Joint correction of attenuation and scatter in image space using deep convolutional neural networks for dedicated brain < sup > 18 < /sup > F-FDG PET.

In conclusion, we demonstrated the feasibility of directly producing PET images corrected for attenuation and scatter using a DCNN (PET&lt;sub&gt;DCNN&lt;/sub&gt;) from PET&lt;sub&gt;NC&lt;/sub&gt; in image space without requiring conventional attenuation map generation and time-consuming scatter correction. Additionally, our DCNN-based method provides a possible alternative to MR-ASC for simultaneous PET/MRI. PMID: 30743246 [PubMed - as supplied by publisher]
Source: Physics in Medicine and Biology - Category: Physics Authors: Tags: Phys Med Biol Source Type: research