A Framework for Guiding DDPM-Based Reconstruction of Damaged CT Projections Using Traditional Methods.
Authors
Affiliations (5)
Affiliations (5)
- Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, Anhui, 230031, China.
- University of Science and Technology of China, Hefei, Anhui, 230026, China.
- Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, Anhui, 230031, China. [email protected].
- Department of Orthopaedics, The First Affiliated Hospital of University of Science and Technology of China, Hefei, Anhui, 230001, China.
- Centre for Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China.
Abstract
Denoising Diffusion Probabilistic Models (DDPM) have emerged as a promising generative framework for sample synthesis, yet their limitations in detail preservation hinder practical applications in computed tomography (CT) image reconstruction. To address these technical constraints and enhance reconstruction quality from compromised CT projection data, this study proposes the Projection Hybrid Inverse Reconstruction Framework (PHIRF) - a novel paradigm integrating conventional reconstruction methodologies with DDPM architecture. The framework implements a dual-phase approach: Initially, conventional CT reconstruction algorithms (e.g., Filtered back projection(FBP), Algebraic Reconstruction Technique(ART), Maximum-Likelihood Expectation Maximization (ML-EM)) are employed to generate preliminary reconstructions from incomplete projections, establishing low-dimensional feature representations. These features are subsequently parameterized and embedded as conditional constraints in the reverse diffusion process of DDPM, thereby guiding the generative model to synthesize enhanced tomographic images with improved structural fidelity. Comprehensive evaluations were conducted on three representative ill-posed projection scenarios: limited-angle projections, sparse-view acquisitions, and low-dose measurements. Experimental results demonstrate that PHIRF achieves state-of-the-art performance across all compromised data conditions, particularly in preserving fine anatomical details and suppressing reconstruction artifacts. Quantitative metrics and visual assessments confirm the framework's consistent superiority over existing deep learning-based reconstruction approaches, substantiating its adaptability to diverse projection degradation patterns. This hybrid architecture establishes a new paradigm for combining physical prior knowledge with data-driven generative models in medical image reconstruction tasks.