The combination of tomographic imaging and deep learning, or machine learning in general, promises to empower not only image analysis but also image reconstruction. The latter aspect is considered in this perspective article with an emphasis on medical imaging to develop a new generation of image reconstruction theories and techniques. This direction might lead to intelligent utilization of domain knowledge from big data, innovative approaches for image reconstruction, and superior performance in clinical and preclinical applications. To realize the full impact of machine learning for tomographic imaging, major theoretical, technical and translational efforts are immediately needed.

A Perspective on Deep Imaging

Sparse coding has become an increasingly popular method in learning and vision for a variety of classification, reconstruction and coding tasks. The canonical approach intrinsically assumes independence between observations during learning. For many natural signals however, sparse coding is applied to sub-elements ( i.e. patches) of the signal, where such an assumption is invalid. Convolutional sparse coding explicitly models local interactions through the convolution operator, however the resulting optimization problem is considerably more complex than traditional sparse coding. In this paper, we draw upon ideas from signal processing and Augmented Lagrange Methods (ALMs) to produce a fast algorithm with globally optimal sub problems and super-linear convergence.

Fast convolutional sparse coding

The combination of tomographic imaging and deep learning, or machine learning in general, promises to empower not only image analysis but also image reconstruction. The latter aspect is considered in this perspective article with an emphasis on medical imaging to develop a new generation of image reconstruction theories and techniques. This direction might lead to intelligent utilization of domain knowledge from big data, innovative approaches for image reconstruction, and superior performance in clinical and preclinical applications. To realize the full impact of machine learning on medical imaging, major challenges must be addressed.

The introduction of photon-counting detectors is expected to be the next major breakthrough in clinical x-ray computed tomography (CT). During the last decade, there has been considerable research activity in the field of photon-counting CT, in terms of both hardware development and theoretical understanding of the factors affecting image quality. In this article, we review the recent progress in this field with the intent of highlighting the relationship between detector design considerations and the resulting image quality. We discuss detector design choices such as converter material, pixel size, and readout electronics design, and then elucidate their impact on detector performance in terms of dose efficiency, spatial resolution, and energy resolution. Furthermore, we give an overview of data processing, reconstruction methods and metrics of imaging performance; outline clinical applications; and discuss potential future developments.

/pdf/photon-counting-x-ray-detectors-for-ct-4ma8oc2u3q.pdf

Photon-counting x-ray detectors for CT

This review describes advances in the XRF group of techniques published approximately between April 2015 and March 2016. Fundamental contributions in the instrumentation sections include the development of synchrotron radiation sources, semiconductor design technology and evaluating the quality of in situ hand-held XRF results. A bench top TXRF spectrometer for the measurement of the elements from carbon to uranium is described that offers achievable detection limits that range from ng g−1 to μg g−1. The applications sections aim to give a representative overview of the range of applications that use XRF techniques with an emphasis on papers that describe technical or application innovation. Sample size investigated ranged from the planet Mercury down to nano-gram quantities of cement secreted by settlement stage barnacle larvae. The archaeological and cultural heritage section this year includes an authentic report on the use of cannabis as a filler in ancient lime plaster and heartening news that the construction of an underground parking garage in the centre of Zurich (Switzerland) unearthed the remains of seven Neolithic settlements from the 4th and 3rd millennium BC. The X-ray excitation of iron present in ancient iron-gall inks was presented as a step toward the non-invasive reading of fragile and/or unopenable documents. Feedback from readers of this review is most welcome and the review coordinator may be contacted using the email address provided.

https://pubs.rsc.org/en/content/articlepdf/2021/ja/d1ja90033a

2016 Atomic Spectrometry Update – a review of advances in X-ray fluorescence spectrometry and its applications

Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. Qualitative and quantitative results demonstrate that the proposed methods achieve better performance than several existing state-of-the-art methods.

