Neural network guided sinogram-domain iterative algorithm for artifact reduction.

Objective. Cone beam computed tomography (CBCT) has been wildly used in clinical treatment of dental diseases. However, patients often have metallic implants in mouth, which will lead to severe metal artifacts in the reconstructed images. To reduce metal artifacts in dental CBCT images, which have a larger amount of data and a limited field of view compared to computed tomography images, a new dental CBCT metal artifact reduction method based on a projection correction and a convolutional neural network (CNN) based image post-processing model is proposed in this paper. Approach. The proposed method consists of three stages: (1) volume reconstruction and metal segmentation in the image domain, using the forward projection to get the metal masks in the projection domain; (2) linear interpolation in the projection domain and reconstruction to build a linear interpolation (LI) corrected volume; (3) take the LI corrected volume as prior and perform the prior based beam hardening correction in the projection domain, and (4) combine the constructed projection corrected volume and LI-volume slice-by-slice in the image domain by two concatenated U-Net based models (CNN1 and CNN2). Simulated and clinical dental CBCT cases are used to evaluate the proposed method. The normalized root means square difference (NRMSD) and the structural similarity index (SSIM) are used for the quantitative evaluation of the method. Main results. The proposed method outperforms the frequency domain fusion method (FS-MAR) and a state-of-art CNN based method on the simulated dataset and yields the best NRMSD and SSIM of 4.0196 and 0.9924, respectively. Visual results on both simulated and clinical images also illustrate that the proposed method can effectively reduce metal artifacts. Significance. This study demonstrated that the proposed dual-domain processing framework is suitable for metal artifact reduction in dental CBCT images.

BackgroundCervical cancer is the fifth most common cancer among women, which is the third leading cause of cancer death in women worldwide. Brachytherapy is the most effective treatment for cervical cancer. For brachytherapy, computed tomography (CT) imaging is necessary since it conveys tissue density information which can be used for dose planning. However, the metal artifacts caused by brachytherapy applicators remain a challenge for the automatic processing of image data for image-guided procedures or accurate dose calculations. Therefore, developing an effective metal artifact reduction (MAR) algorithm in cervical CT images is of high demand.MethodsA novel residual learning method based on convolutional neural network (RL-ARCNN) is proposed to reduce metal artifacts in cervical CT images. For MAR, a dataset is generated by simulating various metal artifacts in the first step, which will be applied to train the CNN. This dataset includes artifact-insert, artifact-free, and artifact-residual images. Numerous image patches are extracted from the dataset for training on deep residual learning artifact reduction based on CNN (RL-ARCNN). Afterwards, the trained model can be used for MAR on cervical CT images.ResultsThe proposed method provides a good MAR result with a PSNR of 38.09 on the test set of simulated artifact images. The PSNR of residual learning (38.09) is higher than that of ordinary learning (37.79) which shows that CNN-based residual images achieve favorable artifact reduction. Moreover, for a 512 × 512 image, the average removal artifact time is less than 1 s.ConclusionsThe RL-ARCNN indicates that residual learning of CNN remarkably reduces metal artifacts and improves critical structure visualization and confidence of radiation oncologists in target delineation. Metal artifacts are eliminated efficiently free of sinogram data and complicated post-processing procedure.

Purpose: Cone-beam computed tomography (CBCT) is commonly used in the operating room to evaluate the placement of surgical implants in relation to critical anatomical structures. A particularly problematic setting, however, is the imaging of metallic implants, where strong artifacts can obscure visualization of both the implant and surrounding anatomy. Such artifacts are compounded when combined with low-dose imaging techniques such as sparse-view acquisition. Approach: This work presents a dual convolutional neural network approach, one operating in the sinogram domain and one in the reconstructed image domain, that is specifically designed for the physics and setting of intraoperative CBCT to address the sources of beam hardening and sparse view sampling that contribute to metal artifacts. The networks were trained with images from cadaver scans with simulated metal hardware. Results: The trained networks were tested on images of cadavers with surgically implanted metal hardware, and performance was compared with a method operating in the image domain alone. While both methods removed most image artifacts, superior performance was observed for the dual-convolutional neural network (CNN) approach in which beam-hardening and view sampling effects were addressed in both the sinogram and image domain. Conclusion: The work demonstrates an innovative approach for eliminating metal and sparsity artifacts in CBCT using a dual-CNN framework which does not require a metal segmentation.

