Investigation of Low-Dose CT Image Denoising Using Unpaired Deep Learning Methods

Towards ultra-low-dose CT for detecting pulmonary nodules using DenseNet

Low-radiation techniques should be used to detect and follow lung nodules on CT images, but reducing radiation dose to ultra-low-dose CT with submilliSievert dose level would drastically impede image quality and sensitivity for nodule detection. This study investigated the feasibility of using DenseNet to suppress image noise in ultra-low-dose CT for lung cancer screening. DenseNet was trained using input-label pairs from 1, 2, 4, and 6 patients. After training, the model was tested with chest CT from 14 patients that were not used in training process. Seven patients have solid nodules and 7 patients have subsolid nodules. Root mean square error (RMSE) and peak signal-to-noise ratio (PSNR) were calculated to quantify the difference between reference and test images. The contrast-to-noise ratio (CNR) between lung nodule and lung parenchyma was calculated to evaluate the target detectability of chest CT. Subjective image quality assessment was performed using 4-point ranking scale to evaluate the visual quality of CT images perceived by end user. Substantial improvements in RMSE and PSNR were observed after denoising. The lung nodules in denoised images could be distinguished more easily in comparison with those in the original ultra-low-dose CT, which is supported by the CNRs and subjective image quality scores. The comparison of intensity profiles for lung nodules demonstrated that the image noise in ultra-low-dose CT could be suppressed effectively after denoising without causing edge blurring or variation in Hounsfield unit (HU) values. A two-sample t-test revealed no statistically significant differences between full-dose CT and denoised ultra-low-dose CT in the evaluation of lung nodules, lung parenchyma, paraspinal muscle, or vertebral body. Since the linear no-threshold model suggests that no amount of ionizing radiation is entirely risk-free, the quest for further dose reduction remains a consistently important focus in radiology. Overall, our findings suggest that DenseNet could be a viable approach for reducing image noise in ultra-low-dose CT scans used for lung cancer screening.

Evaluation of a Deep Learning Denoising Algorithm for Dose Reduction in Whole-Body Photon-Counting CT Imaging: A Cadaveric Study

RATIONALE AND OBJECTIVES

Photon Counting CT (PCCT) offers advanced imaging capabilities with potential for substantial radiation dose reduction; however, achieving this without compromising image quality remains a challenge due to increased noise at lower doses. This study aims to evaluate the effectiveness of a deep learning (DL)-based denoising algorithm in maintaining diagnostic image quality in whole-body PCCT imaging at reduced radiation levels, using real intraindividual cadaveric scans.

MATERIALS AND METHODS

Twenty-four cadaveric human bodies underwent whole-body CT scans on a PCCT scanner (NAEOTOM Alpha, Siemens Healthineers) at four different dose levels (100%, 50%, 25%, and 10% mAs). Each scan was reconstructed using both ADMIRE level 2 and a DL algorithm (ClariCT.AI, ClariPi Inc.), resulting in 192 datasets. Objective image quality was assessed by measuring CT value stability, image noise, and contrast-to-noise ratio (CNR) across consistent regions of interest (ROIs) in the liver parenchyma. Two radiologists independently evaluated subjective image quality based on overall image clarity, sharpness, and contrast. Inter-rater agreement was determined using Spearman's correlation coefficient, and statistical analysis included mixed-effects modeling to assess objective and subjective image quality.

RESULTS

Objective analysis showed that the DL denoising algorithm did not significantly alter CT values (p ≥ 0.9975). Noise levels were consistently lower in denoised datasets compared to the Original (p < 0.0001). No significant differences were observed between the 25% mAs denoised and the 100% mAs original datasets in terms of noise and CNR (p ≥ 0.7870). Subjective analysis revealed strong inter-rater agreement (r ≥ 0.78), with the 50% mAs denoised datasets rated superior to the 100% mAs original datasets (p < 0.0001) and no significant differences detected between the 25% mAs denoised and 100% mAs original datasets (p ≥ 0.9436).

CONCLUSION

The DL denoising algorithm maintains image quality in PCCT imaging while enabling up to a 75% reduction in radiation dose. This approach offers a promising method for reducing radiation exposure in clinical PCCT without compromising diagnostic quality.

A GPU-accelerated fuzzy method for real-time CT volume filtering

During acquisition and reconstruction, medical images may become noisy and lose diagnostic quality. In the case of CT scans, obtaining less noisy images results in a higher radiation dose being administered to the patient. Filtering techniques can be utilized to reduce radiation without losing diagnosis capabilities. The objective in this work is to obtain an implementation of a filter capable of processing medical images in real-time. To achieve this we have developed several filter methods based on fuzzy logic, and their GPU implementations, to reduce mixed Gaussian-impulsive noise. These filters have been developed to work in attenuation coefficients so as to not lose any information from the CT scans. The testing volumes come from the Mayo clinic database and consist of CT volumes at full and at simulated low dose. The GPU parallelizations reach speedups of over 2700 and take less than 0.1 seconds to filter more than 300 slices. In terms of quality the filter is competitive with other state of the art algorithmic and AI filters. The proposed method obtains good performance in terms of quality and the parallelization results in real-time filtering.

