Generative Adversarial Networks for Noise Reduction in Low-Dose CT

GAN-based synthetic FDG PET images from T1 brain MRI can serve to improve performance of deep unsupervised anomaly detection models

BACKGROUND AND OBJECTIVE

Research in the cross-modal medical image translation domain has been very productive over the past few years in tackling the scarce availability of large curated multi-modality datasets with the promising performance of GAN-based architectures. However, only a few of these studies assessed task-based related performance of these synthetic data, especially for the training of deep models.

METHODS

We design and compare different GAN-based frameworks for generating synthetic brain[18F]fluorodeoxyglucose (FDG) PET images from T1 weighted MRI data. We first perform standard qualitative and quantitative visual quality evaluation. Then, we explore further impact of using these fake PET data in the training of a deep unsupervised anomaly detection (UAD) model designed to detect subtle epilepsy lesions in T1 MRI and FDG PET images. We introduce novel diagnostic task-oriented quality metrics of the synthetic FDG PET data tailored to our unsupervised detection task, then use these fake data to train a use case UAD model combining a deep representation learning based on siamese autoencoders with a OC-SVM density support estimation model. This model is trained on normal subjects only and allows the detection of any variation from the pattern of the normal population. We compare the detection performance of models trained on 35 paired real MR T1 of normal subjects paired either on 35 true PET images or on 35 synthetic PET images generated from the best performing generative models. Performance analysis is conducted on 17 exams of epilepsy patients undergoing surgery.

RESULTS

The best performing GAN-based models allow generating realistic fake PET images of control subject with SSIM and PSNR values around 0.9 and 23.8, respectively and in distribution (ID) with regard to the true control dataset. The best UAD model trained on these synthetic normative PET data allows reaching 74% sensitivity.

CONCLUSION

Our results confirm that GAN-based models are the best suited for MR T1 to FDG PET translation, outperforming transformer or diffusion models. We also demonstrate the diagnostic value of these synthetic data for the training of UAD models and evaluation on clinical exams of epilepsy patients. Our code and the normative image dataset are available.

Low dose computed tomography reconstruction with momentum-based frequency adjustment network

BACKGROUND AND OBJECTIVE

Recent investigations into Low-Dose Computed Tomography (LDCT) reconstruction methods have brought Model-Based Data-Driven (MBDD) approaches to the forefront. One prominent architecture within MBDD entails the integration of Model-Based Iterative Reconstruction (MBIR) with Deep Learning (DL). While this approach offers the advantage of harnessing information from sinogram and image domains, it also reveals several deficiencies. First and foremost, the efficacy of DL methods within the realm of MBDD necessitates meticulous enhancement, as it directly impacts the computational cost and the quality of reconstructed images. Next, high computational costs and a high number of iterations limit the development of MBDD methods. Last but not least, CT reconstruction is sensitive to pixel accuracy, and the role of loss functions within DL methods is crucial for meeting this requirement.

METHODS

This paper advances MBDD methods through three principal contributions. Firstly, we introduce an innovative Frequency Adjustment Network (FAN) that effectively adjusts both high and low-frequency components during the inference phase, resulting in substantial enhancements in reconstruction performance. Second, we develop the Momentum-based Frequency Adjustment Network (MFAN), which leverages momentum terms as an extrapolation strategy to facilitate the amplification of changes throughout successive iterations, culminating in a rapid convergence framework. Lastly, we delve into the visual properties of CT images and present a unique loss function named Focal Detail Loss (FDL). The FDL function preserves fine details throughout the training phase, significantly improving reconstruction quality.

RESULTS

Through a series of experiments validation on the AAPM-Mayo public dataset and real-world piglet datasets, the aforementioned three contributions demonstrated superior performance. MFAN achieved convergence in 10 iterations as an iteration method, faster than other methods. Ablation studies further highlight the advanced performance of each contribution.

CONCLUSIONS

This paper presents an MBDD-based LDCT reconstruction method using a momentum-based frequency adjustment network with a focal detail loss function. This approach significantly reduces the number of iterations required for convergence while achieving superior reconstruction results in visual and numerical analyses.

