arXiv subjects

Cunfeng Wei

Publications and source records attributed to Cunfeng Wei.

3 recordsLinked to original sources

arXiv2026

SCOUT: Fast Spectral CT Imaging in Ultra LOw-data Regimes via PseUdo-label GeneraTion

Noise and artifacts during computed tomography (CT) scans are a fundamental challenge affecting disease diagnosis. However, current methods either involve excessively long reconstruction times or rely on data-driven models for optimization, failing to adequately consider the valuable information inherent in the data itself, especially medical 3D data. This work proposes a reconstruction method under ultra-low raw data conditions, requiring no external data and avoiding lengthy pre-training processes. By leveraging spatial nonlocal similarity and the conjugate properties of the projection domain to generate pseudo-3D data for self-supervised training, high-fidelity results can be achieved in a very short time. Extensive experiments demonstrate that this method not only mitigates detector-induced ring artifacts but also exhibits unprecedented capabilities in detail recovery. This method provides a new paradigm for research using unlabeled raw projection data. Code is available at https://github.com/yqx7150/SCOUT.

cs.CV↗

arXiv2025

Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstruction

Current methods based on deep learning for self-supervised low-dose CT (LDCT) reconstruction, while reducing the dependence on paired data, face the problem of significantly decreased generalization when training with single-dose data and extending to other doses. To enable dose-extensive generalization using only single-dose projection data for training, this work proposes a novel method of Extendable GENeraLization self-supervised Diffusion (EGenDiff) for low-dose CT reconstruction. Specifically, a contextual subdata self-enhancing similarity strategy is designed to provide an initial prior for the subsequent progress. During training, the initial prior is used to combine knowledge distillation with a deep combination of latent diffusion models for optimizing image details. On the stage of inference, the pixel-wise self-correcting fusion technique is proposed for data fidelity enhancement, resulting in extensive generalization of higher and lower doses or even unseen doses. EGenDiff requires only LDCT projection data for training and testing. Comprehensive evaluation on benchmark datasets, clinical data, photon counting CT data, and across all three anatomical planes (transverse, coronal, and sagittal) demonstrates that EGenDiff enables extendable generalization multi-dose, yielding reconstructions that consistently outperform leading existing methods.

cs.CV↗

arXiv2015

Performance assessment of CsI(Tl) screens on various substrates for X-ray imaging

Thallium-doped cesium iodide (CsI(Tl)) screens are widely used in X-ray imaging devices because of the columnar structure of CsI(Tl) layer, but few reports focus on the optical role of the substrate in the screen system. In this paper, four substrates including fused silica (SiO2), silver-film coated SiO2, graphite (C) and fiber optic plate (FOP) are used to fabricate CsI(Tl) screens by thermal evaporation. Their imaging performance is evaluated by relative light output (RLO), modulation transfer function (MTF), normalized noise power spectrum (NNPS) and noise equivalent quanta (NEQ). The results reveal that although CsI(Tl) film on graphite plate yields images with the lowest light output, it presents relatively higher spatial resolution and better signal-to-noise characteristics. However, films on SiO2 plate obtain low MTF but high NNPS curves, whether or not coated with silver film. Furthermore, scintillation screens on FOP have bright images with low NNPS and high NEQ, but have the lowest MTF. By controlling the substrate optical features, CsI(Tl) films can be tailed to suit a given application.

physics.ins-det↗