Medical Image Reconstruction Research Articles

Application and prospect for generative adversarial networks in cross-modality reconstruction of medical images.

Cross-modality reconstruction of medical images refers to predicting the image from one modality to another so as to achieve more accurate personalized medicine. Generative adversarial networks is the most commonly used deep learning technique in cross-modality reconstruction. It can generate realistic images by learning features from implicit distributions that follow the distributions of real data and then reconstruct the image of another modality rapidly. With the sharp increase in clinical demand for multi-modality medical image, this technology has been widely used in the task of cross modal reconstruction between different medical image modalities, such as magnetic resonance imaging, computed tomography and positron emission computed tomography. It can achieve accurate and efficient cross-modality image reconstruction in different parts of the body, such as the brain, heart, etc. In addition, although GAN has achieved some success in cross-modality reconstruction, its stability, generalization ability, and accuracy still need further research and improvement.

3D Reconstruction Method based on Medical Image Feature Point Matching.

Medical 3D image reconstruction is an important image processing step in medical image analysis. How to speed up the speed while improving the accuracy in 3D reconstruction is an important issue. To solve this problem, this paper proposes a 3D reconstruction method based on image feature point matching. By improving SIFT, the initial matching of feature points is realized by using the neighborhood voting method, and then the initial matching points are optimized by the improved RANSAC algorithm, and a new SFM reconstruction method is obtained. The experimental results show that the feature matching rate of this algorithm on Fountain data is 95.42% and the matching speed is 4.751 s. It can be seen that this algorithm can shorten the reconstruction time and obtain sparse point clouds with more reasonable distribution and better reconstruction effect.

Study on Key Technologies of Virtual Interactive Surgical Simulation for 3D Reconstruction of Medical Images.

Medical computed tomography (CT), nuclear magnetic resonance imaging (MRI), and other imaging facility produce a large amount of medical image data which has great diagnosis value. Traditional three-dimensional reconstruction of medical images has high requirements for graphics acceleration hardware and the processing speed. In this study, VxWorks embedded real-time process feature is used for CT or MRI DICOM data to real restoration and establishment of virtual three-dimensional model for realizing volume reconstruction, maximum density projection, multiplane reconstruction, dynamic interactive cutting of any surface, dynamic display of three-dimensional model and two-dimensional sectional image, surgical path planning and interactive surgical simulation, and determine the best surgical scheme. The practical application shows that the virtual simulation environment supports the seamless transplantation of code, function debugging, and interaction and solves the issue of high requirements for hardware. It can meet the needs of scientific research and teaching for clinicians and medical imaging workers and can be widely used in the training of virtual surgical anatomy for medical students.

Research on Optimization Scheme for Blocking Artifacts after Patch-Based Medical Image Reconstruction.

Due to limitations of computer resources, when utilizing a neural network to process an image with a high resolution, the typical processing approach is to slice the original image. However, because of the influence of zero-padding in the edge component during the convolution process, the central part of the patch often has more accurate feature information than the edge part, resulting in image blocking artifacts after patch stitching. We studied this problem in this paper and proposed a fusion method that assigns a weight to each pixel in a patch using a truncated Gaussian function as the weighting function. In this method, we used the weighting function to transform the Euclidean-distance between a point in the overlapping part and the central point of the patch where the point was located into a weight coefficient. With increasing distance, the value of the weight coefficient decreased. Finally, the reconstructed image was obtained by weighting. We employed the bias correction model to evaluate our method on the simulated database BrainWeb and the real dataset HCP (Human Connectome Project). The results show that the proposed method is capable of effectively removing blocking artifacts and obtaining a smoother bias field. To verify the effectiveness of our algorithm, we employed a denoising model to test it on the IXI-Guys human dataset. Qualitative and quantitative evaluations of both models show that the fusion method proposed in this paper can effectively remove blocking artifacts and demonstrates superior performance compared to five commonly available and state-of-the-art fusion methods.

