Artificial Intelligence-Based Image Reconstruction for Computed Tomography: A Survey

Attention-driven complementary information fusion network for sparse photoacoustic image reconstruction.

Pulmonary emphysema quantification at low dose chest CT using Deep Learning image reconstruction

Heightened concerns over increasing radiation dose from CT scanning have highlighted limitations of real-time image reconstruction methods using conventional filtered back-projection techniques. Significant advances in computational power have enabled commercial availability of several iterative approaches for CT image reconstruction and processing. These techniques enable radiation dose reduction, as well as opportunity to improve scanner resolution, while reducing some image artifacts. In this chapter, we review the technical basis of conventional and newer reconstruction techniques for CT.

Non-contrast cerebral computed tomography (CT) is frequently performed as a first-line diagnostic approach in patients with suspected ischemic stroke. The purpose of this study was to evaluate the performance of hybrid and model-based iterative image reconstruction for standard-dose (SD) and low-dose (LD) non-contrast cerebral imaging by multi-detector CT (MDCT). We retrospectively analyzed 131 patients with suspected ischemic stroke (mean age: 74.2 ± 14.3 years, 67 females) who underwent initial MDCT with a SD protocol (300 mAs) as well as follow-up MDCT after a maximum of 10 days with a LD protocol (200 mAs). Ischemic demarcation was detected in 26 patients for initial and in 64 patients for follow-up imaging, with diffusion-weighted magnetic resonance imaging (MRI) confirming ischemia in all of those patients. The non-contrast cerebral MDCT images were reconstructed using hybrid (Philips “iDose4”) and model-based iterative (Philips “IMR3”) reconstruction algorithms. Two readers assessed overall image quality, anatomic detail, differentiation of gray matter (GM)/white matter (WM), and conspicuity of ischemic demarcation, if any. Quantitative assessment included signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) calculations for WM, GM, and demarcated areas. Ischemic demarcation was detected in all MDCT images of affected patients by both readers, irrespective of the reconstruction method used. For LD imaging, anatomic detail and GM/WM differentiation was significantly better when using the model-based iterative compared to the hybrid reconstruction method. Furthermore, CNR of GM/WM as well as the SNR of WM and GM of healthy brain tissue were significantly higher for LD images with model-based iterative reconstruction when compared to SD or LD images reconstructed with the hybrid algorithm. For patients with ischemic demarcation, there was a significant difference between images using hybrid versus model-based iterative reconstruction for CNR of ischemic/contralateral unaffected areas (mean ± standard deviation: SD_IMR: 4.4 ± 3.1, SD_iDose: 3.5 ± 2.3, P < 0.0001; LD_IMR: 4.6 ± 2.9, LD_iDose: 3.2 ± 2.1, P < 0.0001). In conclusion, model-based iterative reconstruction provides higher CNR and SNR without significant loss of image quality for non-enhanced cerebral MDCT.