State-of-the-Art Deep Learning CT Reconstruction Algorithms in Abdominal Imaging

The implementation of deep neural networks has spurred the creation of deep learning reconstruction (DLR) CT algorithms. DLR CT techniques encompass a spectrum of deep learning-based methodologies that operate during the different steps of the image creation, prior to or after the traditional image formation process (eg, filtered backprojection [FBP] or iterative reconstruction [IR]), or alternatively by fully replacing FBP or IR techniques. DLR algorithms effectively facilitate the reduction of image noise associated with low photon counts from reduced radiation dose protocols. DLR methods have emerged as an effective solution to ameliorate limitations observed with prior CT image reconstruction algorithms, including FBP and IR algorithms, which are not able to preserve image texture and diagnostic performance at low radiation dose levels. An additional advantage of DLR algorithms is their high reconstruction speed, hence targeting the ideal triad of features for a CT image reconstruction (ie, the ability to consistently provide diagnostic-quality images and achieve radiation dose imaging levels as low as reasonably possible, with high reconstruction speed). An accumulated body of evidence supports the clinical use of DLR algorithms in abdominal imaging across multiple CT imaging tasks. The authors explore the technical aspects of DLR CT algorithms and examine various approaches to image synthesis in DLR creation. The clinical applications of DLR algorithms are highlighted across various abdominal CT imaging domains, with emphasis on the supporting evidence for diverse clinical tasks. An overview of the current limitations of and outlook for DLR algorithms for CT is provided. ©RSNA, 2024.

Deep learning methods for 3D magnetic resonance image denoising, bias field and motion artifact correction: a comprehensive review

Magnetic resonance imaging (MRI) provides detailed structural information of the internal body organs and soft tissue regions of a patient in clinical diagnosis for disease detection, localization, and progress monitoring. MRI scanner hardware manufacturers incorporate various post-acquisition image-processing techniques into the scanner's computer software tools for different post-processing tasks. These tools provide a final image of adequate quality and essential features for accurate clinical reporting and predictive interpretation for better treatment planning. Different post-acquisition image-processing tasks for MRI quality enhancement include noise removal, motion artifact reduction, magnetic bias field correction, and eddy electric current effect removal. Recently, deep learning (DL) methods have shown great success in many research fields, including image and video applications. DL-based data-driven feature-learning approaches have great potential for MR image denoising and image-quality-degrading artifact correction. Recent studies have demonstrated significant improvements in image-analysis tasks using DL-based convolutional neural network techniques. The promising capabilities and performance of DL techniques in various problem-solving domains have motivated researchers to adapt DL methods to medical image analysis and quality enhancement tasks. This paper presents a comprehensive review of DL-based state-of-the-art MRI quality enhancement and artifact removal methods for regenerating high-quality images while preserving essential anatomical and physiological feature maps without destroying important image information. Existing research gaps and future directions have also been provided by highlighting potential research areas for future developments, along with their importance and advantages in medical imaging.

Noise suppression in photon-counting computed tomography using unsupervised Poisson flow generative models

Deep learning (DL) has proven to be important for computed tomography (CT) image denoising. However, such models are usually trained under supervision, requiring paired data that may be difficult to obtain in practice. Diffusion models offer unsupervised means of solving a wide range of inverse problems via posterior sampling. In particular, using the estimated unconditional score function of the prior distribution, obtained via unsupervised learning, one can sample from the desired posterior via hijacking and regularization. However, due to the iterative solvers used, the number of function evaluations (NFE) required may be orders of magnitudes larger than for single-step samplers. In this paper, we present a novel image denoising technique for photon-counting CT by extending the unsupervised approach to inverse problem solving to the case of Poisson flow generative models (PFGM)++. By hijacking and regularizing the sampling process we obtain a single-step sampler, that is NFE = 1. Our proposed method incorporates posterior sampling using diffusion models as a special case. We demonstrate that the added robustness afforded by the PFGM++ framework yields significant performance gains. Our results indicate competitive performance compared to popular supervised, including state-of-the-art diffusion-style models with NFE = 1 (consistency models), unsupervised, and non-DL-based image denoising techniques, on clinical low-dose CT data and clinical images from a prototype photon-counting CT system developed by GE HealthCare.

Unsupervised low-dose CT denoising using bidirectional contrastive network

BACKGROUND AND OBJECTIVE

Low-dose computed tomography (LDCT) scans significantly reduce radiation exposure, but introduce higher levels of noise and artifacts that compromise image quality and diagnostic accuracy. Supervised learning methods have proven effective in denoising LDCT images, but are hampered by the need for large, paired datasets, which pose significant challenges in data acquisition. This study aims to develop a robust unsupervised LDCT denoising method that overcomes the reliance on paired LDCT and normal-dose CT (NDCT) samples, paving the way for more accessible and practical denoising techniques.

METHODS

We propose a novel unsupervised network model, Bidirectional Contrastive Unsupervised Denoising (BCUD), for LDCT denoising. This model innovatively combines a bidirectional network structure with contrastive learning theory to map the precise mutual correspondence between the noisy LDCT image domain and the clean NDCT image domain. Specifically, we employ dual encoders and discriminators for domain-specific data generation, and use unique projection heads for each domain to adaptively learn customized embedded representations. We then align corresponding features across domains within the learned embedding spaces to achieve effective noise reduction. This approach fundamentally improves the model's ability to match features in latent space, thereby improving noise reduction while preserving fine image detail.

