Denoising of ultra-low-dose 15O positron emission tomography images using deep image prior with anatomical information e

PURPOSE: Recent deep-learning methods can recover standard-dose PET images from low-dose images. However, these methods require a large amount of data. We proposed a novel unsupervised learning approach using conditional deep image prior (DIP) with tissue probability maps extr...

• Source: Radiology AI literature (PubMed) (AI)
• Type: Research

RadPigeon summaries are original and for information only. They are not clinical advice.