in quality degradation and loss of information in PET imaging. To address this issue, deep learning methods have been introduced to predict standard PET images (S-PET) from the corresponding low-dose versions (L-PET). The existing deep learning-based denoising methods solely rely on a single dose level of PET images to predict the S-PET images. In this work, we proposed to exploit the prior knowledge in the form of multiple low-dose levels of PET images (in addition to the target low-dose level) to estimate the S-PET images.