Cine cone beam CT reconstruction using low-rank matrix factorization: algorithm and a proof-of-principle study

A review on 4D cone-beam CT (4D-CBCT) in radiation therapy: Technical advances and clinical applications

Cone-beam CT (CBCT) is the most commonly used onboard imaging technique for target localization in radiation therapy. Conventional 3D CBCT acquires x-ray cone-beam projections at multiple angles around the patient to reconstruct 3D images of the patient in the treatment room. However, despite its wide usage, 3D CBCT is limited in imaging disease sites affected by respiratory motions or other dynamic changes within the body, as it lacks time-resolved information. To overcome this limitation, 4D-CBCT was developed to incorporate a time dimension in the imaging to account for the patient's motion during the acquisitions. For example, respiration-correlated 4D-CBCT divides the breathing cycles into different phase bins and reconstructs 3D images for each phase bin, ultimately generating a complete set of 4D images. 4D-CBCT is valuable for localizing tumors in the thoracic and abdominal regions where the localization accuracy is affected by respiratory motions. This is especially important for hypofractionated stereotactic body radiation therapy (SBRT), which delivers much higher fractional doses in fewer fractions than conventional fractionated treatments. Nonetheless, 4D-CBCT does face certain limitations, including long scanning times, high imaging doses, and compromised image quality due to the necessity of acquiring sufficient x-ray projections for each respiratory phase. In order to address these challenges, numerous methods have been developed to achieve fast, low-dose, and high-quality 4D-CBCT. This paper aims to review the technical developments surrounding 4D-CBCT comprehensively. It will explore conventional algorithms and recent deep learning-based approaches, delving into their capabilities and limitations. Additionally, the paper will discuss the potential clinical applications of 4D-CBCT and outline a future roadmap, highlighting areas for further research and development. Through this exploration, the readers will better understand 4D-CBCT's capabilities and potential to enhance radiation therapy.

Low-dose CT reconstruction using dataset-free learning

Low-Dose computer tomography (LDCT) is an ideal alternative to reduce radiation risk in clinical applications. Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging. In this paper, we propose an unsupervised and training data-free learning reconstruction method for LDCT imaging that avoids the requirement for training data. The proposed method is a post-processing technique that aims to enhance the initial low-quality reconstruction results, and it reconstructs the high-quality images by neural work training that minimizes the ℓ1-norm distance between the CT measurements and their corresponding simulated sinogram data, as well as the total variation (TV) value of the reconstructed image. Moreover, the proposed method does not require to set the weights for both the data fidelity term and the plenty term. Experimental results on the AAPM challenge data and LoDoPab-CT data demonstrate that the proposed method is able to effectively suppress the noise and preserve the tiny structures. Also, these results demonstrate the rapid convergence and low computational cost of the proposed method. The source code is available at https://github.com/linfengyu77/IRLDCT.

Dynamic CBCT imaging using prior model-free spatiotemporal implicit neural representation (PMF-STINR)

Objective. Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few x-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g. breathing).Approach. We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired x-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular x-ray projections. Specifically, PMF-STINR uses spatial implicit neural representations to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion of the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning.Main results. PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (∼ 0.1 s) resolution and sub-millimeter accuracy.Significance. PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.

Deep learning-based algorithms for low-dose CT imaging: A review

The computed tomography (CT) technique is extensively employed as an imaging modality in clinical settings. The radiation dose of CT, however, is significantly high, thereby raising concerns regarding the potential radiation damage it may cause. The reduction of X-ray exposure dose in CT scanning may result in a significant decline in imaging quality, thereby elevating the risk of missed diagnosis and misdiagnosis. The reduction of CT radiation dose and acquisition of high-quality images to meet clinical diagnostic requirements have always been a critical research focus and challenge in the field of CT. Over the years, scholars have conducted extensive research on enhancing low-dose CT (LDCT) imaging algorithms, among which deep learning-based algorithms have demonstrated superior performance. In this review, we initially introduced the conventional algorithms for CT image reconstruction along with their respective advantages and disadvantages. Subsequently, we provided a detailed description of four aspects concerning the application of deep neural networks in LDCT imaging process: preprocessing in the projection domain, post-processing in the image domain, dual-domain processing imaging, and direct deep learning-based reconstruction (DLR). Furthermore, an analysis was conducted to evaluate the merits and demerits of each method. The commercial and clinical applications of the LDCT-DLR algorithm were also presented in an overview. Finally, we summarized the existing issues pertaining to LDCT-DLR and concluded the paper while outlining prospective trends for algorithmic advancement.

Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior

Purpose Numerous techniques based on deep learning have been utilized in sparse view computed tomography (CT) imaging. Nevertheless, the majority of techniques are instinctively constructed utilizing state-of-the-art opaque convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields and neglect nonlocal self-similarity prior information. Obtaining diagnostically valuable images from sparsely sampled projections is a challenging and ill-posed task. Method To address this issue, we propose a unique and understandable model named DCDL-GS for sparse view CT imaging. This model relies on a network comprised of convolutional dictionary learning and a nonlocal group sparse prior. To enhance the quality of image reconstruction, we utilize a neural network in conjunction with a statistical iterative reconstruction framework and perform a set number of iterations. Inspired by group sparsity priors, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Furthermore, our DCDL-GS model incorporates filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight and interpretable convolutional dictionary learning network to enhance the applicability of the model. Results The efficiency of our proposed DCDL-GS model in preserving edges and recovering features is demonstrated by the visual results obtained on the LDCT-P and UIH datasets. Compared to the results of the most advanced techniques, the quantitative results are enhanced, with increases of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse prior. Conclusion In this paper, we create a consolidated and enhanced mathematical model by integrating projection data and prior knowledge of images into a deep iterative model. The model is more practical and interpretable than existing approaches. The results from the experiment show that the proposed model performs well in comparison to the others.

A two-stage deep-learning framework for CT denoising based on a clinically structure-unaligned paired data set

Background

In low-dose computed tomography (LDCT) lung cancer screening, soft tissue is hardly appreciable due to high noise levels. While deep learning-based LDCT denoising methods have shown promise, they typically rely on structurally aligned synthesized paired data, which lack consideration of the clinical reality that there are no aligned LDCT and normal-dose CT (NDCT) images available. This study introduces an LDCT denoising method using clinically structure-unaligned but paired data sets (LDCT and NDCT scans from the same patients) to improve lesion detection during LDCT lung cancer screening.

Methods

A cohort of 64 patients undergoing both LDCT and NDCT was randomly divided into training (n=46) and testing (n=18) sets. A two-stage training approach was adopted. First, Gaussian noise was added to NDCT data to create simulated LDCT data for generator training. Then, the model was trained on a clinically structure-unaligned paired data set using a Wasserstein generative adversarial network (WGAN) framework with the initial generator weights obtained during the first stage of training. An attention mechanism was also incorporated into the network.

