Imitation learning for improved 3D PET/MR attenuation correction

Kerstin Kläser,Thomas Varsavsky,Pawel Markiewicz,Tom Vercauteren,Alexander Hammers,David Atkinson,Kris Thielemans,Brian Hutton,M J Cardoso,Sébastien Ourselin

Medical Image Analysis（2021）

引用 8|浏览29

暂无评分

摘要

•CT-based losses neglect the PET data when doing MR to CT synthesis.•MR to CT synthesis networks should account for PET reconstruction error.•Multi-hypothesis uncertainty provides the best approximation of the true PET.•Imitation learning results in a better optima and more generalisable model.

查看译文

关键词

MR to CT synthesis,Deep learning,Imitation learning,Convolutional neural network

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要