In recent several years, motivated by the need to reduce radiation doses in CT exams, all of the major CT manufacturers have commercialized different iterative image reconstruction techniques and these innovative techniques were used in clinical routines with increasing popularity. However, due to the intrinsic nonlinearity of these new techniques, the well accepted quantitative image quality assessment metrics such as spatial resolution and contrast to noise ratio are not sufficient to provide the needed quantitative metrics for assessing image quality and for guiding the CT scan protocol optimization. This symposium aims at providing a thorough update to AAPM community on what we have understood in the past for linear CT imaging system, what are the new challenges and opportunities offered by the nonlinear iterative image reconstruction, and what would be the future directions in quantitative image quality assessment that the AAPM community can work together to address the challenges and to adapt the nonlinear image reconstruction methods to routine clinical practice to improve patient care. Three invited speakers will lead the discussions in this symposium.Dr. Ke Li from the University of Wisconsin‐Madison will be presenting the new challenges introduced in model‐based iterative reconstruction (MBIR) method with a focus on how the nonlinear nature of the MBIR reconstruction poses challenges in quantitative image quality metrics such as spatial resolution, noise power spectrum, and the limitations of CNR in protocol optimization which eventually leads to the need of task‐based detectability index as the metric.Dr. Shuai Leng from Mayo Clinic will then present how the CNR metric is insufficient for nonlinear reconstruction algorithms, and how task based model observers can be used to more accurately quantify image quality, and to optimize imaging system and scanning protocols for nonlinear iterative image reconstruction algorithms based on specific imaging task. Practical considerations regarding the application of task based image quality metrics will also be discussed.Dr. Ehsan Samei from Duke University will start the symposium by summarizing a to‐be‐released AAPM Task Group report (TG 233: Performance Evaluation of Computed Tomography Systems). He will cover what has been understood and accepted for linear CT imaging system, what are the new challenges in CT image quality assessment introduced by the nonlinear iterative reconstruction (IR) techniques, and summarize both taskneutral and task‐based metrologies developed in TG 233 to partially address these challenges, and foresee additional challenges in the future. Learning Objectives: Understand the challenges in quantitative image quality assessment introduced by nonlinear iterative reconstruction techniques Understand the challenges and methods in noise performance assessment for nonlinear iterative reconstruction techniques Understand the challenges and methods in in spatial resolution assessment for nonlinear iterative reconstruction techniques Understand the challenges and methods in in task‐based observer performance assessment for nonlinear iterative reconstruction techniquesFunding support received from NIH and DOD; Funding support received from GE Healthcare; Funding support received from Siemens AX; Patent royalties received from GE Healthcare; S. Leng, R01 EB071095; U01 EB017185; E. Samei, Research grant, Siemens; Research grant, GE; K. Li, Funding from NIH, DOD and AAPM

This work assesses the one-step late maximum likelihood expectation maximization (OSL-MLEM) 4D PET reconstruction algorithm for direct estimation of parametric images from raw PET data when using the simplified reference tissue model with the basis function method (SRTM-BFM) for the kinetic analysis. To date, the OSL-MLEM method has been evaluated using kinetic models based on two-tissue compartments with an irreversible component. We extend the evaluation of this method for two-tissue compartments with a reversible component, using SRTM-BFM on simulated 3D + time data sets (with use of [11C]raclopride time-activity curves from real data) and on real data sets acquired with the high resolution research tomograph. The performance of the proposed method is evaluated by comparing voxel-level binding potential (BPND) estimates with those obtained from conventional post-reconstruction kinetic parameter estimation. For the commonly chosen number of iterations used in practice, our results show that for the 3D + time simulation, the direct method delivers results with lower %RMSE at the normal count level (decreases of 9–10 percentage points, corresponding to a 38–44% reduction), and also at low count levels (decreases of 17–21 percentage points, corresponding to a 26–36% reduction). As for the real 3D data set, the results obtained follow a similar trend, with the direct reconstruction method offering a 21% decrease in %CV compared to the post reconstruction method at low count levels. Thus, based on the results presented herein, using the SRTM-BFM kinetic model in conjunction with the OSL-MLEM direct 4D PET MLEM reconstruction method offers an improvement in performance when compared to conventional post reconstruction methods.

The goal of this paper is to reduce the antenna count in a millimeter (mm)-wave imaging system by proposing both hardware and software solutions. The concept of image sparsity in the transform domain is utilized to present the compressive sensing (CS) formulation for both mono-static and multistatic imaging at mm-wave frequencies. To reduce the complexity of the imaging system and reconstruction process, we introduce 1.5-D array structure, which is a random sparse array with orthogonal element locations. It is shown that the peak signal-to-noise ratio (PSNR) of the reconstructed image obtained by a 1.5-D array with 65% sparsity is very close to the PSNR of a uniform 2-D array for mono-static imaging. Moreover, for multistatic imaging, it is illustrated that a high-quality image is reconstructed with 92% reduction in antenna elements, which significantly reduces the cost, scan time, and system complexity. Furthermore, a 1.5-D array of 16 patch antennas with 60% sparsity, operating from 29 to 32 GHz is designed and implemented to investigate the performance of the proposed 1.5-D array for imaging, as well as the presented CS-based reconstruction method. Measurements show that the quality of the reconstructed image using this 1.5-D array with CS-based reconstruction is very close to a full 2-D array; for example, the PSNR achieved for the reconstructed image of a knife is 33 dB referenced to a uniform 2-D array. The proposed reconstruction method results in 6–11 dB improvement in PSNR compared with the conventional reconstruction methods with a reasonable increase in computing load.