Computed tomography vertebral segmentation from multi-vendor scanner data

Abstract Automatic medical image segmentation is a crucial procedure for computer-assisted surgery. Especially, three-dimensional reconstruction of medical images of the surgical targets can be accurate in fine anatomical structures with optimal image segmentation, thus leading to successful surgical results. However, the performance of the automatic segmentation algorithm highly depends on the consistent properties of medical images. To address this issue, we propose a model for standardizing computed tomography (CT) images. Hence, our CT image-to-image translation network enables diverse CT images (non-standard images) to be translated to images with identical features (standard images) for the more precise performance of U-Net segmentation. Specifically, we combine an image-to-image translation network with a generative adversarial network, consisting of a residual block-based generative network and the discriminative network. Also, we utilize the feature extracting layers of VGG-16 to extract the style of the standard image and the content of the non-standard image. Moreover, for precise diagnosis and surgery, the conservation of anatomical information of the non-standard image is also essential during the synthesis of medical images. Therefore, for performance evaluation, largely three evaluation methods are employed: (i) visualization of the geometrical matching between the non-standard (content) and synthesized images to verify the maintenance of the anatomical structures; (ii) measuring numerical results using image similarity evaluation metrics; and (iii) assessing the performance of U-Net segmentation with our synthesized images. Specifically, we investigate that our model network can transfer the texture from standard CT images to diverse CT images (non-standard) scanned by different scanners and scan protocols. Also, we verify that the synthesized images can retain the global pose and fine structures of the non-standard images. We also compare the predicted segmentation result of the non-standard image and the synthesized image generated from its non-standard image via our proposed network. In addition, the performance of our proposed model is compared with the windowing process, where the window parameter of the standard image is applied to the non-standard image to ensure that our model outperforms the windowing process.

Computational Medical Image Reconstruction Techniques: A Comprehensive Review

Computational Medical Image Reconstruction Techniques: A Comprehensive Review

Sparse regularization with the ℓ0 norm

We consider a minimization problem whose objective function is the sum of a fidelity term, not necessarily convex, and a regularization term defined by a positive regularization parameter [Formula: see text] multiple of the [Formula: see text] norm composed with a linear transform. This problem has wide applications in compressed sensing, sparse machine learning and image reconstruction. The goal of this paper is to understand what choices of the regularization parameter can dictate the level of sparsity under the transform for a global minimizer of the resulting regularized objective function. This is a critical issue but it has been left unaddressed. We address it from a geometric viewpoint with which the sparsity partition of the image space of the transform is introduced. Choices of the regularization parameter are specified to ensure that a global minimizer of the corresponding regularized objective function achieves a prescribed level of sparsity under the transform. Results are obtained for the spacial sparsity case in which the transform is the identity map, a case that covers several applications of practical importance, including machine learning, image/signal processing and medical image reconstruction.

Fast and efficient PAT image reconstruction algorithms: A comparative performance analysis

Medical imaging technology efficiency is determined by how accurate, rapid, invasive, or non-invasive it is. Photoacoustic tomography (PAT) is a noninvasive emerging technology for medical imaging that is able to produce images with high resolution and high contrast in long penetration depths. In PAT, image reconstruction accuracy relies on the accuracy of the system model. Accurate model-based methods can be made use of for efficiently reconstructing a PAT image from the sensor measurements using a pseudo-spectral method which is suggested to produce exactly the same results as that of the k-Wave toolbox in MATLAB. Compressive sensing has been successfully applied for medical image reconstruction as it allows for sparse sampling and sparse reconstruction. Compressive sensing combined with PAT allows for deep tissue imaging at higher resolution at a much lower computational time. A fast and efficient PAT image reconstruction compressive sensing algorithm is needed to be developed, which can image dense tissues (such as breast tissue) rapidly, for early detection of cancer. In this paper, relaxed- Basis pursuit using alternating direction method of multipliers and split Bregman formulation of the total variation regularized least-squares problem is proposed and is observed to work under practical scenarios with fewer samples and sensors. Moreover, a comparative study for the performance analysis of the different compressive sensing algorithms, both iterative and non-iterative, is carried out for a decreased number of sensors and samples. The proposed split Bregman total variation algorithm is fast and produces a high-resolution sparsity preserving image compared to the state-of-the-art algorithms. Moreover, for a reduced number of samples, the proposed relaxed-Basis Pursuit is desired and performs much better than all the algorithms discussed. Implementing Cholesky factorization to the proposed algorithms further reduces the computation time of the split-Bregman algorithm by 90%. The new methods outperform existing ones in practical circumstances recreating a high-resolution image, even when the number of sensors and samples is reduced.

Deep Learning-Based Image Reconstruction for Different Medical Imaging Modalities.