RESULTS

Through extensive experimental validation on the AAPM-Mayo public dataset and real-world clinical datasets, the proposed BCUD method demonstrated superior performance. It achieved a peak signal-to-noise ratio (PSNR) of 31.387 dB, a structural similarity index measure (SSIM) of 0.886, an information fidelity criterion (IFC) of 2.305, and a visual information fidelity (VIF) of 0.373. Notably, subjective evaluation by radiologists resulted in a mean score of 4.23, highlighting its advantages over existing methods in terms of clinical applicability.

CONCLUSIONS

This paper presents an innovative unsupervised LDCT denoising method using a bidirectional contrastive network, which greatly improves clinical applicability by eliminating the need for perfectly matched image pairs. The method sets a new benchmark in unsupervised LDCT image denoising, excelling in noise reduction and preservation of fine structural details.

Tumor conspicuity enhancement-based segmentation model for liver tumor segmentation and RECIST diameter measurement in non-contrast CT images

BACKGROUND AND OBJECTIVE

Liver tumor segmentation (LiTS) accuracy on contrast-enhanced computed tomography (CECT) images is higher than that on non-contrast computed tomography (NCCT) images. However, CECT requires contrast medium and repeated scans to obtain multiphase enhanced CT images, which is time-consuming and cost-increasing. Therefore, despite the lower accuracy of LiTS on NCCT images, which still plays an irreplaceable role in some clinical settings, such as guided brachytherapy, ablation, or evaluation of patients with renal function damage. In this study, we intend to generate enhanced high-contrast pseudo-color CT (PCCT) images to improve the accuracy of LiTS and RECIST diameter measurement on NCCT images.

METHODS

To generate high-contrast CT liver tumor region images, an intensity-based tumor conspicuity enhancement (ITCE) model was first developed. In the ITCE model, a pseudo color conversion function from an intensity distribution of the tumor was established, and it was applied in NCCT to generate enhanced PCCT images. Additionally, we design a tumor conspicuity enhancement-based liver tumor segmentation (TCELiTS) model, which was applied to improve the segmentation of liver tumors on NCCT images. The TCELiTS model consists of three components: an image enhancement module based on the ITCE model, a segmentation module based on a deep convolutional neural network, and an attention loss module based on restricted activation. Segmentation performance was analyzed using the Dice similarity coefficient (DSC), sensitivity, specificity, and RECIST diameter error.

RESULTS

To develop the deep learning model, 100 patients with histopathologically confirmed liver tumors (hepatocellular carcinoma, 64 patients; hepatic hemangioma, 36 patients) were randomly divided into a training set (75 patients) and an independent test set (25 patients). Compared with existing tumor automatic segmentation networks trained on CECT images (U-Net, nnU-Net, DeepLab-V3, Modified U-Net), the DSCs achieved on the enhanced PCCT images are both improved compared with those on NCCT images. We observe improvements of 0.696-0.713, 0.715 to 0.776, 0.748 to 0.788, and 0.733 to 0.799 in U-Net, nnU-Net, DeepLab-V3, and Modified U-Net, respectively, in terms of DSC values. In addition, an observer study including 5 doctors was conducted to compare the segmentation performance of enhanced PCCT images with that of NCCT images and showed that enhanced PCCT images are more advantageous for doctors to segment tumor regions. The results showed an accuracy improvement of approximately 3%-6%, but the time required to segment a single CT image was reduced by approximately 50 %.

CONCLUSIONS

Experimental results show that the ITCE model can generate high-contrast enhanced PCCT images, especially in liver regions, and the TCELiTS model can improve LiTS accuracy in NCCT images.

An efficient lightweight network for image denoising using progressive residual and convolutional attention feature fusion

While deep learning has become the go-to method for image denoising due to its impressive noise removal capabilities, excessive network depth often plagues existing approaches, leading to significant computational burdens. To address this critical bottleneck, we propose a novel lightweight progressive residual and attention mechanism fusion network that effectively alleviates these limitations. This architecture tackles both Gaussian and real-world image noise with exceptional efficacy. Initiated through dense blocks (DB) tasked with discerning the noise distribution, this approach substantially reduces network parameters while comprehensively extracting local image features. The network then adopts a progressive strategy, whereby shallow convolutional features are incrementally integrated with deeper features, establishing a residual fusion framework adept at extracting encompassing global features relevant to noise characteristics. The process concludes by integrating the output feature maps from each DB and the robust edge features from the convolutional attention feature fusion module (CAFFM). These combined elements are then directed to the reconstruction layer, ultimately producing the final denoised image. Empirical analyses conducted in environments characterized by Gaussian white noise and natural noise, spanning noise levels 15-50, indicate a marked enhancement in performance. This assertion is quantitatively corroborated by increased average values in metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Feature Similarity Index for Color images (FSIMc), outperforming the outcomes of more than 20 existing methods across six varied datasets. Collectively, the network delineated in this research exhibits exceptional adeptness in image denoising. Simultaneously, it adeptly preserves essential image features such as edges and textures, thereby signifying a notable progression in the domain of image processing. The proposed model finds applicability in a range of image-centric domains, encompassing image processing, computer vision, video analysis, and pattern recognition.

