Generative Adversarial Networks for Noise Reduction in Low-Dose CT

MDST: multi-domain sparse-view CT reconstruction based on convolution and swin transformer

Objective.Sparse-view computed tomography (SVCT), which can reduce the radiation doses administered to patients and hasten data acquisition, has become an area of particular interest to researchers. Most existing deep learning-based image reconstruction methods are based on convolutional neural networks (CNNs). Due to the locality of convolution and continuous sampling operations, existing approaches cannot fully model global context feature dependencies, which makes the CNN-based approaches less efficient in modeling the computed tomography (CT) images with various structural information.Approach.To overcome the above challenges, this paper develops a novel multi-domain optimization network based on convolution and swin transformer (MDST). MDST uses swin transformer block as the main building block in both projection (residual) domain and image (residual) domain sub-networks, which models global and local features of the projections and reconstructed images. MDST consists of two modules for initial reconstruction and residual-assisted reconstruction, respectively. The sparse sinogram is first expanded in the initial reconstruction module with a projection domain sub-network. Then, the sparse-view artifacts are effectively suppressed by an image domain sub-network. Finally, the residual assisted reconstruction module to correct the inconsistency of the initial reconstruction, further preserving image details.Main results. Extensive experiments on CT lymph node datasets and real walnut datasets show that MDST can effectively alleviate the loss of fine details caused by information attenuation and improve the reconstruction quality of medical images.Significance.MDST network is robust and can effectively reconstruct images with different noise level projections. Different from the current prevalent CNN-based networks, MDST uses transformer as the main backbone, which proves the potential of transformer in SVCT reconstruction.

Low-dose imaging denoising with one pair of noisy images

Low-dose imaging techniques have many important applications in diverse fields, from biological engineering to materials science. Samples can be protected from phototoxicity or radiation-induced damage using low-dose illumination. However, imaging under a low-dose condition is dominated by Poisson noise and additive Gaussian noise, which seriously affects the imaging quality, such as signal-to-noise ratio, contrast, and resolution. In this work, we demonstrate a low-dose imaging denoising method that incorporates the noise statistical model into a deep neural network. One pair of noisy images is used instead of clear target labels and the parameters of the network are optimized by the noise statistical model. The proposed method is evaluated using simulation data of the optical microscope, and scanning transmission electron microscope under different low-dose illumination conditions. In order to capture two noisy measurements of the same information in a dynamic process, we built an optical microscope that is capable of capturing a pair of images with independent and identically distributed noises in one shot. A biological dynamic process under low-dose condition imaging is performed and reconstructed with the proposed method. We experimentally demonstrate that the proposed method is effective on an optical microscope, fluorescence microscope, and scanning transmission electron microscope, and show that the reconstructed images are improved in terms of signal-to-noise ratio and spatial resolution. We believe that the proposed method could be applied to a wide range of low-dose imaging systems from biological to material science.

Generative adversarial network with radiomic feature reproducibility analysis for computed tomography denoising

BACKGROUND

Most computed tomography (CT) denoising algorithms have been evaluated using image quality analysis (IQA) methods developed for natural image, which do not adequately capture the texture details in medical imaging. Radiomics is an emerging image analysis technique that extracts texture information to provide a more objective basis for medical imaging diagnostics, overcoming the subjective nature of traditional methods. By utilizing the difficulty of reproducing radiomics features under different imaging protocols, we can more accurately evaluate the performance of CT denoising algorithms.

METHOD

We introduced radiomic feature reproducibility analysis as an evaluation metric for a denoising algorithm. Also, we proposed a low-dose CT denoising method based on a generative adversarial network (GAN), which outperformed well-known CT denoising methods.

RESULTS

Although the proposed model produced excellent results visually, the traditional image assessment metrics such as peak signal-to-noise ratio and structural similarity failed to show distinctive performance differences between the proposed method and the conventional ones. However, radiomic feature reproducibility analysis provided a distinctive assessment of the CT denoising performance. Furthermore, radiomic feature reproducibility analysis allowed fine-tuning of the hyper-parameters of the GAN.

CONCLUSION

We demonstrated that the well-tuned GAN architecture outperforms the well-known CT denoising methods. Our study is the first to introduce radiomics reproducibility analysis as an evaluation metric for CT denoising. We look forward that the study may bridge the gap between traditional objective and subjective evaluations in the clinical medical imaging field.

A GAN-based method for 3D lung tumor reconstruction boosted by a knowledge transfer approach

Three-dimensional (3D) image reconstruction of tumors has been one of the most effective techniques for accurately visualizing tumor structures and treatment with high resolution, which requires a set of two-dimensional medical images such as CT slices. In this paper we propose a novel method based on generative adversarial networks (GANs) for 3D lung tumor reconstruction by CT images. The proposed method consists of three stages: lung segmentation, tumor segmentation and 3D lung tumor reconstruction. Lung and tumor segmentation are performed using snake optimization and Gustafson-Kessel (GK) clustering. In the 3D reconstruction part first, features are extracted using the pre-trained VGG model from the tumors that detected in 2D CT slices. Then, a sequence of extracted features is fed into an LSTM to output compressed features. Finally, the compressed feature is used as input for GAN, where the generator is responsible for high-level reconstructing the 3D image of the lung tumor. The main novelty of this paper is the use of GAN to reconstruct a 3D lung tumor model for the first time, to the best of our knowledge. Also, we used knowledge transfer to extract features from 2D images to speed up the training process. The results obtained from the proposed model on the LUNA dataset showed better results than state of the art. According to HD and ED metrics, the proposed method has the lowest values ​​of 3.02 and 1.06, respectively, as compared to those of other methods. The experimental results show that the proposed method performs better than previous similar methods and it is useful to help practitioners in the treatment process.

