Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators

TL;DR

Diff-ANO introduces a novel framework combining conditional consistency models and neural operators to enhance the efficiency and quality of high-resolution ultrasound computed tomography reconstructions.

Contribution

The paper presents a new approach that integrates adjoint neural operators with diffusion models to address PDE constraints in USCT, improving computational speed and accuracy.

Findings

Significantly faster reconstruction times compared to traditional methods.

Improved image quality in sparse-view and partial-view scenarios.

Effective replacement of PDE solvers with neural operator surrogates.

Abstract

Ultrasound Computed Tomography (USCT) constitutes a nonlinear inverse problem with inherent ill-posedness that can benefit from regularization through diffusion generative priors. However, traditional approaches for solving Helmholtz equation-constrained USCT face three fundamental challenges when integrating these priors: PDE-constrained gradient computation, discretization-induced approximation errors, and computational imbalance between neural networks and numerical PDE solvers. In this work, we introduce \textbf{Diff-ANO} (\textbf{Diff}usion-based Models with \textbf{A}djoint \textbf{N}eural \textbf{O}perators), a novel framework that combines conditional consistency models with adjoint operator learning to address these limitations. Our two key innovations include: (1) a \textit{conditional consistency model} that enables measurement-conditional few-step sampling by directly learning a self-consistent mapping from diffusion trajectories, and (2) an \textit{adjoint operator learning} module that replaces traditional PDE solvers with neural operator surrogates for efficient adjoint-based gradient computation. To enable practical deployment, we introduce the batch-based Convergent Born Series (BCBS)--a memory-efficient strategy for online generation of neural operator training pairs. Comprehensive experiments demonstrate that Diff-ANO significantly improves both computational efficiency and reconstruction quality, especially under sparse-view and partial-view measurement scenarios.