Iterative reconstruction methods in X-ray CT

DeCoGAN: MVCT image denoising via coupled generative adversarial network

Objective.In helical tomotherapy, image-guided radiotherapy employs megavoltage computed tomography (MVCT) for precise targeting. However, the high voltage of megavoltage radiation introduces substantial noise, significantly compromising MVCT image clarity. This study aims to enhance MVCT image quality using a deep learning-based denoising method.Approach.We propose an unpaired MVCT denoising network using a coupled generative adversarial network framework (DeCoGAN). Our approach assumes that a universal latent code within a shared latent space can reconstruct any given pair of images. By employing an encoder, we enforce this shared-latent space constraint, facilitating the conversion of low-quality (noisy) MVCT images into high-quality (denoised) counterparts. The network learns the joint distribution of images from both domains by leveraging samples from their respective marginal distributions, enhanced by adversarial training for effective denoising.Main Results.Compared to an analytical algorithm (BM3D) and three deep learning-based methods (RED-CNN, WGAN-VGG and CycleGAN), the proposed method excels in preserving image details and enhancing human visual perception by removing most noise and retaining structural features. Quantitative analysis demonstrates that our method achieves the highest peak signal-to-noise ratio and Structural Similarity Index Measurement values, indicating superior denoising performance.Significance.The proposed DeCoGAN method shows remarkable MVCT denoising performance, making it a promising tool in the field of radiation therapy.

Multiobjective optimization guided by image quality index for limited-angle CT image reconstruction

BACKGROUND

Due to the incomplete projection data collected by limited-angle computed tomography (CT), severe artifacts are present in the reconstructed image. Classical regularization methods such as total variation (TV) minimization, ℓ0 minimization, are unable to suppress artifacts at the edges perfectly. Most existing regularization methods are single-objective optimization approaches, stemming from scalarization methods for multiobjective optimization problems (MOP).

OBJECTIVE

To further suppress the artifacts and effectively preserve the edge structures of the reconstructed image.

METHOD

This study presents a multiobjective optimization model incorporates both data fidelity term and ℓ0-norm of the image gradient as objective functions. It employs an iterative approach different from traditional scalarization methods, using the maximization of structural similarity (SSIM) values to guide optimization rather than minimizing the objective function.The iterative method involves two steps, firstly, simultaneous algebraic reconstruction technique (SART) optimizes the data fidelity term using SSIM and the Simulated Annealing (SA) algorithm for guidance. The degradation solution is accepted in the form of probability, and guided image filtering (GIF) is introduced to further preserve the image edge when the degradation solution is rejected. Secondly, the result from the first step is integrated into the second objective function as a constraint, we use ℓ0 minimization to optimize ℓ0-norm of the image gradient, and the SSIM, SA algorithm and GIF are introduced to guide optimization process by improving SSIM value like the first step.

RESULTS

With visual inspection, the peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and SSIM values indicate that our approach outperforms other traditional methods.

CONCLUSIONS

The experiments demonstrate the effectiveness of our method and its superiority over other classical methods in artifact suppression and edge detail restoration.

A cone-beam optical CT based on a convergent light source - Characterization and optimization

PURPOSE

Employing a Fresnel lens and a point-like light source to create a convergent light beam for the camera effectively minimizes stray light and enhances image quality in optical computed tomography (OCT), benefiting 3D dosimetry applications. This study outlines the development of an economical cone-beam optical computed scanner for 3D dosimetry.

METHODS

Optical performance was assessed by calculating modulation transfer function (MTF) with pattern charts. Stray light was evaluated by imaging a cylinder flask and a square grid with 5 mm diameter holes to determine the stray-to-primary ratio. Reconstruction quality was determined using SIRT-TV and compared with spectrophotometry attenuation coefficients, with the best regularization parameter (λ = 0.01) chosen based on contrast-to-noise ratio (CNR). Dosimetry performance was assessed by determining percentage dose depth (PDD) for a 6MV beam with a 5 × 5 cm2 field using FXO-f gel dosimeter, compared with ionization chamber data.

RESULTS

MTF evaluation yielded ≥ 50 % agreement with pattern charts. Stray-to-primary ratio was less than 0.1 or 10 % of the total signal. Reconstruction showed low noise and artifacts, with optimal CNR at λ = 0.01. Attenuation coefficients from optical CT aligned with spectrometer measurements within 1.2 %. PDD calculated with FXO-f gel dosimeter closely matched ionization chamber data (<1.2 % difference), achieving a dose resolution of 0.1 Gy.

CONCLUSION

The built and optimization the de optical-CT based on a convergent beam is read to perform the 3D quality assurance in clinical applications.

An image-based metal artifact reduction technique utilizing forward projection in computed tomography

The projection data generated via the forward projection of a computed tomography (CT) image (FP-data) have useful potentials in cases where only image data are available. However, there is a question of whether the FP-data generated from an image severely corrupted by metal artifacts can be used for the metal artifact reduction (MAR). The aim of this study was to investigate the feasibility of a MAR technique using FP-data by comparing its performance with that of a conventional robust MAR using projection data normalization (NMARconv). The NMARconv was modified to make use of FP-data (FPNMAR). A graphics processing unit was used to reduce the time required to generate FP-data and subsequent processes. The performances of FPNMAR and NMARconv were quantitatively compared using a normalized artifact index (AIn) for two cases each of hip prosthesis and dental fillings. Several clinical CT images with metal artifacts were processed by FPNMAR. The AIn values of FPNMAR and NMARconv were not significantly different from each other, showing almost the same performance between these two techniques. For all the clinical cases tested, FPNMAR significantly reduced the metal artifacts; thereby, the images of the soft tissues and bones obscured by the artifacts were notably recovered. The computation time per image was ~ 56 ms. FPNMAR, which can be applied to CT images without accessing the projection data, exhibited almost the same performance as that of NMARconv, while consuming significantly shorter processing time. This capability testifies the potential of FPNMAR for wider use in clinical settings.

Clinical Super-Resolution Computed Tomography of Bone Microstructure: Application in Musculoskeletal and Dental Imaging

PURPOSE

Clinical cone-beam computed tomography (CBCT) devices are limited to imaging features of half a millimeter in size and cannot quantify the tissue microstructure. We demonstrate a robust deep-learning method for enhancing clinical CT images, only requiring a limited set of easy-to-acquire training data.

METHODS

Knee tissue from five cadavers and six total knee replacement patients, and 14 teeth from eight patients were scanned using laboratory CT as training data for the developed super-resolution (SR) technique. The method was benchmarked against ex vivo test set, 52 osteochondral samples are imaged with clinical and laboratory CT. A quality assurance phantom was imaged with clinical CT to quantify the technical image quality. To visually assess the clinical image quality, musculoskeletal and maxillofacial CBCT studies were enhanced with SR and contrasted to interpolated images. A dental radiologist and surgeon reviewed the maxillofacial images.

RESULTS

The SR models predicted the bone morphological parameters on the ex vivo test set more accurately than conventional image processing. The phantom analysis confirmed higher spatial resolution on the SR images than interpolation, but image grayscales were modified. Musculoskeletal and maxillofacial CBCT images showed more details on SR than interpolation; however, artifacts were observed near the crown of the teeth. The readers assessed mediocre overall scores for both SR and interpolation. The source code and pretrained networks are publicly available.

CONCLUSION

Model training with laboratory modalities could push the resolution limit beyond state-of-the-art clinical musculoskeletal and dental CBCT. A larger maxillofacial training dataset is recommended for dental applications.

Robust residual-guided iterative reconstruction for sparse-view CT in small animal imaging

Objective. We introduce a robust image reconstruction algorithm named residual-guided Golub-Kahan iterative reconstruction technique (RGIRT) designed for sparse-view computed tomography (CT), which aims at high-fidelity image reconstruction from a limited number of projection views.Approach. RGIRT utilizes an inner-outer dual iteration framework, with a flexible least square QR (FLSQR) algorithm implemented in the inner iteration and a restarted iterative scheme applied in the outer iteration. The inner FLSQR employs a flexible Golub-Kahan bidiagonalization method to reduce the size of the inverse problem, and a weighted generalized cross-validation method to adaptively estimate the regularization hyper-parameter. The inner iteration efficiently yields the intermediate reconstruction result, while the outer iteration minimizes the residual and refines the solution by using the result obtained from the inner iteration.Main results. The reconstruction performance of RGIRT is evaluated and compared to other reference methods (FBPConvNet, SART-TV, and FLSQR) using projection data from both numerical phantoms and real experimental Micro-CT data. The experimental findings, from testing various numbers of projection views and different noise levels, underscore the robustness of RGIRT. Meanwhile, theoretical analysis confirms the convergence of residual for our approach.Significance. We propose a robust iterative reconstruction algorithm for x-ray CT scans with sparse views, thereby shortening scanning time and mitigating excessive ionizing radiation exposure to small animals.