QUANTITATIVE BIOMARKERS REPRODUCIBILITY USING GENERATIVE ADVERSARIAL APPROACHES IN REDUCED TO CONVENTIONAL DOSE CT

In recent years, several techniques for image-to-image translation by means of generative adversarial neural networks (GAN) have been proposed to learn mapping characteristics between a source and a target domain. In particular, in the medical imaging field conditional GAN frameworks with paired samples (cGAN) and unconditional cycle-consistent GANs with unpaired data (CycleGAN) have been demonstrated as a powerful scheme to model non-linear mappings that produce realistic target images from different modality sources. When proposing the usage and adaptation of these frameworks for medical image synthesis, quantitative and qualitative validation are usually performed by assessing the similarity between synthetic and target images in terms of metrics such as mean absolute error (MAE) or structural similarity (SSIM) index. However, an evaluation of clinically relevant markers showing that diagnostic information is not overlooked in the translation process is often missing. In this work, we aim at demonstrating the importance of validating medical image-to-image translation techniques by assessing their effect on the measurement of clinically relevant metrics and biomarkers. We implemented both a conditional and an unconditional approach to synthesize conventional dose chest CT scans from reduced dose CT and show that while both visually and in terms of traditional metrics the network appears to successfully minimize perceptual discrepancies, these methods are not reliable to systematically reproduce quantitative measurements of various chest biomarkers.

Applications of Artificial Intelligence in the Radiology Roundtrip: Process Streamlining, Workflow Optimization, and Beyond

There are many impactful applications of artificial intelligence (AI) in the electronic radiology roundtrip and the patient's journey through the healthcare system that go beyond diagnostic applications. These tools have the potential to improve quality and safety, optimize workflow, increase efficiency, and increase patient satisfaction. In this article, we review the role of AI for process improvement and workflow enhancement which includes applications beginning from the time of order entry, scan acquisition, applications supporting the image interpretation task, and applications supporting tasks after image interpretation such as result communication. These non-diagnostic workflow and process optimization tasks are an important part of the arsenal of potential AI tools that can streamline day to day clinical practice and patient care.

United multi-task learning for abdominal contrast-enhanced CT synthesis through joint deformable registration

Synthesizing abdominal contrast-enhanced computed tomography (CECT) images from non-enhanced CT (NECT) images is of great importance, in the delineation of radiotherapy target volumes, to reduce the risk of iodinated contrast agent and the registration error between NECT and CECT for transferring the delineations. NECT images contain structural information that can reflect the contrast difference between lesions and surrounding tissues. However, existing methods treat synthesis and registration as two separate tasks, which neglects the task collaborative and fails to address misalignment between images after the standard image pre-processing in training a CECT synthesis model. Thus, we propose an united multi-task learning (UMTL) for joint synthesis and deformable registration of abdominal CECT. Specifically, our UMTL is an end-to-end multi-task framework, which integrates a deformation field learning network for reducing the misalignment errors and a 3D generator for synthesizing CECT images. Furthermore, the learning of enhanced component images and the multi-loss function are adopted for enhancing the performance of synthetic CECT images. The proposed method is evaluated on two different resolution datasets and a separate test dataset from another center. The synthetic venous phase CECT images of the separate test dataset yield mean absolute error (MAE) of 32.78±7.27 HU, mean MAE of 24.15±5.12 HU on liver region, mean peak signal-to-noise rate (PSNR) of 27.59±2.45 dB, and mean structural similarity (SSIM) of 0.96±0.01. The Dice similarity coefficients of liver region between the true and synthetic venous phase CECT images are 0.96±0.05 (high-resolution) and 0.95±0.07 (low-resolution), respectively. The proposed method has great potential in aiding the delineation of radiotherapy target volumes.

Low-Dose CT Denoising via Sinogram Inner-Structure Transformer

Low-Dose Computed Tomography (LDCT) technique, which reduces the radiation harm to human bodies, is now attracting increasing interest in the medical imaging field. As the image quality is degraded by low dose radiation, LDCT exams require specialized reconstruction methods or denoising algorithms. However, most of the recent effective methods overlook the inner-structure of the original projection data (sinogram) which limits their denoising ability. The inner-structure of the sinogram represents special characteristics of the data in the sinogram domain. By maintaining this structure while denoising, the noise can be obviously restrained. Therefore, we propose an LDCT denoising network namely Sinogram Inner-Structure Transformer (SIST) to reduce the noise by utilizing the inner-structure in the sinogram domain. Specifically, we study the CT imaging mechanism and statistical characteristics of sinogram to design the sinogram inner-structure loss including the global and local inner-structure for restoring high-quality CT images. Besides, we propose a sinogram transformer module to better extract sinogram features. The transformer architecture using a self-attention mechanism can exploit interrelations between projections of different view angles, which achieves an outstanding performance in sinogram denoising. Furthermore, in order to improve the performance in the image domain, we propose the image reconstruction module to complementarily denoise both in the sinogram and image domain.

Fan beam CT image synthesis from cone beam CT image using nested residual UNet based conditional generative adversarial network

A radiotherapy technique called Image-Guided Radiation Therapy adopts frequent imaging throughout a treatment session. Fan Beam Computed Tomography (FBCT) based planning followed by Cone Beam Computed Tomography (CBCT) based radiation delivery drastically improved the treatment accuracy. Furtherance in terms of radiation exposure and cost can be achieved if FBCT could be replaced with CBCT. This paper proposes a Conditional Generative Adversarial Network (CGAN) for CBCT-to-FBCT synthesis. Specifically, a new architecture called Nested Residual UNet (NR-UNet) is introduced as the generator of the CGAN. A composite loss function, which comprises adversarial loss, Mean Squared Error (MSE), and Gradient Difference Loss (GDL), is used with the generator. The CGAN utilises the inter-slice dependency in the input by taking three consecutive CBCT slices to generate an FBCT slice. The model is trained using Head-and-Neck (H&N) FBCT-CBCT images of 53 cancer patients. The synthetic images exhibited a Peak Signal-to-Noise Ratio of 34.04±0.93 dB, Structural Similarity Index Measure of 0.9751±0.001 and a Mean Absolute Error of 14.81±4.70 HU. On average, the proposed model guarantees an improvement in Contrast-to-Noise Ratio four times better than the input CBCT images. The model also minimised the MSE and alleviated blurriness. Compared to the CBCT-based plan, the synthetic image results in a treatment plan closer to the FBCT-based plan. The three-slice to single-slice translation captures the three-dimensional contextual information in the input. Besides, it withstands the computational complexity associated with a three-dimensional image synthesis model. Furthermore, the results demonstrate that the proposed model is superior to the state-of-the-art methods.