Self-supervised dual-domain balanced dropblock-network for low-dose CT denoising

Objective.Self-supervised learning methods have been successfully applied for low-dose computed tomography (LDCT) denoising, with the advantage of not requiring labeled data. Conventional self-supervised methods operate only in the image domain, ignoring valuable priors in the sinogram domain. Recently proposed dual-domain methods address this limitation but encounter issues with blurring artifacts in the reconstructed image due to the inhomogeneous distribution of noise levels in low-dose sinograms.Approach.To tackle this challenge, this paper proposes SDBDNet, an end-to-end dual-domain self-supervised method for LDCT denoising. With the network designed based on the properties of inhomogeneous noise in low-dose sinograms and the principle of moderate sinogram-domain denoising, SDBDNet achieves effective denoising in dual domains without introducing blurring artifacts. Specifically, we split the sinogram into two subsets based on the positions of detector cells to generate paired training data with high similarity and independent noise. These sub-sinograms are then restored to their original size using 1D interpolation and learning-based correction. To achieve adaptive and moderate smoothing in the sinogram domain, we integrate Dropblock, a type of convolution layer with regularization, into SDBDNet, and set a weighted average between the denoised sinograms and their noisy counterparts, leading to a well-balanced dual-domain approach.Main results.Numerical experiments show that our method outperforms popular non-learning and self-supervised learning methods, demonstrating its effectiveness and superior performance.Significance.While introducing a novel high-performance dual-domain self-supervised LDCT denoising method, this paper also emphasizes and verifies the importance of appropriate sinogram-domain denoising in dual-domain methods, which might inspire future work.

Unpaired low-dose computed tomography image denoising using a progressive cyclical convolutional neural network

BACKGROUND

Reducing the radiation dose from computed tomography (CT) can significantly reduce the radiation risk to patients. However, low-dose CT (LDCT) suffers from severe and complex noise interference that affects subsequent diagnosis and analysis. Recently, deep learning-based methods have shown superior performance in LDCT image-denoising tasks. However, most methods require many normal-dose and low-dose CT image pairs, which are difficult to obtain in clinical applications. Unsupervised methods, on the other hand, are more general.

PURPOSE

Deep learning methods based on GAN networks have been widely used for unsupervised LDCT denoising, but the additional memory requirements of the model also hinder its further clinical application. To this end, we propose a simpler multi-stage denoising framework trained using unpaired data, the progressive cyclical convolutional neural network (PCCNN), which can remove the noise from CT images in latent space.

METHODS

Our proposed PCCNN introduces a noise transfer model that transfers noise from LDCT to normal-dose CT (NDCT), denoised CT images generated from unpaired CT images, and noisy CT images. The denoising framework also contains a progressive module that effectively removes noise through multi-stage wavelet transforms without sacrificing high-frequency components such as edges and details.

RESULTS

Compared with seven LDCT denoising algorithms, we perform a quantitative and qualitative evaluation of the experimental results and perform ablation experiments on each network module and loss function. On the AAPM dataset, compared with the contrasted unsupervised methods, our denoising framework has excellent denoising performance increasing the peak signal-to-noise ratio (PSNR) from 29.622 to 30.671, and the structural similarity index (SSIM) was increased from 0.8544 to 0.9199. The PCCNN denoising results were relatively optimal and statistically significant. In the qualitative result comparison, PCCNN without introducing additional blurring and artifacts, the resulting image has higher resolution and complete detail preservation, and the overall structural texture of the image is closer to NDCT. In visual assessments, PCCNN achieves a relatively balanced result in noise suppression, contrast retention, and lesion discrimination.

CONCLUSIONS

Extensive experimental validation shows that our scheme achieves reconstruction results comparable to supervised learning methods and has performed well in image quality and medical diagnostic acceptability.

CT image denoising methods for image quality improvement and radiation dose reduction

With the ever-increasing use of computed tomography (CT), concerns about its radiation dose have become a significant public issue. To address the need for radiation dose reduction, CT denoising methods have been widely investigated and applied in low-dose CT images. Numerous noise reduction algorithms have emerged, such as iterative reconstruction and most recently, deep learning (DL)-based approaches. Given the rapid advancements in Artificial Intelligence techniques, we recognize the need for a comprehensive review that emphasizes the most recently developed methods. Hence, we have performed a thorough analysis of existing literature to provide such a review. Beyond directly comparing the performance, we focus on pivotal aspects, including model training, validation, testing, generalizability, vulnerability, and evaluation methods. This review is expected to raise awareness of the various facets involved in CT image denoising and the specific challenges in developing DL-based models.

