Non-Local SVD Denoising of MRI Based on Sparse Representations

Pilot Lightweight Denoising Algorithm for Multiple Sclerosis on Spine MRI

Multiple sclerosis (MS) is a severely debilitating disease which requires accurate and timely diagnosis. MRI is the primary diagnostic vehicle; however, it is susceptible to noise and artifact which can limit diagnostic accuracy. A myriad of denoising algorithms have been developed over the years for medical imaging yet the models continue to become more complex. We developed a lightweight algorithm which utilizes the image's inherent noise via dictionary learning to improve image quality without high computational complexity or pretraining through a process known as orthogonal matching pursuit (OMP). Our algorithm is compared to existing traditional denoising algorithms to evaluate performance on real noise that would commonly be encountered in a clinical setting. Fifty patients with a history of MS who received 1.5 T MRI of the spine between the years of 2018 and 2022 were retrospectively identified in accordance with local IRB policies. Native resolution 5 mm sagittal images were selected from T2 weighted sequences for evaluation using various denoising techniques including our proposed OMP denoising algorithm. Peak signal to noise ratio (PSNR) and structural similarity index (SSIM) were measured. While wavelet denoising demonstrated an expected higher PSNR than other models, its SSIM was variable and consistently underperformed its comparators (0.94 ± 0.10). Our pilot OMP denoising algorithm provided superior performance with greater consistency in terms of SSIM (0.99 ± 0.01) with similar PSNR to non-local means filtering (NLM), both of which were superior to other comparators (OMP 37.6 ± 2.2, NLM 38.0 ± 1.8). The superior performance of our OMP denoising algorithm in comparison to traditional models is promising for clinical utility. Given its individualized and lightweight approach, implementation into PACS may be more easily incorporated. It is our hope that this technology will provide improved diagnostic accuracy and workflow optimization for Neurologists and Radiologists, as well as improved patient outcomes.

Similarity-Driven Fine-Tuning Methods for Regularization Parameter Optimization in PET Image Reconstruction

We present an adaptive method for fine-tuning hyperparameters in edge-preserving regularization for PET image reconstruction. For edge-preserving regularization, in addition to the smoothing parameter that balances data fidelity and regularization, one or more control parameters are typically incorporated to adjust the sensitivity of edge preservation by modifying the shape of the penalty function. Although there have been efforts to develop automated methods for tuning the hyperparameters in regularized PET reconstruction, the majority of these methods primarily focus on the smoothing parameter. However, it is challenging to obtain high-quality images without appropriately selecting the control parameters that adjust the edge preservation sensitivity. In this work, we propose a method to precisely tune the hyperparameters, which are initially set with a fixed value for the entire image, either manually or using an automated approach. Our core strategy involves adaptively adjusting the control parameter at each pixel, taking into account the degree of patch similarities calculated from the previous iteration within the pixel's neighborhood that is being updated. This approach allows our new method to integrate with a wide range of existing parameter-tuning techniques for edge-preserving regularization. Experimental results demonstrate that our proposed method effectively enhances the overall reconstruction accuracy across multiple image quality metrics, including peak signal-to-noise ratio, structural similarity, visual information fidelity, mean absolute error, root-mean-square error, and mean percentage error.

The effect of a post-scan processing denoising system on image quality and morphometric analysis

PURPOSE

MR image quality and subsequent brain morphometric analysis are inevitably affected by noise. The purpose of this study was to evaluate the effectiveness of an artificial intelligence (AI)-based post-scan processing denoising system, intelligent Quick Magnetic Resonance (iQMR), on MR image quality and brain morphometric analysis.

METHODS

We used 1.5T MP-RAGE MR images acquired from the Alzheimer's Disease Neuroimaging Initiative 1 database. The images of 21 subjects were used for cross-sectional analysis and 15 for longitudinal analysis. In the longitudinal analysis, two timepoints over a 2-year interval were used. Each subject was scanned twice at each timepoint. MR images processed with and without the denoising system were compared both visually and objectively using FreeSurfer cortical thickness analysis.

RESULTS

The denoising system reduced the noise with good white-gray matter contrast (noise: p < 0.001; contrast: p = 0.49). The mean intraclass correlation coefficients (ICCs) of cortical thickness were slightly better in the images processed with the denoising system (0.739/0.859/0.883; Gaussian smoothing kernel of full width at half maximum = 0/10/20) compared with the unprocessed images (0.718/0.854/0.880). In the longitudinal analysis, the mean ICCs of symmetrized percent change improved in images processed with the denoising system (0.202/0.349/0.431) compared with the unprocessed images (0.167/0.325/0.404). In addition, the detectability of significant cortical thickness atrophy improved with denoising.

CONCLUSION

We confirm that the AI-based denoising system could effectively reduce the noise while retaining the contrast. We also confirm the improvement of the reliability and detectability of brain morphometric analysis with the denoising system.