COVID-19 disease identification network based on weakly supervised feature selection

The coronavirus disease 2019 (COVID-19) outbreak has resulted in countless infections and deaths worldwide, posing increasing challenges for the health care system. The use of artificial intelligence to assist in diagnosis not only had a high accuracy rate but also saved time and effort in the sudden outbreak phase with the lack of doctors and medical equipment. This study aimed to propose a weakly supervised COVID-19 classification network (W-COVNet). This network was divided into three main modules: weakly supervised feature selection module (W-FS), deep learning bilinear feature fusion module (DBFF) and Grad-CAM++ based network visualization module (Grad-Ⅴ). The first module, W-FS, mainly removed redundant background features from computed tomography (CT) images, performed feature selection and retained core feature regions. The second module, DBFF, mainly used two symmetric networks to extract different features and thus obtain rich complementary features. The third module, Grad-Ⅴ, allowed the visualization of lesions in unlabeled images. A fivefold cross-validation experiment showed an average classification accuracy of 85.3%, and a comparison with seven advanced classification models showed that our proposed network had a better performance.

Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects

Filtered back projection (FBP) has been the standard CT image reconstruction method for 4 decades. A simple, fast, and reliable technique, FBP has delivered high-quality images in several clinical applications. However, with faster and more advanced CT scanners, FBP has become increasingly obsolete. Higher image noise and more artifacts are especially noticeable in lower-dose CT imaging using FBP. This performance gap was partly addressed by model-based iterative reconstruction (MBIR). Yet, its "plastic" image appearance and long reconstruction times have limited widespread application. Hybrid iterative reconstruction partially addressed these limitations by blending FBP with MBIR and is currently the state-of-the-art reconstruction technique. In the past 5 years, deep learning reconstruction (DLR) techniques have become increasingly popular. DLR uses artificial intelligence to reconstruct high-quality images from lower-dose CT faster than MBIR. However, the performance of DLR algorithms relies on the quality of data used for model training. Higher-quality training data will become available with photon-counting CT scanners. At the same time, spectral data would greatly benefit from the computational abilities of DLR. This review presents an overview of the principles, technical approaches, and clinical applications of DLR, including metal artifact reduction algorithms. In addition, emerging applications and prospects are discussed.

Automated identification of myocardial perfusion defects in dynamic cardiac computed tomography using deep learning

PURPOSE

The purpose of this study was to develop and evaluate deep convolutional neural network (CNN) models for quantifying myocardial blood flow (MBF) as well as for identifying myocardial perfusion defects in dynamic cardiac computed tomography (CT) images.

METHODS

Adenosine stress cardiac CT perfusion data acquired from 156 patients having or being suspected with coronary artery disease were considered for model development and validation. U-net-based deep CNN models were developed to segment the aorta and myocardium and to localize anatomical landmarks. Color-coded MBF maps were obtained in short-axis slices from the apex to the base level and were used to train a deep CNN classifier. Three binary classification models were built for the detection of perfusion defect in the left anterior descending artery (LAD), the right coronary artery (RCA), and the left circumflex artery (LCX) territories.

RESULTS

Mean Dice scores were 0.94 (±0.07) and 0.86 (±0.06) for the aorta and myocardial deep learning-based segmentations, respectively. With the localization U-net, mean distance errors were 3.5 (±3.5) mm and 3.8 (±2.4) mm for the basal and apical center points, respectively. The classification models identified perfusion defects with the accuracy of mean area under the receiver operating curve (AUROC) values of 0.959 (±0.023) for LAD, 0.949 (±0.016) for RCA, and 0.957 (±0.021) for LCX.

CONCLUSION

The presented method has the potential to fully automate the quantification of MBF and subsequently identify the main coronary artery territories with myocardial perfusion defects in dynamic cardiac CT perfusion.

Linearized Analysis of Noise and Resolution for DL-Based Image Generation

Deep-learning (DL) based CT image generation methods are often evaluated using RMSE and SSIM. By contrast, conventional model-based image reconstruction (MBIR) methods are often evaluated using image properties such as resolution, noise, bias. Calculating such image properties requires time consuming Monte Carlo (MC) simulations. For MBIR, linearized analysis using first order Taylor expansion has been developed to characterize noise and resolution without MC simulations. This inspired us to investigate if linearization can be applied to DL networks to enable efficient characterization of resolution and noise. We used FBPConvNet as an example DL network and performed extensive numerical evaluations, including both computer simulations and real CT data. Our results showed that network linearization works well under normal exposure settings. For such applications, linearization can characterize image noise and resolutions without running MC simulations. We provide with this work the computational tools to implement network linearization. The efficiency and ease of implementation of network linearization can hopefully popularize the physics-related image quality measures for DL applications. Our methodology is general; it allows flexible compositions of DL nonlinear modules and linear operators such as filtered-backprojection (FBP). For the latter, we develop a generic method for computing the covariance images that is needed for network linearization.

