A Methodology to Train a Convolutional Neural Network-Based Low-Dose CT Denoiser With an Accurate Image Domain Noise Insertion Technique

Computer algorithms that simulate lower-doses computed tomography (CT) images from clinical-dose images are widely available. However, most operate in the projection domain and assume access to the reconstruction method. Access to commercial reconstruction methods may often not be available in medical research, making image-domain noise simulation methods useful. However, the introduction of non-linear reconstruction methods, such as iterative and deep learning-based reconstruction, makes noise insertion in the image domain intractable, as it is not possible to determine the noise textures analytically. To develop a deep learning-based image-domain method to generate low-dose CT images from clinical-dose CT (CDCT) images for non-linear reconstruction methods. We propose a fully image domain-based method, utilizing a series of three convolutional neural networks (CNNs), which, respectively, denoise CDCT images, predict the standard deviation map of the low-dose image, and generate the noise power spectra (NPS) of local patches throughout the low-dose image. All three models have U-net-based architectures and are partly or fully three-dimensional. As a use case for this study and with no loss of generality, we use paired low-dose and clinical-dose brain CT scans. A dataset of paired scans was retrospectively obtained. All images were acquired with a wide-area detector clinical system and reconstructed using its standard clinical iterative algorithm. Each pair was registered using rigid registration to correct for motion between acquisitions. The data was randomly partitioned into training ( samples), validation ( samples), and test ( samples) sets. The performance of each of these three CNNs was validated separately. For the denoising CNN, the local standard deviation decrease, and bias were determined. For the standard deviation map CNN, the real and estimated standard deviations were compared locally. Finally, for the NPS CNN, the NPS of the synthetic and real low-dose noise were compared inside and outside the skull. Two proof-of-concept denoising studies were performed to determine if the performance of a CNN- or a gradient-based denoising filter on the synthetic low-dose data versus real data differed. The denoising network had a median decrease in noise in the cerebrospinal fluid by a factor of and introduced a median bias of HU. The network for standard deviation map estimation had a median error of HU. The noise power spectrum estimation network was able to capture the anisotropic and shift-variant nature of the noise structure by showing good agreement between the synthetic and real low-dose noise and their corresponding power spectra. The two proof of concept denoising studies showed only minimal difference in standard deviation improvement ratio between the synthetic and real low-dose CT images with the median difference between the two being 0.0 and +0.05 for the CNN- and gradient-based filter, respectively. The proposed method demonstrated good performance in generating synthetic low-dose brain CT scans without access to the projection data or to the reconstruction method. This method can generate multiple low-dose image realizations from one clinical-dose image, so it is useful for validation, optimization, and repeatability studies of image-processing algorithms.

This study aimed to evaluate image quality, the detection rate of enlarged lymph nodes, and radiation dose exposure of ultralow-dose and low-dose abdominopelvic computed tomography (CT) in patients with lymphoma. Patients with lymphoma who underwent abdominopelvic CT using dual-source scanner were retrospectively recruited from a single center. CT images were obtained at 90 kVp dual-source mode reformatted in three data sets using the advanced modelled iterative reconstruction algorithm: 100% (standard-dose CT), 66.7% (low-dose CT), and 33.3% (ultralow-dose CT). Two radiologists analyzed subjective image quality and detection of abdominal enlarged lymph nodes on ultralow-dose, low-dose, and standard-dose CT blindly and independently. The results were compared with reference standards. Three readers (two radiologists and one hematologist) reviewed overall image quality and spleen size. In total, 128 consecutive CT scans (77 complete response, 44 partial response, 6 progressive disease, and 1 initial evaluation) from 86 patients (64 B-cell lymphoma, 14 T/NK-cell lymphoma, and 8 Hodgkin’s lymphoma cases) were assessed. The enlarged lymph node-based detection rates for two readers were 97.0% (96/99) and 94.0% (93/99) on standard-dose CT, 97.0% (96/99) and 94.0% (93/99) on low-dose CT, and 94.0% (93/99) and 89.9% (89/99) on ultralow-dose CT. Overall image quality was 3.8 ± 0.5, 3.9 ± 0.5, and 4.1 ± 0.5 on ultralow-dose CT; 4.7 ± 0.4, 4.6 ± 0.5, and 4.8 ± 0.3 on low-dose CT; and 4.8 ± 0.4, 4.7 ± 0.4, and 4.9 ± 0.2 on standard-dose CT, according to two radiologists and one hematologist, respectively. Intraclass correlation coefficients of spleen size were 0.90 (95% confidence interval [CI], 0.87–0.93), 0.91 (95% CI, 0.88–0.93), and 0.91 (95% CI, 0.88–0.93) on ultralow-dose, low-dose, and standard-dose CT, respectively. Mean effective radiation doses of standard-dose, low-dose, and ultralow-dose CT were 5.7 ±1.8 mSv, 3.8 ± 1.2 mSv, and 1.9 ± 0.6 mSv, respectively. Our findings suggest that ultralow-dose and low-dose CT, even with radiation doses reduced by 66.7% and 33.3%, respectively, maintained adequate image quality. These imaging modalities may be employed for follow-up lymphoma evaluation in consideration of the long surveillance periods.