Pure Vision Transformer (CT-ViT) with Noise2Neighbors Interpolation for Low-Dose CT Image Denoising

Convolutional neural networks (CNN) have been used for a wide variety of deep learning applications, especially in computer vision. For medical image processing, researchers have identified certain challenges associated with CNNs. These challenges encompass the generation of less informative features, limitations in capturing both high and low-frequency information within feature maps, and the computational cost incurred when enhancing receptive fields by deepening the network. Transformers have emerged as an approach aiming to address and overcome these specific limitations of CNNs in the context of medical image analysis. Preservation of all spatial details of medical images is necessary to ensure accurate patient diagnosis. Hence, this research introduced the use of a pure Vision Transformer (ViT) for a denoising artificial neural network for medical image processing specifically for low-dose computed tomography (LDCT) image denoising. The proposed model follows a U-Net framework that contains ViT modules with the integration of Noise2Neighbor (N2N) interpolation operation. Five different datasets containing LDCT and normal-dose CT (NDCT) image pairs were used to carry out this experiment. To test the efficacy of the proposed model, this experiment includes comparisons between the quantitative and visual results among CNN-based (BM3D, RED-CNN, DRL-E-MP), hybrid CNN-ViT-based (TED-Net), and the proposed pure ViT-based denoising model. The findings of this study showed that there is about 15-20% increase in SSIM and PSNR when using self-attention transformers than using the typical pure CNN. Visual results also showed improvements especially when it comes to showing fine structural details of CT images.

Deep-learning reconstruction with low-contrast media and low-kilovoltage peak for CT of the liver

AIM

To compare images using reduced CM, low-kVp scanning and DLR reconstruction with conventional images (no CM reduction, normal tube voltage, reconstructed with HBIR. To compare images using reduced contrast media (CM), low kilovoltage peak (kVp) scanning and deep-learning reconstruction (DLR) with conventional image quality (no CM reduction, normal tube voltage, reconstructed with hybrid-type iterative reconstruction method [HBIR protocol]).

MATERIALS AND METHODS

A retrospective analysis was performed on 70 patients with liver disease and three-phase dynamic imaging using computed tomography (CT) from April 2020 to March 2022 at Oita University Hospital. Of these cases, 39 were reconstructed using the DLR protocol at a tube voltage of 80 kVp and CM of 300 mg iodine/kg while 31 were imaged at a tube voltage of 120 kVp with CM of 600 mg iodine/kg and were reconstructed by the usual HBIR protocol. Images from the DLR and HBIR protocols were analysed and compared based on the contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), figure-of-merit (FOM), and visual assessment. The CT dose index (CTDI)vol and size-specific dose estimates (SSDE) were compared with respect to radiation dose.

RESULTS

The DLR protocol was superior, with significant differences in CNR, SNR, and FOM except hepatic parenchyma in the arterial phase. For visual assessment, the DLR protocol had better values for vascular visualisation for the portal vein, image noise, and contrast enhancement of the hepatic parenchyma. Regarding comparison of the radiation dose, the DLR protocol was superior for all values of CTDIvol and SSDE, with significant differences (p<0.01; max. 52%).

CONCLUSION

Protocols using DLR with reduced CM and low kVp have better image quality and lower radiation dose compared to protocols using conventional HBIR.

Association between vessel-specific coronary Aggregated plaque burden, Agatston score and hemodynamic significance of coronary disease (The CAPTivAte study)

Background

CT coronary angiography (CTCA) is a guideline-endorsed assessment for patients with stable angina and suspected coronary disease. Although associated with excellent negative predictive value in ruling out obstructive coronary disease, there are limitations in the ability of CTCA to predict hemodynamically significant coronary disease. The CAPTivAte study aims to assess the utility of Aggregated Plaque Burden (APB) in predicting ischemia based on Fractional Flow Reserve (FFR).

Methods

In this retrospective study, patients who had a CTCA and invasive FFR of the LAD were included. The entire length of the LAD was analyzed using semi-automated software which characterized total plaque burden and plaque morphological subtype (including Low Attenuation Plaque (LAP), Non-calcific plaque (NCP) and Calcific Plaque (CP). Aggregated Plaque Burden (APB) was calculated. Univariate and multivariate analysis were performed to assess the association between these CT-derived parameters and invasive FFR.

Results

There were 145 patients included in this study. 84.8 % of patients were referred with stable angina. There was a significant linear association between APB and FFR in both univariate and multivariate analysis (Adjusted R-squared = 0.0469; p = 0.035). Mean Agatston scores are higher in FFR positive vessels compared to FFR negative vessels (371.6 (±443.8) vs 251.9 (±283.5, p = 0.0493).

Conclusion

CTCA-derived APB is a reliable predictor of ischemia assessed using invasive FFR and may aid clinicians in rationalizing invasive vs non-invasive management strategies. Vessel-specific Agatston scores are significantly higher in FFR-positive vessels than in FFR-negative vessels. Associations between HU-derived plaque subtype and invasive FFR were inconclusive in this study.

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 Learning Image Reconstruction Algorithm for CCTA: Image Quality Assessment and Clinical Application

OBJECTIVE

The increasing number of coronary computed tomography angiography (CCTA) requests raised concerns about dose exposure. New dose reduction strategies based on artificial intelligence have been proposed to overcome limitations of iterative reconstruction (IR) algorithms. Our prospective study sought to explore the added value of deep-learning image reconstruction (DLIR) in comparison with a hybrid IR algorithm (adaptive statistical iterative reconstruction-veo [ASiR-V]) in CCTA, even in clinical challenging scenarios, as obesity, heavily calcified vessels and coronary stents.

METHODS

We prospectively included 103 consecutive patients who underwent CCTA. Data sets were reconstructed with ASiR-V and DLIR. For each reconstruction signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) was calculated, and qualitative assessment was made with a four-point Likert scale by two independent and blinded radiologists with different expertise.

RESULTS

Both SNR and CNR were significantly higher in DLIR (SNR-DLIR median value [interquartile range] of 13.89 [11.06-16.35] and SNR-ASiR-V 25.42 [22.46-32.22], P < 0.001; CNR-DLIR 16.84 [9.83-27.08] vs CNR-ASiR-V 10.09 [5.69-13.5], P < 0.001).Median qualitative score was 4 for DLIR images versus 3 for ASiR-V ( P < 0.001), with a good interreader reliability [intraclass correlation coefficient(2,1)e intraclass correlation coefficient(3,1) 0.60 for DLIR and 0.62 and 0.73 for ASiR-V].In the obese and in the "calcifications and stents" groups, DLIR showed significantly higher values of SNR (24.23 vs 11.11, P < 0.001 and 24.55 vs 14.09, P < 0.001, respectively) and CNR (16.08 vs 8.04, P = 0.008 and 17.31 vs 10.14, P = 0.003) and image quality.

CONCLUSIONS

Deep-learning image reconstruction in CCTA allows better SNR, CNR, and qualitative assessment than ASiR-V, with an added value in the most challenging clinical scenarios.

A CT deep learning reconstruction algorithm: Image quality evaluation for brain protocol at decreasing dose indexes in comparison with FBP and statistical iterative reconstruction algorithms

PURPOSE

To characterise the impact of Precise Image (PI) deep learning reconstruction algorithm on image quality, compared to filtered back-projection (FBP) and iDose4 iterative reconstruction for brain computed tomography (CT) phantom images.

METHODS

Catphan-600 phantom was acquired with an Incisive CT scanner using a dedicated brain protocol, at six different dose levels (volume computed tomography dose index (CTDIvol): 7/14/29/49/56/67 mGy). Images were reconstructed using FBP, levels 2/5 of iDose4, and PI algorithm (Sharper/Sharp/Standard/Smooth/Smoother). Image quality was assessed by evaluating CT numbers, image histograms, noise, image non-uniformity (NU), noise power spectrum, target transfer function, and detectability index.

RESULTS

The five PI levels did not significantly affect the mean CT number. For a given CTDIvol using Sharper-to-Smoother levels, the spatial resolution for all the investigated materials and the detectability index increased while the noise magnitude decreased, slightly affecting noise texture. For a fixed PI level increasing the CTDIvol the detectability index increased, the noise magnitude decreased. From 29 mGy, NU values converged within 1 Hounsfield Unit from each other without a substantial improvement at higher CTDIvol values.

CONCLUSIONS

The improved performances of intermediate PI levels in brain protocols compared to conventional algorithms seem to suggest a potential reduction of CTDIvol.