3D-MedTranCSGAN: 3D Medical Image Transformation using CSGAN

Computer vision techniques are a rapidly growing area of transforming medical images for various specific medical applications. In an end-to-end application, this paper proposes a 3D Medical Image Transformation Using a CSGAN model named a 3D-MedTranCSGAN. The 3D-MedTranCSGAN model is an integration of non-adversarial loss components and the Cyclic Synthesized Generative Adversarial Networks. The proposed model utilizes PatchGAN's discriminator network, to penalize the difference between the synthesized image and the original image. The model also computes the non-adversary loss functions such as content, perception, and style transfer losses. 3DCascadeNet is a new generator architecture introduced in the paper, which is used to enhance the perceptiveness of the transformed medical image by encoding-decoding pairs. We use the 3D-MedTranCSGAN model to do various tasks without modifying specific applications: PET to CT image transformation; reconstruction of CT to PET; modification of movement artefacts in MR images; and removing noise in PET images. We found that 3D-MedTranCSGAN outperformed other transformation methods in our experiments. For the first task, the proposed model yields SSIM is 0.914, PSNR is 26.12, MSE is 255.5, VIF is 0.4862, UQI is 0.9067 and LPIPs is 0.2284. For the second task, the model yields 0.9197, 25.7, 257.56, 0.4962, 0.9027, 0.2262. For the third task, the model yields 0.8862, 24.94, 0.4071, 0.6410, 0.2196. For the final task, the model yields 0.9521, 33.67, 33.57, 0.6091, 0.9255, 0.0244. Based on the result analysis, the proposed model outperforms the other techniques.

Comparison of Chest Radiograph Captions Based on Natural Language Processing vs Completed by Radiologists

IMPORTANCE

Artificial intelligence (AI) can interpret abnormal signs in chest radiography (CXR) and generate captions, but a prospective study is needed to examine its practical value.

OBJECTIVE

To prospectively compare natural language processing (NLP)-generated CXR captions and the diagnostic findings of radiologists.

DESIGN, SETTING, AND PARTICIPANTS

A multicenter diagnostic study was conducted. The training data set included CXR images and reports retrospectively collected from February 1, 2014, to February 28, 2018. The retrospective test data set included consecutive images and reports from April 1 to July 31, 2019. The prospective test data set included consecutive images and reports from May 1 to September 30, 2021.

EXPOSURES

A bidirectional encoder representation from a transformers model was used to extract language entities and relationships from unstructured CXR reports to establish 23 labels of abnormal signs to train convolutional neural networks. The participants in the prospective test group were randomly assigned to 1 of 3 different caption generation models: a normal template, NLP-generated captions, and rule-based captions based on convolutional neural networks. For each case, a resident drafted the report based on the randomly assigned captions and an experienced radiologist finalized the report blinded to the original captions. A total of 21 residents and 19 radiologists were involved.

MAIN OUTCOMES AND MEASURES

Time to write reports based on different caption generation models.

RESULTS

The training data set consisted of 74 082 cases (39 254 [53.0%] women; mean [SD] age, 50.0 [17.1] years). In the retrospective (n = 8126; 4345 [53.5%] women; mean [SD] age, 47.9 [15.9] years) and prospective (n = 5091; 2416 [47.5%] women; mean [SD] age, 45.1 [15.6] years) test data sets, the mean (SD) area under the curve of abnormal signs was 0.87 (0.11) in the retrospective data set and 0.84 (0.09) in the prospective data set. The residents' mean (SD) reporting time using the NLP-generated model was 283 (37) seconds-significantly shorter than the normal template (347 [58] seconds; P < .001) and the rule-based model (296 [46] seconds; P < .001). The NLP-generated captions showed the highest similarity to the final reports with a mean (SD) bilingual evaluation understudy score of 0.69 (0.24)-significantly higher than the normal template (0.37 [0.09]; P < .001) and the rule-based model (0.57 [0.19]; P < .001).

CONCLUSIONS AND RELEVANCE

In this diagnostic study of NLP-generated CXR captions, prior information provided by NLP was associated with greater efficiency in the reporting process, while maintaining good consistency with the findings of radiologists.

A generative adversarial network with "zero-shot" learning for positron image denoising

Positron imaging technology has shown good practical value in industrial non-destructive testing, but the noise and artifacts generated during the imaging process of flow field images will directly affect the accuracy of industrial fault diagnosis. Therefore, how to obtain high-quality reconstructed images of the positron flow field is a challenging problem. In the existing image denoising methods, the denoising performance of positron images of industrial flow fields in special fields still needs to be strengthened. Considering the characteristics of few sample data and strong regularity of positron flow field image,in this work, we propose a new method for image denoising of positron flow field, which is based on a generative adversarial network with zero-shot learning. This method realizes image denoising under the condition of small sample data, and constrains image generation by constructing the extraction model of image internal features. The experimental results show that the proposed method can reduce the noise while retaining the key information of the image. It has also achieved good performance in the practical application of industrial flow field positron imaging.

An application of deep dual convolutional neural network for enhanced medical image denoising

This work investigates the medical image denoising (MID) application of the dual denoising network (DudeNet) model for chest X-ray (CXR). The DudeNet model comprises four components: a feature extraction block with a sparse mechanism, an enhancement block, a compression block, and a reconstruction block. The developed model uses residual learning to boost denoising performance and batch normalization to accelerate the training process. The name proposed for this model is dual convolutional medical image-enhanced denoising network (DCMIEDNet). The peak signal-to-noise ratio (PSNR) and structure similarity index measurement (SSIM) are used to assess the MID performance for five different additive white Gaussian noise (AWGN) levels of σ = 15, 25, 40, 50, and 60 in CXR images. Presented investigations revealed that the PSNR and SSIM offered by DCMIEDNet are better than several popular state-of-the-art models such as block matching and 3D filtering, denoising convolutional neural network, and feature-guided denoising convolutional neural network. In addition, it is also superior to the recently reported MID models like deep convolutional neural network with residual learning, real-valued medical image denoising network, and complex-valued medical image denoising network. Therefore, based on the presented experiments, it is concluded that applying the DudeNet methodology for DCMIEDNet promises to be quite helpful for physicians.

