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

arXiv: https://arxiv.org/abs/2509.23885 · HTML: https://mlsanity.com/paper/2509.23885/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [High-Quality Self-Supervised Deep Image Denoising](https://mlsanity.com/paper/1901.10277/) (2019)
- [DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics](https://mlsanity.com/paper/2310.13268/) (2023)
- [Noisier2Noise: Learning to Denoise from Unpaired Noisy Data](https://mlsanity.com/paper/1910.11908/) (2019)
- [Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images](https://mlsanity.com/paper/2106.07009/) (2021)
- [Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots](https://mlsanity.com/paper/2203.06967/) (2022)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?](https://mlsanity.com/paper/1811.03691/) (2018)
- [Zero-Shot Self-Supervised Learning for MRI Reconstruction](https://mlsanity.com/paper/2102.07737/) (2021)
- [CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization](https://mlsanity.com/paper/2304.01814/) (2023)
- [Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing](https://mlsanity.com/paper/2311.18608/) (2023)
- [Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance](https://mlsanity.com/paper/2312.16519/) (2023)
- [Self-Guided Diffusion Models](https://mlsanity.com/paper/2210.06462/) (2022)
- [Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data](https://mlsanity.com/paper/2403.08728/) (2024)
- [A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noise](https://mlsanity.com/paper/2205.10278/) (2022)
- [Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction](https://mlsanity.com/paper/2506.22012/) (2025)
- [Rotation-Equivariant Self-Supervised Method in Image Denoising](https://mlsanity.com/paper/2505.19618/) (2025)
- [Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoising](https://mlsanity.com/paper/2502.06432/) (2025)
- [Robust multi-coil MRI reconstruction via self-supervised denoising](https://mlsanity.com/paper/2411.12919/) (2024)
- [A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging](https://mlsanity.com/paper/2410.19288/) (2024)

## Abstract (arXiv)

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.