Achieving high feature reproducibility while preserving biological information is one of the main challenges for the generalizability of current radiomics studies. Non-clinical imaging variables, such as reconstruction kernels, have shown to significantly impact radiomics features. In this study, we retrain an open-source convolutional neural network (CNN) to harmonize computerized tomography (CT) images with various reconstruction kernels to improve feature reproducibility and radiomic model performance using epidermal growth factor receptor (EGFR) mutation prediction in lung cancer as a paradigm. In the training phase, the CNN was retrained and tested on 32 lung cancer patients’ CT images between two different groups of reconstruction kernels (smooth and sharp). In the validation phase, the retrained CNN was validated on an external cohort of 223 lung cancer patients’ CT images acquired using different CT scanners and kernels. The results showed that the retrained CNN could be successfully applied to external datasets with different CT scanner parameters, and harmonization of reconstruction kernels from sharp to smooth could significantly improve the performance of radiomics model in predicting EGFR mutation status in lung cancer. In conclusion, the CNN based method showed great potential in improving feature reproducibility and generalizability by harmonizing medical images with heterogeneous reconstruction kernels.

Computed tomography (CT), as a noninvasive method first invented in the early 1970s, has become a crucial technique in medical imaging with a variety of applications including detections of cancer, cardiovascular, neurological disorders, and so on. However, conventional CT scans are inherited with the issue of a high radiation dose, which may raise health concerns against radiologists and patients. Thus, CT radiation dose is intentionally decreased in exchange for human well-being. However, a lower radiation dose causes the problem of producing a CT image with degraded quality compared with a normal dose. Furthermore, quick and small-scale CT scans are often required when young patients or dynamic organs are being inspected. Therefore, CT scans may fail to capture full-angular coverage or acquire a sufficient number of scans for the patients, thereby having limited-angle and sparse-view of CT images, which makes it hard for them to reflect the accurate features of the target object. To fix these issues while not raising the time and amount of dose of CT scans, low-dose computed tomography (LDCT), limited-angle computed tomography (LACT), and sparse-view computed tomography have emerged as promising solutions for CT image reconstruction. However, traditional approaches in implementing LDCT, LACT, and sparse-view CT may struggle with insufficient data or secondary artifacts. Therefore, it is a foreseeable trend for LDCT, LACT, and sparse-view CT to combine with deep learning so that less data is required to reconstruct CT images with fewer secondary artifacts and improved qualities. For instance, DDPNet model with global residual learning + UNet-structured network and DuDoUFNet with blocked residual learning + UNet-structured network for LDCT; DIOR with residual block + UNet-structured network and DOLCE with denoising diffusion probabilistic model (DDPM) for LACT; PINER with black-box deep model + physical-consistency optimization and DreamNet with residual block + UNet-structured network for sparse-view CT. This paper aims to introduce state-of-the-art deep models in LDCT, LACT, and sparse-view CT based on workflow and data analysis.

In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. The experimental results confirmed that the proposed algorithm effectively removes low-dose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

Positron emission tomography (PET) and computed tomography (CT) play a vital role in tumor-related medical diagnosis, assessment, and treatment planning. However, full-dose PET and CT pose the risk of excessive radiation exposure to patients, whereas low-dose images compromise image quality, impacting subsequent tumor recognition and diseasediagnosis. To solve such problems, we propose a Noise-Assisted Hybrid Attention Network (NAHANet) to reconstruct full-dose PET and CT images from low-dose PET (LDPET) and CT (LDCT) images to reduce patient radiation risks while ensuring the performance of subsequent tumor recognition. NAHANet contains two branches: the noise feature prediction branch (NFPB) and the cascaded reconstruction branch. Among them, NFPB providing noise features for the cascade reconstruction branch. The cascaded reconstruction branch comprises a shallow feature extraction module and a reconstruction module which contains a series of cascaded noise feature fusion blocks (NFFBs). Among these, the NFFB fuses the features extracted from low-dose images with the noise features obtained by NFPB to improve the feature extraction capability. To validate the effectiveness of the NAHANet method, we performed experiments using two public available datasets: the Ultra-low Dose PET Imaging Challenge dataset and Low Dose CT Grand Challengedataset. As a result, the proposed NAHANet achieved higher performance on common indicators. For example, on the CT dataset, the PSNR and SSIM indicators were improved by 4.1dB and 0.06 respectively, and the rMSE indicator was reduced by 5.46 compared with the LDCT; on the PET dataset, the PSNR and SSIM was improved by 3.37dB and 0.02, and the rMSE was reduced by 9.04 compared with theLDPET. This paper proposes a transformer-based denoising algorithm, which utilizes hybrid attention to extract high-level features of low dose images and fuses noise features to optimize the denoising performance of the network, achieving good performance improvements on low-dose CT and PETdatasets.

