Unsupervised Medical Image Translation With Adversarial Diffusion Models
By Muzaffer Ozbey, S. Dar, H. Bedel, Onat Dalmaz, cSaban Ozturk, Alper Gungor, Tolga cCukur. IEEE Transactions on Medical Imaging, 2022
514 citations recorded by the source corpus.
Imputation of missing images via source-to-target modality translation can improve diversity in medical imaging protocols. A pervasive approach for synthesizing target images involves one-shot mapping through generative adversarial networks (GAN). Yet, GAN models that implicitly characterize the image distribution can suffer from limited sample fidelity. Here, we propose a novel method based on adversarial diffusion modeling, SynDiff, for improved performance in medical image translation. To capture a direct correlate of the image distribution, SynDiff leverages a conditional diffusion process that progressively maps noise and source images onto the target image. For fast and accurate image sampling during inference, large diffusion steps are taken with adversarial projections in the reverse diffusion direction. To enable training on unpaired datasets, a cycle-consistent architecture is devised with coupled diffusive and non-diffusive modules that bilaterally translate between two modalities. Extensive assessments are reported on the utility of SynDiff against competing GAN and diffusion models in multi-contrast MRI and MRI-CT translation. Our demonstrations indicate that SynDiff offers quantitatively and qualitatively superior performance against competing baselines.
Subfields: Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/f9583f36414287bd4b7f34a9b178aa9cc3cd471a
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Runsheng Xu
- Bin Cui
- Reza Azad
- Dorit Merhof
- Ehsan Khodapanah Aghdam
- Yue Zhao
- Moein Heidari
- Ming-Hsuan Yang
In Statistical and Nonlinear Physics
- Ehsan Khodapanah Aghdam
- Bin Cui
- Yue Zhao
- Moein Heidari
- Ming-Hsuan Yang
- Dorit Merhof
- Reza Azad
- Ilker Hacihaliloglu
Citations in the corpus
- Diffusion models in medical imaging: A comprehensive survey (2022, methodology): “Algorithm Networks Core Ideas Practical Use Cases Denoising Diffusion Probabilistic Models (DDPMs) (1)AnoDDPM [70] (2)CDPM [71] (3)IITM-Diffusion [72] (4)AnoDDIM [16] (5)PET-DDPM [64] (6)DenoOCT-DDPM [65] (7)brainSPADE [61] (8)DARL [69] (9)IISE [63] (10)*MT-Diffusion [49] (11)SynDiff [51] (12)MC-DDP”
- Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, methodology): “Computer Vision [137] [202],[198],[147],[200],[181], Super Resolution, Inpainting, and Translation [91],[10],[174],[38],[224],[36],[161] Semantic Segmentation [9],[17],[76] Video Generation [89],[93],[268],[275] Point Cloud Completion and Generation [286],[150],[155],[143],[274] Anomaly Detection [2”