Results

Validated on a clinical CT data set, our proposed method outperformed other available methods [CycleGAN, Pixel2Pixel, block-matching and three-dimensional filtering (BM3D)] in noise removal and detail retention tasks in terms of the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and root mean square error (RMSE) metrics. Compared with the results produced by BM3D, our method yielded an average improvement of approximately 7% in terms of the three evaluation indicators. The probability density profile of the denoised CT output produced using our method best fit the reference NDCT scan. Additionally, our two-stage model outperformed the one-stage WGAN-based model in both objective and subjective evaluations, further demonstrating the higher effectiveness of our two-stage training approach.

Conclusions

The proposed method performed the best in removing noise from LDCT scans and exhibited good detail retention, which could potentially enhance the lesion detection and characterization effects obtained for soft tissues in the scanning scope of LDCT lung cancer screening.

Spatiotemporal image reconstruction to enable high-frame-rate dynamic photoacoustic tomography with rotating-gantry volumetric imagers

Significance

Dynamic photoacoustic computed tomography (PACT) is a valuable imaging technique for monitoring physiological processes. However, current dynamic PACT imaging techniques are often limited to two-dimensional spatial imaging. Although volumetric PACT imagers are commercially available, these systems typically employ a rotating measurement gantry in which the tomographic data are sequentially acquired as opposed to being acquired simultaneously at all views. Because the dynamic object varies during the data-acquisition process, the sequential data-acquisition process poses substantial challenges to image reconstruction associated with data incompleteness. The proposed image reconstruction method is highly significant in that it will address these challenges and enable volumetric dynamic PACT imaging with existing preclinical imagers.

Aim

The aim of this study is to develop a spatiotemporal image reconstruction (STIR) method for dynamic PACT that can be applied to commercially available volumetric PACT imagers that employ a sequential scanning strategy. The proposed reconstruction method aims to overcome the challenges caused by the limited number of tomographic measurements acquired per frame.

Approach

A low-rank matrix estimation-based STIR (LRME-STIR) method is proposed to enable dynamic volumetric PACT. The LRME-STIR method leverages the spatiotemporal redundancies in the dynamic object to accurately reconstruct a four-dimensional (4D) spatiotemporal image.

Results

The conducted numerical studies substantiate the LRME-STIR method's efficacy in reconstructing 4D dynamic images from tomographic measurements acquired with a rotating measurement gantry. The experimental study demonstrates the method's ability to faithfully recover the flow of a contrast agent with a frame rate of 10 frames per second, even when only a single tomographic measurement per frame is available.

Conclusions

The proposed LRME-STIR method offers a promising solution to the challenges faced by enabling 4D dynamic imaging using commercially available volumetric PACT imagers. By enabling accurate STIRs, this method has the potential to significantly advance preclinical research and facilitate the monitoring of critical physiological biomarkers.

Dynamic CBCT Imaging using Prior Model-Free Spatiotemporal Implicit Neural Representation (PMF-STINR)

Objective

Dynamic cone-beam computed tomography (CBCT) can capture high-spatial-resolution, time-varying images for motion monitoring, patient setup, and adaptive planning of radiotherapy. However, dynamic CBCT reconstruction is an extremely ill-posed spatiotemporal inverse problem, as each CBCT volume in the dynamic sequence is only captured by one or a few X-ray projections, due to the slow gantry rotation speed and the fast anatomical motion (e.g., breathing).

Approach

We developed a machine learning-based technique, prior-model-free spatiotemporal implicit neural representation (PMF-STINR), to reconstruct dynamic CBCTs from sequentially acquired X-ray projections. PMF-STINR employs a joint image reconstruction and registration approach to address the under-sampling challenge, enabling dynamic CBCT reconstruction from singular X-ray projections. Specifically, PMF-STINR uses spatial implicit neural representation to reconstruct a reference CBCT volume, and it applies temporal INR to represent the intra-scan dynamic motion with respect to the reference CBCT to yield dynamic CBCTs. PMF-STINR couples the temporal INR with a learning-based B-spline motion model to capture time-varying deformable motion during the reconstruction. Compared with the previous methods, the spatial INR, the temporal INR, and the B-spline model of PMF-STINR are all learned on the fly during reconstruction in a one-shot fashion, without using any patient-specific prior knowledge or motion sorting/binning.

Main results

PMF-STINR was evaluated via digital phantom simulations, physical phantom measurements, and a multi-institutional patient dataset featuring various imaging protocols (half-fan/full-fan, full sampling/sparse sampling, different energy and mAs settings, etc.). The results showed that the one-shot learning-based PMF-STINR can accurately and robustly reconstruct dynamic CBCTs and capture highly irregular motion with high temporal (~0.1s) resolution and sub-millimeter accuracy.

Significance

PMF-STINR can reconstruct dynamic CBCTs and solve the intra-scan motion from conventional 3D CBCT scans without using any prior anatomical/motion model or motion sorting/binning. It can be a promising tool for motion management by offering richer motion information than traditional 4D-CBCTs.

StruNet: Perceptual and low-rank regularized transformer for medical image denoising

BACKGROUND

Various types of noise artifacts inevitably exist in some medical imaging modalities due to limitations of imaging techniques, which impair either clinical diagnosis or subsequent analysis. Recently, deep learning approaches have been rapidly developed and applied on medical images for noise removal or image quality enhancement. Nevertheless, due to complexity and diversity of noise distribution representations in different medical imaging modalities, most of the existing deep learning frameworks are incapable to flexibly remove noise artifacts while retaining detailed information. As a result, it remains challenging to design an effective and unified medical image denoising method that will work across a variety of noise artifacts for different imaging modalities without requiring specialized knowledge in performing the task.

PURPOSE

In this paper, we propose a novel encoder-decoder architecture called Swin transformer-based residual u-shape Network (StruNet), for medical image denoising.

METHODS

Our StruNet adopts a well-designed block as the backbone of the encoder-decoder architecture, which integrates Swin Transformer modules with residual block in parallel connection. Swin Transformer modules could effectively learn hierarchical representations of noise artifacts via self-attention mechanism in non-overlapping shifted windows and cross-window connection, while residual block is advantageous to compensate loss of detailed information via shortcut connection. Furthermore, perceptual loss and low-rank regularization are incorporated into loss function respectively in order to constrain the denoising results on feature-level consistency and low-rank characteristics.

RESULTS

To evaluate the performance of the proposed method, we have conducted experiments on three medical imaging modalities including computed tomography (CT), optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA).

CONCLUSIONS

The results demonstrate that the proposed architecture yields a promising performance of suppressing multiform noise artifacts existing in different imaging modalities.

