DNA-Prior: Unsupervised Denoise Anything via Dual-Domain Prior

TL;DR

DNA-Prior introduces an unsupervised, dual-domain prior framework for medical image denoising that effectively preserves structures without needing annotated data, making it suitable for diverse clinical scenarios.

Contribution

The paper presents a novel hybrid prior approach combining implicit architectural and explicit spectral-spatial priors for unsupervised denoising in medical imaging.

Findings

Consistent noise suppression across multiple modalities

Preserves anatomical structures effectively

Operates without external training data

Abstract

Medical imaging pipelines critically rely on robust denoising to stabilise downstream tasks such as segmentation and reconstruction. However, many existing denoisers depend on large annotated datasets or supervised learning, which restricts their usability in clinical environments with heterogeneous modalities and limited ground-truth data. To address this limitation, we introduce DNA-Prior, a universal unsupervised denoising framework that reconstructs clean images directly from corrupted observations through a mathematically principled hybrid prior. DNA-Prior integrates (i) an implicit architectural prior, enforced through a deep network parameterisation, with (ii) an explicit spectral-spatial prior composed of a frequency-domain fidelity term and a spatial regularisation functional. This dual-domain formulation yields a well-structured optimisation problem that jointly preserves global frequency characteristics and local anatomical structure, without requiring any external training data or modality-specific tuning. Experiments across multiple modalities show that DNA achieves consistent noise suppression and structural preservation under diverse noise conditions.