Generation of synthetic PET/MR fusion images from MR images using a combination of generative adversarial networks and conditional denoising diffusion probabilistic models based on simultaneous 18F-FDG PET/MR image data of pyogenic spondylodiscitis.

Euijin JungEunjung KongDongwoo YuHeesung YangPhilip ChicontweSang Hyun ParkIkchan Jeon

Published in: The spine journal : official journal of the North American Spine Society (2024)

The combination of Pix2Pix and cDDPMs demonstrated the potential for cross-modal image generation from MR to PET images, with reliable quantitative and qualitative image similarities.

Keyphrases

deep learning
convolutional neural network
pet ct
positron emission tomography
contrast enhanced
pet imaging
computed tomography
magnetic resonance
artificial intelligence
optical coherence tomography
machine learning
magnetic resonance imaging
systematic review
high resolution
neural network