Asymmetric Convolution-based GAN Framework for Low-Dose CT Image Denoising

Noise reduction is essential to improve the diagnostic quality of low-dose CT (LDCT) images. In this regard, data-driven denoising methods based on generative adversarial networks (GAN) have shown promising results. However, custom designs with 2D convolution may not preserve the correlation of the local and global pixels, which results in the loss of high-frequency (edges/ boundaries of lesions) anatomical details. A recent state-of-the-art method demonstrates that using primitive GAN-based methods may introduce structural (shape) distortion. To address this issue, we develop a novel asymmetric convolution-based generator network (ACGNet), which is constructed by using one-dimensional (1D) asymmetric convolutions and a dynamic attention module (DAM). The 1D asymmetric convolutions (1 × 3 & 3 × 1) can intensify the representation power of square convolution kernels (3 × 3) in horizontal and vertical directions. Consequently, we integrated the highlighted low-level CT voxel details via purposed attention DAM with high-level CT-scan features. As a result, ACGNet efficiently preserves the local and global pixel relations in denoised LDCT images. Furthermore, we propose a novel neural structure preserving loss (NSPL) through which ACGNet learns the neighborhood structure of CT images, preventing structural (shape) distortion. In addition, the ACGNet can reconstruct the CT images with human-perceived quality via back-propagated gradients due to the feature-based NSPL loss. Finally, we include differential content loss in network optimization to restore high-frequency lesion boundaries. The proposed method outperforms many state-of-the-art methods on two publicly accessible datasets: the Mayo 2016 dataset (PSNR: 35.2015 dB, SSIM: 0.9560), and Low-dose CT image and projection dataset (PSNR: 35.2825 dB, SSIM: 0.9566).

Artificial intelligence assisted clinical fluorescence imaging achieves in vivo cellular resolution comparable to adaptive optics ophthalmoscopy

BACKGROUND

Advancements in biomedical optical imaging have enabled researchers to achieve cellular-level imaging in the living human body. However, research-grade technology is not always widely available in routine clinical practice. In this paper, we incorporated artificial intelligence (AI) with standard clinical imaging to successfully obtain images of the retinal pigment epithelial (RPE) cells in living human eyes.

METHODS

Following intravenous injection of indocyanine green (ICG) dye, subjects were imaged by both conventional instruments and adaptive optics (AO) ophthalmoscopy. To improve the visibility of RPE cells in conventional ICG images, we demonstrate both a hardware approach using a custom lens add-on and an AI-based approach using a stratified cycleGAN network.

RESULTS

We observe similar fluorescent mosaic patterns arising from labeled RPE cells on both conventional and AO images, suggesting that cellular-level imaging of RPE may be obtainable using conventional imaging, albeit at lower resolution. Results show that higher resolution ICG RPE images of both healthy and diseased eyes can be obtained from conventional images using AI with a potential 220-fold improvement in time.

CONCLUSIONS

The application of using AI as an add-on module for existing instrumentation is an important step towards routine screening and detection of disease at earlier stages.

Improved biometric quantification in 3D ultrasound biomicroscopy via generative adversarial networks-based image enhancement

This study addresses the limitations of inexpensive, high-frequency ultrasound biomicroscopy (UBM) systems in visualizing small ocular structures and anatomical landmarks, especially outside the focal area, by improving image quality and visibility of important ocular structures for clinical ophthalmology applications. We developed a generative adversarial network (GAN) method for the 3D ultrasound biomicroscopy (3D-UBM) imaging system, called Spatially variant Deconvolution GAN (SDV-GAN). We employed spatially varying deconvolution and patch blending to enhance the original UBM images. This computationally expensive iterative deconvolution process yielded paired original and enhanced images for training the SDV-GAN. SDV-GAN achieved high performance metrics, with a structural similarity index measure (SSIM) of 0.96 and a peak signal-to-noise ratio (PSNR) of 36.92 dB. Structures were more clearly seen with no noticeable artifacts in the test images. SDV-GAN deconvolution improved biometric measurements made from UBM images, giving significant differences in angle opening distance (AOD, p < 0.0001) and angle recess area (ARA, p < 0.0001) measurements before and after SDV-GAN deconvolution. With clearer identification of apex, SDV-GAN improved inter-reader agreement in ARA measurements in images before and after deconvolution (intraclass correlation coefficient, [ICC] of 0.62 and 0.73, respectively). Real-time enhancement was achieved with an inference time of ~ 40 ms/frame (25 frames/s) on a standard GPU, compared to ~ 93 ms/frame (11 frames/s) using iterative deconvolution. SDV-GAN effectively enhanced UBM images, improving visibility and assessment of important ocular structures. Its real-time processing capabilities highlight the clinical potential of GAN enhancement in facilitating accurate diagnosis and treatment planning in ophthalmology using existing scanners.

Synthetic generation of cardiac tissue motion from surface electrocardiograms

Cardiac tissue motion is a sensitive biomarker for detecting early myocardial damage. Here, we show the similarity, interpretability and diagnostic accuracy of synthetic tissue Doppler imaging (TDI) waveforms generated from surface electrocardiograms (ECGs). Prospectively collected ECG and TDI data were cross-matched as 9,144 lateral and 8,722 septal TDI-ECG pairs (463 patients) for generating synthetic TDI across every 1% interval of the cardiac cycle. External validation using 816 lateral and 869 septal TDI-ECG pairs (314 patients) demonstrated strong correlation (repeated-measures r = 0.90, P < 0.0001), cosine similarity (0.89, P < 0.0001) and no differences during a randomized visual Turing test. Synthetic TDI correlated with clinical parameters (585 patients) and detected diastolic and systolic dysfunction with an area under the curve of 0.80 and 0.81, respectively. Furthermore, synthetic TDI systolic and early diastolic measurements generated from an external ECG dataset (233,647 patients) were associated with all-cause mortality during both sinus rhythm and atrial fibrillation, underscoring their potential for personalized cardiac care.