Image reconstruction in magnetic resonance imaging (MRI) and computed tomography (CT) is a mathematical process that generates images at many different angles around the patient. Image reconstruction has a fundamental impact on image quality. In recent years, the literature has focused on deep learning and its applications in medical imaging, particularly image reconstruction. Due to the performance of deep learning models in a wide variety of vision applications, a considerable amount of work has recently been carried out using image reconstruction in medical images. MRI and CT appear as the ultimate scientifically appropriate imaging mode for identifying and diagnosing different diseases in this ascension age of technology. This study demonstrates a number of deep learning image reconstruction approaches and a comprehensive review of the most widely used different databases. We also give the challenges and promising future directions for medical image reconstruction.

VPRNet: Virtual Points Registration Network for Partial-to-Partial Point Cloud Registration

With the development of high-precision and high-frame-rate scanning technology, we can quickly obtain scan data of various large-scale scenes. As a manifestation of information fusion, point cloud registration is of great significance in various fields, such as medical imaging, autonomous driving, and 3D reconstruction. The Iterative Closest Point (ICP) algorithm, as the most classic algorithm, leverages the closest point to search corresponding points, which is the pioneer of correspondences-based approaches. Recently, some deep learning-based algorithms witnessed extracting deep features to compress point cloud information, then calculate corresponding points, and finally output the optimal rigid transformation like Deep Closest Point (DCP) and DeepVCP. However, the partiality of point clouds hinders the acquisition of enough corresponding points when dealing with the partial-to-partial registration problem. To this end, we propose Virtual Points Registration Network (VPRNet) for this intractable problem. We first design a self-supervised virtual point generation network (VPGnet), which utilizes the attention mechanism of Transformer and Self-Attention to fuse the geometric information of two partial point clouds, combined with the Generative Adversarial Network (GAN) structure to produce missing points. Subsequently, the following registration network structure is spliced to the end of VPGnet, thus estimating rich corresponding points. Unlike the existing methods, our network tries to eliminate the side effects of incompleteness on registration. Thus, our method expresses resilience to the initial rotation and sparsity. Various experiments indicate that our proposed algorithm shows advanced performance compared to recent deep learning-based and classical methods.

Arnold Transform Based Medical Image Scrambling and Reconstruction Technique with Improved PSNR Parameter for Increasing the Robustness of Digital Watermarking Algorithms in Comparison with Random Shuffling Method

In this work, a new transform-based technique to secure the data in watermarking algorithm is proposed. Materials and methods: In this research, Arnold transform-based image scrambling method developed and compared with random shuffling method and 30 is the sample size of each group. All medical images are collected from standard medical database. Results: The execution of image scrambling algorithm is calculated using peak signal to noise ratio (PSNR) and universal index quality measure (UIQI) parameters. Low values of PSNR and UIQI represent higher scrambling. Arnold transform provides mean PSNR value of 7.1314db and UIQI is 69.0437%. Random shuffling provides mean PSNR value is 9.2890db, and UIQI is 75.3633%. Conclusion: Based on the experimental and the statistical analysis by using the independent sample T test, the Arnold transform-based image scrambling method performs significantly better than random shuffling method with PSNR (P=0.01) and UIQI (P=0.21).

A new version of Hyper-Fractal Analysis: .Net WPF module for RGB 3D reconstruction of medical three-channel images

