Zhiguo Gui

Discriminative feature representation: an effective postprocessing solution to low dose CT imaging*

This paper proposes a concise and effective approach termed discriminative feature representation (DFR) for low dose computerized tomography (LDCT) image processing, which is currently a challenging problem in medical imaging field. This DFR method assumes LDCT images as the superposition of desirable high dose CT (HDCT) 3D features and undesirable noise-artifact 3D features (the combined term of noise and artifact features induced by low dose scan protocols), and the decomposed HDCT features are used to provide the processed LDCT images with higher quality. The target HDCT features are solved via the DFR algorithm using a featured dictionary composed by atoms representing HDCT features and noise-artifact features. In this study, the featured dictionary is efficiently built using physical phantom images collected from the same CT scanner as the target clinical LDCT images to process. The proposed DFR method also has good robustness in parameter setting for different CT scanner types. This DFR method can be directly applied to process DICOM formatted LDCT images, and has good applicability to current CT systems. Comparative experiments with abdomen LDCT data validate the good performance of the proposed approach.

3D Feature Constrained Reconstruction for Low-Dose CT Imaging

Low-dose computed tomography (LDCT) images are often highly degraded by amplified mottle noise and streak artifacts. Maintaining image quality under low-dose scan protocols is a well-known challenge. Recently, sparse representation-based techniques have been shown to be efficient in improving such CT images. In this paper, we propose a 3D feature constrained reconstruction (3D-FCR) algorithm for LDCT image reconstruction. The feature information used in the 3D-FCR algorithm relies on a 3D feature dictionary constructed from available high quality standard-dose CT sample. The CT voxels and the sparse coefficients are sequentially updated using an alternating minimization scheme. The performance of the 3D-FCR algorithm was assessed through experiments conducted on phantom simulation data and clinical data. A comparison with previously reported solutions was also performed. Qualitative and quantitative results show that the proposed method can lead to a promising improvement of LDCT image quality.

A Novel Fractional-Order Differentiation Model for Low-Dose CT Image Processing

Low-dose CT (LDCT) images tend to be degraded by excessive mottle noise and steak artifacts. In this paper, we proposed a novel fractional-order differentiation model that can be applied to LDCT image processing as a post-processing technique. The anisotropic diffusion model (proposed by Perona and Malik, i.e., PM model) has good performance in flat regions, total variation (TV) model works better in edge preservation, and fractional-order differentiation models can mitigate block effect while preserving fine details and more structure. The proposed model is based on the weighted combinations of the fractional-order PM model and the fractional-order TV model, which maintains the advantages of PM model, TV model, and fractional-order differentiation models. Moreover, the local intensity variance was added to both weighted coefficient and diffusion coefficient of the proposed model to properly preserve edges and details. A variety of simulated phantom data, including the Shepp–Logan head phantom, the pelvis phantom, and the actual thoracic phantom, were used for experimental validation. The results of numerical simulation and clinical data experiments demonstrate that the proposed approach has a better performance in both noise suppression and detail preservation, when compared with several other existing methods.

Learning-Based Artifact Removal via Image Decomposition for Low-Dose CT Image Processing

Streak artifacts and mottle noise often appear in low-dose CT (LDCT) images due to excessive quantum noise in low-dose X-ray imaging process, thus degrading CT image quality. This research is aimed at improving the quality of LDCT images via image decomposition and dictionary learning. The proposed method first decomposes a LDCT image into the low-frequency (LF) and high-frequency (HF) parts by a bilateral filter. The HF part is then decomposed into an artifact component and a tissue component by performing dictionary learning (DL) and sparse coding. The tissue component is combined with the LF part to obtain the artifact-suppressed image. At last, a DL method is applied to further reduce the residual artifacts and noise. Different from previous research works with sparse representation, the proposed method does not need to collect training images in advance. The results of numerical simulation and clinical data experiments indicate the effectiveness of the proposed approach.

Improving Low-Dose CT Image Using Residual Convolutional Network

Low-dose CT is an effective solution to alleviate radiation risk to patients, it also introduces additional noise and streak artifacts. In order to maintain a high image quality for low-dose scanned CT data, we propose a post-processing method based on deep learning and using 2-D and 3-D residual convolutional networks. Experimental results and comparisons with other competing methods show that the proposed approach can effectively reduce the low-dose noise and artifacts while preserving tissue details. It is also pointed out that the 3-D model can achieve better performance in both edge-preservation and noise-artifact suppression. Factors that may influence the model performance, such as model width, depth, and dropout, are also examined.