We evaluated the feasibility of sub-millisievert (mSv) coronary CT angiography (CCTA) using low tube voltage, prospective ECG gating, and a knowledge-based iterative model reconstruction algorithm. Twenty-four non-obese healthy subjects (M:F 13:11; mean age 50.2±7.8years) were enrolled. Three sets of CT images were reconstructed using three different reconstruction methods: filtered back projection (FBP), iterative reconstruction (IR), and knowledge-based iterative model reconstruction (IMR). The scanning parameters were as follows: step-and-shoot axial scanning, 80kVp, and 200mAs. On the three sets of CT images, the attenuation and image noise values were measured at the aortic root. The signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were calculated at the proximal right coronary artery and the left main coronary artery. The qualitative image quality of the CCTA with IMR was assessed using a 4-point grading scale (grade 1, poor; grade 4, excellent). The mean radiation dose of the CCTA was 0.89±0.09mSv. The attenuation values with IMR were not different from those of other reconstruction methods. The image noise with IMR was significantly lower than with IR and FBP. Compared to FBP, the noise reduction rate of IMR was 69%. The SNR and CNR of CCTA with IMR were significantly higher than with FBP or IR. On the qualitative analysis with IMR, all included segments were diagnostic (grades 2, 3, and 4), and the mean image quality score was 3.6±0.6. In conclusion, CCTA with low tube voltage, prospective ECG gating, and an IMR algorithm might be a feasible method that allows for sub-millisievert radiation doses and good image quality when used with non-obese subjects.

Image reconstruction is a crucial aspect of computational imaging. The compressed sensing reconstruction (CS) method has been developed to obtain high-quality images. However, the CS method is commonly time-consuming in image reconstruction. To overcome this drawback, we propose a compressed sensing reconstruction method with fast convolution filtering (F-CS method), which significantly increases reconstruction speed by reducing the number of convolution operations without image fill. The experimental results show that by using the F-CS method, the reconstruction speed can be increased by a factor of 7 compared to the conventional CS method. Moreover, the F-CS method proposed in this paper is compared with the back-propagation reconstruction (BP) method and super-resolution reconstruction (SR) method, and it is validated that the proposed method has a lower computational resource cost for high-quality image reconstruction and exhibits a much more balanced capability.

In the past decade, the compressive sensing (CS) based ISAR imaging methods have gained much interest due to the capability of obtaining high-quality images with under-sampled data. However, both the performance and the application of CS ISAR imaging methods are limited by sparse representations and iterative reconstruction algorithms where the former may be hard to find and the latter may lead to low imaging efficiency. The deep-network (DN) based image reconstruction methods appeared in recent years have been shown to be able to dramatically reduce the computational complexity and ensure the image reconstruction at the same time. The Deep-ADMM-Net (DAN) is a network constructed by iterative steps of the traditional optimization algorithm, Alternating Direction Method of Multipliers (ADMM). The mainly characteristic of DAN is that it is interpretable and efficient. We propose a DAN based ISAR imaging method. The well trained DAN can reconstruct high-quality ISAR image using much fewer measurements than CS based imaging methods. Experimental results show that our proposed imaging method is superior to the existing CS method in both image reconstruction quality and computational efficiency

Sparse-view reconstruction for photoacoustic tomography combining diffusion model with model-based iteration