Unsupervised and Self-supervised Learning in Low-Dose Computed Tomography Denoising: Insights from Training Strategies

In recent years, X-ray low-dose computed tomography (LDCT) has garnered widespread attention due to its significant reduction in the risk of patient radiation exposure. However, LDCT images often contain a substantial amount of noises, adversely affecting diagnostic quality. To mitigate this, a plethora of LDCT denoising methods have been proposed. Among them, deep learning (DL) approaches have emerged as the most effective, due to their robust feature extraction capabilities. Yet, the prevalent use of supervised training paradigms is often impractical due to the challenges in acquiring low-dose and normal-dose CT pairs in clinical settings. Consequently, unsupervised and self-supervised deep learning methods have been introduced for LDCT denoising, showing considerable potential for clinical applications. These methods' efficacy hinges on training strategies. Notably, there appears to be no comprehensive reviews of these strategies. Our review aims to address this gap, offering insights and guidance for researchers and practitioners. Based on training strategies, we categorize the LDCT methods into six groups: (i) cycle consistency-based, (ii) score matching-based, (iii) statistical characteristics of noise-based, (iv) similarity-based, (v) LDCT synthesis model-based, and (vi) hybrid methods. For each category, we delve into the theoretical underpinnings, training strategies, strengths, and limitations. In addition, we also summarize the open source codes of the reviewed methods. Finally, the review concludes with a discussion on open issues and future research directions.

DDoCT: Morphology preserved dual-domain joint optimization for fast sparse-view low-dose CT imaging

Computed tomography (CT) is continuously becoming a valuable diagnostic technique in clinical practice. However, the radiation dose exposure in the CT scanning process is a public health concern. Within medical diagnoses, mitigating the radiation risk to patients can be achieved by reducing the radiation dose through adjustments in tube current and/or the number of projections. Nevertheless, dose reduction introduces additional noise and artifacts, which have extremely detrimental effects on clinical diagnosis and subsequent analysis. In recent years, the feasibility of applying deep learning methods to low-dose CT (LDCT) imaging has been demonstrated, leading to significant achievements. This article proposes a dual-domain joint optimization LDCT imaging framework (termed DDoCT) which uses noisy sparse-view projection to reconstruct high-performance CT images with joint optimization in projection and image domains. The proposed method not only addresses the noise introduced by reducing tube current, but also pays special attention to issues such as streak artifacts caused by a reduction in the number of projections, enhancing the applicability of DDoCT in practical fast LDCT imaging environments. Experimental results have demonstrated that DDoCT has made significant progress in reducing noise and streak artifacts and enhancing the contrast and clarity of the images.

Deep learning analysis for rheumatologic imaging: current trends, future directions, and the role of human

Rheumatic diseases, such as rheumatoid arthritis (RA), osteoarthritis (OA), and spondyloarthritis (SpA), present diagnostic and management challenges due to their impact on connective tissues and the musculoskeletal system. Traditional imaging techniques, including plain radiography, ultrasounds, computed tomography, and magnetic resonance imaging (MRI), play a critical role in diagnosing and monitoring these conditions, but face limitations like inter-observer variability and time-consuming assessments. Recently, deep learning (DL), a subset of artificial intelligence, has emerged as a promising tool for enhancing medical imaging analysis. Convolutional neural networks, a DL model type, have shown great potential in medical image classification, segmentation, and anomaly detection, often surpassing human performance in tasks like tumor identification and disease severity grading. In rheumatology, DL models have been applied to plain radiography, ultrasounds, and MRI for assessing joint damage, synovial inflammation, and disease progression in RA, OA, and SpA patients. Despite the promise of DL, challenges such as data bias, limited explainability, and the need for large annotated datasets remain significant barriers to its widespread adoption. Furthermore, human oversight and value judgment are essential for ensuring the ethical use and effective implementation of DL in clinical settings. This review provides a comprehensive overview of DL's applications in rheumatologic imaging and explores its future potential in enhancing diagnosis, treatment decisions, and personalized medicine.

Artificial intelligence for response prediction and personalisation in radiation oncology

Artificial intelligence (AI) systems may personalise radiotherapy by assessing complex and multifaceted patient data and predicting tumour and normal tissue responses to radiotherapy. Here we describe three distinct generations of AI systems, namely personalised radiotherapy based on pretreatment data, response-driven radiotherapy and dynamically optimised radiotherapy. Finally, we discuss the main challenges in clinical translation of AI systems for radiotherapy personalisation.

