Computer Vision News - October 2022

48 Poster Presentation Jiadong Zhang is in the second year of hismaster study in the IDEALab at the School of Biomedical Engineering, ShanghaiTech University, supervised by Dinggang Shen. His paper explores a novel PET-CT synthesis framework. He spoke to us ahead of his poster presentation. 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. MAPPING IN CYCLES: DUAL-DOMAIN PET-CT SYNTHESIS FRAMEWORK WITH CYCLE-CONSISTENT CONSTRAINTS Jiadong Zhang BEST OF MICCAI