Systematic Review of Advanced AI Methods for Improving Healthcare Data Quality in Post COVID-19 Era

At the beginning of the COVID-19 pandemic, there was significant hype about the potential impact of artificial intelligence (AI) tools in combatting COVID-19 on diagnosis, prognosis, or surveillance. However, AI tools have not yet been widely successful. One of the key reason is the COVID-19 pandemic has demanded faster real-time development of AI-driven clinical and health support tools, including rapid data collection, algorithm development, validation, and deployment. However, there was not enough time for proper data quality control. Learning from the hard lessons in COVID-19, we summarize the important health data quality challenges during COVID-19 pandemic such as lack of data standardization, missing data, tabulation errors, and noise and artifact. Then we conduct a systematic investigation of computational methods that address these issues, including emerging novel advanced AI data quality control methods that achieve better data quality outcomes and, in some cases, simplify or automate the data cleaning process. We hope this article can assist healthcare community to improve health data quality going forward with novel AI development.

Great debates in cardiac computed tomography: OPINION: "Artificial intelligence and the future of cardiovascular CT - Managing expectation and challenging hype"

This manuscript has been written as a follow-up to the "AI/ML great debate" featured at the 2021 Society of Cardiovascular Computed Tomography (SCCT) Annual Scientific Meeting. In debate style, we highlighti the need for expectation management of AI/ML, debunking the hype around current AI techniques, and countering the argument that in its current day format AI/ML is the "silver bullet" for the interpretation of daily clinical CCTA practice.

High-resolution knee plain radiography image synthesis using style generative adversarial network adaptive discriminator augmentation

In this retrospective study, 10,000 anteroposterior (AP) radiography of the knee from a single institution was used to create medical data set that are more balanced and cheaper to create. Two types of convolutional networks were used, deep convolutional GAN (DCGAN) and Style GAN Adaptive Discriminator Augmentation (StyleGAN2-ADA). To verify the quality of generated images from StyleGAN2-ADA compared to real ones, the Visual Turing test was conducted by two computer vision experts, two orthopedic surgeons, and a musculoskeletal radiologist. For quantitative analysis, the Fréchet inception distance (FID), and principal component analysis (PCA) were used. Generated images reproduced the features of osteophytes, joint space narrowing, and sclerosis. Classification accuracy of the experts was 34%, 43%, 44%, 57%, and 50%. FID between the generated images and real ones was 2.96, which is significantly smaller than another medical data set (BreCaHAD = 15.1). PCA showed that no significant difference existed between the PCs of the real and generated images (p > 0.05). At least 2000 images were required to make reliable images optimally. By performing PCA in latent space, we were able to control the desired PC that show a progression of arthritis. Using a GAN, we were able to generate knee X-ray images that accurately reflected the characteristics of the arthritis progression stage, which neither human experts nor artificial intelligence could discern apart from the real images. In summary, our research opens up the potential to adopt a generative model to synthesize realistic anonymous images that can also solve data scarcity and class inequalities.

Brain PET and Cerebrovascular Disease

Cerebrovascular disease encompasses a broad spectrum of diseases such as stroke, hemorrhage, and cognitive decline associated with vascular narrowing, obstruction, rupture, and inflammation, among other issues. Recent advances in hardware and software have led to improvements in brain PET. Although still in its infancy, machine learning using convolutional neural networks is gaining traction in this area, often with a focus on providing high-quality images with reduced noise using a shorter acquisition time or less radiation exposure for the patient.

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.

Solving Inverse Problems With Deep Neural Networks - Robustness Included?

In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical fields, a verification of their reliability appears mandatory. Recent works have pointed out instabilities of deep neural networks for several image reconstruction tasks. In analogy to adversarial attacks in classification, it was shown that slight distortions in the input domain may cause severe artifacts. The present article sheds new light on this concern, by conducting an extensive study of the robustness of deep-learning-based algorithms for solving underdetermined inverse problems. This covers compressed sensing with Gaussian measurements as well as image recovery from Fourier and Radon measurements, including a real-world scenario for magnetic resonance imaging (using the NYU-fastMRI dataset). Our main focus is on computing adversarial perturbations of the measurements that maximize the reconstruction error. A distinctive feature of our approach is the quantitative and qualitative comparison with total-variation minimization, which serves as a provably robust reference method. In contrast to previous findings, our results reveal that standard end-to-end network architectures are not only resilient against statistical noise, but also against adversarial perturbations. All considered networks are trained by common deep learning techniques, without sophisticated defense strategies.

Truncated total variation in fractional B-spline wavelet transform for micro-CT image denoising

BACKGROUND

In medical applications, computed tomography (CT) is widely used to evaluate various sample characteristics. However, image quality of CT reconstruction can be degraded due to artifacts.

OBJECTIVE

To propose and test a truncated total variation (truncation TV) model to solve the problem of large penalties for the total variation (TV) model.

METHODS

In this study, a truncated TV image denoising model in the fractional B-spline wavelet domain is developed to obtain the best solution. The method is validated by the analysis of CT reconstructed images of actual biological Pigeons samples. For this purpose, several indices including the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) and mean square error (MSE) are used to evaluate the quality of images.

RESULTS

Comparing to the conventional truncated TV model that yields 22.55, 0.688 and 361.17 in PSNR, SSIM and MSE, respectively, using the proposed fractional B-spline-truncated TV model, the computed values of these evaluation indices change to 24.24, 0.898 and 244.98, respectively, indicating substantial reduction of image noise with higher PSNR and SSIM, and lower MSE.

CONCLUSIONS

Study results demonstrate that compared with many classic image denoising methods, the new denoising algorithm proposed in this study can more effectively suppresses the reconstructed CT image artifacts while maintaining the detailed image structure.

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.