While X-ray computed tomography (XCT) is pushed further into the micro- and nanoscale, the limitations of various tool components and object motion become more apparent. For high-resolution XCT, it is necessary but practically difficult to align these tool components with sub-micron precision. The aim is to develop a novel reconstruction methodology that considers unavoidable misalignment and object motion during the data acquisition in order to obtain high-quality three-dimensional images and that is applicable for data recovery from incomplete datasets. A reconstruction software empowered by sophisticated correction modules that autonomously estimates and compensates artefacts using gradient descent and deep learning algorithms has been developed and applied. For motion estimation, a novel computer vision methodology coupled with a deep convolutional neural network approach provides estimates for the object motion by tracking features throughout the adjacent projections. The model is trained using the forward projections of simulated phantoms that consist of several simple geometrical features such as sphere, triangle and rectangular. The feature maps extracted by a neural network are used to detect and to classify features done by a support vector machine. For missing data recovery, a novel deep convolutional neural network is used to infer high-quality reconstruction data from incomplete sets of projections. The forward and back projections of simulated geometric shapes from a range of angular ranges are used to train the model. The model is able to learn the angular dependency based on a limited angle coverage and to propose a new set of projections to suppress artefacts. High-quality three-dimensional images demonstrate that it is possible to effectively suppress artefacts caused by thermomechanical instability of tool components and objects resulting in motion, by center of rotation misalignment and by inaccuracy in the detector position without additional computational efforts. Data recovery from incomplete sets of projections result in directly corrected projections instead of suppressing artefacts in the final reconstructed images. The proposed methodology has been proven and is demonstrated for a ball bearing sample. The reconstruction results are compared to prior corrections and benchmarked with a commercially available reconstruction software. Compared to conventional approaches in XCT imaging and data analysis, the proposed methodology for the generation of high-quality three-dimensional X-ray images is fully autonomous. The methodology presented here has been proven for high-resolution micro-XCT and nano-XCT, however, is applicable for all length scales.

ObjectiveTo evaluate the efficacy of single-energy metal artifact reduction (SEMAR) algorithm in removing metallic artifacts for patients with novel leadless pacemakers (PMs) compared to those with conventional transvenous PMs.Methods30 patients with transvenous PMs and 30 patients with leadless PMs having coronary CT angiography (CCTA) were included. Images were reconstructed using two methods: a conventional hybrid-iterative reconstruction (HIR) algorithm separately, and the HIR combined with SEMAR algorithm. The artifact index (AI) was calculated for both datasets to quantitatively assess the artifact reduction. Two senior radiologists independently scored the artifact extent and diagnostic confidence of surrounding tissues. The position of artifacts-impaired tissues was also visually evaluated as follows: non-impaired, impaired, and equivocal. The study was ethics committee-approved.ResultsThe leadless PMSEMAR exhibited significantly lower AIs than the leadless PMnon−SEMAR, with an improvement of hypodense artifacts and a significant reduction of hyperdense artifacts (all p < 0.001). The AIs of leadless PMs performed with and without SEMAR were slightly lower than those of transvenous PMs, although no statistical difference existed (all p > 0.05). Qualitatively, the artifact extent of SEMAR significantly outperformed non-SEMAR in both types of PM (p < 0.001). The aorta, right coronary artery, right atrium, and left ventricle were less impaired in leadless PMnon−SEMAR compared to transvenous PMnon−SEMAR (all p < 0.05).ConclusionsSEMAR provides effective reduction of metallic artifacts from both types of cardiac PMs. The artifact-impaired tissues are fewer on leadless PMs, resulting in an enhanced diagnostic confidence in the surrounding tissues.