Spatiotemporal denoising of low-dose cardiac CT image sequences using RecycleGAN

Electrocardiogram (ECG)-gated multi-phase computed tomography angiography (MP-CTA) is frequently used for diagnosis of coronary artery disease. Radiation dose may become a potential concern as the scan needs to cover a wide range of cardiac phases during a heart cycle. A common method to reduce radiation is to limit the full-dose acquisition to a predefined range of phases while reducing the radiation dose for the rest. Our goal in this study is to develop a spatiotemporal deep learning method to enhance the quality of low-dose CTA images at phases acquired at reduced radiation dose. Recently, we demonstrated that a deep learning method, Cycle-Consistent generative adversarial networks (CycleGAN), could effectively denoise low-dose CT images through spatial image translation without labeled image pairs in both low-dose and full-dose image domains. As CycleGAN does not utilize the temporal information in its denoising mechanism, we propose to use RecycleGAN, which could translate a series of images ordered in time from the low-dose domain to the full-dose domain through an additional recurrent network. To evaluate RecycleGAN, we use the XCAT phantom program, a highly realistic simulation tool based on real patient data, to generate MP-CTA image sequences for 18 patients (14 for training, 2 for validation and 2 for test). Our simulation results show that RecycleGAN can achieve better denoising performance than CycleGAN based on both visual inspection and quantitative metrics. We further demonstrate the superior denoising performance of RecycleGAN using clinical MP-CTA images from 50 patients.

CDDnet: Cross-domain denoising network for low-dose CT image via local and global information alignment

The domain shift problem has emerged as a challenge in cross-domain low-dose CT (LDCT) image denoising task, where the acquisition of a sufficient number of medical images from multiple sources may be constrained by privacy concerns. In this study, we propose a novel cross-domain denoising network (CDDnet) that incorporates both local and global information of CT images. To address the local component, a local information alignment module has been proposed to regularize the similarity between extracted target and source features from selected patches. To align the general information of the semantic structure from a global perspective, an autoencoder is adopted to learn the latent correlation between the source label and the estimated target label generated by the pre-trained denoiser. Experimental results demonstrate that our proposed CDDnet effectively alleviates the domain shift problem, outperforming other deep learning-based and domain adaptation-based methods under cross-domain scenarios.

Addressing inter-device variations in optical coherence tomography angiography: will image-to-image translation systems help?

BACKGROUND

Optical coherence tomography angiography (OCTA) is an innovative technology providing visual and quantitative data on retinal microvasculature in a non-invasive manner.

MAIN BODY

Due to variations in the technical specifications of different OCTA devices, there are significant inter-device differences in OCTA data, which can limit their comparability and generalizability. These variations can also result in a domain shift problem that may interfere with applicability of machine learning models on data obtained from different OCTA machines. One possible approach to address this issue may be unsupervised deep image-to-image translation leveraging systems such as Cycle-Consistent Generative Adversarial Networks (Cycle-GANs) and Denoising Diffusion Probabilistic Models (DDPMs). Through training on unpaired images from different device domains, Cycle-GANs and DDPMs may enable cross-domain translation of images. They have been successfully applied in various medical imaging tasks, including segmentation, denoising, and cross-modality image-to-image translation. In this commentary, we briefly describe how Cycle-GANs and DDPMs operate, and review the recent experiments with these models on medical and ocular imaging data. We then discuss the benefits of applying such techniques for inter-device translation of OCTA data and the potential challenges ahead.

CONCLUSION

Retinal imaging technologies and deep learning-based domain adaptation techniques are rapidly evolving. We suggest exploring the potential of image-to-image translation methods in improving the comparability of OCTA data from different centers or devices. This may facilitate more efficient analysis of heterogeneous data and broader applicability of machine learning models trained on limited datasets in this field.

Self-trained deep convolutional neural network for noise reduction in CT

Purpose

Supervised deep convolutional neural network (CNN)-based methods have been actively used in clinical CT to reduce image noise. The networks of these methods are typically trained using paired high- and low-quality data from a massive number of patients and/or phantom images. This training process is tedious, and the network trained under a given condition may not be generalizable to patient images acquired and reconstructed under different conditions. We propose a self-trained deep CNN (ST_CNN) method for noise reduction in CT that does not rely on pre-existing training datasets.

Approach

The ST_CNN training was accomplished using extensive data augmentation in the projection domain, and the inference was applied to the data itself. Specifically, multiple independent noise insertions were applied to the original patient projection data to generate multiple realizations of low-quality projection data. Then, rotation augmentation was adopted for both the original and low-quality projection data by applying the rotation angle directly on the projection data so that images were rotated at arbitrary angles without introducing additional bias. A large number of paired low- and high-quality images from the same patient were reconstructed and paired for training the ST_CNN model.

Results

No significant difference was found between the ST_CNN and conventional CNN models in terms of the peak signal-to-noise ratio and structural similarity index measure. The ST_CNN model outperformed the conventional CNN model in terms of noise texture and homogeneity in liver parenchyma as well as better subjective visualization of liver lesions. The ST_CNN may sacrifice the sharpness of vessels slightly compared to the conventional CNN model but without affecting the visibility of peripheral vessels or diagnosis of vascular pathology.

Conclusions

The proposed ST_CNN method trained from the data itself may achieve similar image quality in comparison with conventional deep CNN denoising methods pre-trained on external datasets.

