Kai Zeng

A fast CT reconstruction scheme for a general multi-core PC

Expensive computational cost is a severe limitation in CT reconstruction for clinical applications that need real-time feedback. A primary example is bolus-chasing computed tomography (CT) angiography (BCA) that we have been developing for the past several years. To accelerate the reconstruction process using the filtered backprojection (FBP) method, specialized hardware or graphics cards can be used. However, specialized hardware is expensive and not flexible. The graphics processing unit (GPU) in a current graphic card can only reconstruct images in a reduced precision and is not easy to program. In this paper, an acceleration scheme is proposed based on a multi-core PC. In the proposed scheme, several techniques are integrated, including utilization of geometric symmetry, optimization of data structures, single-instruction multiple-data (SIMD) processing, multithreaded computation, and an Intel C++ compilier. Our scheme maintains the original precision and involves no data exchange between the GPU and CPU. The merits of our scheme are demonstrated in numerical experiments against the traditional implementation. Our scheme achieves a speedup of about 40, which can be further improved by several folds using the latest quad-core processors.

An error-reduction-based algorithm for cone-beam computed tomography.

Image reconstruction from cone-beam projections collected along a single circular source trajectory is commonly done using the Feldkamp algorithm, which performs well only with a small cone angle. In this report, we propose an error-reduction-based algorithm to increase the cone angle by several folds to achieve satisfactory image quality at the same radiation dose. In our scheme, we first reconstruct the object using the Feldkamp algorithm. Then, we synthesize cone-beam projection data from the reconstructed volume in the same geometry, and reconstruct the volume again from the synthesized projections. Finally, these two reconstruction results are combined to reduce the reconstruction error and produce a superior image volume. The merit of this algorithm is demonstrated in numerical simulation.

Spatial resolution enhancement in CT iterative reconstruction

Iterative reconstruction (IR) has recently been proposed to improve multiple aspects of image quality over conventional filtered backprojection (FBP) in X-ray computed tomography (CT). FBP reconstruction and its corresponding reconstruction kernels have been optimized for decades to provide the best possible image quality. IR does not have the notion of reconstruction kernels but uses other mechanisms to change the image resolution and image noise. This paper presents one computationally efficient technique to enhance the spatial resolution of IR images reconstructed from high resolution scans, based on the introduction of an enlarged voxel footprint in the forward model, combined with a band-suppression filter designed to eliminate any undesirable over- or under-shoot artifacts that may arise from the use of the enlarged voxels. The proposed technique achieves higher spatial resolution than high resolution FBP with significantly lower noise. Results are shown on both phantom and clinical patient data.

Completeness map evaluation demonstrated with candidate next‐generation cardiac CT architectures

PURPOSE In this report, the authors introduce the general concept of the completeness map, as a means to evaluate the completeness of data acquired by a given CT system design (architecture and scan mode). They illustrate the utility of completeness map by applying the completeness map concept to a number of candidate CT system designs, as part of a study to advance the state-of-the-art in cardiac CT. METHODS In order to optimally reconstruct a point within a volume of interest (VOI), the Radon transform on all possible planes through that point should be measured. The authors quantified the extent to which this ideal condition is satisfied for the entire image volume. They first determined a Radon completeness number for each point in the VOI, as the percentage of possible planes that is actually measured. A completeness map is then defined as a 3D matrix of the completeness numbers for the entire VOI. The authors proposed algorithms to analyze the projection datasets in Radon space and compute the completeness number for a fixed point and apply these algorithms to various architectures and scan modes that they are evaluating. In this report, the authors consider four selected candidate architectures, operating with different scan modes, for a total of five system design alternatives. Each of these alternatives is evaluated using completeness map. RESULTS If the detector size and cone angle are large enough to cover the entire cardiac VOI, a single-source circular scan can have ≥99% completeness over the entire VOI. However, only the central z-slice can be exactly reconstructed, which corresponds to 100% completeness. For a typical single-source architecture, if the detector is limited to an axial dimension of 40 mm, a helical scan needs about five rotations to form an exact reconstruction region covering the cardiac VOI, while a triple-source helical scan only requires two rotations, leading to a 2.5x improvement in temporal resolution. If the source and detector of an inverse-geometry (IGCT) system have the same axial extent, and the spacing of source points in the axial and transaxial directions is sufficiently small, the IGCT can also form an exact reconstruction region for the cardiac VOI. If the VOI can be covered by the x-ray beam in any view, a composite-circling scan can generate an exact reconstruction region covering the VOI. CONCLUSIONS The completeness map evaluation provides useful information for selecting the next-generation cardiac CT system design. The proposed completeness map method provides a practical tool for analyzing complex scanning trajectories, where the theoretical image quality for some complex system designs is impossible to predict, without yet-undeveloped reconstruction algorithms.

Cone-beam mammo-computed tomography from data along two tilting arcs

Over the past several years there has been an increasing interest in cone-beam computed tomography (CT) for breast imaging. In this article, we propose a new scheme for theoretically exact cone-beam mammo-CT and develop a corresponding Katsevich-type reconstruction algorithm. In our scheme, cone-beam scans are performed along two tilting arcs to collect a sufficient amount of information for exact reconstruction. In our algorithm, cone-beam data are filtered in a shift-invariant fashion and then weighted backprojected into the three-dimensional space for the final reconstruction. Our approach has several desirable features, including tolerance of axial data truncation, efficiency in sequential/parallel implementation, and accuracy for quantitative analysis. We also demonstrate the system performance and clinical utility of the proposed technique in numerical simulations.