Objective. The study aims to systematically characterize the effect of CT parameter variations on images and lung radiomic and deep features, and to evaluate the ability of different image harmonization methods to mitigate the observed variations.Approach. A retrospective in-house sinogram dataset of 100 low-dose chest CT scans was reconstructed by varying radiation dose (100%, 25%, 10%) and reconstruction kernels (smooth, medium, sharp). A set of image processing, convolutional neural network (CNNs), and generative adversarial network-based (GANs) methods were trained to harmonize all image conditions to a reference condition (100% dose, medium kernel). Harmonized scans were evaluated for image similarity using peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS), and for the reproducibility of radiomic and deep features using concordance correlation coefficient (CCC).Main Results. CNNs consistently yielded higher image similarity metrics amongst others; for Sharp/10%, which exhibited the poorest visual similarity, PSNR increased from a mean ± CI of 17.763 ± 0.492 to 31.925 ± 0.571, SSIM from 0.219 ± 0.009 to 0.754 ± 0.017, and LPIPS decreased from 0.490 ± 0.005 to 0.275 ± 0.016. Texture-based radiomic features exhibited a greater degree of variability across conditions, i.e. a CCC of 0.500 ± 0.332, compared to intensity-based features (0.972 ± 0.045). GANs achieved the highest CCC (0.969 ± 0.009 for radiomic and 0.841 ± 0.070 for deep features) amongst others. CNNs are suitable if downstream applications necessitate visual interpretation of images, whereas GANs are better alternatives for generating reproducible quantitative image features needed for machine learning applications.Significance. Understanding the efficacy of harmonization in addressing multi-parameter variability is crucial for optimizing diagnostic accuracy and a critical step toward building generalizable models suitable for clinical use.

Noise is inherent to low-dose CT acquisition. We propose to train a convolutional neural network (CNN) jointly with an adversarial CNN to estimate routine-dose CT images from low-dose CT images and hence reduce noise. A generator CNN was trained to transform low-dose CT images into routine-dose CT images using voxelwise loss minimization. An adversarial discriminator CNN was simultaneously trained to distinguish the output of the generator from routine-dose CT images. The performance of this discriminator was used as an adversarial loss for the generator. Experiments were performed using CT images of an anthropomorphic phantom containing calcium inserts, as well as patient non-contrast-enhanced cardiac CT images. The phantom and patients were scanned at 20% and 100% routine clinical dose. Three training strategies were compared: the first used only voxelwise loss, the second combined voxelwise loss and adversarial loss, and the third used only adversarial loss. The results showed that training with only voxelwise loss resulted in the highest peak signal-to-noise ratio with respect to reference routine-dose images. However, CNNs trained with adversarial loss captured image statistics of routine-dose images better. Noise reduction improved quantification of low-density calcified inserts in phantom CT images and allowed coronary calcium scoring in low-dose patient CT images with high noise levels. Testing took less than 10 s per CT volume. CNN-based low-dose CT noise reduction in the image domain is feasible. Training with an adversarial network improves the CNNs ability to generate images with an appearance similar to that of reference routine-dose CT images.

Computed Tomography (CT) images play a crucial role in medical diagnosis and treatment planning. However, acquiring CT images can be difficult in certain scenarios, such as patients inability to undergo radiation exposure or unavailability of CT scanner. An alternative solution can be generating CT images from other imaging modalities. In this work, we propose a medical image translation pipeline for generating high-quality CT images from Positron Emission Tomography (PET) images using a Pix2Pix Generative Adversarial Network (GAN), which are effective in image translation tasks. However, traditional GAN loss functions often fail to capture the structural similarity between generated and target image. To alleviate this issue, we introduce a Multi-Scale Structural Similarity Index Measure (MS-SSIM) loss in addition to the GAN loss to ensure that the generated images preserve the anatomical structures and patterns present in the real CT images. Experiments on the ‘QIN-Breast’ dataset demonstrate that our proposed architecture achieves a Peak Signal-to-Noise Ratio (PSNR) of 17.70 dB and a Structural Similarity Index Measure (SSIM) of 42.51% in the region of interest.

Low-dose computed tomography (CT) is desirable for treatment planning and simulation in radiation therapy. Multiple rescanning and replanning during the treatment course with a smaller amount of dose than a single conventional full-dose CT simulation is a crucial step in adaptive radiation therapy. We developed a machine learning-based method to improve image quality of low-dose CT for radiation therapy treatment simulation. We used a residual block concept and a self-attention strategy with a cycle-consistent adversarial network framework. A fully convolution neural network with residual blocks and attention gates (AGs) was used in the generator to enable end-to-end transformation. We have collected CT images from 30 patients treated with frameless brain stereotactic radiosurgery (SRS) for this study. These full-dose images were used to generate projection data, which were then added with noise to simulate the low-mAs scanning scenario. Low-dose CT images were reconstructed from this noise-contaminated projection data and were fed into our network along with the original full-dose CT images for training. The performance of our network was evaluated by quantitatively comparing the high-quality CT images generated by our method with the original full-dose images. When mAs is reduced to 0.5% of the original CT scan, the mean square error of the CT images obtained by our method is , with respect to the original full-dose images. The proposed method successfully improved the noise, contract-to-noise ratio, and nonuniformity level to be close to those of full-dose CT images and outperforms a state-of-the-art iterative reconstruction method. Dosimetric studies show that the average differences of dose-volume histogram metrics are ( ). These quantitative results strongly indicate that the denoised low-dose CT images using our method maintains image accuracy and quality and are accurate enough for dose calculation in current CT simulation of brain SRS treatment. We also demonstrate the great potential for low-dose CT in the process of simulation and treatment planning.

X-ray computed tomography (CT) imaging plays an essential role in disease diagnosis due to its noninvasive, painless mode and superior penetration depth. However, the resolution of the soft tissue ...

A retrospective study. To evaluate the reliability of computed tomography (CT) with low radiation dose in the assessment of implant status in patients with adolescent idiopathic scoliosis (AIS). The use of all-pedicle screw construct in scoliosis corrective surgery continues to gain increasing popularity since their introduction 1994 although their use in the thoracic spine carries a potential risk for neurovascular complications. CT is the method widely used to evaluate screw placement. Retrospective analysis of 46 consecutive low-dose spine CT in patients with AIS after posterior corrective surgery. Status of 809 titanium screws (642 thoracic) was evaluated. The degree of interobserver and intraobserver agreements about implant status was used as an indicator of the reliability of the low-dose spine CT in the assessment of accuracy of pedicle screw insertion. A new grading system has been developed for this purpose. Five types of misplacement have been evaluated: lateral, medial, and anterior cortical perforations; endplate perforation; and foraminal perforation. The analysis has shown a substantial interobserver and intraobserver agreements (kappa: 0.69 and 0.76, respectively) in differentiating pedicle screws with acceptable placement from screws with partial or total cortical perforation. None of the examinations was subjectively classified as unreliable. The study has shown that low-dose spine CT is a reliable method in evaluating screw placement in patients with AIS after posterior scoliosis surgery with titanium implants, using the here proposed grading system. The new grading system of screw misplacement was feasible and in line with the general agreement about the harmlessness of misplacement with minor pedicle breach. The reliability of low-dose spine CT in evaluation of lateral and medial cortical perforations was substantial. To reduce the radiation load, the postoperative assessment of titanium implants should be performed with low-dose CT.

Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.

Planar X-ray mammography is the standard medical imaging modality for the early detection of breast cancer. Based on advancements in digital flat-panel detector technology, dedicated x-ray computed tomography (CT) mammography is a modality under investigation that offers the potential for improved breast tumor imaging. We have implemented a prototype half cone-beam CT breast imaging system that utilizes an indirect flat-panel detector. This prototype can be used to explore and evaluate the effect of varying acquisition and reconstruction parameters on image quality. This report describes our system and characterizes the performance of the system through the analysis of Modulation Transfer Function (MTF) and Noise Power Spectrum (NPS). All CT reconstructions were made using Feldkamp's filtered backprojection algorithm. The 3D MTF was determined by the analysis of the plane spread function (PlSF) derived from the surface spread function (SSF) of reconstructed 6.3mm spheres. 3D NPS characterization was performed through the analysis of a 3D volume extracted from zero-mean CT noise of air reconstructions. The effect of varying locations on MTF and the effect of different Butterworth filter cutoff frequencies on NPS are reported. Finally, we present CT images of mastectomy excised breast tissue. Breast specimen images were acquired on our CTMS using an x-ray technique similar to the one used during performance characterization. Specimen images demonstrate the inherent CT capability to reduce the masking effect of anatomical noise. Both the quantitative system characterization and the breast specimen images continue to reinforce the hope that dedicated flat-panel detector, x-ray cone-beam CT will eventually provide enhanced breast cancer detection capability.

CT image quality enhancement via a dual-channel neural network with jointing denoising and super-resolution