Convolutional Sparse Coding for Compressed Sensing CT Reconstruction

Over the past few years, dictionary learning (DL)-based methods have been successfully used in various image reconstruction problems. However, the traditional DL-based computed tomography (CT) reconstruction methods are patch-based and ignore the consistency of pixels in overlapped patches. In addition, the features learned by these methods always contain shifted versions of the same features. In recent years, convolutional sparse coding (CSC) has been developed to address these problems. In this paper, inspired by several successful applications of CSC in the field of signal processing, we explore the potential of CSC in sparse-view CT reconstruction. By directly working on the whole image, without the necessity of dividing the image into overlapped patches in DL-based methods, the proposed methods can maintain more details and avoid artifacts caused by patch aggregation. With predetermined filters, an alternating scheme is developed to optimize the objective function. Extensive experiments with simulated and real CT data were performed to validate the effectiveness of the proposed methods. The qualitative and quantitative results demonstrate that the proposed methods achieve better performance than the several existing state-of-the-art methods.

Computed tomography (CT) reconstruction with low radiation dose is a significant research point in current medical CT field. Compressed sensing has shown great potential reconstruct high-quality CT images from few-view or sparse-view data. In this paper, we use the sparser L1/2 regularization operator to replace the traditional L1 regularization and combine the Split Bregman method to reconstruct CT images, which has good unbiasedness and can accelerate iterative convergence. In the reconstruction experiments with simulation and real projection data, we analyze the quality of reconstructed images using different reconstruction methods in different projection angles and iteration numbers. Compared with algebraic reconstruction technique (ART) and total variance (TV) based approaches, the proposed reconstruction algorithm can not only get better images with higher quality from few-view data but also need less iteration numbers.

/pdf/a-ct-reconstruction-algorithm-based-on-l1-2-regularization-2rtetvvd1y.pdf

A CT Reconstruction Algorithm Based on L1/2 Regularization.

For X-ray computed tomography (CT), geometric calibration and rigid patient motion compensation are inter- related issues for optimization of image reconstruction quality. Non-calibrated system geometry and patient movement during a CT scan will result in streak-like, blurring and other artifacts in reconstructed images. In this paper, we propose a locally linear embedding based calibration approach to address this challenge under a rigid 2D object assumption and a more general way than what has been reported before. In this method, projections are linearly represented by up-sampled neighbors via locally linear embedding, and CT system parameters are iteratively estimated from projection data themselves. Numerical and experimental studies show that images reconstructed with calibrated parameters are in excellent agreement with the counterparts reconstructed with the true parameters.

X-ray CT geometrical calibration via locally linear embedding.

Background Spectral computed tomography (CT) has the capability to resolve the energy levels of incident photons, which has the potential to distinguish different material compositions. Although material decomposition methods based on x-ray attenuation characteristics have good performance in dual-energy CT imaging, there are some limitations in terms of image contrast and noise levels. Objective This study focused on multi-material decomposition of spectral CT images based on a deep learning approach. Methods To classify and quantify different materials, we proposed a multi-material decomposition method via the improved Fully Convolutional DenseNets (FC-DenseNets). A mouse specimen was first scanned by spectral CT system based on a photon-counting detector with different energy ranges. We then constructed a training set from the reconstructed CT images for deep learning to decompose different materials. Results Experimental results demonstrated that the proposed multi-material decomposition method could more effectively identify bone, lung and soft tissue than the basis material decomposition based on post-reconstruction space in high noise levels. Conclusions The new proposed approach yielded good performance on spectral CT material decomposition, which could establish guidelines for multi-material decomposition approaches based on the deep learning algorithm.

Mianyi Chen

Papers

Convolutional Sparse Coding for Compressed Sensing CT Reconstruction

Convolutional Sparse Coding for Compressed Sensing CT Reconstruction

A CT Reconstruction Algorithm Based on L1/2 Regularization.

X-ray CT geometrical calibration via locally linear embedding.

Multi-material decomposition of spectral CT images via Fully Convolutional DenseNets.