28 June 2024 in IEEE Transactions on Medical Imaging
The multi-source stationary CT, where both the detector and X-ray source are fixed, represents a novel imaging system with high temporal resolution that has garnered significant interest. Limited space within the system restricts the number of X-ray sources, leading to sparse-view CT imaging challenges. Recent diffusion models for reconstructing sparse-view CT have generally focused separately on sinogram or image domains. Sinogram-centric models effectively estimate missing projections but may introduce artifacts, lacking mechanisms to ensure image correctness. Conversely, image-domain models, while capturing detailed image features, often struggle with complex data distribution, leading to inaccuracies in projections. Addressing these issues, the Dual-domain Collaborative Diffusion Sampling (DCDS) model integrates sinogram and image domain diffusion processes for enhanced sparse-view reconstruction. This model combines the strengths of both domains in an optimized mathematical framework. A collaborative diffusion mechanism underpins this model, improving sinogram recovery and image generative capabilities. This mechanism facilitates feedback-driven image generation from the sinogram domain and uses image domain results to complete missing projections. Optimization of the DCDS model is further achieved through the alternative direction iteration method, focusing on data consistency updates. Extensive testing, including numerical simulations, real phantoms, and clinical cardiac datasets, demonstrates the DCDS model’s effectiveness. It consistently outperforms various state-of-the-art benchmarks, delivering exceptional reconstruction quality and precise sinogram.
24 June 2024 in IEEE Transactions on Medical Imaging
The score-based generative model (SGM) has received significant attention in the field of medical imaging, particularly in the context of limited-angle computed tomography (LACT). Traditional SGM approaches achieved robust reconstruction performance by incorporating a substantial number of sampling steps during the inference phase. However, these established SGM-based methods require large computational cost to reconstruct one case. The main challenge lies in achieving high-quality images with rapid sampling while preserving sharp edges and small features. In this study, we propose an innovative rapid-sampling strategy for SGM, which we have aptly named the time-reversion fast-sampling (TIFA) score-based model for LACT reconstruction. The entire sampling procedure adheres steadfastly to the principles of robust optimization theory and is firmly grounded in a comprehensive mathematical model. TIFA’s rapid-sampling mechanism comprises several essential components, including jump sampling, time-reversion with re-sampling, and compressed sampling. In the initial jump sampling stage, multiple sampling steps are bypassed to expedite the attainment of preliminary results. Subsequently, during the time-reversion process, the initial results undergo controlled corruption by introducing small-scale noise. The re-sampling process then diligently refines the initially corrupted results. Finally, compressed sampling fine-tunes the refinement outcomes by imposing regularization term. Quantitative and qualitative assessments conducted on numerical simulations, real physical phantom, and clinical cardiac datasets, unequivocally demonstrate that TIFA method (using 200 steps) outperforms other state-of-the-art methods (using 2000 steps) from available [0°, 90°] and [0°, 60°]. Furthermore, experimental results underscore that our TIFA method continues to reconstruct high-quality images even with 10 steps. Our code at https://github.com/tianzhijiaoziA/TIFADiffusion.
4 March 2025 in Journal of Colloid and Interface Science
11 March 2024 in IEEE Transactions on Instrumentation and Measurement
Low-dose Digital Radiography (DR) is a commonly used imaging technique in clinical practice to minimize the harmful radiation for patients. At the same time, DR images are susceptible to noise and they often have degraded information contents, calling for effective image denoising techniques. The typical existing image denoising methods are supervised and they require clean samples at the training stage. Such requirement limits their clinical applicability since the clean samples are difficult to obtain in practice. To address this challenge, we propose a self-fusion diffusion model, denoted as S 3 -DDPM, with simplex noise in the frequency domain. Specifically, the proposed method firstly incorporates spectrum learning to capture rich image information in various frequency ranges without requirement of clean training samples. Secondly, it utilizes simplex noise instead of the typical Gaussian noise to enhance the diversity of the generated noise. Thirdly, our method employs an alternating compensation strategy during each diffusion process, where a series of intermediate results are weighted and combined through self-fusion to derive a new denoised sample. The experimental results on clinical low-dose DR and CT images demonstrate the superiority of the proposed method over the state-of-the-art unsupervised methods, achieving favorable denoising performance.
31 January 2025 in IEEE Transactions on Image Processing
The reconstruction of limited data computed tomography (CT) aims to obtain high-quality images from a reduced set of projection views acquired from sparse views or limited angles. This approach is utilized to reduce radiation exposure or expedite the scanning process. Deep Learning (DL) techniques have been incorporated into limited data CT reconstruction tasks and achieve remarkable performance. However, these DL methods suffer from various limitations. Firstly, the distribution inconsistency between the simulation data and the real data hinders the generalization of these DL-based methods. Secondly, these DL-based methods could be unstable due to lack of kernel awareness. This paper addresses these issues by proposing an unrolling framework called Progressive Artifact Image Learning (PAIL) for limited data CT reconstruction. The proposed PAIL primarily consists of three key modules, i.e., a residual domain module (RDM), an image domain module (IDM), and a wavelet domain module (WDM). The RDM is designed to refine features from residual images and suppress the observable artifacts from the reconstructed images. This module could effectively alleviate the effects of distribution inconsistency among different data sets by transferring the optimization space from the original data domain to the residual data domain. The IDM is designed to suppress the unobservable artifacts in the image space. The RDM and IDM collaborate with each other during the iterative optimization process, progressively removing artifacts and reconstructing the underlying CT image. Furthermore, in order to void the potential hallucinations generated by the RDM and IDM, an additional WDM is incorporated into the network to enhance its stability. This is achieved by making the network become kernel-aware via integrating wavelet-based compressed sensing. The effectiveness of the proposed PAIL method has been consistently verified on two simulated CT data sets, a clinical cardiac data set and a sheep lung data set. Compared to other state-of-the-art methods, the proposed PAIL method achieves superior performance in various limited data CT reconstruction tasks, demonstrating its promising generalization and stability.
1 September 2026 in IEEE Transactions on Radiation and Plasma Medical Sciences
Stationary head CT (sHCT) plays a critical role in detecting intracranial lesions. However, its fixed gantry restricts projection angles and undermines reconstruction accuracy. Recent studies have shown that score-based generative models (SGMs) can restore high-quality images from limited projections in two-dimensional (2D) limited-angle CT. Extending SGMs to three-dimensional (3D) sHCT is still challenging, as achieving high-resolution images without incurring excessive computational cost remains an open problem. To address this challenge, this study proposes a mutually orthogonal plane-based optical-flow-regulated (MOPO) diffusion model that effectively balances sampling efficiency and reconstruction accuracy. Specifically, we establish a 3D artifact-aware framework that incorporates a cross-plane attention mechanism to explicitly model and mitigate inter-slice artifact propagation. Furthermore, we design a mutually orthogonal plane-based (MOP) accelerated sampler capable of reducing the sampling process to as few as 10–20 steps. This approach achieves up to a 160× speedup while maintaining high reconstruction accuracy. To ensure global consistency, an anisotropic optical flow regularization is introduced, constructing non-rigid displacement fields between adjacent slices for structural coherence. Experimental results demonstrate that the MOPO-based framework outperforms existing methods in artifact suppression, detail preservation, and computational efficiency, providing a novel solution for high-fidelity and accelerated sHCT reconstruction.