Metal artifact reduction in kV CT images throughout two-step sequential deep convolutional neural networks by combining multi-modal imaging (MARTIAN)

This work attempted to construct a new metal artifact reduction (MAR) framework in kilo-voltage (kV) computed tomography (CT) images by combining (1) deep learning and (2) multi-modal imaging, defined as MARTIAN (Metal Artifact Reduction throughout Two-step sequentIAl deep convolutional neural Networks). Most CNNs under supervised learning require artifact-free images to artifact-contaminated images for artifact correction. Mega-voltage (MV) CT is insensitive to metal artifacts, unlike kV CT due to different physical characteristics, which can facilitate the generation of artifact-free synthetic kV CT images throughout the first network (Network 1). The pairs of true kV CT and artifact-free kV CT images after post-processing constructed a subsequent network (Network 2) to conduct the actual MAR process. The proposed framework was implemented by GAN from 90 scans for head-and-neck and brain radiotherapy and validated with 10 independent cases against commercial MAR software. The artifact-free kV CT images following Network 1 and post-processing led to structural similarity (SSIM) of 0.997, and mean-absolute-error (MAE) of 10.2 HU, relative to true kV CT. Network 2 in charge of actual MAR successfully suppressed metal artifacts, relative to commercial MAR, while retaining the detailed imaging information, yielding the SSIM of 0.995 against 0.997 from the commercial MAR.

Segmentation-guided Denoising Network for Low-dose CT Imaging

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

RAD-UNet: a Residual, Attention-Based, Dense UNet for CT Sparse Reconstruction

To suppress the streak artifacts in images reconstructed from sparse-view projections in computed tomography (CT), a residual, attention-based, dense UNet (RAD-UNet) deep network is proposed to achieve accurate sparse reconstruction. The filtered back projection (FBP) algorithm is used to reconstruct the CT image with streak artifacts from sparse-view projections. Then, the image is processed by the RAD-UNet to suppress streak artifacts and obtain high-quality CT image. Those images with streak artifacts are used as the input of the RAD-UNet, and the output-label images are the corresponding high-quality images. Through training via the large-scale training data, the RAD-UNet can obtain the capability of suppressing streak artifacts. This network combines residual connection, attention mechanism, dense connection and perceptual loss. This network can improve the nonlinear fitting capability and the performance of suppressing streak artifacts. The experimental results show that the RAD-UNet can improve the reconstruction accuracy compared with three existing representative deep networks. It may not only suppress streak artifacts but also better preserve image details. The proposed networks may be readily applied to other image processing tasks including image denoising, image deblurring, and image super-resolution.

Computed Tomography of the Spine

The introduction of the first whole-body CT scanner in 1974 marked the beginning of cross-sectional spine imaging. In the last decades, the technological advancement, increasing availability and clinical success of CT led to a rapidly growing number of CT examinations, also of the spine. After initially being primarily used for trauma evaluation, new indications continued to emerge, such as assessment of vertebral fractures or degenerative spine disease, preoperative and postoperative evaluation, or CT-guided interventions at the spine; however, improvements in patient management and clinical outcomes come along with higher radiation exposure, which increases the risk for secondary malignancies. Therefore, technical developments in CT acquisition and reconstruction must always include efforts to reduce the radiation dose. But how exactly can the dose be reduced? What amount of dose reduction can be achieved without compromising the clinical value of spinal CT examinations and what can be expected from the rising stars in CT technology: artificial intelligence and photon counting CT? In this article, we try to answer these questions by systematically reviewing dose reduction techniques with respect to the major clinical indications of spinal CT. Furthermore, we take a concise look on the dose reduction potential of future developments in CT hardware and software.

Clinician's guide to trustworthy and responsible artificial intelligence in cardiovascular imaging

A growing number of artificial intelligence (AI)-based systems are being proposed and developed in cardiology, driven by the increasing need to deal with the vast amount of clinical and imaging data with the ultimate aim of advancing patient care, diagnosis and prognostication. However, there is a critical gap between the development and clinical deployment of AI tools. A key consideration for implementing AI tools into real-life clinical practice is their "trustworthiness" by end-users. Namely, we must ensure that AI systems can be trusted and adopted by all parties involved, including clinicians and patients. Here we provide a summary of the concepts involved in developing a "trustworthy AI system." We describe the main risks of AI applications and potential mitigation techniques for the wider application of these promising techniques in the context of cardiovascular imaging. Finally, we show why trustworthy AI concepts are important governing forces of AI development.

ERA-WGAT: Edge-enhanced residual autoencoder with a window-based graph attention convolutional network for low-dose CT denoising

Computed tomography (CT) has become a powerful tool for medical diagnosis. However, minimizing X-ray radiation risk for the patient poses significant challenges to obtain suitable low dose CT images. Although various low-dose CT methods using deep learning techniques have produced impressive results, convolutional neural network based methods focus more on local information and hence are very limited for non-local information extraction. This paper proposes ERA-WGAT, a residual autoencoder incorporating an edge enhancement module that performs convolution with eight types of learnable operators providing rich edge information and a window-based graph attention convolutional network that combines static and dynamic attention modules to explore non-local self-similarity. We use the compound loss function that combines MSE loss and multi-scale perceptual loss to mitigate the over-smoothing problem. Compared with current low-dose CT denoising methods, ERA-WGAT confirmed superior noise suppression and perceived image quality.

Synthetic Time of Flight Magnetic Resonance Angiography Generation Model Based on Cycle-Consistent Generative Adversarial Network Using PETRA-MRA in the Patients With Treated Intracranial Aneurysm

BACKGROUND

Pointwise encoding time reduction with radial acquisition (PETRA) magnetic resonance angiography (MRA) is useful for evaluating intracranial aneurysm recurrence, but the problem of severe background noise and low peripheral signal-to-noise ratio (SNR) remain. Deep learning could reduce noise using high- and low-quality images.

PURPOSE

To develop a cycle-consistent generative adversarial network (cycleGAN)-based deep learning model to generate synthetic TOF (synTOF) using PETRA.

STUDY TYPE

Retrospective.