Quantum annealing-based computed tomography using variational approach for a real-number image reconstruction

Objective. Despite recent advancements in quantum computing, the limited number of available qubits has hindered progress in CT reconstruction. This study investigates the feasibility of utilizing quantum annealing-based computed tomography (QACT) with current quantum bit levels.Approach. The QACT algorithm aims to precisely solve quadratic unconstrained binary optimization problems. Furthermore, a novel approach is proposed to reconstruct images by approximating real numbers using the variational method. This approach allows for accurate CT image reconstruction using a small number of qubits. The study examines the impact of projection data quantity and noise on various image sizes ranging from 4 × 4 to 24 × 24 pixels. The reconstructed results are compared against conventional reconstruction algorithms, namely maximum likelihood expectation maximization (MLEM) and filtered back projection (FBP).Main result. By employing the variational approach and utilizing two qubits for each pixel of the image, accurate reconstruction was achieved with an adequate number of projections. Under conditions of abundant projections and lower noise levels, the image quality in QACT algorithm outperformed that of MLEM and FBP algorithms. However, in situations with limited projection data and in the presence of noise, the image quality in QACT was inferior to that in MLEM.Significance. This study developed the QACT reconstruction algorithm using the variational approach for real-number reconstruction. Remarkably, only 2 qubits were required for each pixel representation, demonstrating their sufficiency for accurate reconstruction.

Synthetization of high-dose images using low-dose CT scans

BACKGROUND

Radiation dose reduction has been the focus of many research activities in x-ray CT. Various approaches were taken to minimize the dose to patients, ranging from the optimization of clinical protocols, refinement of the scanner hardware design, and development of advanced reconstruction algorithms. Although significant progress has been made, more advancements in this area are needed to minimize the radiation risks to patients.

PURPOSE

Reconstruction algorithm-based dose reduction approaches focus mainly on the suppression of noise in the reconstructed images while preserving detailed anatomical structures. Such an approach effectively produces synthesized high-dose images (SHD) from the data acquired with low-dose scans. A representative example is the model-based iterative reconstruction (MBIR). Despite its widespread deployment, its full adoption in a clinical environment is often limited by an undesirable image texture. Recent studies have shown that deep learning image reconstruction (DLIR) can overcome this shortcoming. However, the limited availability of high-quality clinical images for training and validation is often the bottleneck for its development. In this paper, we propose a novel approach to generate SHD with existing low-dose clinical datasets that overcomes both the noise texture issue and the data availability issue.

METHODS

Our approach is based on the observation that noise in the image can be effectively reduced by performing image processing orthogonal to the imaging plane. This process essentially creates an equivalent thick-slice image (TSI), and the characteristics of TSI depend on the nature of the image processing. An advantage of this approach is its potential to reduce impact on the noise texture. The resulting image, however, is likely corrupted by the anatomical structural degradation due to partial volume effects. Careful examination has shown that the differential signal between the original and the processed image contains sufficient information to identify regions where anatomical structures are modified. The differential signal, unfortunately, contains significant noise and has to be removed. The noise removal can be accomplished by performing iterative noise reduction to preserve structural information. The processed differential signal is subsequently subtracted from TSI to arrive at SHD.

RESULTS

The algorithm was evaluated extensively with phantom and clinical datasets. For better visual inspection, difference images between the original and SHD were generated and carefully examined. Negligible residual structure could be observed. In addition to the qualitative inspection, quantitative analyses were performed on clinical images in terms of the CT number consistency and the noise reduction characteristics. Results indicate that no CT number bias is introduced by the proposed algorithm. In addition, noise reduction capability is consistent across different patient anatomical regions. Further, simulated water phantom scans were utilized in the generation of the noise power spectrum (NPS) to demonstrate the preservation of the noise-texture.

CONCLUSIONS

We present a method to generate SHD datasets from regularly acquired low-dose CT scans. Images produced with the proposed approach exhibit excellent noise-reduction with the desired noise-texture. Extensive clinical and phantom studies have demonstrated the efficacy and robustness of our approach. Potential limitations of the current implementation are discussed and further research topics are outlined.

Deep learning enables time-efficient soft tissue enhancement in CBCT: Proof-of-concept study for dentomaxillofacial applications

PURPOSE

The use of iterative and deep learning reconstruction methods, which would allow effective noise reduction, is limited in cone-beam computed tomography (CBCT). As a consequence, the visibility of soft tissues is limited with CBCT. The study aimed to improve this issue through time-efficient deep learning enhancement (DLE) methods.

METHODS

Two DLE networks, UNIT and U-Net, were trained with simulated CBCT data. The performance of the networks was tested with three different test data sets. The quantitative evaluation measured the structural similarity index measure (SSIM) and the peak signal-to-noise ratio (PSNR) of the DLE reconstructions with respect to the ground truth iterative reconstruction method. In the second assessment, a dentomaxillofacial radiologist assessed the resolution of hard tissue structures, visibility of soft tissues, and overall image quality of real patient data using the Likert scale. Finally, the technical image quality was determined using modulation transfer function, noise power spectrum, and noise magnitude analyses.

RESULTS

The study demonstrated that deep learning CBCT denoising is feasible and time efficient. The DLE methods, trained with simulated CBCT data, generalized well, and DLE provided quantitatively (SSIM/PSNR) and visually similar noise-reduction as conventional IR, but with faster processing time. The DLE methods improved soft tissue visibility compared to the conventional Feldkamp-Davis-Kress (FDK) algorithm through noise reduction. However, in hard tissue quantification tasks, the radiologist preferred the FDK over the DLE methods.

CONCLUSION

Post-reconstruction DLE allowed feasible reconstruction times while yielding improvements in soft tissue visibility in each dataset.

A generalization of the maximum likelihood expectation maximization (MLEM) method: Masked-MLEM

Objective.In our previous work on image reconstruction for single-layer collimatorless scintigraphy, we developed the min-min weighted robust least squares (WRLS) optimization algorithm to address the challenge of reconstructing images when both the system matrix and the projection data are uncertain. Whereas the WRLS algorithm has been successful in two-dimensional (2D) reconstruction, expanding it to three-dimensional (3D) reconstruction is difficult since the WRLS optimization problem is neither smooth nor strongly-convex. To overcome these difficulties and achieve robust image reconstruction in the presence of system uncertainties and projection noise, we propose a generalized iterative method based on the maximum likelihood expectation maximization (MLEM) algorithm, hereinafter referred to as the Masked-MLEM algorithm.Approach.In the Masked-MLEM algorithm, only selected subsets ('masks') from the system matrix and the projection contribute to the image update to satisfy the constraints imposed by the system uncertainties. We validate the Masked-MLEM algorithm and compare it to the standard MLEM algorithm using experimental data obtained from both collimated and uncollimated imaging instruments, including parallel-hole collimated SPECT, 2D collimatorless scintigraphy, and 3D collimatorless tomography. Additionally, we conduct comprehensive Monte Carlo simulations for 3D collimatorless tomography to further validate the effectiveness of the Masked-MLEM algorithm in handling different levels of system uncertainties.Main results.The Masked-MLEM and standard MLEM reconstructions are similar in cases with negligible system uncertainties, whereas the Masked-MLEM algorithm outperforms the standard MLEM algorithm when the system matrix is an approximation. Importantly, the Masked-MLEM algorithm ensures reliable image reconstruction across varying levels of system uncertainties.Significance.With a good choice of system uncertainty and without requiring accurate knowledge of the actual system matrix, the Masked-MLEM algorithm yields more robust image reconstruction than the standard MLEM algorithm, effectively reducing the likelihood of erroneously reconstructing higher activities in regions without radioactive sources.

A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.

Physical characteristics of deep learning-based image processing software in computed tomography: a phantom study

PURPOSE

This study aimed to assess the image characteristics of deep-learning-based image processing software (DLIP; FCT PixelShine, FUJIFILM, Tokyo, Japan) and compare it with filtered back projection (FBP), model-based iterative reconstruction (MBIR), and deep-learning-based reconstruction (DLR).

METHODS

This phantom study assessed the object-specific spatial resolution (task-based transfer function [TTF]), noise characteristics (noise power spectrum [NPS]), and low-contrast detectability (low-contrast object-specific contrast-to-noise ratio [CNRLO]) at three different output doses (standard: 10 mGy; low: 3.9 mGy; ultralow: 2.0 mGy). The processing strength of DLIPFBP with A1, A4, and A9 was compared with those of FBP, MBIR, and DLR.

RESULT

The standard dose with high-contrast TTFs of DLIPFBP exceeded that of FBP. Low-contrast TTFs were comparable to or lower than that of FBP. The NPS peak frequency (fP) of DLIPFBP shifts to low spatial frequencies of up to 8.6% at ultralow doses compared to the standard FBP dose. MBIR shifted the most fP compared to FBP-a marked shift of up to 49%. DLIPFBP showed a CNRLO equal to or greater than that of DLR in standard or low doses. In contrast, the CNRLO of the DLIPFBP was equal to or lower than that of the DLR in ultralow doses.