Noise Suppression With Similarity-Based Self-Supervised Deep Learning

Image denoising is a prerequisite for downstream tasks in many fields. Low-dose and photon-counting computed tomography (CT) denoising can optimize diagnostic performance at minimized radiation dose. Supervised deep denoising methods are popular but require paired clean or noisy samples that are often unavailable in practice. Limited by the independent noise assumption, current self-supervised denoising methods cannot process correlated noises as in CT images. Here we propose the first-of-its-kind similarity-based self-supervised deep denoising approach, referred to as Noise2Sim, that works in a nonlocal and nonlinear fashion to suppress not only independent but also correlated noises. Theoretically, Noise2Sim is asymptotically equivalent to supervised learning methods under mild conditions. Experimentally, Nosie2Sim recovers intrinsic features from noisy low-dose CT and photon-counting CT images as effectively as or even better than supervised learning methods on practical datasets visually, quantitatively and statistically. Noise2Sim is a general self-supervised denoising approach and has great potential in diverse applications.

Noise-resilient deep learning for integrated circuit tomography

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

Deep learning based unpaired image-to-image translation applications for medical physics: a systematic review

Purpose. There is a growing number of publications on the application of unpaired image-to-image (I2I) translation in medical imaging. However, a systematic review covering the current state of this topic for medical physicists is lacking. The aim of this article is to provide a comprehensive review of current challenges and opportunities for medical physicists and engineers to apply I2I translation in practice.Methods and materials. The PubMed electronic database was searched using terms referring to unpaired (unsupervised), I2I translation, and medical imaging. This review has been reported in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. From each full-text article, we extracted information extracted regarding technical and clinical applications of methods, Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) study type, performance of algorithm and accessibility of source code and pre-trained models.Results. Among 461 unique records, 55 full-text articles were included in the review. The major technical applications described in the selected literature are segmentation (26 studies), unpaired domain adaptation (18 studies), and denoising (8 studies). In terms of clinical applications, unpaired I2I translation has been used for automatic contouring of regions of interest in MRI, CT, x-ray and ultrasound images, fast MRI or low dose CT imaging, CT or MRI only based radiotherapy planning, etc Only 5 studies validated their models using an independent test set and none were externally validated by independent researchers. Finally, 12 articles published their source code and only one study published their pre-trained models.Conclusion. I2I translation of medical images offers a range of valuable applications for medical physicists. However, the scarcity of external validation studies of I2I models and the shortage of publicly available pre-trained models limits the immediate applicability of the proposed methods in practice.

A densely connected LDCT image denoising network based on dual-edge extraction and multi-scale attention under compound loss

BACKGROUND

Low dose computed tomography (LDCT) uses lower radiation dose, but the reconstructed images contain higher noise that can have negative impact in disease diagnosis. Although deep learning with the edge extraction operators reserves edge information well, only applying the edge extraction operators to input LDCT images does not yield overall satisfactory results.

OBJECTIVE

To improve LDCT images quality, this study proposes and tests a dual edge extraction multi-scale attention mechanism convolution neural network (DEMACNN) based on a compound loss.

METHODS

The network uses edge extraction operators to extract edge information from both the input images and the feature maps in the network, improving the utilization of the edge operators and retaining the images edge information. The feature enhancement block is constructed by fusing the attention mechanism and multi-scale module, enhancing effective information, while suppressing useless information. The residual learning method is used to learn the network, improving the performance of the network, and solving the problem of gradient disappearance. Except for the network structure, a compound loss function, which consists of the MSE loss, the proposed joint total variation loss, and the edge loss, is proposed to enhance the denoising ability of the network and reserve the edge of images.

RESULTS

Compared with other advanced methods (REDCNN, CT-former and EDCNN), the proposed new network achieves the best PSNR and SSIM values in LDCT images of the abdomen, which are 33.3486 and 0.9104, respectively. In addition, the new network also performs well on head and chest image data.

CONCLUSION

The experimental results demonstrate that the proposed new network structure and denoising algorithm not only effectively removes the noise in LDCT images, but also protects the edges and details of the images well.

Texture transformer super-resolution for low-dose computed tomography

Computed tomography (CT) is widely used to diagnose many diseases. Low-dose CT has been actively pursued to lower the ionizing radiation risk. A relatively smoother kernel is typically used in low-dose CT to suppress image noise, which may sacrifice spatial resolution. In this work, we propose a texture transformer network to simultaneously reduce image noise and improve spatial resolution in CT images. This network, referred to as Texture Transformer for Super Resolution (TTSR), is a reference-based deep-learning image super-resolution method built upon a generative adversarial network (GAN). The noisy low-resolution CT (LRCT) image and the routine-dose high-resolution (HRCT) image are severed as the query and key in a transformer, respectively. Image translation is optimized through deep neural network (DNN) texture extraction, correlation embedding, and attention-based texture transfer and synthesis to achieve joint feature learning between LRCT and HRCT images for super-resolution CT (SRCT) images. To evaluate SRCT performance, we use the data from both simulations of the XCAT phantom program and the real patient data. Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and feature similarity (FSIM) index are used as quantitative metrics. For comparison of SRCT performance, the cubic spline interpolation, SRGAN (a GAN super-resolution with an additional content loss), and GAN-CIRCLE (a GAN super-resolution with cycle consistency) were used. Compared to the other two methods, TTSR can restore more details in SRCT images and achieve better PSNR, SSIM, and FSIM for both simulation and real-patient data. In addition, we show that TTSR can yield better image quality and demand much less computation time than high-resolution low-dose CT images denoised by block-matching and 3D filtering (BM3D) and GAN-CIRCLE. In summary, the proposed TTSR method based on texture transformer and attention mechanism provides an effective and efficient tool to improve spatial resolution and suppress noise of low-dose CT images.