A cascade-based dual-domain data correction network for sparse view CT image reconstruction

Computed tomography (CT) provides non-invasive anatomical structures of the human body and is also widely used for clinical diagnosis, but excessive ionizing radiation in X-rays can cause harm to the human body. Therefore, the researchers obtained sparse sinograms reconstructed sparse view CT images (SVCT) by reducing the amount of X-ray projection, thereby reducing the radiological effects caused by radiation. This paper proposes a cascade-based dual-domain data correction network (CDDCN), which can effectively combine the complementary information contained in the sinogram domain and the image domain to reconstruct high-quality CT images from sparse view sinograms. Specifically, several encoder-decoder subnets are cascaded in the sinogram domain to reconstruct artifact-free and noise-free CT images. In the encoder-decoder subnets, spatial-channel domain learning is designed to achieve efficient feature fusion through a group merging structure, providing continuous and elaborate pixel-level features and improving feature extraction efficiency. At the same time, to ensure that the original sinogram data collected can be retained, a sinogram data consistency layer is proposed to ensure the fidelity of the sinogram data. To further maintain the consistency between the reconstructed image and the reference image, a multi-level composite loss function is designed for regularization to compensate for excessive smoothing and distortion of the image caused by pixel loss and preserve image details and texture. Quantitative and qualitative analysis shows that CDDCN achieves competitive results in artifact removal, edge preservation, detail restoration, and visual improvement for sparsely sampled data under different views.

MLNAN: Multi-level noise-aware network for low-dose CT imaging implemented with constrained cycle Wasserstein generative adversarial networks

Low-dose CT techniques attempt to minimize the radiation exposure of patients by estimating the high-resolution normal-dose CT images to reduce the risk of radiation-induced cancer. In recent years, many deep learning methods have been proposed to solve this problem by building a mapping function between low-dose CT images and their high-dose counterparts. However, most of these methods ignore the effect of different radiation doses on the final CT images, which results in large differences in the intensity of the noise observable in CT images. What'more, the noise intensity of low-dose CT images exists significantly differences under different medical devices manufacturers. In this paper, we propose a multi-level noise-aware network (MLNAN) implemented with constrained cycle Wasserstein generative adversarial networks to recovery the low-dose CT images under uncertain noise levels. Particularly, the noise-level classification is predicted and reused as a prior pattern in generator networks. Moreover, the discriminator network introduces noise-level determination. Under two dose-reduction strategies, experiments to evaluate the performance of proposed method are conducted on two datasets, including the simulated clinical AAPM challenge datasets and commercial CT datasets from United Imaging Healthcare (UIH). The experimental results illustrate the effectiveness of our proposed method in terms of noise suppression and structural detail preservation compared with several other deep-learning based methods. Ablation studies validate the effectiveness of the individual components regarding the afforded performance improvement. Further research for practical clinical applications and other medical modalities is required in future works.

Beam angle optimization for proton therapy via group-sparsity based angle generation method

BACKGROUND

In treatment planning, beam angle optimization (BAO) refers to the selection of a subset with a given number of beam angles from all available angles that provides the best plan quality. BAO is a NP-hard combinatorial problem. Although exhaustive search (ES) can exactly solve BAO by exploring all possible combinations, ES is very time-consuming and practically infeasible.

PURPOSE

To the best of our knowledge, (1) no optimization method has been demonstrated that can provide the exact solution to BAO, and (2) no study has validated an optimization method for solving BAO by benchmarking with the optimal BAO solution (e.g., via ES), both of which will be addressed by this work.

METHODS

This work considers BAO for proton therapy, for example, the selection of 2-4 beam angles for IMPT. The optimal BAO solution is obtained via ES and serves as the ground truth. A new BAO algorithm, namely angle generation (AG) method, is proposed, and demonstrated to provide nearly-exact solutions for BAO in reference to the ES solution. AG iteratively optimizes the angular set via group-sparsity (GS) regularization, until the planning objective does not decrease further.

RESULTS

Since GS alone can also solve BAO, AG was validated and compared with GS for 2-angle brain, 3-angle lung, and 4-angle brain cases, in reference to the optimal BAO solutions obtained by ES: the AG solution had the rank (1/276, 1/2024, 4/10 626), while the GS solution had the rank (42/276, 279/2024, 4328/10 626).

CONCLUSIONS

A new BAO algorithm called AG is proposed and shown to provide substantially improved accuracy for BAO from current methods with nearly-exact solutions to BAO, in reference to the ground truth of optimal BAO solution via ES.

Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

Since 2016, deep learning (DL) has advanced tomographic imaging with remarkable successes, especially in low-dose computed tomography (LDCT) imaging. Despite being driven by big data, the LDCT denoising and pure end-to-end reconstruction networks often suffer from the black box nature and major issues such as instabilities, which is a major barrier to apply deep learning methods in low-dose CT applications. An emerging trend is to integrate imaging physics and model into deep networks, enabling a hybridization of physics/model-based and data-driven elements. In this paper, we systematically review the physics/model-based data-driven methods for LDCT, summarize the loss functions and training strategies, evaluate the performance of different methods, and discuss relevant issues and future directions.

An iterative convex relaxation method for proton LET optimization

Objective:A constant relative biological effectiveness of 1.1 in current clinical practice of proton radiotherapy (RT) is a crude approximation and may severely underestimate the biological dose from proton RT to normal tissues, especially near the treatment target at the end of Bragg peaks that exhibits high linear energy transfer (LET). LET optimization can account for biological effectiveness of protons during treatment planning, for minimizing biological proton dose and hot spots to normal tissues. However, the LET optimization is usually nonlinear and nonconvex to solve, for which this work will develop an effective optimization method based on iterative convex relaxation (ICR).Approach: In contrast to the generic nonlinear optimization method, such as Quasi-Newton (QN) method, that does not account for specific characteristics of LET optimization, ICR is tailored to LET modeling and optimization in order to effectively and efficiently solve the LET problem. Specifically, nonlinear dose-averaged LET term is iteratively linearized and becomes convex during ICR, while nonconvex dose-volume constraint and minimum-monitor-unit constraint are also handled by ICR, so that the solution for LET optimization is obtained by solving a sequence of convex and linearized convex subproblems. Since the high LET mostly occurs near the target, a 1 cm normal-tissue expansion of clinical target volume (CTV) (excluding CTV), i.e. CTV1cm, is defined to as an auxiliary structure during treatment planning, where LET is minimized.Main results: ICR was validated in comparison with QN for abdomen, lung, and head-and-neck cases. ICR was effective for LET optimization, as ICR substantially reduced the LET and biological dose in CTV1cm the ring, with preserved dose conformality to CTV. Compared to QN, ICR had smaller LET, physical and biological dose in CTV1cm, and higher conformity index values; ICR was also computationally more efficient, which was about 3 times faster than QN.Significance: A LET-specific optimization method based on ICR has been developed for solving proton LET optimization, which has been shown to be more computationally efficient than generic nonlinear optimizer via QN, with better plan quality in terms of LET, biological and physical dose conformality.