Role of Artificial Intelligence in Congenital Heart Disease and Interventions

Artificial intelligence has promising impact on patients with congenital heart disease, a vulnerable population with life-long health care needs and, often, a substantially higher risk of death than the general population. This review explores the role artificial intelligence has had on cardiac imaging, electrophysiology, interventional procedures, and intensive care monitoring as it relates to children and adults with congenital heart disease. Machine learning and deep learning algorithms have enhanced not only imaging segmentation and processing but also diagnostic accuracy namely reducing interobserver variability. This has a meaningful impact in complex congenital heart disease improving anatomic diagnosis, assessment of cardiac function, and predicting long-term outcomes. Image processing has benefited procedural planning for interventional cardiology, allowing for a higher quality and density of information to be extracted from the same imaging modalities. In electrophysiology, deep learning models have enhanced the diagnostic potential of electrocardiograms, detecting subtle yet meaningful variation in signals that enable early diagnosis of cardiac dysfunction, risk stratification of mortality, and more accurate diagnosis and prediction of arrhythmias. In the congenital heart disease population, this has the potential for meaningful prolongation of life. Postoperative care in the cardiac intensive care unit is a data-rich environment that is often overwhelming. Detection of subtle data trends in this environment for early detection of morbidity is a ripe avenue for artificial intelligence algorithms to be used. Examples like early detection of catheter-induced thrombosis have already been published. Despite their great promise, artificial intelligence algorithms are still limited by hurdles such as data standardization, algorithm validation, drift, and explainability.

Artificial Intelligence in Computed Tomography Image Reconstruction: A Review of Recent Advances

The development of novel image reconstruction algorithms has been pivotal in enhancing image quality and reducing radiation dose in computed tomography (CT) imaging. Traditional techniques like filtered back projection perform well under ideal conditions but fail to generate high-quality images under low-dose, sparse-view, and limited-angle conditions. Iterative reconstruction methods improve upon filtered back projection by incorporating system models and assumptions about the patient, yet they can suffer from patchy image textures. The emergence of artificial intelligence (AI), particularly deep learning, has further advanced CT reconstruction. AI techniques have demonstrated great potential in reducing radiation dose while preserving image quality and noise texture. Moreover, AI has exhibited unprecedented performance in addressing challenging CT reconstruction problems, including low-dose CT, sparse-view CT, limited-angle CT, and interior tomography. This review focuses on the latest advances in AI-based CT reconstruction under these challenging conditions.

Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction

X-ray computed tomography (CT) is a commonly used imaging modality in clinical practice. Recent years have seen increasing public concern regarding the ionizing radiation from CT. Low-dose CT (LDCT) has been proven to be effective in reducing patients' radiation exposure, but it results in CT images with low signal-to-noise ratio (SNR), failing to meet the image quality required for diagnosis. To enhance the SNR of LDCT images, numerous denoising strategies based on deep learning have been introduced, leading to notable advancements. Despite these advancements, most methods have relied on a supervised training paradigm. The challenge in acquiring aligned pairs of low-dose and normal-dose images in a clinical setting has limited their applicability. Recently, some self-supervised deep learning methods have enabled denoising using only noisy samples. However, these techniques are based on overly simplistic assumptions about noise and focus solely on CT sinogram denoising or image denoising, compromising their effectiveness. To address this, we introduce the Dual-Domain Self-supervised framework, termed DDoS, to accomplish effective LDCT denoising and reconstruction. The framework includes denoising in the sinogram domain, filtered back-projection reconstruction, and denoising in the image domain. By identifying the statistical characteristics of sinogram noise and CT image noise, we develop sinogram-denoising and CT image-denoising networks that are fully adapted to these characteristics. Both networks utilize a unified hybrid architecture that combines graph convolution and incorporates multiple channel attention modules, facilitating the extraction of local and non-local multi-scale features. Comprehensive experiments on two large-scale LDCT datasets demonstrate the superiority of DDoS framework over existing state-of-the-art methods.

The Heart of Transformation: Exploring Artificial Intelligence in Cardiovascular Disease

The application of artificial intelligence (AI) and machine learning (ML) in medicine and healthcare has been extensively explored across various areas. AI and ML can revolutionize cardiovascular disease management by significantly enhancing diagnostic accuracy, disease prediction, workflow optimization, and resource utilization. This review summarizes current advancements in AI and ML concerning cardiovascular disease, including their clinical investigation and use in primary cardiac imaging techniques, common cardiovascular disease categories, clinical research, patient care, and outcome prediction. We analyze and discuss commonly used AI and ML models, algorithms, and methodologies, highlighting their roles in improving clinical outcomes while addressing current limitations and future clinical applications. Furthermore, this review emphasizes the transformative potential of AI and ML in cardiovascular practice by improving clinical decision making, reducing human error, enhancing patient monitoring and support, and creating more efficient healthcare workflows for complex cardiovascular conditions.

