Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Ruijin Center, Shanghai, China.
Nat Commun. 2022 Oct 6;13(1):5882. doi: 10.1038/s41467-022-33562-9.
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.
尽管基于深度学习（DL）的方法在替代基于 CT 的 PET 衰减和散射校正以实现无 CT 的 PET 成像方面具有潜力，但一个关键的瓶颈是它们在处理 PET 成像示踪剂和扫描仪的大异质性方面的能力有限。本研究采用一种简单的方法将领域知识集成到无 CT 的 PET 成像的深度学习中。与传统的直接 DL 方法相比，我们通过域分解来简化复杂的问题，使得依赖解剖结构的衰减校正的学习可以在低频域中稳健地实现，同时在处理过程中保留原始的与解剖结构无关的高频纹理。即使仅使用一个扫描仪上的一个示踪剂进行训练，我们提出的方法在对不同扫描仪上的各种外部成像示踪剂的测试中也证实了其有效性和稳健性。稳健、可推广和透明的 DL 开发可能会增强其临床转化的潜力。