Research on Visual Positioning of a Roadheader and Construction of an Environment Map

The autonomous positioning of tunneling equipment is the key to intellectualization and robotization of a tunneling face. In this paper, a method based on simultaneous localization and mapping (SLAM) to estimate the body pose of a roadheader and build a navigation map of a roadway is presented. In terms of pose estimation, an RGB-D camera is used to collect images, and a pose calculation model of a roadheader is established based on random sample consensus (RANSAC) and iterative closest point (ICP); constructing a pose graph optimization model with closed-loop constraints. An iterative equation based on Levenberg–Marquadt is derived, which can achieve the optimal estimation of the body pose. In terms of mapping, LiDAR is used to experimentally construct the grid map based on open-source algorithms, such as Gmapping, Cartographer, Karto, and Hector. A point cloud map, octree map, and compound map are experimentally constructed based on the open-source library RTAB-MAP. By setting parameters, such as the expansion radius of an obstacle and the updating frequency of the map, a cost map for the navigation of a roadheader is established. Combined with algorithms, such as Dijskra and timed-elastic-band, simulation experiments show that the combination of octree map and cost map can support global path planning and local obstacle avoidance.

Denoising of 3D Brain MR Images with Parallel Residual Learning of Convolutional Neural Network Using Global and Local Feature Extraction

Magnetic resonance (MR) images often suffer from random noise pollution during image acquisition and transmission, which impairs disease diagnosis by doctors or automated systems. In recent years, many noise removal algorithms with impressive performances have been proposed. In this work, inspired by the idea of deep learning, we propose a denoising method named 3D-Parallel-RicianNet, which will combine global and local information to remove noise in MR images. Specifically, we introduce a powerful dilated convolution residual (DCR) module to expand the receptive field of the network and to avoid the loss of global features. Then, to extract more local information and reduce the computational complexity, we design the depthwise separable convolution residual (DSCR) module to learn the channel and position information in the image, which not only reduces parameters dramatically but also improves the local denoising performance. In addition, a parallel network is constructed by fusing the features extracted from each DCR module and DSCR module to improve the efficiency and reduce the complexity for training a denoising model. Finally, a reconstruction (REC) module aims to construct the clean image through the obtained noise deviation and the given noisy image. Due to the lack of ground-truth images in the real MR dataset, the performance of the proposed model was tested qualitatively and quantitatively on one simulated T1-weighted MR image dataset and then expanded to four real datasets. The experimental results show that the proposed 3D-Parallel-RicianNet network achieves performance superior to that of several state-of-the-art methods in terms of the peak signal-to-noise ratio, structural similarity index, and entropy metric. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation.

Testing the Accuracy of the Modified ICP Algorithm with Multimodal Weighting Factors

SLAM technology is increasingly used to self-locate mobile robots in an unknown environment. One of the methods used in this technology is called scan matching. Increasing evidence is placed on the accuracy and speed of the methods used in terms of navigating mobile robots. The aim of this article is to present a modification to the standard method of Iterative Closest Point (ICP) environment scan matching using the authors’ three original weighting factors based on the error modeling. The presented modification was supported by a simulation study whose aim was not exclusively to check the effect of the factors but also to examine the effect of the number of points in scans on the correct and accurate development of the rotation matrix and the translation vector. The study demonstrated both an increase in the accuracy of ICP results following the implementation of the proposed modification and a noticeable increase in accuracy with an increase in the mapping device’s angular resolution. The proposed method has a positive impact on reducing number of iteration and computing time. The research results have shown to be promising and will be extended to 3D space in the future.

Towards to Optimal Wavelet Denoising Scheme-A Novel Spatial and Volumetric Mapping of Wavelet-Based Biomedical Data Smoothing

Wavelet transformation is one of the most frequent procedures for data denoising, smoothing, decomposition, features extraction, and further related tasks. In order to perform such tasks, we need to select appropriate wavelet settings, including particular wavelet, decomposition level and other parameters, which form the wavelet transformation outputs. Selection of such parameters is a challenging area due to absence of versatile recommendation tools for suitable wavelet settings. In this paper, we propose a versatile recommendation system for prediction of suitable wavelet selection for data smoothing. The proposed system is aimed to generate spatial response matrix for selected wavelets and the decomposition levels. Such response enables the mapping of selected evaluation parameters, determining the efficacy of wavelet settings. The proposed system also enables tracking the dynamical noise influence in the context of Wavelet efficacy by using volumetric response. We provide testing on computed tomography (CT) and magnetic resonance (MR) image data and EMG signals mostly of musculoskeletal system to objectivise system usability for clinical data processing. The experimental testing is done by using evaluation parameters such is MSE (Mean Squared Error), ED (Euclidean distance) and Corr (Correlation index). We also provide the statistical analysis of the results based on Mann-Whitney test, which points out on statistically significant differences for individual Wavelets for the data corrupted with Salt and Pepper and Gaussian noise.