Syn2Real: synthesis of CT image ring artifacts for deep learning-based correction

Objective. We strive to overcome the challenges posed by ring artifacts in x-ray computed tomography (CT) by developing a novel approach for generating training data for deep learning-based methods. Training such networks require large, high quality, datasets that are often generated in the data domain, time-consuming and expensive. Our objective is to develop a technique for synthesizing realistic ring artifacts directly in the image domain, enabling scalable production of training data without relying on specific imaging system physics.Approach. We develop 'Syn2Real,' a computationally efficient pipeline that generates realistic ring artifacts directly in the image domain. To demonstrate the effectiveness of our approach, we train two versions of UNet, vanilla and a high capacity version with self-attention layers that we call UNetpp, withℓ2and perceptual losses, as well as a diffusion model, on energy-integrating CT images with and without these synthetic ring artifacts.Main Results.Despite being trained on conventional single-energy CT images, our models effectively correct ring artifacts across various monoenergetic images, at different energy levels and slice thicknesses, from a prototype photon-counting CT system. This generalizability validates the realism and versatility of our ring artifact generation process.Significance.Ring artifacts in x-ray CT pose a unique challenge to image quality and clinical utility. By focusing on data generation, our work provides a foundation for developing more robust and adaptable ring artifact correction methods for pre-clinical, clinical and other CT applications.

Dual-domain Wasserstein Generative Adversarial Network with Hybrid Loss for Low-dose CT Imaging

Objective.Low-dose computed tomography (LDCT) has gained significant attention in hospitals and clinics as a popular imaging modality for reducing the risk of x-ray radiation. However, reconstructed LDCT images often suffer from undesired noise and artifacts, which can negatively impact diagnostic accuracy. This study aims to develop a novel approach to improve LDCT imaging performance.Approach.A dual-domain Wasserstein generative adversarial network (DWGAN) with hybrid loss is proposed as an effective and integrated deep neural network (DNN) for LDCT imaging. The DWGAN comprises two key components: a generator (G) network and a discriminator (D) network. TheGnetwork is a dual-domain DNN designed to predict high-quality images by integrating three essential components: the projection-domain denoising module, filtered back-projection-based reconstruction layer, and image-domain enhancement module. TheDnetwork is a shallow convolutional neural network used to differentiate between real (label) and generated images. To prevent the reconstructed images from becoming excessively smooth and to preserve both structural and textural details, a hybrid loss function with weighting coefficients is incorporated into the DWGAN.Main results.Numerical experiments demonstrate that the proposed DWGAN can effectively suppress noise and better preserve image details compared with existing methods. Moreover, its application to head CT data confirms the superior performance of the DWGAN in restoring structural and textural details.Significance.The proposed DWGAN framework exhibits excellent performance in recovering structural and textural details in LDCT images. Furthermore, the framework can be applied to other tomographic imaging techniques that suffer from image distortion problems.

Generative Artificial Intelligence Use in Healthcare: Opportunities for Clinical Excellence and Administrative Efficiency

Generative Artificial Intelligence (Gen AI) has transformative potential in healthcare to enhance patient care, personalize treatment options, train healthcare professionals, and advance medical research. This paper examines various clinical and non-clinical applications of Gen AI. In clinical settings, Gen AI supports the creation of customized treatment plans, generation of synthetic data, analysis of medical images, nursing workflow management, risk prediction, pandemic preparedness, and population health management. By automating administrative tasks such as medical documentations, Gen AI has the potential to reduce clinician burnout, freeing more time for direct patient care. Furthermore, application of Gen AI may enhance surgical outcomes by providing real-time feedback and automation of certain tasks in operating rooms. The generation of synthetic data opens new avenues for model training for diseases and simulation, enhancing research capabilities and improving predictive accuracy. In non-clinical contexts, Gen AI improves medical education, public relations, revenue cycle management, healthcare marketing etc. Its capacity for continuous learning and adaptation enables it to drive ongoing improvements in clinical and operational efficiencies, making healthcare delivery more proactive, predictive, and precise.

Early pigment spot segmentation and classification from iris cellular image analysis with explainable deep learning and multiclass support vector machine

Globally, retinal disorders impact thousands of individuals. Early diagnosis and treatment of these anomalies might halt their development and prevent many people from developing preventable blindness. Iris spot segmentation is critical due to acquiring iris cellular images that suffer from the off-angle iris, noise, and specular reflection. Most currently used iris segmentation techniques are based on edge data and noncellular images. The size of the pigment patches on the surface of the iris increases with eye syndrome. In addition, iris images taken in uncooperative settings frequently have negative noise, making it difficult to segment them precisely. The traditional diagnosis processes are costly and time consuming since they require highly qualified personnel and have strict environments. This paper presents an explainable deep learning model integrated with a multiclass support vector machine to analyze iris cellular images for early pigment spot segmentation and classification. Three benchmark datasets MILE, UPOL, and Eyes SUB were used in the experiments to test the proposed methodology. The experimental results are compared on standard metrics, demonstrating that the proposed model outperformed the methods reported in the literature regarding classification errors. Additionally, it is observed that the proposed parameters are highly effective in locating the micro pigment spots on the iris surfaces.

