Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction

Authors:
Publisher website
Google Scholar
Abstract
Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge. Using a diffusion model on an out-of-distribution dataset, realistic reconstructions can be generated, but with hallucinating image features that are uniquely present in the training dataset. To address this discrepancy and improve reconstruction accuracy, we introduce a novel test-time adaptation sampling framework called Steerable Conditional Diffusion. Specifically, this framework adapts the diffusion model, concurrently with image reconstruction, based solely on the information provided by the available measurement. Utilising the proposed method, we achieve substantial enhancements in out-of-distribution performance across diverse imaging modalities, advancing the robust deployment of denoising diffusion models in real-world applications.
Funding Information
  • i4health Ph.D. Studentship through U.K. Engineering and Physical Sciences Research Council (EP/S021930/1)
  • Deutsche Forschungsgemeinschaft (281474342/GRK2224/2)
  • EPSRC Program (EP/V026259/1)
  • U.K. EPSRC (EP/T000864/1, EP/V026259/1)
  • DFGNSFC Project of the Sino-German Center Mobility Program (M-0187)
  • BAB-Project PY2DLL [European Regional Development Fund (EFRE)]

This publication has 35 references indexed in Scilit: