Diffusion-Based Fourier Domain Deconvolution with Application to Ultrasound Image Restoration
Abstract
Deconvolution remains an ongoing challenge in ultrasound (US) imaging. Model-based techniques require extensive parameter tuning and are computationally demanding, whereas convolutional neural networks struggle due to the scarcity of labeled US data. To overcome these challenges, we propose a prior-driven, weakly supervised, diffusion-based deconvolution method. By operating in the Fourier domain, our approach improves image quality while maintaining computational efficiency and avoiding an explicit decomposition of the blur operator. Experimental results on simulated and in vivo datasets demonstrate the effectiveness of our method compared to benchmarks.
Fields of Study & Subjects
Ultrasound Imaging and Elastography
Generative Adversarial Networks and Image Synthesis
Ultrasound and Hyperthermia Applications
Publication details
- Journal / source
- 2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)
- Publisher
- IEEE
- Pages
- 1–4
- Publication date
- 8 April 2026
- Language
- EN