Dynamic cone-beam CT reconstruction using spatial and temporal implicit neural representation learning (STINR)

Objective. Dynamic cone-beam CT (CBCT) imaging is highly desired in image-guided radiation therapy to provide volumetric images with high spatial and temporal resolutions to enable applications including tumor motion tracking/prediction and intra-delivery dose calculation/accumulation. However, dynamic CBCT reconstruction is a substantially challenging spatiotemporal inverse problem, due to the extremely limited projection sample available for each CBCT reconstruction (one projection for one CBCT volume).Approach. We developed a simultaneous spatial and temporal implicit neural representation (STINR) method for dynamic CBCT reconstruction. STINR mapped the unknown image and the evolution of its motion into spatial and temporal multi-layer perceptrons (MLPs), and iteratively optimized the neuron weightings of the MLPs via acquired projections to represent the dynamic CBCT series. In addition to the MLPs, we also introduced prior knowledge, in the form of principal component analysis (PCA)-based patient-specific motion models, to reduce the complexity of the temporal mapping to address the ill-conditioned dynamic CBCT reconstruction problem. We used the extended-cardiac-torso (XCAT) phantom and a patient 4D-CBCT dataset to simulate different lung motion scenarios to evaluate STINR. The scenarios contain motion variations including motion baseline shifts, motion amplitude/frequency variations, and motion non-periodicity. The XCAT scenarios also contain inter-scan anatomical variations including tumor shrinkage and tumor position change.Main results. STINR shows consistently higher image reconstruction and motion tracking accuracy than a traditional PCA-based method and a polynomial-fitting-based neural representation method. STINR tracks the lung target to an average center-of-mass error of 1-2 mm, with corresponding relative errors of reconstructed dynamic CBCTs around 10%.Significance. STINR offers a general framework allowing accurate dynamic CBCT reconstruction for image-guided radiotherapy. It is a one-shot learning method that does not rely on pre-training and is not susceptible to generalizability issues. It also allows natural super-resolution. It can be readily applied to other imaging modalities as well.

Segmentation-guided Denoising Network for Low-dose CT Imaging

BACKGROUND

To reduce radiation exposure and improve diagnosis in low-dose computed tomography, several deep learning (DL)-based image denoising methods have been proposed to suppress noise and artifacts over the past few years. However, most of them seek an objective data distribution approximating the gold standard and neglect structural semantic preservation. Moreover, the numerical response in CT images presents substantial regional anatomical differences among tissues in terms of X-ray absorbency.

METHODS

In this paper, we introduce structural semantic information for low-dose CT imaging. First, the regional segmentation prior to low-dose CT can guide the denoising process. Second the structural semantical results can be considered as evaluation metrics on the estimated normal-dose CT images. Then, a semantic feature transform is engaged to combine the semantic and image features on a semantic fusion module. In addition, the structural semantic loss function is introduced to measure the segmentation difference.

RESULTS

Experiments are conducted on clinical abdomen data obtained from a clinical hospital, and the semantic labels consist of subcutaneous fat, muscle and visceral fat associated with body physical evaluation. Compared with other DL-based methods, the proposed method achieves better performance on quantitative metrics and better semantic evaluation.

CONCLUSIONS

The quantitative experimental results demonstrate the promising performance of the proposed methods in noise reduction and structural semantic preservation. While, the proposed method may suffer from several limitations on abnormalities, unknown noise and different manufacturers. In the future, the proposed method will be further explored, and wider applications in PET/CT and PET/MR will be sought.

MRCON-Net: Multiscale reweighted convolutional coding neural network for low-dose CT imaging

BACKGROUND AND OBJECTIVE

Low-dose computed tomography (LDCT) has become increasingly important for alleviating X-ray radiation damage. However, reducing the administered radiation dose may lead to degraded CT images with amplified mottle noise and nonstationary streak artifacts. Previous studies have confirmed that deep learning (DL) is promising for improving LDCT imaging. However, most DL-based frameworks are built intuitively, lack interpretability, and suffer from image detail information loss, which has become a general challenging issue.

METHODS

A multiscale reweighted convolutional coding neural network (MRCON-Net) is developed to address the above problems. MRCON-Net is compact and more explainable than other networks. First, inspired by the learning-based reweighted iterative soft thresholding algorithm (ISTA), we extend traditional convolutional sparse coding (CSC) to its reweighted convolutional learning form. Second, we use dilated convolution to extract multiscale image features, allowing our single model to capture the correlations between features of different scales. Finally, to automatically adjust the elements in the feature code to correct the obtained solution, a channel attention (CA) mechanism is utilized to learn appropriate weights.

RESULTS

The visual results obtained based on the American Association of Physicians in Medicine (AAPM) Challenge and United Image Healthcare (UIH) clinical datasets confirm that the proposed model significantly reduces serious artifact noise while retaining the desired structures. Quantitative results show that the average structural similarity index measurement (SSIM) and peak signal-to-noise ratio (PSNR) achieved on the AAPM Challenge dataset are 0.9491 and 40.66, respectively, and the SSIM and PSNR achieved on the UIH clinical dataset are 0.915 and 42.44, respectively; these are promising quantitative results.

CONCLUSION

Compared with recent state-of-the-art methods, the proposed model achieves subtle structure-enhanced LDCT imaging. In addition, through ablation studies, the components of the proposed model are validated to achieve performance improvements.

Low-Rank and Framelet Based Sparsity Decomposition for Interventional MRI Reconstruction

OBJECTIVE

Interventional MRI (i-MRI) is crucial for MR image-guided therapy. Current image reconstruction methods for dynamic MR imaging are mostly retrospective that may not be suitable for i-MRI in real-time. Therefore, an algorithm to reconstruct images without a temporal pattern as in dynamic imaging is needed for i-MRI.

METHODS

We proposed a low-rank and sparsity (LS) decomposition algorithm with framelet transform to reconstruct the interventional feature with a high temporal resolution. Different from the existing LS based algorithm, the spatial sparsity of both the low-rank and sparsity components was used. We also used a primal dual fixed point (PDFP) method for optimization of the objective function to avoid solving sub-problems. Intervention experiments with gelatin and brain phantoms were carried out for validation.

RESULTS

The LS decomposition with framelet transform and PDFP could provide the best reconstruction performance compared with those without. Satisfying reconstruction results were obtained with only 10 radial spokes for a temporal resolution of 60 ms.

CONCLUSION AND SIGNIFICANCE

The proposed method has the potential for i-MRI in many different application scenarios.

Degradation-Aware Deep Learning Framework for Sparse-View CT Reconstruction

Sparse-view CT reconstruction is a fundamental task in computed tomography to overcome undesired artifacts and recover the details of textual structure in degraded CT images. Recently, many deep learning-based networks have achieved desirable performances compared to iterative reconstruction algorithms. However, the performance of these methods may severely deteriorate when the degradation strength of the test image is not consistent with that of the training dataset. In addition, these methods do not pay enough attention to the characteristics of different degradation levels, so solely extending the training dataset with multiple degraded images is also not effective. Although training plentiful models in terms of each degradation level can mitigate this problem, extensive parameter storage is involved. Accordingly, in this paper, we focused on sparse-view CT reconstruction for multiple degradation levels. We propose a single degradation-aware deep learning framework to predict clear CT images by understanding the disparity of degradation in both the frequency domain and image domain. The dual-domain procedure can perform particular operations at different degradation levels in frequency component recovery and spatial details reconstruction. The peak signal-to-noise ratio (PSNR), structural similarity (SSIM) and visual results demonstrate that our method outperformed the classical deep learning-based reconstruction methods in terms of effectiveness and scalability.

MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold space. The experiments show that our proposed method outperforms both the quantitative and qualitative aspects of state-of-the-art methods. In addition, aided by a projection loss component, our proposed method also demonstrates superior performance for semi-supervised learning. The network can remove most noise while maintaining the details of only 10% (40 slices) of the training data labeled.

CT Image Reconstruction via Nonlocal Low-Rank Regularization and Data-Driven Tight Frame

X-ray computed tomography (CT) is widely used in medical applications, where many efforts have been made for decades to eliminate artifacts caused by incomplete projection. In this paper, we propose a new CT image reconstruction model based on nonlocal low-rank regularity and data-driven tight frame (NLR-DDTF). Unlike the Spatial-Radon domain data-driven tight frame regularization, the proposed NLR-DDTF model uses an asymmetric treatment for image reconstruction and Radon domain inpainting, which combines the nonlocal low-rank approximation method for spatial domain CT image reconstruction and data-driven tight frame-based regularization for Radon domain image inpainting. An alternative direction minimization algorithm is designed to solve the proposed model. Several numerical experiments and comparisons are provided to illustrate the superior performance of the NLR-DDTF method.

Spatially Coherent Clustering Based on Orthogonal Nonnegative Matrix Factorization

Classical approaches in cluster analysis are typically based on a feature space analysis. However, many applications lead to datasets with additional spatial information and a ground truth with spatially coherent classes, which will not necessarily be reconstructed well by standard clustering methods. Motivated by applications in hyperspectral imaging, we introduce in this work clustering models based on Orthogonal Nonnegative Matrix Factorization (ONMF), which include an additional Total Variation (TV) regularization procedure on the cluster membership matrix to enforce the needed spatial coherence in the clusters. We propose several approaches with different optimization techniques, where the TV regularization is either performed as a subsequent post-processing step or included into the clustering algorithm. Finally, we provide a numerical evaluation of 12 different TV regularized ONMF methods on a hyperspectral dataset obtained from a matrix-assisted laser desorption/ionization imaging measurement, which leads to significantly better clustering results compared to classical clustering models.

InNetGAN: Inception Network-Based Generative Adversarial Network for Denoising Low-Dose Computed Tomography

Low-dose Computed Tomography (LDCT) has gained a great deal of attention in clinical procedures due to its ability to reduce the patient's risk of exposure to the X-ray radiation. However, reducing the X-ray dose increases the quantum noise and artifacts in the acquired LDCT images. As a result, it produces visually low-quality LDCT images that adversely affect the disease diagnosing and treatment planning in clinical procedures. Deep Learning (DL) has recently become the cutting-edge technology of LDCT denoising due to its high performance and data-driven execution compared to conventional denoising approaches. Although the DL-based models perform fairly well in LDCT noise reduction, some noise components are still retained in denoised LDCT images. One reason for this noise retention is the direct transmission of feature maps through the skip connections of contraction and extraction path-based DL modes. Therefore, in this study, we propose a Generative Adversarial Network with Inception network modules (InNetGAN) as a solution for filtering the noise transmission through skip connections and preserving the texture and fine structure of LDCT images. The proposed Generator is modeled based on the U-net architecture. The skip connections in the U-net architecture are modified with three different inception network modules to filter out the noise in the feature maps passing over them. The quantitative and qualitative experimental results have shown the performance of the InNetGAN model in reducing noise and preserving the subtle structures and texture details in LDCT images compared to the other state-of-the-art denoising algorithms.

Low-Dose CT Image Denoising with Improving WGAN and Hybrid Loss Function

The X-ray radiation from computed tomography (CT) brought us the potential risk. Simply decreasing the dose makes the CT images noisy and diagnostic performance compromised. Here, we develop a novel denoising low-dose CT image method. Our framework is based on an improved generative adversarial network coupling with the hybrid loss function, including the adversarial loss, perceptual loss, sharpness loss, and structural similarity loss. Among the loss function terms, perceptual loss and structural similarity loss are made use of to preserve textural details, and sharpness loss can make reconstruction images clear. The adversarial loss can sharp the boundary regions. The results of experiments show the proposed method can effectively remove noise and artifacts better than the state-of-the-art methods in the aspects of the visual effect, the quantitative measurements, and the texture details.

Learning a Deep CNN Denoising Approach Using Anatomical Prior Information Implemented With Attention Mechanism for Low-Dose CT Imaging on Clinical Patient Data From Multiple Anatomical Sites

Dose reduction in computed tomography (CT) has gained considerable attention in clinical applications because it decreases radiation risks. However, a lower dose generates noise in low-dose computed tomography (LDCT) images. Previous deep learning (DL)-based works have investigated ways to improve diagnostic performance to address this ill-posed problem. However, most of them disregard the anatomical differences among different human body sites in constructing the mapping function between LDCT images and their high-resolution normal-dose CT (NDCT) counterparts. In this article, we propose a novel deep convolutional neural network (CNN) denoising approach by introducing information of the anatomical prior. Instead of designing multiple networks for each independent human body anatomical site, a unified network framework is employed to process anatomical information. The anatomical prior is represented as a pattern of weights of the features extracted from the corresponding LDCT image in an anatomical prior fusion module. To promote diversity in the contextual information, a spatial attention fusion mechanism is introduced to capture many local regions of interest in the attention fusion module. Although many network parameters are saved, the experimental results demonstrate that our method, which incorporates anatomical prior information, is effective in denoising LDCT images. Furthermore, the anatomical prior fusion module could be conveniently integrated into other DL-based methods and avails the performance improvement on multiple anatomical data.

Noise2Context: Context-assisted learning 3D thin-layer for low-dose CT

PURPOSE

Computed tomography (CT) has played a vital role in medical diagnosis, assessment, and therapy planning, etc. In clinical practice, concerns about the increase of x-ray radiation exposure attract more and more attention. To lower the x-ray radiation, low-dose CT (LDCT) has been widely adopted in certain scenarios, while it will induce the degradation of CT image quality. In this paper, we proposed a deep learning-based method that can train denoising neural networks without any clean data.

METHODS

In this work, for 3D thin-slice LDCT scanning, we first drive an unsupervised loss function which was equivalent to a supervised loss function with paired noisy and clean samples when the noise in the different slices from a single scan was uncorrelated and zero-mean. Then, we trained the denoising neural network to map one noise LDCT image to its two adjacent LDCT images in a single 3D thin-layer LDCT scanning, simultaneously. In essence, with some latent assumptions, we proposed an unsupervised loss function to train the denoising neural network in an unsupervised manner, which integrated the similarity between adjacent CT slices in 3D thin-layer LDCT.

RESULTS

Further experiments on Mayo LDCT dataset and a realistic pig head were carried out. In the experiments using Mayo LDCT dataset, our unsupervised method can obtain performance comparable to that of the supervised baseline. With the realistic pig head, our method can achieve optimal performance at different noise levels as compared to all the other methods that demonstrated the superiority and robustness of the proposed Noise2Context.