POPULATION

A total of 377 patients (mean age: 60 ± 11; 293 females) with treated intracranial aneurysms who underwent both PETRA and TOF from October 2017 to January 2021. Data were randomly divided into training (49.9%, 188/377) and validation (50.1%, 189/377) groups.

FIELD STRENGTH/SEQUENCE

Ultra-short echo time and TOF-MRA on a 3-T MR system.

ASSESSMENT

For the cycleGAN model, the peak SNR (PSNR) and structural similarity (SSIM) were evaluated. Image quality was compared qualitatively (5-point Likert scale) and quantitatively (SNR). A multireader diagnostic optimality evaluation was performed with 17 radiologists (experience of 1-18 years).

STATISTICAL TESTS

Generalized estimating equation analysis, Friedman's test, McNemar test, and Spearman's rank correlation. P < 0.05 indicated statistical significance.

RESULTS

The PSNR and SSIM between synTOF and TOF were 17.51 [16.76; 18.31] dB and 0.71 ± 0.02. The median values of overall image quality, noise, sharpness, and vascular conspicuity were significantly higher for synTOF than for PETRA (4.00 [4.00; 5.00] vs. 4.00 [3.00; 4.00]; 5.00 [4.00; 5.00] vs. 3.00 [2.00; 4.00]; 4.00 [4.00; 4.00] vs. 4.00 [3.00; 4.00]; 3.00 [3.00; 4.00] vs. 3.00 [2.00; 3.00]). The SNRs of the middle cerebral arteries were the highest for synTOF (synTOF vs. TOF vs. PETRA; 63.67 [43.25; 105.00] vs. 52.42 [32.88; 74.67] vs. 21.05 [12.34; 37.88]). In the multireader evaluation, there was no significant difference in diagnostic optimality or preference between synTOF and TOF (19.00 [18.00; 19.00] vs. 20.00 [18.00; 20.00], P = 0.510; 8.00 [6.00; 11.00] vs. 11.00 [9.00, 14.00], P = 1.000).

DATA CONCLUSION

The cycleGAN-based deep learning model provided synTOF free from background artifact. The synTOF could be a versatile alternative to TOF in patients who have undergone PETRA for evaluating treated aneurysms.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Medical image translation using an edge-guided generative adversarial network with global-to-local feature fusion

In this paper, we propose a framework based deep learning for medical image translation using paired and unpaired training data. Initially, a deep neural network with an encoder-decoder structure is proposed for image-to-image translation using paired training data. A multi-scale context aggregation approach is then used to extract various features from different levels of encoding, which are used during the corresponding network decoding stage. At this point, we further propose an edge-guided generative adversarial network for image-to-image translation based on unpaired training data. An edge constraint loss function is used to improve network performance in tissue boundaries. To analyze framework performance, we conducted five different medical image translation tasks. The assessment demonstrates that the proposed deep learning framework brings significant improvement beyond state-of-the-arts.

The current and future roles of artificial intelligence in pediatric radiology

Artificial intelligence (AI) is a broad and complicated concept that has begun to affect many areas of medicine, perhaps none so much as radiology. While pediatric radiology has been less affected than other radiology subspecialties, there are some well-developed and some nascent applications within the field. This review focuses on the use of AI within pediatric radiology for image interpretation, with descriptive summaries of the literature to date. We highlight common features that enable successful application of the technology, along with some of the limitations that can inhibit the development of this field. We present some ideas for further research in this area and challenges that must be overcome, with an understanding that technology often advances in unpredictable ways.

Deep-Learning-Based Ultrasound Sound-Speed Tomography Reconstruction with Tikhonov Pseudo-Inverse Priori

Ultrasound sound-speed tomography (USST) is a promising technology for breast imaging and breast cancer detection. Its reconstruction is a complex non-linear mapping from the projection data to the sound-speed image (SSI). The traditional reconstruction methods include mainly the ray-based methods and the waveform-based methods. The ray-based methods with linear approximation have low computational cost but low reconstruction quality; the full wave-based methods with the complex non-linear model have high quality but high cost. To achieve both high quality and low cost, we introduced traditional linear approximation as prior knowledge into a deep neural network and treated the complex non-linear mapping of USST reconstruction as a combination of linear mapping and non-linear mapping. In the proposed method, the linear mapping was seamlessly implemented with a fully connected layer and initialized using the Tikhonov pseudo-inverse matrix. The non-linear mapping was implemented using a U-shape Net (U-Net). Furthermore, we proposed the Tikhonov U-shape net (TU-Net), in which the linear mapping was done before the non-linear mapping, and the U-shape Tikhonov net (UT-Net), in which the non-linear mapping was done before the linear mapping. Moreover, we conducted simulations and experiments for evaluation. In the numerical simulation, the root-mean-squared error was 6.49 and 4.29 m/s for the UT-Net and TU-Net, the peak signal-to-noise ratio was 49.01 and 52.90 dB, the structural similarity was 0.9436 and 0.9761 and the reconstruction time was 10.8 and 11.3 ms, respectively. In this study, the SSIs obtained with the proposed methods exhibited high sound-speed accuracy. Both the UT-Net and the TU-Net achieved high quality and low computational cost.