In Grossu et al. (2022) [1] we presented a module for fractal analysis of three-channel (most commonly CT: native, arterial contrast, and venous contrast) medical images stored in csv specific files coming from various sources (CT, MRI etc). In current paper we extended these functionalities to file series. We also developed a .Net WPF user control (a “three-dimensional Picture Box”) for facilitating 3D image reconstruction. For a better representation, the application allows various ways of filtering and highlighting the volumes of interest (specify parallelepipedal selections, apply classical or fuzzy band-pass filters, set voxel transparency and/or slice spacing, and representing each slice matrix component on a separated RGB channel). New version program summaryProgram Title: Hyper-Fractal Analysis v07CPC Library link to program files:https://doi.org/10.17632/z9knmny56p.3Licensing provisions: GPLv2Programming language: C# 7.3 /.Net Framework 4.7.1External routines: Prism, https://github.com/PrismLibrary/Prism-DocumentationJournal reference of previous version: Comput. Phys. Commun. 273 (2022) 108255Does the new version supersede the previous version?: YesNature of problem: Estimating the fractal dimension of images, multi-dimensional objects, and three-channel images. 3D reconstruction of medical images.Solution method: .Net WPF user control for representing 3D three-channel medical images stored in specific csv file series.Reasons for the new version: Develop a RGB 3D image reconstruction module for CT, MRI etc. three-channel images.Summary of revisions:• Hyper-Fractal Analysis v06 [1] allows opening specific csv files (.ct.csv) containing up to three matrices of integers (three-channel images). Although this functionality was initially intended for CT images [2], one could notice the high generality of the proposed solution. Thus, the csv data could come from various other DICOM sources (e.g. MRI). In order to better illustrate this fact, we changed the expected file extension to slice.csv.• The current version was also extended for opening folders containing image series. Following this purpose, each data “slice” must be stored in a separated three-channel csv file conforming to the following file name convention: [Name].[SliceIndex].slice.csv. The folder must also include a metadata file (meta.csv) containing various information of interest (pixel size, slice thickness, spacing between slices, and so on). The application GUI allows navigating between slices.• The ThreeDimPictureBox component was developed in Windows Presentation Foundation (WPF) UI framework [3] on top of the Model View-ViewModel (MVVM) pattern [4]. It was designed as a “3D PictureBox” user control for graphically representing a set of voxels specified as an input parameter.• One important challenge in 3D medical image reconstruction is related to the massive amount of data (e.g. 94,371,840 triangles for only 30 slices at 512 X 512 pixels). Taking into account the medical specific requirements, we mainly focused on representation's accuracy. Thus, for avoiding artifacts generated by interpolation algorithms, we did not implement any method of adapting slices with different resolutions [5]. The impact on performance is mainly managed by all filtering the pixels using the existing band-pass tool, restricting the analyzed data to a desired subset (parallelepipedal selection), choosing a lower resolution, and reducing the number of RGB colors. The algorithm will also merge the row adjacent voxels with the same color. As a transparency alternative, the user could opt for increasing the slice spacing (Fig. 1). For each combination of parameters, the numbers of necessary triangles and colors are priorly calculated, thus allowing the user to decide rendering or not the output voxels, as a function of known available resources.• In the previous version, we used three image channels for storing the native, arterial contrast, and venous contrast CT information. Each of the corresponding matrices is represented on a different RGB channel [6,7], which results in highlighting the image differences. The RGB colors resulting from this technique are also assigned to the voxels in the 3D reconstruction algorithm.• For avoiding the OutOfMemory exception, the application platform target was changed from Any CPU to x64.• Considering the 3D visualization difficulties involved by voxels occultation effects (even when setting high transparency levels) all previously mentioned functionalities were designed for helping the physician isolating and highlighting specific 3D data sub-sets, which is expected to be of significant interest in various medical areas [8–10].

The Role of Three-Dimensional Reconstruction of Medical Images and Virtual Reality in Nursing Experimental Teaching.

With the continuous advancement of medicine and computer science, medical image processing technology is also constantly advancing, and at the same time, it puts forward the needs of its own development. The purpose of this article is to combine the three-dimensional reconstruction of medical images and virtual reality (VR) technology in nursing experiment teaching to help students understand more easily and to simplify the teachers' teaching process and make the VR application technology. It is the most popular and effective in medical teaching. This article proposes the C-V model and the geometric active contour model to help us more clearly understand the pathology in this environment, where the specific symptoms appear, and bring a more easy-to-understand model for teaching and improving teaching quality. This article also designs nursing experiment teaching. The experimental results of this paper show that, after using VR courseware for teaching, the optimal test rate of the experimental class is 15% higher than that of the control class, and the transition rate is 8%. The actual test excellent rate and success rate of the experimental class are much higher than those of the control class. Therefore, it can be concluded that the application of VR technology in nursing teaching helps teachers improve their practical ability. The excellent teaching feedback rate is 95%, which is higher than 80.5% in the control group, indicating that the patient teaching simulation is approved by the observation group. The program can effectively improve the feedback rate of excellent teaching and provide students with better teaching services.