CONCLUSION

DLIPFBP reduced image noise while maintaining a resolution similar to commercially available MBIR and DLR. The slight spatial frequency shift of fP in DLIPFBP contributed to the noise texture degradation suppression. The NPS suppression in the low spatial frequency range effectively improved the low-contrast detectability.

Impact of a Deep Learning-based Super-resolution Image Reconstruction Technique on High-contrast Computed Tomography: A Phantom Study

RATIONALE AND OBJECTIVES

Deep-learning-based super-resolution image reconstruction (DLSRR) is a novel image reconstruction technique that is expected to contribute to improvement in spatial resolution as well as noise reduction through learning from high-resolution computed tomography (CT). This study aims to evaluate image quality obtained with DLSRR and assess its clinical potential.

MATERIALS AND METHODS

CT images of a Mercury CT 4.0 phantom were obtained using a 320-row multi-detector scanner at tube currents of 100, 200, and 300 mA. Image data were reconstructed by filtered back projection (FBP), hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), deep-learning-based image reconstruction (DLR), and DLSRR at image reconstruction strength levels of mild, standard, and strong. Noise power spectrum (NPS), task transfer function (TTF), and detectability index were calculated.

RESULTS

The magnitude of the noise-reducing effect in comparison with FBP was in the order MBIR

CONCLUSION

The present results suggest that DLSRR can achieve greater noise reduction and improved spatial resolution in the high-contrast region compared with conventional DLR and iterative reconstruction techniques.

Collapse

Key Words

• deep-learning-based super-resolution image reconstruction
• detectability index
• iterative reconstruction
• noise power spectrum
• task transfer function

Collapse

MESH Headings Collapse

Grants Collapse

Affiliation(s)

Hideyuki Sato Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Shinichiro Fujimoto Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Tokyo, Japan.
Nobuo Tomizawa Department of Radiology, Juntendo University Graduate School of Medicine, Tokyo, Japan
Hidekazu Inage Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Takuya Yokota Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Hikaru Kudo Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Ruiheng Fan Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Keiichi Kawamoto Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Yuri Honda Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan
Takayuki Kobayashi Department of Radiological Technology, Kitasato University Kitasato Institute Hospital, Tokyo, Japan
Tohru Minamino Department of Cardiovascular Biology and Medicine, Juntendo University Graduate School of Medicine, Tokyo, Japan
Yosuke Kogure Department of Radiological Technology, Juntendo University Hospital, Tokyo, Japan

Collapse

Implementation of AI image reconstruction in CT-how is it validated and what dose reductions can be achieved

CT reconstruction has undergone a substantial change over the last decade with the introduction of iterative reconstruction (IR) and now with deep learning reconstruction (DLR). In this review, DLR will be compared to IR and filtered back-projection (FBP) reconstructions. Comparisons will be made using image quality metrics such as noise power spectrum, contrast-dependent task-based transfer function, and non-prewhitening filter detectability index (dNPW'). Discussion on how DLR has impacted CT image quality, low-contrast detectability, and diagnostic confidence will be provided. DLR has shown the ability to improve in areas that IR is lacking, namely: noise magnitude reduction does not alter noise texture to the degree that IR did, and the noise texture found in DLR is more aligned with noise texture of an FBP reconstruction. Additionally, the dose reduction potential for DLR is shown to be greater than IR. For IR, the consensus was dose reduction should be limited to no more than 15-30% to preserve low-contrast detectability. For DLR, initial phantom and patient observer studies have shown acceptable dose reduction between 44 and 83% for both low- and high-contrast object detectability tasks. Ultimately, DLR is able to be used for CT reconstruction in place of IR, making it an easy "turnkey" upgrade for CT reconstruction. DLR for CT is actively being improved as more vendor options are being developed and current DLR options are being enhanced with second generation algorithms being released. DLR is still in its developmental early stages, but is shown to be a promising future for CT reconstruction.

Trade-off between the radiation parameters and image quality using iterative reconstruction techniques in head computed tomography: a phantom study

BACKGROUND

Iterative reconstruction techniques (IRTs) are commonly used in computed tomography (CT) and help to reduce image noise.

PURPOSE

To determine the minimum radiation dose while preserving image quality in head CT using IRTs.

MATERIAL AND METHODS

The anthropomorphic phantom was used to scan nine head CT image series with varied radiation parameters. CT dose parameters, including volume CT dose index (CTDIvol [in mGy]) and dose length product (DLP [in mGy/cm]), were recorded for each scan series. Different noise levels (iDoseL1-6) were used in IRT reconstructions for soft and bone tissues. In total, 15 measurements were taken from five regions of interest (ROI) with an area of 10 mm2. The signal-to-noise ratio (SNR) and noise values obtained at different ROIs were compared among various reconstruction methods with repeated measures of statistical analysis.

RESULTS

In the head CT scan, applying IRT iDoseL5 had the lowest noise and highest SNR for soft tissue (P < 0.05), and increased iDose can decrease CT dose by 54.6% without compromising image quality. While for bone tissue reconstruction, no clear association was found between the level of iDose and noise. However, when CTDIvol is >20 mGy, iDoseL4 is slightly superior to other reconstruction methods (P < 0.065).

CONCLUSION

Using IRTs in head CTs reduces radiation dose while maintaining image quality. IDoseL5 provided optimal balance for soft tissue.

Bayesian Reconstruction Algorithms for Low-Dose Computed Tomography Are Not Yet Suitable in Clinical Context

Computed tomography (CT) is a widely used examination technique that usually requires a compromise between image quality and radiation exposure. Reconstruction algorithms aim to reduce radiation exposure while maintaining comparable image quality. Recently, unsupervised deep learning methods have been proposed for this purpose. In this study, a promising sparse-view reconstruction method (posterior temperature optimized Bayesian inverse model; POTOBIM) is tested for its clinical applicability. For this study, 17 whole-body CTs of deceased were performed. In addition to POTOBIM, reconstruction was performed using filtered back projection (FBP). An evaluation was conducted by simulating sinograms and comparing the reconstruction with the original CT slice for each case. A quantitative analysis was performed using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM). The quality was assessed visually using a modified Ludewig's scale. In the qualitative evaluation, POTOBIM was rated worse than the reference images in most cases. A partially equivalent image quality could only be achieved with 80 projections per rotation. Quantitatively, POTOBIM does not seem to benefit from more than 60 projections. Although deep learning methods seem suitable to produce better image quality, the investigated algorithm (POTOBIM) is not yet suitable for clinical routine.

Coronary artery calcium quantification: comparison between filtered-back projection, hybrid iterative reconstruction, and deep learning reconstruction techniques

BACKGROUND

The reference protocol for the quantification of coronary artery calcium (CAC) should be updated to meet the standards of modern imaging techniques.

PURPOSE

To assess the influence of filtered-back projection (FBP), hybrid iterative reconstruction (IR), and three levels of deep learning reconstruction (DLR) on CAC quantification on both in vitro and in vivo studies.

MATERIAL AND METHODS

In vitro study was performed with a multipurpose anthropomorphic chest phantom and small pieces of bones. The real volume of each piece was measured using the water displacement method. In the in vivo study, 100 patients (84 men; mean age = 71.2 ± 8.7 years) underwent CAC scoring with a tube voltage of 120 kVp and image thickness of 3 mm. The image reconstruction was done with FBP, hybrid IR, and three levels of DLR including mild (DLRmild), standard (DLRstd), and strong (DLRstr).

RESULTS

In the in vitro study, the calcium volume was equivalent (P = 0.949) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. In the in vivo study, the image noise was significantly lower in images that used DLRstr-based reconstruction, when compared images other reconstructions (P < 0.001). There were no significant differences in the calcium volume (P = 0.987) and Agatston score (P = 0.991) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. The highest overall agreement of Agatston scores was found in the DLR groups (98%) and hybrid IR (95%) when compared to standard FBP reconstruction.

CONCLUSION

The DLRstr presented the lowest bias of agreement in the Agatston scores and is recommended for the accurate quantification of CAC.

Multi-Scale Feature Fusion Network for Low-Dose CT Denoising

Computed tomography (CT) is an imaging technique extensively used in medical treatment, but too much radiation dose in a CT scan will cause harm to the human body. Decreasing the dose of radiation will result in increased noise and artifacts in the reconstructed image, blurring the internal tissue and edge details. To get high-quality CT images, we present a multi-scale feature fusion network (MSFLNet) for low-dose CT (LDCT) denoising. In our MSFLNet, we combined multiple feature extraction modules, effective noise reduction modules, and fusion modules constructed using the attention mechanism to construct a horizontally connected multi-scale structure as the overall architecture of the network, which is used to construct different levels of feature maps at all scales. We innovatively define a composite loss function composed of pixel-level loss based on MS-SSIM-L1 and edge-based edge loss for LDCT denoising. In short, our approach learns a rich set of features that combine contextual information from multiple scales while maintaining the spatial details of denoised CT images. Our laboratory results indicate that compared with the existing methods, the peak signal-to-noise ratio (PSNR) value of CT images of the AAPM dataset processed by the new model is 33.6490, and the structural similarity (SSIM) value is 0.9174, which also achieves good results on the Piglet dataset with different doses. The results also show that the method removes noise and artifacts while effectively preserving CT images' architecture and grain information.

