# FD-DiT: Frequency Domain-Directed Diffusion Transformer for Low-Dose CT Reconstruction

arXiv: https://arxiv.org/abs/2506.23466 · HTML: https://mlsanity.com/paper/2506.23466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Neighborhood Attention Transformer](https://mlsanity.com/paper/2204.07143/) (2022)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss](https://mlsanity.com/paper/1708.00961/) (2017)
- [Intriguing Findings of Frequency Selection for Image Deblurring](https://mlsanity.com/paper/2111.11745/) (2021)
- [CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization](https://mlsanity.com/paper/2304.01814/) (2023)
- [Generative Image Modeling using Style and Structure Adversarial Networks](https://mlsanity.com/paper/1603.05631/) (2016)
- [DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising](https://mlsanity.com/paper/2108.10772/) (2021)
- [Learning Frequency-aware Dynamic Network for Efficient Super-Resolution](https://mlsanity.com/paper/2103.08357/) (2021)
- [DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition](https://mlsanity.com/paper/2302.01791/) (2023)
- [WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion](https://mlsanity.com/paper/2404.09533/) (2024)

## Abstract (arXiv)

Low-dose computed tomography (LDCT) reduces radiation exposure but suffers from image artifacts and loss of detail due to quantum and electronic noise, potentially impacting diagnostic accuracy. Transformer combined with diffusion models has been a promising approach for image generation. Nevertheless, existing methods exhibit limitations in preserving finegrained image details. To address this issue, frequency domain-directed diffusion transformer (FD-DiT) is proposed for LDCT reconstruction. FD-DiT centers on a diffusion strategy that progressively introduces noise until the distribution statistically aligns with that of LDCT data, followed by denoising processing. Furthermore, we employ a frequency decoupling technique to concentrate noise primarily in high-frequency domain, thereby facilitating effective capture of essential anatomical structures and fine details. A hybrid denoising network is then utilized to optimize the overall data reconstruction process. To enhance the capability in recognizing high-frequency noise, we incorporate sliding sparse local attention to leverage the sparsity and locality of shallow-layer information, propagating them via skip connections for improving feature representation. Finally, we propose a learnable dynamic fusion strategy for optimal component integration. Experimental results demonstrate that at identical dose levels, LDCT images reconstructed by FD-DiT exhibit superior noise and artifact suppression compared to state-of-the-art methods.