Helical CT has been widely used in clinical diagnosis. Sparsely spaced multidetector in z direction can increase the coverage of the detector provided limited detector rows. It can speed up volumetric CT scan, lower the radiation dose and reduce motion artifacts. However, it leads to insufficient data for reconstruction. That means reconstructions from general analytical methods will have severe artifacts. Iterative reconstruction methods might be able to deal with this situation but with the cost of huge computational load. In this work, we propose a cascaded dual-domain deep learning method that completes both data transformation in projection domain and error reduction in image domain. First, a convolutional neural network (CNN) in projection domain is constructed to estimate missing helical projection data and converting helical projection data to 2D fan-beam projection data. This step is to suppress helical artifacts and reduce the following computational cost. Then, an analytical linear operator is followed to transfer the data from projection domain to image domain. Finally, an image domain CNN is added to improve image quality further. These three steps work as an entirety and can be trained end to end. The overall network is trained using a simulated lung CT dataset with Poisson noise from 25 patients. We evaluate the trained network on another three patients and obtain very encouraging results with both visual examination and quantitative comparison. The resulting RRMSE is 6.56% and the SSIM is 99.60%. In addition, we test the trained network on the lung CT dataset with different noise level and a new dental CT dataset to demonstrate the generalization and robustness of our method.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG

This work studies the dual formulation of a penalized maximum likelihood reconstruction problem in x-ray CT. The primal objective function is a Poisson log-likelihood combined with a weighted cross-entropy penalty term. The dual formulation of the primal optimization problem is then derived and the optimization procedure outlined. The dual formulation better exploits the structure of the problem, which translates to faster convergence of iterative reconstruction algorithms. A gradient descent algorithm is implemented for solving the dual problem and its performance is compared with the filtered back-projection algorithm, and with the primal formulation optimized by using surrogate functions. The 3D XCAT phantom and an analytical x-ray CT simulator are used to generate noise-free and noisy CT projection data set with monochromatic and polychromatic x-ray spectrums. The reconstructed images from the dual formulation delineate the internal structures at early iterations better than the primal formulation using surrogate functions. However the body contour is slower to converge in the dual than in the primal formulation. The dual formulation demonstrate better noise-resolution tradeoff near the internal organs than the primal formulation. Since the surrogate functions in general can provide a diagonal approximation of the Hessian matrix of the objective function, further convergence speed up may be achieved by deriving the surrogate function of the dual objective function.

Metal in CT-imaged objects drastically reduces the quality of these images due to the severe artifacts it can cause. Most metal artifacts reduction (MAR) algorithms consider the metal-affected sinogram portions as the corrupted data and replace them via sophisticated interpolation methods. While these schemes are successful in removing the metal artifacts, they fail to recover some of the edge information. To address these problems, the frequency shift metal artifact reduction algorithm (FSMAR) was recently proposed. It exploits the information hidden in the uncorrected image and combines the high frequency (edge) components of the uncorrected image with the low frequency components of the corrected image. Although this can effectively transfer the edge information of the uncorrected image, it also introduces some unwanted artifacts. The essential problem of these algorithms is that they lack the capability of detecting the artifacts and as a result cannot discriminate between desired and undesired edges. We propose a scheme that does better in these respects. Our Metal Artifact Detection and Reduction (MADR) scheme constructs a weight map which stores whether a pixel in the uncorrected image belongs to an artifact region or a non-artifact region. This weight matrix is optimal in the Linear Minimum Mean Square Sense (LMMSE). Our results demonstrate that MADR outperforms the existing algorithms and ensures that the anatomical structures close to metal implants are better preserved.