Fast and low-dose medical imaging generation empowered by hybrid deep-learning and iterative reconstruction

Fast and low-dose reconstructions of medical images are highly desired in clinical routines. We propose a hybrid deep-learning and iterative reconstruction (hybrid DL-IR) framework and apply it for fast magnetic resonance imaging (MRI), fast positron emission tomography (PET), and low-dose computed tomography (CT) image generation tasks. First, in a retrospective MRI study (6,066 cases), we demonstrate its capability of handling 3- to 10-fold under-sampled MR data, enabling organ-level coverage with only 10- to 100-s scan time; second, a low-dose CT study (142 cases) shows that our framework can successfully alleviate the noise and streak artifacts in scans performed with only 10% radiation dose (0.61 mGy); and last, a fast whole-body PET study (131 cases) allows us to faithfully reconstruct tumor-induced lesions, including small ones (<4 mm), from 2- to 4-fold-accelerated PET acquisition (30-60 s/bp). This study offers a promising avenue for accurate and high-quality image reconstruction with broad clinical value.

Machine learning assists in increasing the time resolution of X-ray computed tomography applied to mineral precipitation in porous media

Many subsurface engineering technologies or natural processes cause porous medium properties, such as porosity or permeability, to evolve in time. Studying and understanding such processes on the pore scale is strongly aided by visualizing the details of geometric and morphological changes in the pores. For realistic 3D porous media, X-Ray Computed Tomography (XRCT) is the method of choice for visualization. However, the necessary high spatial resolution requires either access to limited high-energy synchrotron facilities or data acquisition times which are considerably longer (e.g. hours) than the time scales of the processes causing the pore geometry change (e.g. minutes). Thus, so far, conventional benchtop XRCT technologies are often too slow to allow for studying dynamic processes. Interrupting experiments for performing XRCT scans is also in many instances no viable approach. We propose a novel workflow for investigating dynamic precipitation processes in porous media systems in 3D using a conventional XRCT technology. Our workflow is based on limiting the data acquisition time by reducing the number of projections and enhancing the lower-quality reconstructed images using machine-learning algorithms trained on images reconstructed from high-quality initial- and final-stage scans. We apply the proposed workflow to induced carbonate precipitation within a porous-media sample of sintered glass-beads. So we were able to increase the temporal resolution sufficiently to study the temporal evolution of the precipitate accumulation using an available benchtop XRCT device.

Dual-domain fusion deep convolutional neural network for low-dose CT denoising

BACKGROUND

In view of the underlying health risks posed by X-ray radiation, the main goal of the present research is to achieve high-quality CT images at the same time as reducing x-ray radiation. In recent years, convolutional neural network (CNN) has shown excellent performance in removing low-dose CT noise. However, previous work mainly focused on deepening and feature extraction work on CNN without considering fusion of features from frequency domain and image domain.

OBJECTIVE

To address this issue, we propose to develop and test a new LDCT image denoising method based on a dual-domain fusion deep convolutional neural network (DFCNN).

METHODS

This method deals with two domains, namely, the DCT domain and the image domain. In the DCT domain, we design a new residual CBAM network to enhance the internal and external relations of different channels while reducing noise to promote richer image structure information. For the image domain, we propose a top-down multi-scale codec network as a denoising network to obtain more acceptable edges and textures while obtaining multi-scale information. Then, the feature images of the two domains are fused by a combination network.

RESULTS

The proposed method was validated on the Mayo dataset and the Piglet dataset. The denoising algorithm is optimal in both subjective and objective evaluation indexes as compared to other state-of-the-art methods reported in previous studies.

CONCLUSIONS

The study results demonstrate that by applying the new fusion model denoising, denoising results in both image domain and DCT domain are better than other models developed using features extracted in the single image domain.

Noise-resilient deep learning for integrated circuit tomography

X-ray tomography is a non-destructive imaging technique that reveals the interior of an object from its projections at different angles. Under sparse-view and low-photon sampling, regularization priors are required to retrieve a high-fidelity reconstruction. Recently, deep learning has been used in X-ray tomography. The prior learned from training data replaces the general-purpose priors in iterative algorithms, achieving high-quality reconstructions with a neural network. Previous studies typically assume the noise statistics of test data are acquired a priori from training data, leaving the network susceptible to a change in the noise characteristics under practical imaging conditions. In this work, we propose a noise-resilient deep-reconstruction algorithm and apply it to integrated circuit tomography. By training the network with regularized reconstructions from a conventional algorithm, the learned prior shows strong noise resilience without the need for additional training with noisy examples, and allows us to obtain acceptable reconstructions with fewer photons in test data. The advantages of our framework may further enable low-photon tomographic imaging where long acquisition times limit the ability to acquire a large training set.

Deep image and feature prior algorithm based on U-ConformerNet structure

PURPOSE

The reconstruction performance of the deep image prior (DIP) approach is limited by the conventional convolutional layer structure and it is difficult to enhance its potential. In order to improve the quality of image reconstruction and suppress artifacts, we propose a DIP algorithm with better performance, and verify its superiority in the latest case.

METHODS

We construct a new U-ConformerNet structure as the DIP algorithm's network, replacing the traditional convolutional layer-based U-net structure, and introduce the 'lpips' deep network based feature distance regularization method. Our algorithm can switch between supervised and unsupervised modes at will to meet different needs.

RESULTS

The reconstruction was performed on the low dose CT dataset (LoDoPaB). Our algorithm attained a PSNR of more than 35 dB under unsupervised conditions, and the PSNR under the supervised condition is greater than 36 dB. Both of which are better than the performance of the DIP-TV. Furthermore, the accuracy of this method is positively connected with the quality of the a priori image with the help of deep networks. In terms of noise eradication and artifact suppression, the DIP algorithm with U-ConformerNet structure outperforms the standard DIP method based on convolutional structure.

CONCLUSIONS

It is known by experimental verification that, in unsupervised mode, the algorithm improves the output PSNR by at least 2-3 dB when compared to the DIP-TV algorithm (proposed in 2020). In supervised mode, our algorithm approaches that of the state-of-the-art end-to-end deep learning algorithms.

"Image quality evaluation of the Precise image CT deep learning reconstruction algorithm compared to Filtered Back-projection and iDose4: a phantom study at different dose levels"

PURPOSE

To characterize the performance of the Precise Image (PI) deep learning reconstruction (DLR) algorithm for abdominal Computed Tomography (CT) imaging.

METHODS

CT images of the Catphan-600 phantom (equipped with an external annulus) were acquired using an abdominal protocol at four dose levels and reconstructed using FBP, iDose⁴ (levels 2,5) and PI ('Soft Tissue' definition, levels 'Sharper','Sharp','Standard','Smooth','Smoother'). Image noise, image non-uniformity, noise power spectrum (NPS), target transfer function (TTF), detectability index (d'), CT numbers accuracy and image histograms were analyzed.

RESULTS

The behavior of the PI algorithm depended strongly on the selected level of reconstruction. The phantom analysis suggested that the PI image noise decreased linearly by varying the level of reconstruction from Sharper to Smoother, expressing a noise reduction up to 80% with respect to FBP. Additionally, the non-uniformity decreased, the histograms became narrower, and d' values increased as PI reconstruction levels changed from Sharper to Smoother. PI had no significant impact on the average CT number of different contrast objects. The conventional FBP NPS was deeply altered only by Smooth and Smoother levels of reconstruction. Furthermore, spatial resolution was found to be dose- and contrast-dependent, but in each analyzed condition it was greater than or comparable to FBP and iDose⁴ TTFs.

CONCLUSIONS

The PI algorithm can reduce image noise with respect to FBP and iDose⁴; spatial resolution, CT numbers and image uniformity are generally preserved by the algorithm but changes in NPS for the Smooth and Smoother levels need to be considered in protocols implementation.