Emulating Low-Dose PCCT Image Pairs With Independent Noise for Self-Supervised Spectral Image Denoising

Photon counting CT (PCCT) acquires spectral measurements and enables generation of material decomposition (MD) images that provide distinct advantages in various clinical situations. However, noise amplification is observed in MD images, and denoising is typically applied. Clean or high-quality references are rare in clinical scans, often making supervised learning (Noise2Clean) impractical. Noise2Noise is a self-supervised counterpart, using noisy images and corresponding noisy references with zero-mean, independent noise. PCCT counts transmitted photons separately, and raw measurements are assumed to follow a Poisson distribution in each energy bin, providing the possibility to create noise-independent pairs. The approach is to use binomial selection to split the counts into two low-dose scans with independent noise. We prove that the reconstructed spectral images inherit the noise independence from counts domain through noise propagation analysis and also validated it in numerical simulation and experimental phantom scans. The method offers the flexibility to split measurements into desired dose levels while ensuring the reconstructed images share identical underlying features, thereby strengthening the model's robustness for input dose levels and capability of preserving fine details. In both numerical simulation and experimental phantom scans, we demonstrated that Noise2Noise with binomial selection outperforms other common self-supervised learning methods based on different presumptive conditions.

Noise-assisted hybrid attention networks for low-dose PET and CT denoising

BACKGROUND

Positron emission tomography (PET) and computed tomography (CT) play a vital role in tumor-related medical diagnosis, assessment, and treatment planning. However, full-dose PET and CT pose the risk of excessive radiation exposure to patients, whereas low-dose images compromise image quality, impacting subsequent tumor recognition and disease diagnosis.

PURPOSE

To solve such problems, we propose a Noise-Assisted Hybrid Attention Network (NAHANet) to reconstruct full-dose PET and CT images from low-dose PET (LDPET) and CT (LDCT) images to reduce patient radiation risks while ensuring the performance of subsequent tumor recognition.

METHODS

NAHANet contains two branches: the noise feature prediction branch (NFPB) and the cascaded reconstruction branch. Among them, NFPB providing noise features for the cascade reconstruction branch. The cascaded reconstruction branch comprises a shallow feature extraction module and a reconstruction module which contains a series of cascaded noise feature fusion blocks (NFFBs). Among these, the NFFB fuses the features extracted from low-dose images with the noise features obtained by NFPB to improve the feature extraction capability. To validate the effectiveness of the NAHANet method, we performed experiments using two public available datasets: the Ultra-low Dose PET Imaging Challenge dataset and Low Dose CT Grand Challenge dataset.

RESULTS

As a result, the proposed NAHANet achieved higher performance on common indicators. For example, on the CT dataset, the PSNR and SSIM indicators were improved by 4.1 dB and 0.06 respectively, and the rMSE indicator was reduced by 5.46 compared with the LDCT; on the PET dataset, the PSNR and SSIM was improved by 3.37 dB and 0.02, and the rMSE was reduced by 9.04 compared with the LDPET.

CONCLUSIONS

This paper proposes a transformer-based denoising algorithm, which utilizes hybrid attention to extract high-level features of low dose images and fuses noise features to optimize the denoising performance of the network, achieving good performance improvements on low-dose CT and PET datasets.

Real-World Low-Dose CT Image Denoising by Patch Similarity Purification

Reducing the radiation dose in CT scanning is important to alleviate the damage to the human health in clinical scenes. A promising way is to replace the normal-dose CT (NDCT) imaging by low-dose CT (LDCT) imaging with lower tube voltage and tube current. This often brings severe noise to the LDCT images, which adversely affects the diagnosis accuracy. Most of existing LDCT image denoising networks are trained either with synthetic LDCT images or real-world LDCT and NDCT image pairs with huge spatial misalignment. However, the synthetic noise is very different from the complex noise in real-world LDCT images, while the huge spatial misalignment brings inaccurate predictions of tissue structures in the denoised LDCT images. To well utilize real-world LDCT and NDCT image pairs for LDCT image denoising, in this paper, we introduce a new Patch Similarity Purification (PSP) strategy to construct high-quality training dataset for network training. Specifically, our PSP strategy first perform binarization for each pair of image patches cropped from the corresponding LDCT and NDCT image pairs. For each pair of binary masks, it then computes their similarity ratio by common mask calculation, and the patch pair can be selected as a training sample if their mask similarity ratio is higher than a threshold. By using our PSP strategy, each training set of our Rabbit and Patient datasets contain hundreds of thousands of real-world LDCT and NDCT image patch pairs with negligible misalignment. Extensive experiments demonstrate the usefulness of our PSP strategy on purifying the training data and the effectiveness of training LDCT image denoising networks on our datasets. The code and dataset are provided at https://github.com/TuTusong/PSP.

Deep learning based ultra-low dose fan-beam computed tomography image enhancement algorithm: Feasibility study in image quality for radiotherapy

OBJECTIVE

We investigated the feasibility of deep learning-based ultra-low dose kV-fan-beam computed tomography (kV-FBCT) image enhancement algorithm for clinical application in abdominal and pelvic tumor radiotherapy.