High-attenuation objects like metals will result in metal artifacts in computed tomography images. Compared with single metallic object, artifacts due to multiple and large-scaled metallic objects is more complicated in representation and have much worse effects on reconstructed image. State-of-the-art metal artifacts reduction for multiple metal objects based on interpolation method cannot solve the beam hardening inside the metals, and can easily make mistakes in segmentation and interpolation. Aiming at reduction of multiple metallic objects, this paper simulates the production of the artifacts and proposes a metal artifacts reduction method based on projections correction. In this method, metal regions are firstly segmented directly from projection domain, and then a correction model is established for projections in metal regions. Finally, correction is made by adjusting parameters of the model. The optimal solution of the parameters is achieved by NM-simplex method that makes the gray entropy of the reconstructed image minimum. The simulation results and obtained data show that the present method significantly improves metal artifact due to multiple metallic objects and provides a better image quality than that obtained using interpolation.

Brain tumors are formed due to the abnormal growth of the cells that get multiplied and become in uncontrollable perspective. Tumors can damage brain cells by pressing down the skull, which consociate begins in, which negatively affects human health. In advanced stages, a brain tumor is a more dangerous infection that cannot be relieved. Brain tumor detection and early prevention are necessary in today's world. An extreme learning machine (ELM) is a widely adopted algorithm in machine learning. It is proposed to use classification models in brain tumor imaging. This classification is based on the techniques implemented: Convolutional Neural Networks(CNN) and Generative Adversarial Networks(GAN). CNN efficiently solves the convex optimization problem and is faster, requiring less human effort. The algorithmic architecture of GAN uses two neural networks, pocking one against the other. These networks are implemented in various fields to classify brain Tumor images. The present study mainly aims to introduce a new proposed classification system of preschool children brain imaging with Hybrid Convolutional Neural Networks and with the techniques of GAN. The proposed technique is compared with the existing hybrid-CNN and hybrid-GAN techniques. The outcomes are encouraging because the loss is deduced, and the accuracy facet increases. The proposed system achieved a training accuracy of 97.8% and a validation accuracy of 89%. The outcomes of the studies show that ELM in the platform of GAN for preschool children brain imaging classification has achieved higher predictive performance than the traditional classification mechanisms in increasingly complex scenarios. Time elapsed for training brain images samples finds inference value for training samples and time elapsed value increased by 28.9855%. Approximation ratio for cost based on probability, finding Approximation ratio for low probability range is increased by 88.1%. The combination of CNN, GAN and hybrid-CNN, hybrid-GAN, and hybrid CNN + GAN, compared with the proposed hybrid system, increased Detection latency for low range learning rate by 3.31%.

The report presents an algorithm for constructing a convolutional hierarchical neural network classifier, which is a modification of the algorithm for constructing hierarchical neural network classifiers suggested before. The original algorithm was designed to exploit intrinsic class hierarchy to build a class tree with a neural network in each node classifying groups of initial classes (in a non-terminal node) or a subset of original classes (in a terminal node). The convolutional modification utilizes convolutional neural networks instead of regular fully connected networks in order to apply the model to image classification tasks. Use of class hierarchy for image classification should reduce the number of adjusted neural network parameters compared to deep convolutional neural networks, and therefore it should reduce training and inference time. In this context the algorithm may be compared with some pruning techniques. The convolutional hierarchical neural network classifier inherits some hyperparameters of a conventional hierarchical neural network classifier, like the activation threshold and the threshold by the share of voting patterns. The goal of this study was to explore different strategies of choosing these hyperparameters. To test these strategies, we used the CIFAR-10 dataset. Also, for demonstration purposes we apply the convolutional hierarchical neural network classifier to the CIFAR-100 dataset.

In this paper, alternative direction finding methods have been proposed using deep learning techniques. Firstly, Regeression and Classification models have created by using Convolutional Neural Networks (CNNs). In the second Convolutional Neural Networks and Recurrent Neural Networks (RNNs) have been utilized in the proposed methods. Despite having vast amount of direction finding studies, utilization of neural networks is scarce in literature and past works mostly only includes usage of CNNs. In this study, direction finding is performed by learning signals reaching multiple antenna arrays by networks. Created neural networks have been fed with different data formats and their performances against noisy and no-noise data have been shown. In addition, comparative analysis of the developed models were made in the similar Signal-to-Noise Ratio (SNR) range with the subspace based MUSIC algorithm, which is frequently used in direction finding.

Neural networks in medical imaging