Low-dose CT statistical iterative reconstruction via modified MRF regularization

It is desirable to reduce the excessive radiation exposure to patients in repeated medical CT applications. One of the most effective ways is to reduce the X-ray tube current (mAs) or tube voltage (kVp). However, it is difficult to achieve accurate reconstruction from the noisy measurements. Compared with the conventional filtered back-projection (FBP) algorithm leading to the excessive noise in the reconstructed images, the approaches using statistical iterative reconstruction (SIR) with low mAs show greater image quality. To eliminate the undesired artifacts and improve reconstruction quality, we proposed, in this work, an improved SIR algorithm for low-dose CT reconstruction, constrained by a modified Markov random field (MRF) regularization. Specifically, the edge-preserving total generalized variation (TGV), which is a generalization of total variation (TV) and can measure image characteristics up to a certain degree of differentiation, was introduced to modify the MRF regularization. In addition, a modified alternating iterative algorithm was utilized to optimize the cost function. Experimental results demonstrated that images reconstructed by the proposed method could not only generate high accuracy and resolution properties, but also ensure a higher peak signal-to-noise ratio (PSNR) in comparison with those using existing methods.

A gradient-based adaptive nonlocal means algorithm for image denoising

In this paper, a modified adaptive nonlocal means (ANLM) filter is investigated for image denoising by introducing the image gradient into the classical nonlocal means filter. The proposed algorithm takes the orientation of matching neighborhood into consideration and can adaptively select the filtering parameter based on image gradient. Moreover, the symmetry or approximate symmetry of some filtered images is also considered. Therefore, comparing with the classical nonlocal means filter, the new method can exploit much more similar pixels. The proposed approach is applied to several real images corrupted by white Gaussian noise with different standard deviation. The comparative experimental results show that the improved ANLM filter obtains superior denoising performance.

Discriminative Prior - Prior Image Constrained Compressed Sensing Reconstruction for Low-Dose CT Imaging

X-ray computed tomography (CT) has been widely used to provide patient-specific anatomical information in the forms of tissue attenuation. However, the cumulative radiation induced in CT scan has raised extensive concerns in recently years. How to maintain reconstruction image quality is a major challenge for low-dose CT (LDCT) imaging. Generally, LDCT imaging can be greatly improved by incorporating prior knowledge in some specific forms. A joint estimation framework termed discriminative prior-prior image constrained compressed sensing (DP-PICCS) reconstruction is proposed in this paper. This DP-PICCS algorithm utilizes discriminative prior knowledge via two feature dictionary constraints which built on atoms from the samples of tissue attenuation feature patches and noise-artifacts residual feature patches, respectively. Also, the prior image construction relies on a discriminative feature representation (DFR) processing by two feature dictionary. Its comparison to other competing methods through experiments on low-dose projections acquired from torso phantom simulation study and clinical abdomen study demonstrated that the DP-PICCS method achieved promising improvement in terms of the effectively-suppressed noise and the well-retained structures.

Application of optimization model with piecewise penalty to intensity-modulated radiation therapy

Abstract Purpose: Both maximum-dose-based and generalized equivalent uniform dose (gEUD)-based quadratic sub-scores, which penalize doses higher than the prescribed dose, exhibit the shortcomings of semi-deviation and a vanishing gradient in the feasible solution space. To address these drawbacks, this study proposes new sub-scores for the maximum dose criterion and the gEUD criterion. Methods: In new sub-scores, a dosage lower than the prescribed dose is assigned a linear penalty function, and one higher than the prescribed dose is assigned an extra quadratic penalty function. To test their efficiency, they were incorporated into a physical model and a hybrid physical–biological model, respectively, and were tested on a phantom TG119 and two types of clinic cases. The improved methods were compared with their original methods and the dose-volume (DV)-based optimization method. Additionally, the improved gEUD-based method was compared with another gEUD-based quadratic optimization method. The gradient-based optimization algorithm was applied to solve these large-scale optimization problems. Results: For similar or better PTV coverage, optimization based on our proposed quadratic models is capable of improving the OARs sparing. In practice, by using multiple DV constraints for each optimized structures, the DV based optimization may be able to arrive at similar plan, whereas greater trial-and-error is performed to adjust parameters of optimization model. Although the optimal prescribed dose remains unclear, at the same prescribed dose, our proposed optimization method can obtain better plan. Conclusion: Our proposed optimization method has the potential to expand the solution space and improve the quality of radiotherapy plan.

Image Denoising via Sparse Representation Over Grouped Dictionaries With Adaptive Atom Size

The classic K-SVD based sparse representation denoising algorithm trains the dictionary only with one fixed atom size for the whole image, which is limited in accurately describing the image. To overcome this shortcoming, this paper presents an effective image denoising algorithm with the improved dictionaries. First, according to both geometrical and photometrical similarities, image patches are clustered into different groups. Second, these groups are classified into the flat category, the texture category, and the edge category. In different categories, the atom sizes of dictionaries are designed differently. Then, the dictionary of each group is trained with the atom size determined by the category that the group belongs to and the noisy level. Finally, the denoising method is presented by using sparse representation over the constructed grouped dictionaries with adaptive atom size. Experimental results show that the proposed method achieves better denoising performance than related denoising algorithms, especially in image structure preservation.