CONCLUSIONS

In this work, we present a generalizable LDCT image denoising method without any clean data. As a result, our method not only gets rid of the complex artificial image priors but also amounts of paired high-quality training datasets.

Image-domain Material Decomposition for Spectral CT using a Generalized Dictionary Learning

The spectral computed tomography (CT) has huge advantages by providing accurate material information. Unfortunately, due to the instability or overdetermination of material decomposition model, the accuracy of material decomposition can be compromised in practice. Very recently, the dictionary learning based image-domain material decomposition (DLIMD) can obtain high accuracy for material decompositions from reconstructed spectral CT images. This method can explore the correlation of material components to some extent by training a unified dictionary from all material images. In addition, the dictionary learning based prior as a penalty is applied on material components independently, and many parameters would be carefully elaborated in practice. Because the concentration of contrast agent in clinical applications is low, it can result in data inconsistency for dictionary based representation during the iteration process. To avoid the aforementioned limitations and further improve the accuracy of materials, we first construct a generalized dictionary learning based image-domain material decomposition (GDLIMD) model. Then, the material tensor image is unfolded along the mode-1 to enhance the correlation of different materials. Finally, to avoid the data inconsistency of low iodine contrast, a normalization strategy is employed. Both physical phantom and tissue-synthetic phantom experiments demonstrate the proposed GDLIMD method outperforms the DLIMD and direct inversion (DI) methods.

A review on Deep Learning approaches for low-dose Computed Tomography restoration

Computed Tomography (CT) is a widely use medical image modality in clinical medicine, because it produces excellent visualizations of fine structural details of the human body. In clinical procedures, it is desirable to acquire CT scans by minimizing the X-ray flux to prevent patients from being exposed to high radiation. However, these Low-Dose CT (LDCT) scanning protocols compromise the signal-to-noise ratio of the CT images because of noise and artifacts over the image space. Thus, various restoration methods have been published over the past 3 decades to produce high-quality CT images from these LDCT images. More recently, as opposed to conventional LDCT restoration methods, Deep Learning (DL)-based LDCT restoration approaches have been rather common due to their characteristics of being data-driven, high-performance, and fast execution. Thus, this study aims to elaborate on the role of DL techniques in LDCT restoration and critically review the applications of DL-based approaches for LDCT restoration. To achieve this aim, different aspects of DL-based LDCT restoration applications were analyzed. These include DL architectures, performance gains, functional requirements, and the diversity of objective functions. The outcome of the study highlights the existing limitations and future directions for DL-based LDCT restoration. To the best of our knowledge, there have been no previous reviews, which specifically address this topic.

Modularized data-driven reconstruction framework for nonideal focal spot effect elimination in computed tomography

PURPOSE

High-performance computed tomography (CT) plays a vital role in clinical decision-making. However, the performance of CT imaging is adversely affected by the nonideal focal spot size of the x-ray source or degraded by an enlarged focal spot size due to aging. In this work, we aim to develop a deep learning-based strategy to mitigate the problem so that high spatial resolution CT images can be obtained even in the case of a nonideal x-ray source.

METHODS

To reconstruct high-quality CT images from blurred sinograms via joint image and sinogram learning, a cross-domain hybrid model is formulated via deep learning into a modularized data-driven reconstruction (MDR) framework. The proposed MDR framework comprises several blocks, and all the blocks share the same network architecture and network parameters. In essence, each block utilizes two sub-models to generate an estimated blur kernel and a high-quality CT image simultaneously. In this way, our framework generates not only a final high-quality CT image but also a series of intermediate images with gradually improved anatomical details, enhancing the visual perception for clinicians through the dynamic process. We used simulated training datasets to train our model in an end-to-end manner and tested our model on both simulated and realistic experimental datasets.

RESULTS

On the simulated testing datasets, our approach increases the information fidelity criterion (IFC) by up to 34.2%, the universal quality index (UQI) by up to 20.3%, the signal-to-noise (SNR) by up to 6.7%, and reduces the root mean square error (RMSE) by up to 10.5% as compared with FBP. Compared with the iterative deconvolution method (NSM), MDR increases IFC by up to 24.7%, UQI by up to 16.7%, SNR by up to 6.0%, and reduces RMSE by up to 9.4%. In the modulation transfer function (MTF) experiment, our method improves the MTF_50% by 34.5% and MTF_10% by 18.7% as compared with FBP, Similarly remarkably, our method improves MTF_50% by 14.3% and MTF_10% by 0.9% as compared with NSM. Also, our method shows better imaging results in the edge of bony structures and other tiny structures in the experiments using phantom consisting of ham and a bottle of peanuts.

CONCLUSIONS

A modularized data-driven CT reconstruction framework is established to mitigate the blurring effect caused by a nonideal x-ray source with relatively large focal spot. The proposed method enables us to obtain high-resolution images with less ideal x-ray source.

Fully Automatic Sliding Motion Compensated and Simultaneous 4D-CBCT via Bilateral Filtering

Purpose

To incorporate the bilateral filtering into the Deformable Vector Field (DVF) based 4D-CBCT reconstruction for realizing a fully automatic sliding motion compensated 4D-CBCT.

Materials and Methods

Initially, a motion compensated simultaneous algebraic reconstruction technique (mSART) is used to generate a high quality reference phase (e.g. 0% phase) by using all phase projections together with the initial 4D-DVFs. The initial 4D-DVF were generated via Demons registration between 0% phase and each other phase image. The 4D-DVF will then kept updating by matching the forward projection of the deformed high quality 0% phase with the measured projection of the target phase. The loss function during this optimization contains an projection intensity difference matching criterion plus a DVF smoothing constrain term. We introduce a bilateral filtering kernel into the DVF constrain term to estimate the sliding motion automatically. The bilateral filtering kernel contains three sub-kernels: 1) an spatial domain Guassian kernel; 2) an image intensity domain Guassian kernel; and 3) a DVF domain Guassian kernel. By choosing suitable kernel variances, the sliding motion can be extracted. A non-linear conjugate gradient optimizer was used. We validated the algorithm on a non-uniform rotational B-spline based cardiac-torso (NCAT) phantom and four anonymous patient data. For quantification, we used: 1) the Root-Mean-Square-Error (RMSE) together with the Maximum-Error (MaxE); 2) the Dice coefficient of the extracted lung contour from the final reconstructed images and 3) the relative reconstruction error (RE) to evaluate the algorithm's performance.

Results

For NCAT phantom, the motion trajectory's RMSE/MaxE are 0.796/1.02 mm for bilateral filtering reconstruction; and 2.704/4.08 mm for original reconstruction. For patient pilot study, the 4D-Dice coefficient obtained with bilateral filtering are consistently higher than that without bilateral filtering. Meantime several image content such as the rib position, the heart edge definition, the fibrous structures all has been better corrected with bilateral filtering.

Conclusion

We developed a bilateral filtering based fully automatic sliding motion compensated 4D-CBCT scheme. Both digital phantom and initial patient pilot studies confirmed the improved motion estimation and image reconstruction ability. It can be used as a 4D-CBCT image guidance tool for lung SBRT treatment.

