TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction

Xueqi Guo, Luyao Shi, Xiongchao Chen, Qiong Liu, Bo Zhou, Huidong Xie, Yi-Hwa Liu, Richard Palyo, Edward J. Miller, Albert J. Sinusas, Lawrence H. Staib, Bruce Spottiswoode, Chi Liu, Nicha C. Dvornek

Abstract: Highlights•Temporally + Anatomically Informed GAN frame conversion in cardiac motion correction•Feature-wise linear modulation to address tracer distribution variability•Dual-channel input with anatomical locators to address spatial mismatch•Improved current motion correction methods and the downstream MBF quantification