A Medical Image Reconstruction Algorithm Based on Composite Cosine Function Family

A Medical Image Reconstruction Algorithm Based on Composite Cosine Function Family

High-performance reconstruction of CT medical images by using out-of-core methods in GPU

Background and objective:Since Computed Tomography (CT) is one of the most widely used medical imaging tests, it is essential to work on methods that reduce the radiation the patient is exposed to. Although there are several possible approaches to achieve this, we focus on reducing the exposure time through sparse sampling. With this approach, efficient algebraic methods are needed to be able to generate the images in real time, and since their computational cost is high, using high-performance computing is essential. Methods:In this paper we present a GPU (Graphics Processing Unit) software for solving the CT image reconstruction problem using the QR factorization performed with out-of-core (OOC) techniques. This implementation is optimized to reduce the data transfer times between disk, CPU, and GPU, as well as to overlap input/output operations and computations. Results:The experimental study shows that a block cache stored on main page-locked memory is more efficient than using a cache on GPU memory or mirroring it in both GPU and CPU memory. Compared to a CPU version, this implementation is up to 6.5 times faster, providing an improved image quality when compared to other reconstruction methods. Conclusions:The software developed is an optimized version of the QR factorization for GPU that allows the algebraic reconstruction of CT images with high quality and resolution, with a performance that can be compared with state-of-the-art methods used in clinical practice. This approach allows reducing the exposure time of the patient and thus the radiation dose.

A Review of Deep Learning Methods for Compressed Sensing Image Reconstruction and Its Medical Applications

Compressed sensing (CS) and its medical applications are active areas of research. In this paper, we review recent works using deep learning method to solve CS problem for images or medical imaging reconstruction including computed tomography (CT), magnetic resonance imaging (MRI) and positron-emission tomography (PET). We propose a novel framework to unify traditional iterative algorithms and deep learning approaches. In short, we define two projection operators toward image prior and data consistency, respectively, and any reconstruction algorithm can be decomposed to the two parts. Though deep learning methods can be divided into several categories, they all satisfies the framework. We built the relationship between different reconstruction methods of deep learning, and connect them to traditional methods through the proposed framework. It also indicates that the key to solve CS problem and its medical applications is how to depict the image prior. Based on the framework, we analyze the current deep learning methods and point out some important directions of research in the future.

An asynchronous inertial algorithm for solving convex feasibility problems with strict pseudo-contractions in Hilbert spaces

AbstractFinding a common point in a finite intersection of sets, say, $C=\cap _{i=1}^{n} F(T_i)$, where each $T_i$ is a non-expansive-type mapping, is a central task in mathematics as it cuts across different areas of application, such as road design and medical image reconstruction. There are many algorithms for approximating solutions of such problems. Of particular interest in the implementation of these algorithms are cost and speed. This is due to the large computations to be performed at each step of the iterative process. One of the most efficient methods that optimizes the time of computation and cost of implementation is the asynchronous-parallel algorithm method. In this paper, we prove a weak convergence theorem for the asynchronous sequential inertial (ASI) algorithm (introduced by Heaton and Censor in [H. Heaton and Y. Censor, Asynchronous sequential inertial iterations for common fixed points problems with an application to linear systems, J. Glob. Optim. 74 (2019), 95–119.] ) for strictly pseudo-contractive mappings in Hilbert spaces. Under additional mild conditions, we also obtain a strong convergence theorem. Finally, we apply the ASI algorithm to solving convex minimization problems and Hammerstein integral equations.

Reconstruction of a 3D medical image from pre-processed 2D DICOM slices : clinical application

Reconstruction of a 3D medical image from pre-processed 2D DICOM slices : clinical application

Spatial Information Regularized Tensor Decomposition Framework for Super-Resolution Reconstruction of Medical MRI and Radiographs

Super-resolution reconstruction of medical images effectually enhances visual qualities to provide clear visions on anatomical structures. However, the spatial information, which abounds in low-resolution images, has received scant attention in the task of super-resolution, resulting in suppressed reconstruction qualities. This paper brings the spatial information into effective action by virtue of high-dimensional structures of tensor-format data, and presents a method named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Tensor Decomposition based medical Image Super-resolution reconstruction</i> (TDIS). In particular, TDIS employs tensors to preserve rich image spatial information and effectually processes the spatial information contained in image tensors by reformulating transposed convolutional layers using tensor decomposition. Moreover, TDIS provides tensor based error terms to capture spatial differences between generated and target images to reduce visual contrasts between them. Experimental results about reconstructing a range of medical images empirically demonstrate the competence of TDIS compared to the state-of-the-art methods.

New Method for 4D Reconstruction of Medical Images

New Method for 4D Reconstruction of Medical Images