Enhanced Low-Dose CT Image Reconstruction by Domain and Task Shifting Gaussian Denoisers
Not on the map. Why?
Abstract (arXiv)
Computed tomography from a low radiation dose (LDCT) is challenging due to high noise in the projection data. Popular approaches for LDCT image reconstruction are two-stage methods, typically consisting of the filtered backprojection (FBP) algorithm followed by a neural network for LDCT image enhancement. Two-stage methods are attractive for their simplicity and potential for computational efficiency, typically requiring only a single FBP and a neural network forward pass for inference. However, the best reconstruction quality is currently achieved by unrolled iterative methods (Learned Primal-Dual and ItNet), which are more complex and thus have a higher computational cost for training and inference. We propose a method combining the simplicity and efficiency of two-stage methods with state-of-the-art reconstruction quality. Our strategy utilizes a neural network pretrained for Gaussian noise removal from natural grayscale images, fine-tuned for LDCT image enhancement. We call this method FBP-DTSGD (Domain and Task Shifted Gaussian Denoisers) as the fine-tuning is a task shift from Gaussian denoising to enhancing LDCT images and a domain shift from natural grayscale to LDCT images. An ablation study with three different pretrained Gaussian denoisers indicates that the performance of FBP-DTSGD does not depend on a specific denoising architecture, suggesting future advancements in Gaussian denoising could benefit the method. The study also shows that pretraining on natural images enhances LDCT reconstruction quality, especially with limited training data. Notably, pretraining involves no additional cost, as existing pretrained models are used. The proposed method currently holds the top mean position in the LoDoPaB-CT challenge.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 72 references that are in the map. First posted on arXiv 6 Mar 2024.
Builds on
33 of 72 references.
References · 33
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
- 2020Knowledge Distillation: A Surveycited by 1,578
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
- 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
- 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2023VILA: On Pre-training for Visual Language Modelscited by 686
- 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 550
- 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
21 more
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
- 2018Rethinking ImageNet Pre-trainingcited by 376
- 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
- 2017Road Extraction by Deep Residual U-Netcited by 333
- 2020A Brief Review of Domain Adaptationcited by 287
- 2023Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessmentcited by 227
- 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
- 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
- 2017Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Losscited by 161
- 2022UIU-Net: U-Net in U-Net for Infrared Small Object Detectioncited by 124
- 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
- 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
- 20183D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Networkcited by 47
- 2023Learning from models beyond fine-tuningcited by 47
- 2022CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoisingcited by 46
- 2019Quadratic Autoencoder (Q-AE) for Low-dose CT Denoisingcited by 35
- 2017Sharpness-aware Low dose CT denoising using conditional generative adversarial networkcited by 28
- 2020EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoisingcited by 26
- 2022Near-Exact Recovery for Tomographic Inverse Problems via Deep Learningcited by 13
- 2020Learning Multiscale Convolutional Dictionaries for Image Reconstructioncited by 11
- 2020Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstructioncited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.