Search

To facilitate a prospective estimation of CT effective dose and risk minimization process, a prospective spatial dose estimation and the known anatomical structures are expected. To this end, a CT reconstruction method is required to reconstruct CT volumes from as few projections as possible, i.e. by using the topograms, with anatomical structures as correct as possible. In this work, an optimized CT reconstruction model based on a generative adversarial network (GAN) is proposed. The GAN is trained to reconstruct 3D volumes from an anterior-posterior and a lateral CT projection. To enhance anatomical structures, a pre-trained organ segmentation network and the 3D perceptual loss are applied during the training phase, so that the model can then generate both organ-enhanced CT volume and the organ segmentation mask. The proposed method can reconstruct CT volumes with PSNR of 26.49, RMSE of 196.17, and SSIM of 0.64, compared to 26.21, 201.55 and 0.63 using the baseline method. In terms of the anatomical structure, the proposed method effectively enhances the organ shape and boundary and allows for a straight-forward identification of the relevant anatomical structures. We note that conventional reconstruction metrics fail to indicate the enhancement of anatomical structures. In addition to such metrics, the evaluation is expanded with assessing the organ segmentation performance. The average organ dice of the proposed method is 0.71 compared with 0.63 in baseline model, indicating the enhancement of anatomical structures.

Long lasting efforts have been made to reduce radiation dose and thus the potential radiation risk to the patient for computed tomography acquisitions without severe deterioration of image quality. To this end, numerous reconstruction and noise reduction algorithms have been developed, many of which are based on iterative reconstruction techniques, incorporating prior knowledge in the projection or image domain. Recently, deep learning-based methods became increasingly popular and a multitude of papers claim ever improving performance both quantitatively and qualitatively. In this work, we find that the lack of a common benchmark setup and flaws in the experimental setup of many publications hinder verifiability of those claims. We propose a benchmark setup to overcome those flaws and improve reproducibility and verifiability of experimental results in the field. In a comprehensive and fair evaluation of several deep learning-based low dose CT denoising algorithms, we find that most methods perform statistically similar and improvements over the past six years have been marginal at best.

In computed tomography (CT), automatic exposure control (AEC) is frequently used to reduce radiation dose exposure to patients. For organ-specific AEC, a preliminary CT reconstruction is necessary to estimate organ shapes for dose optimization, where only a few projections are allowed for real-time reconstruction. In this work, we investigate the performance of automated transform by manifold approximation (AUTOMAP) in such applications. For proof of concept, we investigate its performance on the MNIST dataset first, where the dataset containing all the 10 digits are randomly split into a training set and a test set. We train the AUTOMAP model for image reconstruction from 2 projections or 4 projections directly. The test results demonstrate that AUTOMAP is able to reconstruct most digits well with a false rate of 1.6% and 6.8% respectively. In our subsequent experiment, the MNIST dataset is split in a way that the training set contains 9 digits only while the test set contains the excluded digit only, for instance "2". In the test results, the digit "2"s are falsely predicted as "3" or "5" when using 2 projections for reconstruction, reaching a false rate of 94.4%. For the application in medical images, AUTOMAP is also trained on patients' CT images. The test images reach an average root-mean-square error of 290 HU. Although the coarse body outlines are well reconstructed, some organs are misshaped., Comment: Proceedings for "2020 IEEE Nuclear Science Symposium and Medical Imaging Conference"

Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a C-arm system. However, the projective data provide only limited information about the spatial structure and position of interventional tools such as stents, guide wires or coils. In this work we propose a deep learning-based pipeline for real-time tomographic (four-dimensional) interventional guidance at acceptable dose levels. In the first step, interventional tools are extracted from four cone-beam CT projections using a deep convolutional neural network (CNN). These projections are then reconstructed and fed into a second CNN, which maps this highly undersampled reconstruction to a segmentation of the interventional tools. Our pipeline is capable of reconstructing interventional tools from only four x-ray projections without the need for a patient prior with very high accuracy. Therefore, the proposed approach is capable of overcoming the drawbacks of today's interventional guidance and could enable the development of new minimally invasive radiological interventions by providing full spatiotemporal information about the interventional tools., Comment: Updated with final version of this article, as published in Medical Physics; 14 pages, 12 figures

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks and cascaded neural networks have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by decoupling the regularization of the solution from ensuring consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained neural network which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative networks. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude.

Automatic multi-organ segmentation of the dual energy computed tomography (DECT) data can be beneficial for biomedical research and clinical applications. However, it is a challenging task. Recent advances in deep learning showed the feasibility to use 3-D fully convolutional networks (FCN) for voxel-wise dense predictions in single energy computed tomography (SECT). In this paper, we proposed a 3D FCN based method for automatic multi-organ segmentation in DECT. The work was based on a cascaded FCN and a general model for the major organs trained on a large set of SECT data. We preprocessed the DECT data by using linear weighting and fine-tuned the model for the DECT data. The method was evaluated using 42 torso DECT data acquired with a clinical dual-source CT system. Four abdominal organs (liver, spleen, left and right kidneys) were evaluated. Cross-validation was tested. Effect of the weight on the accuracy was researched. In all the tests, we achieved an average Dice coefficient of 93% for the liver, 90% for the spleen, 91% for the right kidney and 89% for the left kidney, respectively. The results show our method is feasible and promising., Comment: 5 pagens, 4 figures, conference

Implementation of real-time, continuous, and three-dimensional imaging (4D intervention guidance) would be a quantum leap for minimally-invasive medicine. It allows guidance during interventions by assessing the spatial position of instruments continuously in respect to their surroundings. Recent research showed that it is feasible using X-ray and novel tomographic reconstruction approaches. Radiation dose stays within reasonable limits. This article provides abstractions and background information together with an outlook on these prospects. There are explanations of how situational awareness during interventions is generated today and how they will be in future. The differences between fluoroscopically and CT-guided interventions are eluted to within the context of these developments. The exploration of uncharted terrain between these current methods is worth pursuing. Necessary image quality of 4D intervention guidance varies relevantly from that of standard computed tomography. Means to analyze the risk-benefit ratio of 4D intervention guidance are provided and arguments for gantry-based setups vs C-arm based setups are given. Due to the lack of moving organs, neuro-interventions might be the first field in which 4D intervention guidance might become available, however, registration and fusion algorithms might make it applicable in complex whole-body interventions such as aortic valve replacement soon thereafter.

In the last decade C-arm-based cone-beam CT became a widely used modality for intraoperative imaging. Typically a C-arm scan is performed using a circle-like trajectory around a region of interest. Therefor an angular range of at least 180{\deg} plus fan-angle must be covered to ensure a completely sampled data set. This fact defines some constraints on the geometry and technical specifications of a C-arm system, for example a larger C radius or a smaller C opening respectively. These technical modifications are usually not benificial in terms of handling and usability of the C-arm during classical 2D applications like fluoroscopy. The method proposed in this paper relaxes the constraint of 180{\deg} plus fan-angle rotation to acquire a complete data set. The proposed C-arm trajectory requires a motorization of the orbital axis of the C and of ideally two orthogonal axis in the C plane. The trajectory consists of three parts: A rotation of the C around a defined iso-center and two translational movements parallel to the detector plane at the begin and at the end of the rotation. Combining these three parts to one trajectory enables for the acquisition of a completely sampled dataset using only 180{\deg} minus fan-angle of rotation. To evaluate the method we show animal scans acquired with a mobile C-arm prototype. We expect that the transition of this method into clinical routine will lead to a much broader use of intraoperative 3D imaging in a wide field of clinical applications.