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

Rui Guo, Song Xue, Jiaxi Hu, Hasan Sari, Clemens Mingels, Konstantinos Zeimpekis, George Prenosil, Yue Wang, Yu Zhang, Marco Viscione, Raphael Sznitman, Axel Rominger, Biao Li () and Kuangyu Shi
Additional contact information
Rui Guo: Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Song Xue: Bern University Hospital, University of Bern
Jiaxi Hu: Bern University Hospital, University of Bern
Hasan Sari: Bern University Hospital, University of Bern
Clemens Mingels: Bern University Hospital, University of Bern
Konstantinos Zeimpekis: Bern University Hospital, University of Bern
George Prenosil: Bern University Hospital, University of Bern
Yue Wang: Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Yu Zhang: Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Marco Viscione: Bern University Hospital, University of Bern
Raphael Sznitman: ARTORG Center, University of Bern
Axel Rominger: Bern University Hospital, University of Bern
Biao Li: Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Kuangyu Shi: Bern University Hospital, University of Bern

Nature Communications, 2022, vol. 13, issue 1, 1-9

Abstract: Abstract 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.

Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-022-33562-9 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-33562-9

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-33562-9

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().