Edge feature extraction-based dual CNN for LDCT denoising

In low-dose computed tomography (LDCT) denoising tasks, it is often difficult to balance edge/detail preservation and noise/artifact reduction. To solve this problem, we propose a dual convolutional neural network (CNN) based on edge feature extraction (Ed-DuCNN) for LDCT. Ed-DuCNN consists of two branches. One branch is the edge feature extraction subnet (Edge_Net) that can fully extract the edge details in the image. The other branch is the feature fusion subnet (Fusion_Net) that introduces an attention mechanism to fuse edge features and noisy image features. Specifically, first, shallow edge-specific detail features are extracted by trainable Sobel convolutional blocks and then are integrated into Edge_Net together with the LDCT images to obtain deep edge detail features. Finally, the input image, shallow edge detail, and deep edge detail features are fused in Fusion_Net to generate the final denoised image. The experimental results show that the proposed Ed-DuCNN can achieve competitive performance in terms of quantitative metrics and visual perceptual quality compared with that of state-of-the-art methods.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Image Recovery from Synthetic Noise Artifacts in CT Scans Using Modified U-Net

Computed Tomography (CT) is commonly used for cancer screening as it utilizes low radiation for the scan. One problem with low-dose scans is the noise artifacts associated with low photon count that can lead to a reduced success rate of cancer detection during radiologist assessment. The noise had to be removed to restore detail clarity. We propose a noise removal method using a new model Convolutional Neural Network (CNN). Even though the network training time is long, the result is better than other CNN models in quality score and visual observation. The proposed CNN model uses a stacked modified U-Net with a specific number of feature maps per layer to improve the image quality, observable on an average PSNR quality score improvement out of 174 images. The next best model has 0.54 points lower in the average score. The score difference is less than 1 point, but the image result is closer to the full-dose scan image. We used separate testing data to clarify that the model can handle different noise densities. Besides comparing the CNN configuration, we discuss the denoising quality of CNN compared to classical denoising in which the noise characteristics affect quality.

Wavelet subband-specific learning for low-dose computed tomography denoising

Deep neural networks have shown great improvements in low-dose computed tomography (CT) denoising. Early algorithms were primarily optimized to obtain an accurate image with low distortion between the denoised image and reference full-dose image at the cost of yielding an overly smoothed unrealistic CT image. Recent research has sought to preserve the fine details of denoised images with high perceptual quality, which has been accompanied by a decrease in objective quality due to a trade-off between perceptual quality and distortion. We pursue a network that can generate accurate and realistic CT images with high objective and perceptual quality within one network, achieving a better perception-distortion trade-off. To achieve this goal, we propose a stationary wavelet transform-assisted network employing the characteristics of high- and low-frequency domains of the wavelet transform and frequency subband-specific losses defined in the wavelet domain. We first introduce a stationary wavelet transform for the network training procedure. Then, we train the network using objective loss functions defined for high- and low-frequency domains to enhance the objective quality of the denoised CT image. With this network design, we train the network again after replacing the objective loss functions with perceptual loss functions in high- and low-frequency domains. As a result, we acquired denoised CT images with high perceptual quality using this strategy while minimizing the objective quality loss. We evaluated our algorithms on the phantom and clinical images, and the quantitative and qualitative results indicate that ours outperform the existing state-of-the-art algorithms in terms of objective and perceptual quality.

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.

Virtual contrast enhancement for CT scans of abdomen and pelvis

Contrast agents are commonly used to highlight blood vessels, organs, and other structures in magnetic resonance imaging (MRI) and computed tomography (CT) scans. However, these agents may cause allergic reactions or nephrotoxicity, limiting their use in patients with kidney dysfunctions. In this paper, we propose a generative adversarial network (GAN) based framework to automatically synthesize contrast-enhanced CTs directly from the non-contrast CTs in the abdomen and pelvis region. The respiratory and peristaltic motion can affect the pixel-level mapping of contrast-enhanced learning, which makes this task more challenging than other body parts. A perceptual loss is introduced to compare high-level semantic differences of the enhancement areas between the virtual contrast-enhanced and actual contrast-enhanced CT images. Furthermore, to accurately synthesize the intensity details as well as remain texture structures of CT images, a dual-path training schema is proposed to learn the texture and structure features simultaneously. Experiment results on three contrast phases (i.e. arterial, portal, and delayed phase) show the potential to synthesize virtual contrast-enhanced CTs directly from non-contrast CTs of the abdomen and pelvis for clinical evaluation.

Finetuned Super-Resolution Generative Adversarial Network (Artificial Intelligence) Model for Calcium Deblooming in Coronary Computed Tomography Angiography

The purpose of this study was to finetune a deep learning model, real-enhanced super-resolution generative adversarial network (Real-ESRGAN), and investigate its diagnostic value in calcified coronary plaques with the aim of suppressing blooming artifacts for the further improvement of coronary lumen assessment. We finetuned the Real-ESRGAN model and applied it to 50 patients with 184 calcified plaques detected at three main coronary arteries (left anterior descending [LAD], left circumflex [LCx] and right coronary artery [RCA]). Measurements of coronary stenosis were collected from original coronary computed tomography angiography (CCTA) and Real-ESRGAN-processed images, including Real-ESRGAN-high-resolution, Real-ESRGAN-average and Real-ESRGAN-median (Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M) with invasive coronary angiography as the reference. Our results showed specificity and positive predictive value (PPV) of the Real-ESRGAN-processed images were improved at all of the three coronary arteries, leading to significant reduction in the false positive rates when compared to those of the original CCTA images. The specificity and PPV of the Real-ESRGAN-M images were the highest at the RCA level, with values being 80% (95% CI: 64.4%, 90.9%) and 61.9% (95% CI: 45.6%, 75.9%), although the sensitivity was reduced to 81.3% (95% CI: 54.5%, 95.9%) due to false negative results. The corresponding specificity and PPV of the Real-ESRGAN-M images were 51.9 (95% CI: 40.3%, 63.5%) and 31.5% (95% CI: 25.8%, 37.8%) at LAD, 62.5% (95% CI: 40.6%, 81.2%) and 43.8% (95% CI: 30.3%, 58.1%) at LCx, respectively. The area under the receiver operating characteristic curve was also the highest at the RCA with value of 0.76 (95% CI: 0.64, 0.89), 0.84 (95% CI: 0.73, 0.94), 0.85 (95% CI: 0.75, 0.95) and 0.73 (95% CI: 0.58, 0.89), corresponding to original CCTA, Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M images, respectively. This study proves that the finetuned Real-ESRGAN model significantly improves the diagnostic performance of CCTA in assessing calcified plaques.