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.

Mitigating Bias in Radiology Machine Learning: 3. Performance Metrics

The increasing use of machine learning (ML) algorithms in clinical settings raises concerns about bias in ML models. Bias can arise at any step of ML creation, including data handling, model development, and performance evaluation. Potential biases in the ML model can be minimized by implementing these steps correctly. This report focuses on performance evaluation and discusses model fitness, as well as a set of performance evaluation toolboxes: namely, performance metrics, performance interpretation maps, and uncertainty quantification. By discussing the strengths and limitations of each toolbox, our report highlights strategies and considerations to mitigate and detect biases during performance evaluations of radiology artificial intelligence models. Keywords: Segmentation, Diagnosis, Convolutional Neural Network (CNN) © RSNA, 2022.

Deep learning-based low-dose CT for adaptive radiotherapy of abdominal and pelvic tumors

The shape and position of abdominal and pelvic organs change greatly during radiotherapy, so image-guided radiation therapy (IGRT) is urgently needed. The world’s first integrated CT-linac platform, equipped with fan beam CT (FBCT), can provide a diagnostic-quality FBCT for achieve adaptive radiotherapy (ART). However, CT scans will bring the risk of excessive scanning radiation dose. Reducing the tube current of the FBCT system can reduce the scanning dose, but it will lead to serious noise and artifacts in the reconstructed images. In this study, we proposed a deep learning method, Content-Noise Cycle-Consistent Generative Adversarial Network (CNCycle-GAN), to improve the image quality and CT value accuracy of low-dose FBCT images to meet the requirements of adaptive radiotherapy. We selected 76 patients with abdominal and pelvic tumors who received radiation therapy. The patients received one low-dose CT scan and one normal-dose CT scan in IGRT mode during different fractions of radiotherapy. The normal dose CT images (NDCT) and low dose CT images (LDCT) of 70 patients were used for network training, and the remaining 6 patients were used to validate the performance of the network. The quality of low-dose CT images after network restoration (RCT) were evaluated in three aspects: image quality, automatic delineation performance and dose calculation accuracy. Taking NDCT images as a reference, RCT images reduced MAE from 34.34 ± 5.91 to 20.25 ± 4.27, PSNR increased from 34.08 ± 1.49 to 37.23 ± 2.63, and SSIM increased from 0.92 ± 0.08 to 0.94 ± 0.07. The P value is less than 0.01 of the above performance indicators indicated that the difference were statistically significant. The Dice similarity coefficients (DCS) between the automatic delineation results of organs at risk such as bladder, femoral heads, and rectum on RCT and the results of manual delineation by doctors both reached 0.98. In terms of dose calculation accuracy, compared with the automatic planning based on LDCT, the difference in dose distribution between the automatic planning based on RCT and the automatic planning based on NDCT were smaller. Therefore, based on the integrated CT-linac platform, combined with deep learning technology, it provides clinical feasibility for the realization of low-dose FBCT adaptive radiotherapy for abdominal and pelvic tumors.

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

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

Artificial Intelligence in Radiation Therapy

Artificial intelligence (AI) has great potential to transform the clinical workflow of radiotherapy. Since the introduction of deep neural networks, many AI-based methods have been proposed to address challenges in different aspects of radiotherapy. Commercial vendors have started to release AI-based tools that can be readily integrated to the established clinical workflow. To show the recent progress in AI-aided radiotherapy, we have reviewed AI-based studies in five major aspects of radiotherapy including image reconstruction, image registration, image segmentation, image synthesis, and automatic treatment planning. In each section, we summarized and categorized the recently published methods, followed by a discussion of the challenges, concerns, and future development. Given the rapid development of AI-aided radiotherapy, the efficiency and effectiveness of radiotherapy in the future could be substantially improved through intelligent automation of various aspects of radiotherapy.

Denoising of pediatric low dose abdominal CT using deep learning based algorithm

OBJECTIVES

To evaluate standard dose-like computed tomography (CT) images generated by a deep learning method, trained using unpaired low-dose CT (LDCT) and standard-dose CT (SDCT) images.

MATERIALS AND METHODS

LDCT (80 kVp, 100 mAs, n = 83) and SDCT (120 kVp, 200 mAs, n = 42) images were divided into training (42 LDCT and 42 SDCT) and validation (41 LDCT) sets. A generative adversarial network framework was used to train unpaired datasets. The trained deep learning method generated virtual SDCT images (VIs) from the original LDCT images (OIs). To test the proposed method, LDCT images (80 kVp, 262 mAs, n = 33) were collected from another CT scanner using iterative reconstruction (IR). Image analyses were performed to evaluate the qualities of VIs in the validation set and to compare the performance of deep learning and IR in the test set.