X-ray CT image denoising with MINF: A modularized iterative network framework for data from multiple dose levels

In clinical applications, multi-dose scan protocols will cause the noise levels of computed tomography (CT) images to fluctuate widely. The popular low-dose CT (LDCT) denoising network outputs denoised images through an end-to-end mapping between an LDCT image and its corresponding ground truth. The limitation of this method is that the reduced noise level of the image may not meet the diagnostic needs of doctors. To establish a denoising model adapted to the multi-noise levels robustness, we proposed a novel and efficient modularized iterative network framework (MINF) to learn the feature of the original LDCT and the outputs of the previous modules, which can be reused in each following module. The proposed network can achieve the goal of gradual denoising, outputting clinical images with different denoising levels, and providing the reviewing physicians with increased confidence in their diagnosis. Moreover, a multi-scale convolutional neural network (MCNN) module is designed to extract as much feature information as possible during the network's training. Extensive experiments on public and private clinical datasets were carried out, and comparisons with several state-of-the-art methods show that the proposed method can achieve satisfactory results for noise suppression of LDCT images. In further comparisons with modularized adaptive processing neural network (MAP-NN), the proposed network shows superior step-by-step or gradual denoising performance. Considering the high quality of gradual denoising results, the proposed method can obtain satisfactory performance in terms of image contrast and detail protection as the level of denoising increases, which shows its potential to be suitable for a multi-dose levels denoising task.

Deep learning image reconstruction for quality assessment of iodine concentration in computed tomography: A phantom study

BACKGROUND

Recently, deep learning reconstruction (DLR) technology aiming to improve image quality with minimal radiation dose has been applied not only to pediatric scans, but also to computed tomography angiography (CTA).

OBJECTIVE

To evaluate image quality characteristics of filtered back projection (FBP), hybrid iterative reconstruction [Adaptive Iterative Dose Reduction 3D (AIDR 3D)], and DLR (AiCE) using different iodine concentrations and scan parameters.

METHODS

Phantoms with eight iodine concentrations (ranging from 1.2 to 25.9 mg/mL) located at the edge of a cylindrical water phantom with a diameter of 19 cm were scanned. Data were reconstructed with FBP, AIDR 3D, and AiCE using various scan parameters of tube current and voltage using a 320 row-detector CT scanner. Data obtained using different reconstruction techniques were quantitatively compared by analyzing Hounsfield units (HU), noise, and contrast-to-noise ratios (CNRs).

RESULTS

HU values of FBP and AIDR 3D were constant even when the iodine concentration was changed, whereas AiCE showed the highest HU value when the iodine concentration was low, but the HU value reversed when the iodine concentration exceeded a certain value. In the AIDR 3D and AiCE, the noise decreased as the tube current increased, and the change in noise when the iodine concentration was inconsistent. AIDR 3D and AiCE yielded better noise reduction rates than with FBP at a low tube current. The noise reduction rate of AIDR 3D and AiCE compared to that of FBP showed characteristics ranging from 7% to 35%, and the noise reduction rate of AiCE compared to that of AIDR 3D ranged from 2.0% to 13.3%.

CONCLUSIONS

The evaluated reconstruction techniques showed different image quality characteristics (HU value, noise, and CNR) according to dose and scan parameters, and users must consider these results and characteristics before performing patient scans.

Total-body low-dose CT image denoising using a prior knowledge transfer technique with a contrastive regularization mechanism

PURPOSE

Reducing the radiation exposure experienced by patients in total-body computed tomography (CT) imaging has attracted extensive attention in the medical imaging community. A low radiation dose may result in increased noise and artifacts that greatly affect the subsequent clinical diagnosis. To obtain high-quality total-body low-dose CT (LDCT) images, previous deep learning-based research works developed various network architectures. However, most of these methods only employ normal-dose CT (NDCT) images as ground truths to guide the training process of the constructed denoising network. As a result of this simple restriction, the reconstructed images tend to lose favorable image details and easily generate oversmoothed textures. This study explores how to better utilize the information contained in the feature spaces of NDCT images to guide the LDCT image reconstruction process and achieve high-quality results.

METHODS

We propose a novel intratask knowledge transfer (KT) method that leverages the knowledge distilled from NDCT images as an auxiliary component of the LDCT image reconstruction process. Our proposed architecture is named the teacher-student consistency network (TSC-Net), which consists of teacher and student networks with identical architectures. By employing the designed KT loss, the student network is encouraged to emulate the teacher network in the representation space and gain robust prior content. In addition, to further exploit the information contained in CT scans, a contrastive regularization mechanism (CRM) built upon contrastive learning is introduced. The CRM aims to minimize and maximize the L2 distances from the predicted CT images to the NDCT samples and to the LDCT samples in the latent space, respectively. Moreover, based on attention and the deformable convolution approach, we design a dynamic enhancement module (DEM) to improve the network capability to transform input information flows.

RESULTS

By conducting ablation studies, we prove the effectiveness of the proposed KT loss, CRM, and DEM. Extensive experimental results demonstrate that the TSC-Net outperforms the state-of-the-art methods in both quantitative and qualitative evaluations. Additionally, the excellent results obtained for clinical readings also prove that our proposed method can reconstruct high-quality CT images for clinical applications.

CONCLUSIONS

Based on the experimental results and clinical readings, the TSC-Net has better performance than other approaches. In our future work, we may explore the reconstruction of LDCT images by fusing the positron emission tomography (PET) and CT modalities to further improve the visual quality of the reconstructed CT images.

Three-Dimensional Dosimetry by Optical-CT and Radiochromic Gel Dosimeter of a Multiple Isocenter Craniospinal Radiation Therapy Procedure

Craniospinal irradiation (CSI) is a complex radiation technique employed to treat patients with primitive neuroectodermal tumors such as medulloblastoma or germinative brain tumors with the risk of leptomeningeal spread. In adults, this technique poses a technically challenging planning process because of the complex shape and length of the target volume. Thus, it requires multiple fields and different isocenters to guarantee the primary-tumor dose delivery. Recently, some authors have proposed the use IMRT technique for this planning with the possibility of overlapping adjacent fields. The high-dose delivery complexity demands three-dimensional dosimetry (3DD) to verify this irradiation procedure and motivated this study. We used an optical CT and a radiochromic Fricke-xylenol-orange gel with the addition of formaldehyde (FXO-f) to evaluate the doses delivered at the field junction region of this treatment. We found 96.91% as the mean passing rate using the gamma analysis with 3%/2 mm criteria at the junction region. However, the concentration of fail points in a determined region called attention to this evaluation, indicating the advantages of employing a 3DD technique in complex dose-distribution verifications.

Dedicated convolutional neural network for noise reduction in ultra-high-resolution photon-counting detector computed tomography

Objective.To develop a convolutional neural network (CNN) noise reduction technique for ultra-high-resolution photon-counting detector computed tomography (UHR-PCD-CT) that can be efficiently implemented using only clinically available reconstructed images. The developed technique was demonstrated for skeletal survey, lung screening, and head angiography (CTA).Approach. There were 39 participants enrolled in this study, each received a UHR-PCD and an energy integrating detector (EID) CT scan. The developed CNN noise reduction technique uses image-based noise insertion and UHR-PCD-CT images to train a U-Net via supervised learning. For each application, 13 patient scans were reconstructed using filtered back projection (FBP) and iterative reconstruction (IR) and allocated into training, validation, and testing datasets (9:1:3). The subtraction of FBP and IR images resulted in approximately noise-only images. The 5-slice average of IR produced a thick reference image. The CNN training input consisted of thick reference images with reinsertion of spatially decoupled noise-only images. The training target consisted of the corresponding thick reference images without noise insertion. Performance was evaluated based on difference images, line profiles, noise measurements, nonlinear perturbation assessment, and radiologist visual assessment. UHR-PCD-CT images were compared with EID images (clinical standard).Main results.Up to 89% noise reduction was achieved using the proposed CNN. Nonlinear perturbation assessment indicated reasonable retention of 1 mm radius and 1000 HU contrast signals (>80% for skeletal survey and head CTA, >50% for lung screening). A contour plot indicated reduced retention for small-radius and low contrast perturbations. Radiologists preferred CNN over IR for UHR-PCD-CT noise reduction. Additionally, UHR-PCD-CT with CNN was preferred over standard resolution EID-CT images.Significance.CT images reconstructed with very sharp kernels and/or thin sections suffer from increased image noise. Deep learning noise reduction can be used to offset noise level and increase utility of UHR-PCD-CT images.

The Actual Role of Iterative Reconstruction Algorithm Methods in Several Saudi Hospitals As A Tool For Radiation Dose Minimization of Ct Scan Examinations

Background

Iterative reconstruction algorithm (IR) techniques were developed to maintain a lower radiation dose for patients as much as possible while achieving the required image quality and medical benefits. The main purpose of the current research was to assess the level and usage extent of IR techniques in computed tomographic (CT) scan exams. Also, the obligation of practitioners in several hospitals in Saudi Arabia to implement IR in CT exams was assessed.

Material and Methodology

The recent research was based on two studies: data collection and a survey study. Data on the CT scan examinations were retrospectively collected from CT scanners. The survey was conducted using a questionnaire to evaluate radiographers’ and radiologists’ perceptions about IR and their practices with IR techniques. The statistical analysis results were performed to measure the usage strength level of IR methods.