METHODS

A total of 76 patients of abdominal and pelvic tumors were prospectively selected. The Catphan504 was acquired with the same conditions as the standard phantom test set. We used a CycleGAN-based model for image enhancement. Normal dose CT (NDCT), ultra-low dose CT (LDCT) and deep learning enhanced CT (DLR) were evaluated by subjective and objective analyses in terms of imaging quality, HU accuracy, and image signal-to-noise ratio (SNR).

RESULTS

The image noise of DLR was significantly reduced, and the contrast-to-noise ratio (CNR) was significantly improved compared to the LDCT. The most significant improvement was the acrylic which represented soft tissue in CNR from 1.89 to 3.37, improving by 76%, nearly approaching the NDCT, and in low-density resolution from 7.64 to 12.6, improving by 64%. The spatial frequencies of MTF10 and MTF50 in DLR were 4.28 and 2.35 cycles/mm in DLR, respectively, which are higher than LDCT 3.87 and 2.12 cycles/mm, and even slightly higher than NDCT 4.15 and 2.28 cycles/mm. The accuracy and stability of HU values of DLR were similar to NDCT. The image quality evaluation of the two doctors agreed well with DLR and NDCT. A two-by-two comparison between groups showed that the differences in image scores of LDCT compared with NDCT and DLR were all statistically significant (p < 0.05), and the subjective scores of DLR were close to NDCT.

CONCLUSION

The image quality of DLR was close to NDCT with reduced radiation dose, which can fully meet the needs of conventional image-guided adaptive radiotherapy (ART) and achieve the quality requirements of clinical radiotherapy. The proposed method provided a technical basis for LDCT-guided ART.

Self-supervised learning for CT image denoising and reconstruction: a review

This article reviews the self-supervised learning methods for CT image denoising and reconstruction. Currently, deep learning has become a dominant tool in medical imaging as well as computer vision. In particular, self-supervised learning approaches have attracted great attention as a technique for learning CT images without clean/noisy references. After briefly reviewing the fundamentals of CT image denoising and reconstruction, we examine the progress of deep learning in CT image denoising and reconstruction. Finally, we focus on the theoretical and methodological evolution of self-supervised learning for image denoising and reconstruction.

Cross-modality image translation of 3 Tesla Magnetic Resonance Imaging to 7 Tesla using Generative Adversarial Networks

The rapid advancements in magnetic resonance imaging (MRI) technology have precipitated a new paradigm wherein cross-modality data translation across diverse imaging platforms, field strengths, and different sites is increasingly challenging. This issue is particularly accentuated when transitioning from 3 Tesla (3T) to 7 Tesla (7T) MRI systems. This study proposes a novel solution to these challenges using generative adversarial networks (GANs)-specifically, the CycleGAN architecture-to create synthetic 7T images from 3T data. Employing a dataset of 1112 and 490 unpaired 3T and 7T MR images, respectively, we trained a 2-dimensional (2D) CycleGAN model, evaluating its performance on a paired dataset of 22 participants scanned at 3T and 7T. Independent testing on 22 distinct participants affirmed the model's proficiency in accurately predicting various tissue types, encompassing cerebral spinal fluid, gray matter, and white matter. Our approach provides a reliable and efficient methodology for synthesizing 7T images, achieving a median Dice of 6.82%,7,63%, and 4.85% for Cerebral Spinal Fluid (CSF), Gray Matter (GM), and White Matter (WM), respectively, in the testing dataset, thereby significantly aiding in harmonizing heterogeneous datasets. Furthermore, it delineates the potential of GANs in amplifying the contrast-to-noise ratio (CNR) from 3T, potentially enhancing the diagnostic capability of the images. While acknowledging the risk of model overfitting, our research underscores a promising progression towards harnessing the benefits of 7T MR systems in research investigations while preserving compatibility with existent 3T MR data. This work was previously presented at the ISMRM 2021 conference (Diniz, Helmet, Santini, Aizenstein, & Ibrahim, 2021).

The Integration of Radiomics and Artificial Intelligence in Modern Medicine

With profound effects on patient care, the role of artificial intelligence (AI) in radiomics has become a disruptive force in contemporary medicine. Radiomics, the quantitative feature extraction and analysis from medical images, offers useful imaging biomarkers that can reveal important information about the nature of diseases, how well patients respond to treatment and patient outcomes. The use of AI techniques in radiomics, such as machine learning and deep learning, has made it possible to create sophisticated computer-aided diagnostic systems, predictive models, and decision support tools. The many uses of AI in radiomics are examined in this review, encompassing its involvement of quantitative feature extraction from medical images, the machine learning, deep learning and computer-aided diagnostic (CAD) systems approaches in radiomics, and the effect of radiomics and AI on improving workflow automation and efficiency, optimize clinical trials and patient stratification. This review also covers the predictive modeling improvement by machine learning in radiomics, the multimodal integration and enhanced deep learning architectures, and the regulatory and clinical adoption considerations for radiomics-based CAD. Particular emphasis is given to the enormous potential for enhancing diagnosis precision, treatment personalization, and overall patient outcomes.