DaNet: dose-aware network embedded with dose-level estimation for low-dose CT imaging

Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on low-dose training data without considering dose differences. However, the radiation dose difference has a great impact on the ultimate results, and lower doses increase the difficulty of restoration. Moreover, there is increasing demand to design and estimate acceptable scanning doses for patients in clinical practice, necessitating dose-aware networks embedded with adaptive dose estimation. In this paper, we consider these dose differences of input LDCT images and propose an adaptive dose-aware network. First, considering a large dose distribution range for simulation convenience, we coarsely define five dose levels in advance as lowest, lower, mild, higher and highest radiation dose levels. Instead of directly building the end-to-end mapping function between LDCT images and high-dose CT counterparts, the dose level is primarily estimated in the first stage. In the second stage, the adaptively learned low-dose level is used to guide the image restoration process as the pattern of prior information through the channel feature transform. We conduct experiments on a simulated dataset based on original high dose parts of American Association of Physicists in Medicine challenge datasets from the Mayo Clinic. Ablation studies validate the effectiveness of the dose-level estimation, and the experimental results show that our method is superior to several other DL-based methods. Specifically, our method provides obviously better performance in terms of the peak signal-to-noise ratio and visual quality reflected in subjective scores. Due to the dual-stage process, our method may suffer limitations under more parameters and coarse dose-level definitions, and thus, further improvements in clinical practical applications with different CT equipment vendors are planned in future work.

Low-dose CT with deep learning regularization via proximal forward-backward splitting

Low-dose x-ray computed tomography (LDCT) is desirable for reduced patient dose. This work develops new image reconstruction methods with deep learning (DL) regularization for LDCT. Our methods are based on the unrolling of a proximal forward-backward splitting (PFBS) framework with data-driven image regularization via deep neural networks. In contrast to PFBS-IR, which utilizes standard data fidelity updates via an iterative reconstruction (IR) method, PFBS-AIR involves preconditioned data fidelity updates that fuse the analytical reconstruction (AR) and IR methods in a synergistic way, i.e. fused analytical and iterative reconstruction (AIR). The results suggest that the DL-regularized methods (PFBS-IR and PFBS-AIR) provide better reconstruction quality compared to conventional methods (AR or IR). In addition, owing to the AIR, PFBS-AIR noticeably outperformed PFBS-IR and another DL-based postprocessing method, FBPConvNet.

Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising

Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of "quadratic-neuron-based deep learning". Our prior theoretical studies have shown important merits of quadratic neurons and networks in representation, efficiency, and interpretability. In this paper, we use quadratic neurons to construct an encoder-decoder structure, referred as the quadratic autoencoder, and apply it to low-dose CT denoising. The experimental results on the Mayo low-dose CT dataset demonstrate the utility and robustness of quadratic autoencoder in terms of image denoising and model efficiency. To our best knowledge, this is the first time that the deep learning approach is implemented with a new type of neurons and demonstrates a significant potential in the medical imaging field.

Impact of Esophageal Motion on Dosimetry and Toxicity With Thoracic Radiation Therapy

Purpose:

To investigate the impact of intra- and inter-fractional esophageal motion on dosimetry and observed toxicity in a phase I dose escalation study of accelerated radiotherapy with concurrent chemotherapy for locally advanced lung cancer.

Methods and Materials:

Patients underwent computed tomography imaging for radiotherapy treatment planning (CT1 and 4DCT1) and at 2 weeks (CT2 and 4DCT2) and 5 weeks (CT3 and 4DCT3) after initiating treatment. Each computed tomography scan consisted of 10-phase 4DCTs in addition to a static free-breathing or breath-hold computed tomography. The esophagus was independently contoured on all computed tomographies and 4DCTs. Both CT2 and CT3 were rigidly registered with CT1 and doses were recalculated using the original intensity-modulated radiation therapy plan based on CT1 to assess the impact of interfractional motion on esophageal dosimetry. Similarly, 4DCT1 data sets were rigidly registered with CT1 to assess the impact of intrafractional motion. The motion was characterized based on the statistical analysis of slice-by-slice center shifts (after registration) for the upper, middle, and lower esophageal regions, respectively. For the dosimetric analysis, the following quantities were calculated and assessed for correlation with toxicity grade: the percent volumes of esophagus that received at least 20 Gy (V20) and 60 Gy (V60), maximum esophageal dose, equivalent uniform dose, and normal tissue complication probability.

Results:

The interfractional center shifts were 4.4 ± 1.7 mm, 5.5 ± 2.0 mm and 4.9 ± 2.1 mm for the upper, middle, and lower esophageal regions, respectively, while the intrafractional center shifts were 0.6 ± 0.4 mm, 0.7 ± 0.7 mm, and 0.9 ± 0.7 mm, respectively. The mean V60 (and corresponding normal tissue complication probability) values estimated from the interfractional motion analysis were 7.8% (10%), 4.6% (7.5%), 7.5% (8.6%), and 31% (26%) for grade 0, grade 1, grade 2, and grade 3 toxicities, respectively.

Conclusions:

Interfractional esophageal motion is significantly larger than intrafractional motion. The mean values of V60 and corresponding normal tissue complication probability, incorporating interfractional esophageal motion, correlated positively with esophageal toxicity grade.

Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging

The wide applications of X-ray computed tomography (CT) bring low-dose CT (LDCT) into a clinical prerequisite, but reducing the radiation exposure in CT often leads to significantly increased noise and artifacts, which might lower the judgment accuracy of radiologists. In this paper, we put forward a domain progressive 3D residual convolution network (DP-ResNet) for the LDCT imaging procedure that contains three stages: sinogram domain network (SD-net), filtered back projection (FBP), and image domain network (ID-net). Though both are based on the residual network structure, the SD-net and ID-net provide complementary effect on improving the final LDCT quality. The experimental results with both simulated and real projection data show that this domain progressive deep-learning network achieves significantly improved performance by combing the network processing in the two domains.

Gradient regularized convolutional neural networks for low-dose CT image enhancement

The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively.

ADMM-based deep reconstruction for limited-angle CT

In the real applications of computed tomography (CT) imaging, the projection data of the scanned objects are usually acquired within a limited-angle range because of the limitation of the scanning condition. Under these circumstances, conventional analytical algorithms, such as filtered back-projection (FBP), do not work because the projection data are incomplete. The regularization method has proven to be effective for tomographic reconstruction from under-sampled measurements. To deal with the limited-angle CT reconstruction problem, the regularization method is commonly used, but it is difficult to find a generic regularization term and choose the regularization parameters. Moreover, in some cases, the quality of reconstructed images is less than satisfactory. To solve this problem, we developed an alternating direction method of multipliers (ADMM)-based deep reconstruction (ADMMBDR) algorithm for limited-angle CT. First, we used the ADMM algorithm to decompose a regularization reconstruction model. Then, we utilized a deep convolutional neural network (CNN) to replace a part of the ADMM algorithm to reduce artifacts and avoid the choice of the regularization term and the regularization parameter. Furthermore, we conducted some numerical experiments to evaluate the feasibility and the advantages of the proposed algorithm. The results showed that the proposed algorithm had a better performance than several state-of-the-art algorithms; with respect to structure preservation and artifact reduction.