Results and Discussions

The IR strength level of 50% was selected for nearly 80% of different CT examinations and patients of different ages and weights. About 46% of the participants had not learned about IR methods during their college studies, and 54% had not received formal training in applying IR techniques. Only 32% of the participants had adequate experience with IR. Half of the participants were not involved in the updating process of the CT protocol.

Conclusion

The results indicate that the majority of radiographer and radiologist at four different hospitals in Saudi Arabia have no explicit or understandable knowledge of selecting IR strength levels during the CT examination of patients. There is a need for more training in IR applications for both radiologists and radiographers. Training sessions were suggested to support radiographers and radiologists to efficiently utilize IR techniques to optimize image quality. Further studies are required to adjust CT exam protocols effectively to utilize the IR technique.

Fully automated image quality evaluation on patient CT: Multi-vendor and multi-reconstruction study

While the recent advancements of computed tomography (CT) technology have contributed in reducing radiation dose and image noise, an objective evaluation of image quality in patient scans has not yet been established. In this study, we present a patient-specific CT image quality evaluation method that includes fully automated measurements of noise level, structure sharpness, and alteration of structure. This study used the CT images of 120 patients from four different CT scanners reconstructed with three types of algorithm: filtered back projection (FBP), vendor-specific iterative reconstruction (IR), and a vendor-agnostic deep learning model (DLM, ClariCT.AI, ClariPi Inc.). The structure coherence feature (SCF) was used to divide an image into the homogeneous (RH) and structure edge (RS) regions, which in turn were used to localize the regions of interests (ROIs) for subsequent analysis of image quality indices. The noise level was calculated by averaging the standard deviations from five randomly selected ROIs on RH, and the mean SCFs on RS was used to estimate the structure sharpness. The structure alteration was defined by the standard deviation ratio between RS and RH on the subtraction image between FBP and IR or DLM, in which lower structure alterations indicate successful noise reduction without degradation of structure details. The estimated structure sharpness showed a high correlation of 0.793 with manually measured edge slopes. Compared to FBP, IR and DLM showed 34.38% and 51.30% noise reduction, 2.87% and 0.59% lower structure sharpness, and 2.20% and -12.03% structure alteration, respectively, on an average. DLM showed statistically superior performance to IR in all three image quality metrics. This study is expected to contribute to enhance the CT protocol optimization process by allowing a high throughput and quantitative image quality evaluation during the introduction or adjustment of lower-dose CT protocol into routine practice.

CCN-CL: A content-noise complementary network with contrastive learning for low-dose computed tomography denoising

In recent years, low-dose computed tomography (LDCT) has played an increasingly important role in the diagnosis CT to reduce the potential adverse effects of x-ray radiation on patients while maintaining the same diagnostic image quality. Current deep learning-based denoising methods applied to LDCT imaging only use normal dose CT (NDCT) images as positive examples to guide the denoising process. Recent studies on contrastive learning have proved that the original images as negative examples can also be helpful for network learning. Therefore, this paper proposes a novel content-noise complementary network with contrastive learning for an LDCT denoising task. First, to better train our proposed network, a contrastive learning loss, taking the NDCT image as a positive example and the original LDCT image as a negative example to guide the network learning is added. Furthermore, we also design a network structure that combines content-noise complementary learning strategy, attention mechanism, and deformable convolution for better network performance. In an evaluation study, we compare the performance of our designed network with some of the state-of-the-art methods in the 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset. The quantitative and qualitative evaluation results demonstrate the feasibility and effectiveness of applying our proposed CCN-CL network model as a new deep learning-based LDCT denoising method.

Performance evaluation of image reconstruction algorithms for a megavoltage computed tomography system on a helical tomotherapy unit

Objective. To evaluate the impact of image reconstruction algorithm selection, as well as imaging mode and the reconstruction interval, on image quality metrics for megavoltage computed tomography (MVCT) image acquisition for use in image-guided (IGRT) and adaptive radiotherapy (ART) on a next-generation helical tomotherapy system.Approach. A CT image quality phantom was scanned across all available acquisition modes for filtered back projection (FBP) and both iterative reconstruction (IR) algorithms available on the system. Image quality metrics including noise, uniformity, contrast, spatial resolution, and mean CT number were compared. Analysis of DICOM data was performed using ImageJ software and Python code. ANOVA single factor and Tukey's honestly significant difference post-hoc tests were utilized for statistical analysis.Main Results. Application of both IR algorithms noticeably improved noise and image contrast when compared to the FBP algorithm available on all previous-generation helical tomotherapy systems. Use of the FBP algorithm improved image uniformity and spatial resolution in the axial plane, though values for the IR algorithms were well within tolerances recommended for IGRT and/or MVCT-based ART implementation by the American Association of Physicists in Medicine (AAPM). Additionally, longitudinal resolution showed little dependence on the reconstruction algorithm, while a negligible variation in mean CT number was observed regardless of the reconstruction algorithm or acquisition parameters. Statistical analysis confirmed the significance of these results.Significance. An overall improvement in image quality for metrics most important to IGRT and ART-mainly image noise and contrast-was evident in the application of IR when compared to FBP. Furthermore, since other imaging parameters remain identical regardless of the reconstruction algorithm, this improved image quality does not come at the expense of additional patient dose or an increased scan acquisition time for otherwise identical parameters. These improvements are expected to enhance fidelity in IGRT and ART implementation.

Clinical validation of an AI-based motion correction reconstruction algorithm in cerebral CT

OBJECTIVES

To evaluate the clinical performance of an artificial intelligence (AI)-based motion correction (MC) reconstruction algorithm for cerebral CT.

METHODS

A total of 53 cases, where motion artifacts were found in the first scan so that an immediate rescan was taken, were retrospectively enrolled. While the rescanned images were reconstructed with a hybrid iterative reconstruction (IR) algorithm (reference group), images of the first scan were reconstructed with both the hybrid IR (motion group) and the MC algorithm (MC group). Image quality was compared in terms of standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mutual information (MI), as well as subjective scores. The diagnostic performance for each case was evaluated accordingly by lesion detectability or the Alberta Stroke Program Early CT Score (ASPECTS) assessment.

RESULTS

Compared with the motion group, the SNR and CNR of the MC group were significantly increased. The MSE, PSNR, SSIM, and MI with respect to the reference group were improved by 44.1%, 15.8%, 7.4%, and 18.3%, respectively (all p < 0.001). Subjective image quality indicators were scored higher for the MC than the motion group (p < 0.05). Improved lesion detectability and higher AUC (0.817 vs 0.614) in the ASPECTS assessment were found for the MC to the motion group.

CONCLUSIONS

The AI-based MC reconstruction algorithm has been clinically validated for reducing motion artifacts and improving diagnostic performance of cerebral CT.

KEY POINTS

• An artificial intelligence-based motion correction (MC) reconstruction algorithm has been clinically validated in both qualitative and quantitative manner. • The MC algorithm reduces motion artifacts in cerebral CT and increases the diagnostic confidence for brain lesions. • The MC algorithm can help avoiding rescans caused by motion and improving the efficiency of cerebral CT in the emergency department.

End-to-end deep learning for interior tomography with low-dose x-ray CT

Objective. There are several x-ray computed tomography (CT) scanning strategies used to reduce radiation dose, such as (1) sparse-view CT, (2) low-dose CT and (3) region-of-interest (ROI) CT (called interior tomography). To further reduce the dose, sparse-view and/or low-dose CT settings can be applied together with interior tomography. Interior tomography has various advantages in terms of reducing the number of detectors and decreasing the x-ray radiation dose. However, a large patient or a small field-of-view (FOV) detector can cause truncated projections, and then the reconstructed images suffer from severe cupping artifacts. In addition, although low-dose CT can reduce the radiation exposure dose, analytic reconstruction algorithms produce image noise. Recently, many researchers have utilized image-domain deep learning (DL) approaches to remove each artifact and demonstrated impressive performances, and the theory of deep convolutional framelets supports the reason for the performance improvement. Approach. In this paper, we found that it is difficult to solve coupled artifacts using an image-domain convolutional neural network (CNN) based on deep convolutional framelets. Significance. To address the coupled problem, we decouple it into two sub-problems: (i) image-domain noise reduction inside the truncated projection to solve low-dose CT problem and (ii) extrapolation of the projection outside the truncated projection to solve the ROI CT problem. The decoupled sub-problems are solved directly with a novel proposed end-to-end learning method using dual-domain CNNs. Main results. We demonstrate that the proposed method outperforms the conventional image-domain DL methods, and a projection-domain CNN shows better performance than the image-domain CNNs commonly used by many researchers.

