Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction.

Guo, Rui; Xue, Song; Hu, Jiaxi; Sari, Hasan; Mingels, Clemens; Zeimpekis, Konstantinos; Prenosil, George; Wang, Yue; Zhang, Yu; Viscione, Marco; Sznitman, Raphael; Rominger, Axel; Li, Biao; Shi, Kuangyu (2022). Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction. Nature Communications, 13(1), p. 5882. Springer Nature 10.1038/s41467-022-33562-9

Preview

Text s41467-022-33562-9-1.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (4MB) | Preview

Despite the potential of deep learning (DL)-based methods in substituting CT-based PET attenuation and scatter correction for CT-free PET imaging, a critical bottleneck is their limited capability in handling large heterogeneity of tracers and scanners of PET imaging. This study employs a simple way to integrate domain knowledge in DL for CT-free PET imaging. In contrast to conventional direct DL methods, we simplify the complex problem by a domain decomposition so that the learning of anatomy-dependent attenuation correction can be achieved robustly in a low-frequency domain while the original anatomy-independent high-frequency texture can be preserved during the processing. Even with the training from one tracer on one scanner, the effectiveness and robustness of our proposed approach are confirmed in tests of various external imaging tracers on different scanners. The robust, generalizable, and transparent DL development may enhance the potential of clinical translation.

Interest & Impact

Downloads

13 since deposited on 10 Oct 2022
13 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item