SNRAware: Improved Deep Learning MRI Denoising with SNR Unit Training and G-factor Map Augmentation

• URL: http://arxiv.org/abs/2503.18162v1
• Date: Sun, 23 Mar 2025 18:16:36 GMT
• Title: SNRAware: Improved Deep Learning MRI Denoising with SNR Unit Training and G-factor Map Augmentation
• Authors: Hui Xue, Sarah M. Hooper, Iain Pierce, Rhodri H. Davies, John Stairs, Joseph Naegele, Adrienne E. Campbell-Washburn, Charlotte Manisty, James C. Moon, Thomas A. Treibel, Peter Kellman, Michael S. Hansen,
• Abstract summary: This retrospective study trained 14 different transformer and convolutional models with two backbone architectures on a large dataset of 2,885,236 images from 96,605 cardiac retro-gated cine complex series acquired at 3T.<n>The proposed training scheme, termed SNRAware, leverages knowledge of the MRI reconstruction process to improve denoising performance by simulating large, high quality, and diverse synthetic datasets, and providing quantitative information about the noise distribution to the model.
• Score: 4.45678909876146
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To develop and evaluate a new deep learning MR denoising method that leverages quantitative noise distribution information from the reconstruction process to improve denoising performance and generalization. This retrospective study trained 14 different transformer and convolutional models with two backbone architectures on a large dataset of 2,885,236 images from 96,605 cardiac retro-gated cine complex series acquired at 3T. The proposed training scheme, termed SNRAware, leverages knowledge of the MRI reconstruction process to improve denoising performance by simulating large, high quality, and diverse synthetic datasets, and providing quantitative information about the noise distribution to the model. In-distribution testing was performed on a hold-out dataset of 3000 samples with performance measured using PSNR and SSIM, with ablation comparison without the noise augmentation. Out-of-distribution tests were conducted on cardiac real-time cine, first-pass cardiac perfusion, and neuro and spine MRI, all acquired at 1.5T, to test model generalization across imaging sequences, dynamically changing contrast, different anatomies, and field strengths. The best model found in the in-distribution test generalized well to out-of-distribution samples, delivering 6.5x and 2.9x CNR improvement for real-time cine and perfusion imaging, respectively. Further, a model trained with 100% cardiac cine data generalized well to a T1 MPRAGE neuro 3D scan and T2 TSE spine MRI.

Related papers

• Enhancing Deep Learning-Driven Multi-Coil MRI Reconstruction via Self-Supervised Denoising [4.6017417632210655]
  Self-supervised denoising is a pre-processing step for training deep learning (DL) based reconstruction methods. We show that denoising is an essential pre-processing technique capable of improving the efficacy of DL-based MRI reconstruction methods.
  arXiv  Detail & Related papers  (2024-11-19T23:17:09Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  Deep neural networks have shown great potential for reconstructing high-fidelity images from undersampled measurements.<n>Our model is based on neural operators, a discretization-agnostic architecture.<n>Our inference speed is also 1,400x faster than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI [34.361078452552945]
  Real-world MRI acquisitions already contain inherent noise due to thermal fluctuations. We propose a posterior sampling strategy with a novel NoIse Level Adaptive Data Consistency (Nila-DC) operation. Our method surpasses the state-of-the-art MRI reconstruction methods, and is highly robust against various noise levels.
  arXiv  Detail & Related papers  (2024-03-08T12:07:18Z)
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction [83.73429628413773]
  Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth. We propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN) Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles.
  arXiv  Detail & Related papers  (2023-12-19T22:40:51Z)
• DiffCMR: Fast Cardiac MRI Reconstruction with Diffusion Probabilistic Models [11.068359534951783]
  DiffCMR perceives conditioning signals from the under-sampled MRI image slice and generates its corresponding fully-sampled MRI image slice. We validate DiffCMR with cine reconstruction and T1/T2 mapping tasks on MICCAI 2023 Cardiac MRI Reconstruction Challenge dataset. Results show that our method achieves state-of-the-art performance, exceeding previous methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-08T06:11:21Z)
• Denoising Simulated Low-Field MRI (70mT) using Denoising Autoencoders (DAE) and Cycle-Consistent Generative Adversarial Networks (Cycle-GAN) [68.8204255655161]
  Cycle Consistent Generative Adversarial Network (GAN) is implemented to yield high-field, high resolution, high signal-to-noise ratio (SNR) Magnetic Resonance Imaging (MRI) images. Images were utilized to train a Denoising Autoencoder (DAE) and a Cycle-GAN, with paired and unpaired cases. This work demonstrates the use of a generative deep learning model that can outperform classical DAEs to improve low-field MRI images and does not require image pairs.
  arXiv  Detail & Related papers  (2023-07-12T00:01:00Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models [75.52575380824051]
  We present a learning method to optimize sub-sampling patterns for compressed sensing multi-coil MRI. We use a single-step reconstruction based on the posterior mean estimate given by the diffusion model and the MRI measurement process. Our method requires as few as five training images to learn effective sampling patterns.
  arXiv  Detail & Related papers  (2023-06-05T22:09:06Z)
• DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models [0.3149883354098941]
  We propose a self-supervised denoising method for MRI denoising using diffusion denoising generative models. Our framework integrates statistic-based denoising theory into diffusion models and performs denoising through conditional generation.
  arXiv  Detail & Related papers  (2023-02-06T18:56:39Z)
• The role of noise in denoising models for anomaly detection in medical images [62.0532151156057]
  Pathological brain lesions exhibit diverse appearance in brain images. Unsupervised anomaly detection approaches have been proposed using only normal data for training. We show that optimization of the spatial resolution and magnitude of the noise improves the performance of different model training regimes.
  arXiv  Detail & Related papers  (2023-01-19T21:39:38Z)
• Denoising of Three-Dimensional Fast Spin Echo Magnetic Resonance Images of Knee Joints using Spatial-Variant Noise-Relevant Residual Learning of Convolution Neural Network [0.0]
  Two-dimensional (2D) fast spin echo (FSE) techniques play a central role in the clinical magnetic resonance imaging (MRI) of knee joints. 3D FSE provides high-isotropic-resolution magnetic resonance (MR) images of knee joints, but it has a reduced signal-to-noise ratio compared to 2D FSE. Deep-learning denoising methods are a promising approach for denoising MR images, but they are often trained using synthetic noise.
  arXiv  Detail & Related papers  (2022-04-21T03:45:11Z)
• Negligible effect of brain MRI data preprocessing for tumor segmentation [36.89606202543839]
  We conduct experiments on three publicly available datasets and evaluate the effect of different preprocessing steps in deep neural networks. Our results demonstrate that most popular standardization steps add no value to the network performance. We suggest that image intensity normalization approaches do not contribute to model accuracy because of the reduction of signal variance with image standardization.
  arXiv  Detail & Related papers  (2022-04-11T17:29:36Z)
• Fast T2w/FLAIR MRI Acquisition by Optimal Sampling of Information Complementary to Pre-acquired T1w MRI [52.656075914042155]
  We propose an iterative framework to optimize the under-sampling pattern for MRI acquisition of another modality. We have demonstrated superior performance of our learned under-sampling patterns on a public dataset.
  arXiv  Detail & Related papers  (2021-11-11T04:04:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.