Suppressing multi-material and streak artifacts with an accelerated 3D iterative image reconstruction algorithm for in-line X-ray phase-contrast computed tomography

In-line X-ray phase-contrast computed tomography typically contains two independent procedures: phase retrieval and computed tomography reconstruction, in which multi-material and streak artifacts are two important problems. To address these problems simultaneously, an accelerated 3D iterative image reconstruction algorithm is proposed. It merges the above-mentioned two procedures into one step, and establishes the data fidelity term in raw projection domain while introducing 3D total variation regularization term in image domain. Specifically, a transport-of-intensity equation (TIE)-based phase retrieval method is updated alternately for different areas of the multi-material sample. Simulation and experimental results validate the effectiveness and efficiency of the proposed algorithm.

Block-Iterative Reconstruction from Dynamically Selected Sparse Projection Views Using Extended Power-Divergence Measure

Iterative reconstruction of density pixel images from measured projections in computed tomography has attracted considerable attention. The ordered-subsets algorithm is an acceleration scheme that uses subsets of projections in a previously decided order. Several methods have been proposed to improve the convergence rate by permuting the order of the projections. However, they do not incorporate object information, such as shape, into the selection process. We propose a block-iterative reconstruction from sparse projection views with the dynamic selection of subsets based on an estimating function constructed by an extended power-divergence measure for decreasing the objective function as much as possible. We give a unified proposition for the inequality related to the difference between objective functions caused by one iteration as the theoretical basis of the proposed optimization strategy. Through the theory and numerical experiments, we show that nonuniform and sparse use of projection views leads to a reconstruction of higher-quality images and that an ordered subset is not the most effective for block-iterative reconstruction. The two-parameter class of extended power-divergence measures is the key to estimating an effective decrease in the objective function and plays a significant role in constructing a robust algorithm against noise.

Ultra low-parameter denoising: Trainable bilateral filter layers in computed tomography

BACKGROUND

Computed tomography (CT) is widely used as an imaging tool to visualize three-dimensional structures with expressive bone-soft tissue contrast. However, CT resolution can be severely degraded through low-dose acquisitions, highlighting the importance of effective denoising algorithms.

PURPOSE

Most data-driven denoising techniques are based on deep neural networks and, therefore, contain hundreds of thousands of trainable parameters, making them incomprehensible and prone to prediction failures. Developing understandable and robust denoising algorithms achieving state-of-the-art performance helps to minimize radiation dose while maintaining data integrity.

METHODS

This work presents an open-source CT denoising framework based on the idea of bilateral filtering. We propose a bilateral filter that can be incorporated into any deep learning pipeline and optimized in a purely data-driven way by calculating the gradient flow toward its hyperparameters and its input. Denoising in pure image-to-image pipelines and across different domains such as raw detector data and reconstructed volume, using a differentiable backprojection layer, is demonstrated. In contrast to other models, our bilateral filter layer consists of only four trainable parameters and constrains the applied operation to follow the traditional bilateral filter algorithm by design.

RESULTS

Although only using three spatial parameters and one intensity range parameter per filter layer, the proposed denoising pipelines can compete with deep state-of-the-art denoising architectures with several hundred thousand parameters. Competitive denoising performance is achieved on x-ray microscope bone data and the 2016 Low Dose CT Grand Challenge data set. We report structural similarity index measures (SSIM) of 0.7094 and 0.9674 and peak signal-to-noise ratio (PSNR) values of 33.17 and 43.07 on the respective data sets.

CONCLUSIONS

Due to the extremely low number of trainable parameters with well-defined effect, prediction reliance and data integrity is guaranteed at any time in the proposed pipelines, in contrast to most other deep learning-based denoising architectures. This article is protected by copyright. All rights reserved.

Training low dose CT denoising network without high quality reference data

Objective. Currently, the field of low-dose CT (LDCT) denoising is dominated by supervised learning based methods, which need perfectly registered pairs of LDCT and its corresponding clean reference image (normal-dose CT). However, training without clean labels is more practically feasible and significant, since it is clinically impossible to acquire a large amount of these paired samples. In this paper, a self-supervised denoising method is proposed for LDCT imaging. Approach. The proposed method does not require any clean images. In addition, the perceptual loss is used to achieve data consistency in feature domain during the denoising process. Attention blocks used in decoding phase can help further improve the image quality. Main results. In the experiments, we validate the effectiveness of our proposed self-supervised framework and compare our method with several state-of-the-art supervised and unsupervised methods. The results show that our proposed model achieves competitive performance in both qualitative and quantitative aspects to other methods. Significance. Our framework can be directly applied to most denoising scenarios without collecting pairs of training data, which is more flexible for real clinical scenario.

Limited parameter denoising for low-dose X-ray computed tomography using deep reinforcement learning

BACKGROUND

The use of deep learning has successfully solved several problems in the field of medical imaging. Deep learning has been applied to the CT denoising problem successfully. However, the use of deep learning requires large amounts of data to train deep convolutional networks (CNNs). Moreover, due to large parameter count, such deep CNNs may cause unexpected results.

PURPOSE

In this study, we introduce a novel CT denoising framework, which has interpretable behaviour, and provides useful results with limited data.

METHODS

We employ bilateral filtering in both the projection and volume domains to remove noise. To account for non-stationary noise, we tune the σ parameters of the volume for every projection view, and for every volume pixel. The tuning is carried out by two deep CNNs. Due to impracticality of labelling, the two deep CNNs are trained via a Deep-Q reinforcement learning task. The reward for the task is generated by using a custom reward function represented by a neural network. Our experiments were carried out on abdominal scans for the Mayo Clinic TCIA dataset, and the AAPM Low Dose CT Grand Challenge.

RESULTS

Our denoising framework has excellent denoising performance increasing the PSNR from 28.53 to 28.93, and increasing the SSIM from 0.8952 to 0.9204. We outperform several state-of-the-art deep CNNs, which have several orders of magnitude higher number of parameters (p-value (PSNR) = 0.000, p-value (SSIM) = 0.000). Our method does not introduce any blurring, which is introduced by MSE loss based methods, or any deep learning artifacts, which are introduced by WGAN based models. Our ablation studies show that parameter tuning and using our reward network results in the best possible results.

CONCLUSIONS

We present a novel CT denoising framework, which focuses on interpretability to deliver good denoising performance, especially with limited data. Our method outperforms state-of-the-art deep neural networks. Future work will be focused on accelerating our method, and generalizing to different geometries and body parts. This article is protected by copyright. All rights reserved.

Performance evaluation of a micro-CT system for laboratory animal imaging with iterative reconstruction capabilities

BACKGROUND

In recent years, there has been a rapid proliferation in micro-computed tomography (micro-CT) systems becoming more available for routine preclinical research, with applications in many areas including bone, lung, cancer and cardiac imaging. Micro-CT provides the means to non-invasively acquire detailed anatomical information, but high-resolution imaging comes at the cost of longer scan times and higher doses, which is not desirable given the potential risks related to x-ray radiation. To achieve dose reduction and higher throughputs without compromising image quality (noise management), fewer projections can be acquired. This is where iterative reconstruction methods can have the potential to reduce noise since these algorithms can better handle sparse projection data, compared to filtered backprojection PURPOSE: We evaluate the performance characteristics of a compact benchtop micro-CT scanner that provides iterative reconstruction capabilities with GPU-based acceleration. More specifically, we thereby investigate the potential benefit of iterative reconstruction methods for dose reduction.

METHODS

Based on a series of phantom experiments, the benchtop micro-CT system was characterized in terms of image uniformity, noise, low contrast detectability, linearity and spatial resolution. Whole-body images of a plasticized ex vivo mouse phantom were also acquired. Different acquisition protocols (general-purpose versus high-resolution, including low dose scans) and different reconstruction strategies (analytic versus iterative algorithms: FDK, ISRA, ISRA-TV) were compared.

RESULTS

Signal uniformity was maintained across the radial and axial field-of-view (no cupping effect) with an average difference in Hounsfield units (HU) between peripheral and central regions below 50. For low contrast detectability, regions with at least ∆HU of 40 to surrounding material could be discriminated (for rods of 2.5 mm diameter). A high linear correlation (R² = 0.997) was found between measured CT values and iodine concentrations (0-40 mg/ml). Modulation transfer function (MTF) calculations on a wire phantom evaluated a resolution of 10.2 lp/mm at 10% MTF that was consistent with the 8.3% MTF measured on the 50 μm bars (10 lp/mm) of a bar-pattern phantom. Noteworthy changes in signal-to-noise and contrast-to-noise values were found for different acquisition and reconstruction protocols. Our results further showed the potential of iterative reconstruction methods to deliver images with less noise and artefacts.

CONCLUSIONS

In summary, the micro-CT system for laboratory animal imaging that was evaluated in the present work was shown to provide a good combination of performance characteristics between image uniformity, low contrast detectability and resolution in short scan times. With the iterative reconstruction capabilities of this micro-CT system in mind (ISRA and ISRA-TV), the adoption of such algorithms by GPU-based acceleration enables the integration of noise reduction methods which here demonstrated potential for high quality imaging at reduced doses. This article is protected by copyright. All rights reserved.