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.

Joint Demosaicing and Denoising Based on Interchannel Nonlocal Mean Weighted Moving Least Squares Method.

Nowadays, the sizes of pixel sensors in digital cameras are decreasing as the resolution of the image sensor increases. Due to the decreased size, the pixel sensors receive less light energy, which makes it more sensitive to thermal noise. Even a small amount of noise in the color filter array (CFA) can have a significant effect on the reconstruction of the color image, as two-thirds of the missing data would have to be reconstructed from noisy data; because of this, direct denoising would need to be performed on the raw CFA to obtain a high-resolution color image. In this paper, we propose an interchannel nonlocal weighted moving least square method for the noise removal of the raw CFA. The proposed method is our first attempt of applying a two dimensional (2-D) polynomial approximation to denoising the CFA. Previous works make use of 2-D linear or directional 1-D polynomial approximations. The reason that 2-D polynomial approximation methods have not been applied to this problem is the difficulty of the weight control in the 2-D polynomial approximation method, as a small amount of noise can have a large effect on the approximated 2-D shape. This makes CFA denoising more important, as the approximated 2-D shape has to be reconstructed from only one-third of the original data. To address this problem, we propose a method that reconstructs the approximated 2-D shapes corresponding to the RGB color channels based on the measure of the similarities of the patches directly on the CFA. By doing so, the interchannel information is incorporated into the denoising scheme, which results in a well-controlled and higher order of polynomial approximation of the color channels. Compared to other nonlocal-mean-based denoising methods, the proposed method uses an extra reproducing constraint, which guarantees a certain degree of the approximation order; therefore, the proposed method can reduce the number of false reconstruction artifacts that often occur in nonlocal-mean-based denoising methods. Experimental results demonstrate the performance of the proposed algorithm.

Patch similarity in ultrasound images with hypothesis testing and stochastic distances.

Patch-based techniques have been largely applied to process ultrasound (US) images, with applications in various fields as denoising, segmentation, and registration. An important aspect of the performance of these techniques is how to measure the similarity between patches. While it is usual to base the similarity on the Euclidean distance when processing images corrupted by additive Gaussian noise, finding measures suitable for the multiplicative nature of the speckle in US images is still an open research. In this work, we propose new stochastic distances based on the statistical characteristics of speckle in US. Additionally, we derive statistical measures to compose hypothesis tests that allow a quantitative decision on the patch similarity of US images. Good results with experiments in denoising, segmentation and selecting similar patches confirm the potential of the proposed measures.

Medical Images Fusion with Patch Based Structure Tensor.

Nowadays medical imaging has played an important role in clinical use, which provide important clues for medical diagnosis. In medical image fusion, the extraction of some fine details and description is critical. To solve this problem, a modified structure tensor by considering similarity between two patches is proposed. The patch based filter can suppress noise and add the robustness of the eigen-values of the structure tensor by allowing the use of more information of far away pixels. After defining the new structure tensor, we apply it into medical image fusion with a multi-resolution wavelet theory. The features are extracted and described by the eigen-values of two multi-modality source data. To test the performance of the proposed scheme, the CT and MR images are used as input source images for medical image fusion. The experimental results show that the proposed method can produce better results compared to some related approaches.