3D algebraic iterative reconstruction for cone-beam x-ray differential phase-contrast computed tomography

Novel Feature Selection and Voting Classifier Algorithms for COVID-19 Classification in CT Images

Diagnosis is a critical preventive step in Coronavirus research which has similar manifestations with other types of pneumonia. CT scans and X-rays play an important role in that direction. However, processing chest CT images and using them to accurately diagnose COVID-19 is a computationally expensive task. Machine Learning techniques have the potential to overcome this challenge. This article proposes two optimization algorithms for feature selection and classification of COVID-19. The proposed framework has three cascaded phases. Firstly, the features are extracted from the CT scans using a Convolutional Neural Network (CNN) named AlexNet. Secondly, a proposed features selection algorithm, Guided Whale Optimization Algorithm (Guided WOA) based on Stochastic Fractal Search (SFS), is then applied followed by balancing the selected features. Finally, a proposed voting classifier, Guided WOA based on Particle Swarm Optimization (PSO), aggregates different classifiers' predictions to choose the most voted class. This increases the chance that individual classifiers, e.g. Support Vector Machine (SVM), Neural Networks (NN), k-Nearest Neighbor (KNN), and Decision Trees (DT), to show significant discrepancies. Two datasets are used to test the proposed model: CT images containing clinical findings of positive COVID-19 and CT images negative COVID-19. The proposed feature selection algorithm (SFS-Guided WOA) is compared with other optimization algorithms widely used in recent literature to validate its efficiency. The proposed voting classifier (PSO-Guided-WOA) achieved AUC (area under the curve) of 0.995 that is superior to other voting classifiers in terms of performance metrics. Wilcoxon rank-sum, ANOVA, and T-test statistical tests are applied to statistically assess the quality of the proposed algorithms as well.

Revising the lower statistical limit of x-ray grating-based phase-contrast computed tomography

Phase-contrast x-ray computed tomography (PCCT) is currently investigated as an interesting extension of conventional CT, providing high soft-tissue contrast even if examining weakly absorbing specimen. Until now, the potential for dose reduction was thought to be limited compared to attenuation CT, since meaningful phase retrieval fails for scans with very low photon counts when using the conventional phase retrieval method via phase stepping. In this work, we examine the statistical behaviour of the reverse projection method, an alternative phase retrieval approach and compare the results to the conventional phase retrieval technique. We investigate the noise levels in the projections as well as the image quality and quantitative accuracy of the reconstructed tomographic volumes. The results of our study show that this method performs better in a low-dose scenario than the conventional phase retrieval approach, resulting in lower noise levels, enhanced image quality and more accurate quantitative values. Overall, we demonstrate that the lower statistical limit of the phase stepping procedure as proposed by recent literature does not apply to this alternative phase retrieval technique. However, further development is necessary to overcome experimental challenges posed by this method which would enable mainstream or even clinical application of PCCT.

In-line phase-contrast breast tomosynthesis: a phantom feasibility study at a synchrotron radiation facility

The major objective is to adopt, apply and test developed in-house algorithms for volumetric breast reconstructions from projection images, obtained in in-line phase-contrast mode. Four angular sets, each consisting of 17 projection images obtained from four physical phantoms, were acquired at beamline ID17, European Synchroton Radiation Facility, Grenoble, France. The tomosynthesis arc was  ±32°. The physical phantoms differed in complexity of texture and introduced features of interest. Three of the used phantoms were in-house developed, and made of epoxy resin, polymethyl-methacrylate and paraffin wax, while the fourth phantom was the CIRS BR3D. The projection images had a pixel size of 47 µm  ×  47 µm. Tomosynthesis images were reconstructed with standard shift-and-add (SAA) and filtered backprojection (FBP) algorithms. It was found that the edge enhancement observed in planar x-ray images is preserved in tomosynthesis images from both phantoms with homogeneous and highly heterogeneous backgrounds. In case of BR3D, it was found that features not visible in the planar case were well outlined in the tomosynthesis slices. In addition, the edge enhancement index calculated for features of interest was found to be much higher in tomosynthesis images reconstructed with FBP than in planar images and tomosynthesis images reconstructed with SAA. The comparison between images reconstructed by the two reconstruction algorithms shows an advantage for the FBP method in terms of better edge enhancement. Phase-contrast breast tomosynthesis realized in in-line mode benefits the detection of suspicious areas in mammography images by adding the edge enhancement effect to the reconstructed slices.

Fast 3D reconstruction method for differential phase contrast X-ray CT

We present a fast algorithm for fully 3D regularized X-ray tomography reconstruction for both traditional and differential phase contrast measurements. In many applications, it is critical to reduce the X-ray dose while producing high-quality reconstructions. Regularization is an excellent way to do this, but in the differential phase contrast case it is usually applied in a slice-by-slice manner. We propose using fully 3D regularization to improve the dose/quality trade-off beyond what is possible using slice-by-slice regularization. To make this computationally feasible, we show that the two computational bottlenecks of our iterative optimization process can be expressed as discrete convolutions; the resulting algorithms for computation of the X-ray adjoint and normal operator are fast and simple alternatives to regridding. We validate this algorithm on an analytical phantom as well as conventional CT and differential phase contrast measurements from two real objects. Compared to the slice-by-slice approach, our algorithm provides a more accurate reconstruction of the analytical phantom and better qualitative appearance on one of the two real datasets.

Multi-Mounted X-Ray Computed Tomography

Most existing X-ray computed tomography (CT) techniques work in single-mounted mode and need to scan the inspected objects one by one. It is time-consuming and not acceptable for the inspection in a large scale. In this paper, we report a multi-mounted CT method and its first engineering implementation. It consists of a multi-mounted scanning geometry and the corresponding algebraic iterative reconstruction algorithm. This approach permits the CT rotation scanning of multiple objects simultaneously without the increase of penetration thickness and the signal crosstalk. Compared with the conventional single-mounted methods, it has the potential to improve the imaging efficiency and suppress the artifacts from the beam hardening and the scatter. This work comprises a numerical study of the method and its experimental verification using a dataset measured with a developed multi-mounted X-ray CT prototype system. We believe that this technique is of particular interest for pushing the engineering applications of X-ray CT.

Analysis and Correction of Dynamic Geometric Misalignment for Nano-Scale Computed Tomography at BSRF

Due to its high spatial resolution, synchrotron radiation x-ray nano-scale computed tomography (nano-CT) is sensitive to misalignments in scanning geometry, which occurs quite frequently because of mechanical errors in manufacturing and assembly or from thermal expansion during the time-consuming scanning. Misalignments degrade the imaging results by imposing artifacts on the nano-CT slices. In this paper, the geometric misalignment of the synchrotron radiation nano-CT has been analyzed by partial derivatives on the CT reconstruction algorithm and a correction method, based on cross correlation and least-square sinusoidal fitting, has been reported. This work comprises a numerical study of the method and its experimental verification using a dataset measured with the full-field transmission x-ray microscope nano-CT at the beamline 4W1A of the Beijing Synchrotron Radiation Facility. The numerical and experimental results have demonstrated the validity of the proposed approach. It can be applied for dynamic geometric misalignment and needs neither phantom nor additional correction scanning. We expect that this method will simplify the experimental operation of synchrotron radiation nano-CT.