Hazique Aetesam - Magnetic Resonance Imaging

L2-L1 Fidelity based Elastic Net Regularisation for Magnetic Resonance Image Denoising

Abstract: In this paper, we design an optimization problem for denoising 3 dimensional Magnetic Resonance Image (MRI) data. The problem is formulated as a variational technique considering the underlying of noise to be Gaussian and Laplacian. We propose a mixed noise removal technique which simultaneously handles noise of two different nature rather than initially detecting impulse noise corrupted outlier pixels and then handling additive white Gaussian noise. This is made possible by the combination of L2-L1 data fidelity terms along with regularization penalty terms. Using Total Variation and Tikhonov as two different regularization terms offer better reconstruction quality. Experiments conducted on synthetically corrupted phantom brain MR data and real noisy knee MRI image obtained from patients show that our proposed technique outperforms comparing techniques even under higher intensity of noise levels. (Online)

Cite this as: Aetesam, Hazique, and Suman Kumar Maji. "ℓ 2− ℓ 1 Fidelity based Elastic Net Regularisation for Magnetic Resonance Image Denoising." 2020 International Conference on Contemporary Computing and Applications (IC3A). IEEE, 2020.

Noise Dependent Training for Deep Parallel Ensemble Denoising in Magnetic Resonance Images

Abstract: In this paper, a deep learning technique is proposed for the removal of Gaussian-impulse noise from Magnetic Resonance images (MRI). The proposed technique is inspired from the Bayesian maximum a posteriori (MAP) derivation of the Gaussian-impulse likelihood. A discriminative learning strategy under fully convolutional neural network (CNN) is used which focuses on the importance of loss layer during training. Residual learning is combined with 3D convolution for multi-dimensional extraction of image features from noisy data, on a wide range of noise levels. The problem of vanishing gradient in a very deep network is handled through the usage of a wide network, which is built by incorporating two parallel models (thereby resulting in decreased depth of the network). The approach is called ensemble because features are obtained along the two parallel paths working independently, using normal and dilated convolutions. Results on model convergence support advantages observed by these considerations. Experiments are conducted on synthetically corrupted MRI data and real spin echo MRI sequence. Better visual and metric results as well as fast testing performance support the argument of boosted denoising capability against a majority of the benchmarks for MRI noise removal. (Online)

Cite this as: Aetesam, Hazique, and Suman Kumar Maji. "Noise dependent training for deep parallel ensemble denoising in magnetic resonance images." Biomedical Signal Processing and Control 66 (2021): 102405.

Attention-Based Noise Prior Network For Magnetic Resonance Image Denoising

Abstract: Data obtained from magnitude magnetic resonance images (MRI) are corrupted by signal-dependent and spatially variant Rician noise. The contribution of this work can be discussed at three different levels. Firstly, Rician noise-level estimation map is fed as prior concatenated with the noisy input data; to handle spatially variant noise and achieve an optimal compromise between noise removal and detail preservation. Secondly, modified U-Net architecture is used to accommodate non-local multi-level and multi-scale features. Thirdly, to preserve the long-range dependencies lost in farther symmetric layers, features obtained from symmetric-group attention block is fed as input to the deconvolution layers for nonlocal high- and low-level feature mapping. Experimental results over synthetically corrupted MR images and real data obtained from MR scanners suggest the potential utility of our proposed technique over a wide-range of noise levels. (Online)

Index Terms— Attention network, magnetic resonance imaging, noise level estimation, Rician distribution.

Cite this as: Aetesam, Hazique, and Suman Kumar Maji. "Attention-based noise prior network for magnetic resonance image denoising." 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE, 2022.

Perceptually Motivated Generative Model for Magnetic Resonance Image Denoising

Abstract: Image denoising is an important preprocessing step in low-level vision problems involving biomedical images. Noise removal techniques can greatly benefit raw corrupted magnetic resonance images (MRI). It has been discovered that the MR data is corrupted by a mixture of Gaussian-impulse noise caused by detector flaws and transmission errors. This paper proposes a deep generative model (GenMRIDenoiser) for dealing with this mixed noise scenario. This work makes four contributions. To begin, Wasserstein generative adversarial network (WGAN) is used in model training to mitigate the problem of vanishing gradient, mode collapse, and convergence issues encountered while training a vanilla GAN. Second, a perceptually motivated loss function is used to guide the training process in order to preserve the low-level details in the form of high-frequency components in the image. Third, batch renormalization is used between the convolutional and activation layers to prevent performance degradation under the assumption of non-independent and identically distributed (non-iid) data. Fourth, global feature attention module (GFAM) is appended at the beginning and end of the parallel ensemble blocks to capture the longrange dependencies that are often lost due to the small receptive field of convolutional filters. The experimental results over synthetic data and MRI stack obtained from real MR scanners indicate the potential utility of the proposed technique across a wide range of degradation scenarios. (Online)

Keywords: Magnetic resonance imaging · Image denoising · Gaussian-impulse noise · Perceptually motivated loss · Adversarial training · Attention block

Cite this as: Aetesam, Hazique, and Suman Kumar Maji. "Perceptually motivated generative model for magnetic resonance image denoising." Journal of Digital Imaging 36.2 (2023): 725-738.

Deep Variational Magnetic Resonance Image Denoising via Network Conditioning

Abstract: In this paper, we propose a variational approach towards denoising magnetic resonance images (MRI) corrupted by spatially variant and signal-dependent Rician noise in a deep learning framework. To obtain a mathematically sound inference network, approximate variational posteriors are designed keeping in mind the Rician nature of noise. The proposed work tackles the denoising problem in several different ways. Firstly, the prior assumption on data in the variational posterior is motivated by the heavy-tailed marginal distribution of image gradients in natural images. This is captured by the sparsity promoting hyper-Laplacian prior on MR data. Similarly, median absolute deviation under Gaussian prior helps in the estimation of noise in the variational lower bound of marginal log likelihood term. Secondly, noise estimation from the background regions of the noisy data under the assumption of Rayleigh distribution prevents the addition of extra subnetwork for the estimation of spatially variant noise level parameters. Thirdly, feature-wise transformation of intermediate layers is performed using anatomical planes segmentation maps (APSM) for context-based network conditioning. Here, affine transformation parameters generated from APSM are modulated with the input features for spatial feature transformation. Fourthly, to capture the long-range dependencies lost in deeper convolutional layers, multiscale global feature fusion block (GFFuB) is used. Lastly, experimental results over synthetically corrupted MR data and real data obtained from MR scanners suggest the potential utility of the proposed model in real time. (Online)

Keywords: Magnetic resonance imaging, Noise estimation, Rician distribution, Variational autoencoder, Network conditioning

Cite this as: Aetesam, Hazique, and Suman Kumar Maji. "Deep variational magnetic resonance image denoising via network conditioning." Biomedical Signal Processing and Control 95 (2024): 106452.

Page updated

Google Sites

Report abuse