Due to the correlated nature of diffused light, the problem of reconstructing optical properties using diffuse optical tomography (DOT) is ill-posed. US-, MRI- or x-ray-guided DOT approaches can reduce the total number of parameters to be estimated and improve optical reconstruction accuracy. However, when the target volume is large, the number of parameters to estimate can exceed the number of measurements, resulting in an underdetermined imaging model. In such cases, accurate image reconstruction is difficult and regularization methods should be employed to obtain a useful solution. In this manuscript, a simple two-step reconstruction method that can produce useful image estimates in DOT is proposed and investigated. In the first step, a truncated Moore-Penrose Pseudoinverse solution is computed to obtain a preliminary estimate of the image that can be reliably determined from the measured data; subsequently, this preliminary estimate is incorporated into the design of a penalized least squares estimator that is employed to compute the final image estimate. By use of phantom data, the proposed method was demonstrated to yield more accurate images than those produced by conventional reconstruction methods. The method was also evaluated with clinical data that included 10 benign and 10 malignant cases. The capability of reconstructing high contrast malignant lesions was demonstrated to be improved by use of the proposed method.

Reconstruction of parametric images from dynamic single photon emission computed tomography (SPECT) data acquired with slow rotating cameras is a challenge because the estimation of the time-activity curves (TACs) may involve fitting data to an inconsistent underdetermined system of equations. This work presents a novel algorithm for the estimation of the blood input function and myocardial TAC with high accuracy and high efficiency directly from these projections. In the proposed dynamic reconstruction method, the information from the segmentation of functional regions from the static reconstructed image was used as a prior to construct a sparse matrix, through which the spatial distribution of the radioactive tracer was represented. Then the temporal distribution of the radioactive tracer was modeled by nonuniform B-spline basis functions which were determined according to a new selection rule. With reduction in both the spatial and temporal dimensions of the reconstructed image, the blood input function and myocardial TAC were estimated using the 4D maximum likelihood expectation maximization algorithm. The method was validated using data from both digital phantom simulations and an experimental rat study. Compared with the conventional dynamic SPECT reconstruction method without the reduction in spatial dimensions, the proposed method provides more accurate TACs with less computation time in both phantom simulation studies and a rat experimental study. The proposed method is promising in both providing more accurate time-activity curves and reducing the computation time, which makes it practical for small animal studies using clinical systems with slow rotating cameras.

BackgroundIterative computed tomography (CT) image reconstruction shows high potential for the preservation of image quality in diagnostic CT while reducing patients’ exposure; it has become available for low-dose CT (LD-CT) in high-end hybrid imaging systems (e.g. single-photon emission computed tomography [SPECT]-CT).PurposeTo examine the effect of an iterative CT reconstruction algorithm on image quality, image noise, detectability, and the reader’s confidence for LD-CT data by a subjective assessment.Material and MethodsThe LD-CT data were validated for 40 patients examined by an abdominal hybrid SPECT-CT (U = 120 kV, I = 40 mA, pitch = 1.375). LD-CT was reconstructed using either filtered back projection (FBP) or an iterative image reconstruction algorithm (Adaptive Statistical Iterative Reconstruction [ASIR]®) with different parameters (ASIR levels 50% and 100%). The data were validated by two independent blinded readers using a scoring system for image quality, image noise, detectability, and reader confidence, for a predefined set of 16 anatomic substructures.ResultsThe image quality was significantly improved by iterative reconstruction of the LD-CT data compared with FBP (P ≤ 0.0001). While detectability increased in only 2/16 structures (P ≤ 0.03), the reader’s confidence increased significantly due to iterative reconstruction (P ≤ 0.002). Meanwhile, at the ASIR level of 100%, the detectability in bone structure was highly reduced (P = 0.003).ConclusionAn ASIR level of 50% represents a good compromise in abdominal LD-CT image reconstruction. The specific ASIR level improved image quality (reduced image noise) and reader confidence, while preserving detectability of bone structure.

Super-Resolution Image Reconstruction Using Diffuse Source Models