Spatial-Spectral Cube Matching Frame for Spectral CT Reconstruction

Spectral computed tomography (CT) reconstructs the same scanned object from projections of multiple narrow energy windows, and it can be used for material identification and decomposition. However, the multi-energy projection dataset has a lower signal-noise-ratio (SNR), resulting in poor reconstructed image quality. To address this thorny problem, we develop a spectral CT reconstruction method, namely spatial-spectral cube matching frame (SSCMF). This method is inspired by the following three facts: i) human body usually consists of two or three basic materials implying that the reconstructed spectral images have a strong sparsity; ii) the same basic material component in a single channel image has similar intensity and structures in local regions. Different material components within the same energy channel share similar structural information; iii) multi-energy projection datasets are collected from the subject by using different narrow energy windows, which means images reconstructed from different energy-channels share similar structures. To explore those information, we first establish a tensor cube matching frame (CMF) for a BM4D denoising procedure. Then, as a new regularizer, the CMF is introduced into a basic spectral CT reconstruction model, generating the SSCMF method. Because the SSCMF model contains an L0-norm minimization of 4D transform coefficients, an effective strategy is employed for optimization. Both numerical simulations and realistic preclinical mouse studies are performed. The results show that the SSCMF method outperforms the state-of-the-art algorithms, including the simultaneous algebraic reconstruction technique, total variation minimization, total variation plus low rank, and tensor dictionary learning.

A modified McKinnon-Bates (MKB) algorithm for improved 4D cone-beam computed tomography (CBCT) of the lung

PURPOSE

Four-dimensional (4D) cone-beam computed tomography (CBCT) of the lung is an effective tool for motion management in radiotherapy but presents a challenge because of slow gantry rotation times. Sorting the individual projections by breathing phase and using an established technique such as Feldkamp-Davis-Kress (FDK) to generate corresponding phase-correlated (PC) three-dimensional (3D) images results in reconstructions (FDK-PC) that often contain severe streaking artifacts due to the sparse angular sampling distributions. These can be reduced by further slowing down the gantry at the expense of incurring unwanted increases in scan times and dose. A computationally efficient alternative is the McKinnon-Bates (MKB) reconstruction algorithm that has shown promise in reducing view aliasing-induced streaking but can produce ghosting artifacts that reduce contrast and impede the determination of motion trajectories. The purpose of this work was to identify and correct shortcomings in the MKB algorithm.

METHODS

In the general MKB approach, a time-averaged 3D prior image is first reconstructed. The prior is then forward-projected at the same angles as the original projection data creating time-averaged reprojections. These reprojections are subsequently subtracted from the original (unblurred) projections to create motion-encoded difference projections. The difference projections are reconstructed into PC difference images that are added to the well-sampled 3D prior to create the higher quality 4D image. The cause of the ghosting in the traditional 4D MKB images was studied and traced to motion-induced streaking in the prior that, when reprojected, has the undesirable effect of re-encoding for motion in what should be a purely time-averaged reprojection. A new method, designated as the modified McKinnon-Bates (mMKB) algorithm, was developed based on destreaking the prior. This was coupled with a postprocessing 4D bilateral filter for noise suppression and edge preservation (mMKBbf ). The algorithms were tested with the 4D XCAT phantom using four simulated scan times (57, 60, 120, 180 s) and with two in vivo thorax studies (acquisition time of 60 and 90 s). Contrast-to-noise ratios (CNRs) of the target lesions and overall visual quality of the images were assessed.

RESULTS

Prior destreaking (mMKB algorithm) reduced ghosting artifacts and increased CNRs for all cases, with the biggest impacts seen in the end inhale (EI) and end exhale (EE) phases of the respiratory cycle. For the XCAT phantom, mMKB lesion CNR was 44% higher than the MKB lesion CNR and was 81% higher than the FDK-PC lesion CNR (EI and EE phases). The bilateral filter provided a further average CNR improvement of 87% with the highest increases associated with longer scan times. Across all phases and scan times, the maximum mMKBbf -to-FDK-PC CNR improvement was over 300%. In vivo results agreed with XCAT results. Significantly less ghosting was observed throughout the mMKB images including near the lesions-of-interest and the diaphragm allowing for, in one case, visualization of a small tumor with nearly 30 mm of motion. The maximum FDK-PC-to-MKBbf CNR improvement for Patient 1's lesion was 261% and for Patient 2's lesion was 318%.

CONCLUSIONS

The 4D mMKB algorithm yields good quality coronal and sagittal images in the thorax that may provide sufficient information for patient verification.

3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network

Low-dose computed tomography (LDCT) has attracted major attention in the medical imaging field, since CT-associated X-ray radiation carries health risks for patients. The reduction of the CT radiation dose, however, compromises the signal-to-noise ratio, which affects image quality and diagnostic performance. Recently, deep-learning-based algorithms have achieved promising results in LDCT denoising, especially convolutional neural network (CNN) and generative adversarial network (GAN) architectures. This paper introduces a conveying path-based convolutional encoder-decoder (CPCE) network in 2-D and 3-D configurations within the GAN framework for LDCT denoising. A novel feature of this approach is that an initial 3-D CPCE denoising model can be directly obtained by extending a trained 2-D CNN, which is then fine-tuned to incorporate 3-D spatial information from adjacent slices. Based on the transfer learning from 2-D to 3-D, the 3-D network converges faster and achieves a better denoising performance when compared with a training from scratch. By comparing the CPCE network with recently published work based on the simulated Mayo data set and the real MGH data set, we demonstrate that the 3-D CPCE denoising model has a better performance in that it suppresses image noise and preserves subtle structures.

A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution

Sparse-view computed tomography (CT) holds great promise for speeding up data acquisition and reducing radiation dose in CT scans. Recent advances in reconstruction algorithms for sparse-view CT, such as iterative reconstruction algorithms, obtained high-quality image while requiring advanced computing power. Lately, deep learning (DL) has been widely used in various applications and has obtained many remarkable outcomes. In this paper, we propose a new method for sparse-view CT reconstruction based on the DL approach. The method can be divided into two steps. First, filter backprojection (FBP) was used to reconstruct the CT image from sparsely sampled sinogram. Then, the FBP results were fed to a DL neural network, which is a DenseNet and deconvolution-based network (DD-Net). The DD-Net combines the advantages of DenseNet and deconvolution and applies shortcut connections to concatenate DenseNet and deconvolution to accelerate the training speed of the network; all of those operations can greatly increase the depth of network while enhancing the expression ability of the network. After the training, the proposed DD-Net achieved a competitive performance relative to the state-of-the-art methods in terms of streaking artifacts removal and structure preservation. Compared with the other state-of-the-art reconstruction methods, the DD-Net method can increase the structure similarity by up to 18% and reduce the root mean square error by up to 42%. These results indicate that DD-Net has great potential for sparse-view CT image reconstruction.