RESULTS

The noise of the VIs was the lowest in both validation and test sets (all p<0.001). The mean CT number of the VIs for the portal vein and liver was lower than that of OIs in both validation and test sets (all p<0.001) and was similar to those of SDCT. The contrast-to-noise ratio of portal vein and the signal-to-noise ratio (SNR) of portal vein and liver of VIs were higher than those of SDCT (all p<0.05). The SNR of VIs in test sets was the highest among three images.

CONCLUSION

The deep learning method trained by unpaired datasets could reduce noise of LDCT images and showed similar performance to SAFIRE. It can be applied to LDCT images of older CT scanners without IR.

Low-dose CT noise reduction based on local total variation and improved wavelet residual CNN

BACKGROUND

Low-dose computed tomography (LDCT) is an effective method for reducing radiation exposure. However, reducing radiation dose leads to considerable noise in the reconstructed image that can affect doctor's judgment.

OBJECTIVE

To solve this problem, this study proposes a local total variation and improved wavelet residual convolutional neural network (LTV-WRCNN) denoising model.

METHODS

The model first introduces local total variation (LTV) to decompose the LDCT image into cartoon and texture image. Next, the texture image is filtered using the non-local mean (NLM). Then, the cartoon image is added to the filtered texture image to obtain the preprocessing image. Finally, the pre-processed image is fed into the improved wavelet residual neural network (WRCNN) to obtain an improved image. Additionally, we also introduce a compound loss in wavelet domain that combines mean squared error loss and directional regularization loss to separate the structural details from noise more thoroughly.

RESULTS

Compared with state-of-the-art methods, the peak-signal-to-noise ratio (PSNR) value and the structure similarity (SSIM) value of the processed CT images using the new proposed model are 33.4229 dB and 0.9158. Study also shows that applying new model obtains better results visually and numerically, especially in terms of the preservation of structural details.

CONCLUSIONS

The proposed new model is feasible and effective in improving the quality of LDCT images.

Unpaired Stain Transfer Using Pathology-Consistent Constrained Generative Adversarial Networks

Pathological examination is the gold standard for the diagnosis of cancer. Common pathological examinations include hematoxylin-eosin (H&E) staining and immunohistochemistry (IHC). In some cases, it is hard to make accurate diagnoses of cancer by referring only to H&E staining images. Whereas, the IHC examination can further provide enough evidence for the diagnosis process. Hence, the generation of virtual IHC images from H&E-stained images will be a good solution for current IHC examination hard accessibility issue, especially for some low-resource regions. However, existing approaches have limitations in microscopic structural preservation and the consistency of pathology properties. In addition, pixel-level paired data is hard available. In our work, we propose a novel adversarial learning method for effective Ki-67-stained image generation from corresponding H&E-stained image. Our method takes fully advantage of structural similarity constraint and skip connection to improve structural details preservation; and pathology consistency constraint and pathological representation network are first proposed to enforce the generated and source images hold the same pathological properties in different staining domains. We empirically demonstrate the effectiveness of our approach on two different unpaired histopathological datasets. Extensive experiments indicate the superior performance of our method that surpasses the state-of-the-art approaches by a significant margin. In addition, our approach also achieves a stable and good performance on unbalanced datasets, which shows our method has strong robustness. We believe that our method has significant potential in clinical virtual staining and advance the progress of computer-aided multi-staining histology image analysis.

Low-dose CT image and projection dataset

PURPOSE

To describe a large, publicly available dataset comprising computed tomography (CT) projection data from patient exams, both at routine clinical doses and simulated lower doses.

ACQUISITION AND VALIDATION METHODS

The library was developed under local ethics committee approval. Projection and image data from 299 clinically performed patient CT exams were archived for three types of clinical exams: noncontrast head CT scans acquired for acute cognitive or motor deficit, low-dose noncontrast chest scans acquired to screen high-risk patients for pulmonary nodules, and contrast-enhanced CT scans of the abdomen acquired to look for metastatic liver lesions. Scans were performed on CT systems from two different CT manufacturers using routine clinical protocols. Projection data were validated by reconstructing the data using several different reconstruction algorithms and through use of the data in the 2016 Low Dose CT Grand Challenge. Reduced dose projection data were simulated for each scan using a validated noise-insertion method. Radiologists marked location and diagnosis for detected pathologies. Reference truth was obtained from the patient medical record, either from histology or subsequent imaging.

DATA FORMAT AND USAGE NOTES

Projection datasets were converted into the previously developed DICOM-CT-PD format, which is an extended DICOM format created to store CT projections and acquisition geometry in a nonproprietary format. Image data are stored in the standard DICOM image format and clinical data in a spreadsheet. Materials are provided to help investigators use the DICOM-CT-PD files, including a dictionary file, data reader, and user manual. The library is publicly available from The Cancer Imaging Archive (https://doi.org/10.7937/9npb-2637).

POTENTIAL APPLICATIONS

This CT data library will facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence. The provided clinical information allows evaluation of task-based diagnostic performance.