POUR-Net: A Population-Prior-Aided Over-Under-Representation Network for Low-Count PET Attenuation Map Generation

• Published in: IEEE transactions on medical imaging Vol. 44; no. 4; pp. 1699 - 1710
• Main Authors: Zhou, Bo, Hou, Jun, Chen, Tianqi, Zhou, Yinchi, Chen, Xiongchao, Xie, Huidong, Liu, Qiong, Guo, Xueqi, Xia, Menghua, Tsai, Yu-Jung, Panin, Vladimir Y., Toyonaga, Takuya, Duncan, James S., Liu, Chi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2025
• Subjects: Algorithms; Attenuation; attenuation correction; attenuation map generation; Biomedical imaging; Brain - diagnostic imaging; Computed tomography; deep learning; Feature extraction; Humans; Image Processing, Computer-Assisted - methods; Image reconstruction; Image resolution; Imaging; Iterative methods; Low-count PET; Neural Networks, Computer; population prior; Positron emission tomography; Positron-Emission Tomography - methods; Radiology
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2024.3514925

Low-dose PET offers a valuable means of minimizing radiation exposure in PET imaging. However, the prevalent practice of employing additional CT scans for generating attenuation maps (<inline-formula> <tex-math notation="LaTeX">\mu </tex-math></inline-formula>-map) for PET attenuation correction significantly elevates radiation doses. To address this concern and further mitigate radiation exposure in low-dose PET exams, we propose an innovative Population-prior-aided Over-Under-Representation Network (POUR-Net) that aims for high-quality attenuation map generation from low-dose PET. First, POUR-Net incorporates an Over-Under-Representation Network (OUR-Net) to facilitate efficient feature extraction, encompassing both low-resolution abstracted and fine-detail features, for assisting deep generation on the full-resolution level. Second, complementing OUR-Net, a population prior generation machine (PPGM) utilizing a comprehensive CT-derived <inline-formula> <tex-math notation="LaTeX">\mu </tex-math></inline-formula>-map dataset, provides additional prior information to aid OUR-Net generation. The integration of OUR-Net and PPGM within a cascade framework enables iterative refinement of <inline-formula> <tex-math notation="LaTeX">\mu </tex-math></inline-formula>-map generation, resulting in the production of high-quality <inline-formula> <tex-math notation="LaTeX">\mu </tex-math></inline-formula>-maps. Experimental results underscore the effectiveness of POUR-Net, showing it as a promising solution for accurate CT-free low-count PET attenuation correction, which also surpasses the performance of previous baseline methods.