MICCAI 2022 Daily – Tuesday

PET is a vital medical imaging technique for people suffering from cancer and brain disorders. CT is needed for anatomical localization and also PET attenuation correction during PET scanning. But acquisition of CT increases risk of radiation exposure. This work proposes using PET image to synthesize CT image for non- diagnosis purpose. Most existing works use learning-based image synthesis to build cross-modality mapping in the image domain, without considering the projection domain, leading to inconsistency between information in the two domains. “ Our framework uses dual-domain knowledge in two different modalities, PET and CT, and keeps dual-domain consistency in the synthesis process, ” Jiadong explains. “ To the best of our knowledge, ours is the first paper to exploit dual- domain information for two different modalities. Other works just use one modality, such as low-dose and standard-dose CT. We hope this work can make a significant contribution to cross-modality synthesis tasks. ” 14 DAILY MICCAI Tuesday Poster Presentation Mapping in Cycles: Dual-Domain PET-CT Synthesis Framework with Cycle-Consistent Constraints Jiadong Zhang is in the second year of his master study in the IDEA Lab at the School of Biomedical Engineering, ShanghaiTech University, supervised by Dinggang Shen. His paper explores a novel PET-CT synthesis framework. He speaks to us ahead of his poster today Ashley Bruce