← Back to all news
arXiv Computer Vision By Xianlei Han, Shaoyu Wang, Jiancheng Fang, Weiwen Wu, Qiegen Liu

Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising

Read the original on arXiv Computer Vision →

The paper introduces a physics‑driven, cross‑domain iterative framework for self‑supervised low‑dose CT denoising. It first uses a learned sinogram prior and the LDCT noise model to separate Poisson and Gaussian noise components, then applies binomial and Gaussian data thinning to create two training pairs with independent noise realizations. These pairs train an image‑domain network whose outputs are forward‑projected to refine the prior, yielding consistent performance gains over existing self‑supervised baselines and comparable results to supervised methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
6d ago

Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matching

Noise2Match is a self‑supervised method for low‑dose CT denoising that uses an adaptive inter‑slice matching network to model and correct the label transition between adjacent slices. By ensuring the equal‑mean condition of the Noise2Noise framework, it theoretically matches supervised training with paired noisy‑clean data. The approach also extends effectively to low‑dose cone‑beam CT, outperforming existing image‑domain self‑supervised methods.

More like this →
arXiv Machine Learning
Jul 15

GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization

arXiv:2607. 11941v1 Announce Type: cross Abstract: Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality.

By Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, Kah Ong Michael Goh, S. M. Hasan Mahmud, Md Mahfuzur Rahman
ragdiffusionbenchmarks
More like this →
arXiv AI
Sep 17

Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction

The paper introduces Dose-Aware Cold Diffusion (DACD), a physics-consistent framework that treats radiation dose as a continuous latent variable in a cold diffusion process for low-dose CT reconstruction. DACD combines dose-aware perception, multi-scale structural priors, and dose-calibrated step allocation to guide denoising, and adds an iterative forward-backprojection correction to enforce projection-domain consistency. Experiments on Mayo-2020, Mayo-2016, and LoDoPaB-CT show DACD outperforms existing diffusion-based and physics-guided methods, especially at ultra-low doses, and generalizes robustly across continuous, unseen dose levels.

By Md Imam Ahasan, Guangchao Yang, A F M Abdun Noor, S M Hasan Mahmud, Md Mahfuzur Rahman
diffusionbenchmarks
More like this →
arXiv AI
Aug 11

Toward CT-Equivalent Image Quality in Low-Dose Radiotherapy Planning: Conditional Diffusion-Based CBCT-to-CT Synthesis and the Impact of CBCT Input Representation

arXiv:2608. 08919v1 Announce Type: cross Abstract: During standard radiotherapy planning, repeated CT acquisitions are often required for patient registration, verification, and adaptive planning, resulting in increased cumulative X-ray dose.

By Alzahra Altalib, Chunhui Li, Christopher Hamill Taylor, Sankar Pillai, Alessandro Perelli
diffusion
More like this →