A preliminary investigation of 3D preconditioned conjugate gradient reconstruction for cone-beam CT

Model-based iterative reconstruction (MBIR) methods based on maximum a posteriori (MAP) estimation have been recently introduced to multi-slice CT scanners. The model-based approach has shown promising image quality improvement with reduced radiation dose compared to conventional FBP methods, but the associated high computation cost limits its widespread use in clinical environments. Among the various choices of numerical algorithms to optimize the MAP cost function, simultaneous update methods such as the conjugate gradient (CG) method have a relatively high level of parallelism to take full advantage of a new generation of many-core computing hardware. With proper preconditioning techniques, fast convergence speeds of CG algorithms have been demonstrated in 3D emission and 2D transmission reconstruction. However, 3D transmission reconstruction using preconditioned conjugate gradient (PCG) has not been reported. Additional challenges in applying PCG in 3D CT reconstruction include the large size of clinical CT data, shift-variant and incomplete sampling, and complex regularization schemes to meet the diagnostic standard of image quality. In this paper, we present a ramp-filter based PCG algorithm for 3D CT MBIR. Convergence speeds of algorithms with and without using the preconditioner are compared.

Digital tomosynthesis aided by low-resolution exact computed tomography.

Tomosynthesis reconstructs 3-dimensional images of an object from a significantly fewer number of projections as compared with that required by computed tomography (CT). A major problem with tomosynthesis is image artifacts associated with the data incompleteness. In this article, we propose a hybrid tomosynthesis approach to achieve higher image quality as compared with competing methods. In this approach, a low-resolution CT scan is followed by a high-resolution tomosynthesis scan. Then, both scans are combined to reconstruct images. To evaluate the image quality of the proposed method, we design a new breast phantom for numerical simulation and physical experiments. The results show that images obtained by our approach are clearly better than those obtained without such a CT scan.

Cardiac CT: A system architecture study.

BACKGROUND We are interested in exploring dedicated, high-performance cardiac CT systems optimized to provide the best tradeoff between system cost, image quality, and radiation dose. OBJECTIVE We sought to identify and evaluate a broad range of CT architectures that could provide an optimal, dedicated cardiac CT solution. METHODS We identified and evaluated thirty candidate architectures using consistent design choices. We defined specific evaluation metrics related to cost and performance. We then scored the candidates versus the defined metrics. Lastly, we applied a weighting system to combine scores for all metrics into a single overall score for each architecture. CT experts with backgrounds in cardiovascular radiology, x-ray physics, CT hardware and CT algorithms performed the scoring and weighting. RESULTS We found nearly a twofold difference between the most and the least promising candidate architectures. Architectures employed by contemporary commercial diagnostic CT systems were among the highest-scoring candidates. We identified six architectures that show sufficient promise to merit further in-depth analysis and comparison. CONCLUSION Our results suggest that contemporary diagnostic CT system architectures outperform most other candidates that we evaluated, but the results for a few alternatives were relatively close. We selected six representative high-scoring candidates for more detailed design and further comparative evaluation.

SU-C-134-03: Selecting a Cardiac-Specific CT System Architecture

PURPOSE To identify the most promising system architecture(s) for a cardiac CT-specific scanner of the future by performing a broad search and comparative evaluation of candidate architectures. METHODS We first performed a literature survey and consulted with cardiologists in order to identify the critical requirements for a cardiac CT scanner. Based on these requirements, we considered a broad range of potential architectures. We developed a scoring system to rate these candidates with respect to performance, development simplicity, and production cost (value). We applied our scoring system to identify the most promising candidate architectures. We then performed a more detailed analysis of six high-scoring candidates; we evaluated the detailed results using a Six Sigma Priority Matrix. RESULTS We identified the following key requirements for a cardiac-specific CT scanner: 300 mm transaxial field of view (FOV); 160 mm longitudinal coverage; 50 ms temporal resolution; 20 lp/mm spatial resolution; 10 Hounsfield Units (HU) noise; and <1 mSv radiation dose. Facilitated using TRIZ methods, we identified thirty potential architectures that could be applied for a cardiac-specific CT scanner. These architectures were selected from classes including single-and multiple-source/detector third-generation designs; designs with multiple focal spots in one and two dimensions; a variety of fully-and semi-stationary designs; and two rather novel concepts. Of these, we ultimately identified two architectures that best satisfy the key requirements and are most likely to provide a solution as a high performance CT scanner of the future: a triple-source system and an arc-source system. CONCLUSION This work indicates that there is an opportunity to develop a CT system specifically for cardiac imaging that can substantially exceed the performance of contemporary general-purpose CT scanners, and provide very high temporal resolution, diagnostic quality images of the entire heart, at very low radiation dose. This work was supported by NIH/NIBIB grant EB011785.

Geometrical study on two tilting arcs based exact cone-beam CT for breast imaging

Breast cancer is the second leading cause of cancer death in women in the United States. Currently, X-ray mammography is the method of choice for screening and diagnosing breast cancer. However, this 2D projective modality is far from perfect; with up to 17% breast cancer going unidentified. Over past several years, there has been an increasing interest in cone-beam CT for breast imaging. However, previous methods utilizing cone-beam CT only produce approximate reconstructions. Following Katsevichs recent work, we propose a new scanning mode and associated exact cone-beam CT method for breast imaging. In our design, cone-beam scans are performed along two tilting arcs for collection of a sufficient amount of data for exact reconstruction. In our Katsevich-type algorithm, conebeam data is filtered in a shift-invariant fashion and then backprojected in 3D for the final reconstruction. This approach has several desirable features. First, it allows data truncation unavoidable in practice. Second, it optimizes image quality for quantitative analysis. Third, it is efficient for sequential/parallel computation. Furthermore, we analyze the reconstruction region and the detection window in detail, which are important for numerical implementation.