[Artificial intelligence in diagnostic radiology for dose management : Advances and perspectives using the example of computed tomography]

CLINICAL-METHODOLOGICAL PROBLEM

Imaging procedures employing ionizing radiation require compliance with European directives and national regulations in order to protect patients. Each exposure must be indicated, individually adapted, and documented. Unacceptable dose exceedances must be detected and reported. These tasks are time-consuming and require meticulous diligence.

STANDARD RADIOLOGICAL METHODS

Computed tomography (CT) is the most important contributor to medical radiation exposure. Optimizing the patient's dose is therefore mandatory. Use of modern technology and reconstruction algorithms already reduces exposure. Checking the indication, planning, and performing the examination are further important process steps with regard to radiation protection. Patient exposure is usually monitored by dose management systems (DMS). In special cases, a risk assessment is required by calculating the organ doses.

METHODOLOGICAL INNOVATIONS

Artificial intelligence (AI)-assisted techniques are increasingly used in various steps of the process: they support examination planning, improve patient positioning, and enable automated scan length adjustments. They also provide real-time estimates of individual organ doses.

EVALUATION

The integration of AI into medical imaging is proving successful in terms of dose optimization in various areas of the radiological workflow, from reconstruction to examination planning and performing exams. However, the use of AI in conjunction with DMS has not yet been considered on a large scale.

PRACTICAL RECOMMENDATION

AI processes offer promising tools to support dose management. However, their implementation in the clinical setting requires further research, extensive validation, and continuous monitoring.

Advancements and applications of artificial intelligence in cardiovascular imaging: a comprehensive review

Artificial intelligence (AI) is transforming cardiovascular imaging by offering advancements across multiple modalities, including echocardiography, cardiac computed tomography (CCT), cardiovascular magnetic resonance (CMR), interventional cardiology, nuclear medicine, and electrophysiology. This review explores the clinical applications of AI within each of these areas, highlighting its ability to improve patient selection, reduce image acquisition time, enhance image optimization, facilitate the integration of data from different imaging modality and clinical sources, improve diagnosis and risk stratification. Moreover, we illustrate both the advantages and the limitations of AI across these modalities, acknowledging that while AI can significantly aid in diagnosis, risk stratification, and workflow efficiency, it cannot replace the expertise of cardiologists. Instead, AI serves as a powerful tool to streamline routine tasks, allowing clinicians to focus on complex cases where human judgement remains essential. By accelerating image interpretation and improving diagnostic accuracy, AI holds great potential to improve patient care and clinical decision-making in cardiovascular imaging.

Dual stage MRI image restoration based on blind spot denoising and hybrid attention

BACKGROUND

Magnetic Resonance Imaging (MRI) is extensively utilized in clinical diagnostics and medical research, yet the imaging process is often compromised by noise interference. This noise arises from various sources, leading to a reduction in image quality and subsequently hindering the accurate interpretation of image details by clinicians. Traditional denoising methods typically assume that noise follows a Gaussian distribution, thereby neglecting the more complex noise types present in MRI images, such as Rician noise. As a result, denoising remains a challenging and practical task.

METHOD

The main research work of this paper focuses on modifying mask information based on a global mask mapper. The mask mapper samples all blind spot pixels on the denoised image and maps them to the same channel. By incorporating perceptual loss, it utilizes all available information to improve performance while avoiding identity mapping. During the denoising process, the model may mistakenly remove some useful information as noise, resulting in a loss of detail in the denoised image. To address this issue, we train a generative adversarial network (GAN) with adaptive hybrid attention to restore the detailed information in the denoised MRI images.

RESULT

The two-stage model NRAE shows an improvement of nearly 1.4 dB in PSNR and approximately 0.1 in SSIM on clinical datasets compared to other classic models. Specifically, compared to the baseline model, PSNR is increased by about 0.6 dB, and SSIM is only 0.015 lower. From a visual perspective, NRAE more effectively restores the details in the images, resulting in richer and clearer representation of image details.

CONCLUSION

We have developed a deep learning-based two-stage model to address noise issues in medical MRI images. This method not only successfully reduces noise signals but also effectively restores anatomical details. The current results indicate that this is a promising approach. In future work, we plan to replace the current denoising network with more advanced models to further enhance performance.

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.

Improved brain metastases segmentation using generative adversarial network and conditional random field optimization mask R-CNN

BACKGROUND

In radiotherapy, the delineation of the gross tumor volume (GTV) in brain metastases using computed tomography (CT) simulation localization is very important. However, despite the criticality of this process, a pronounced gap exists in the availability of tools tailored for the automatic segmentation of the GTV based on CT simulation localization images.

PURPOSE

This study aims to fill this gap by devising an effective tool specifically for the automatic segmentation of the GTV using CT simulation localization images.

METHODS

A dual-network generative adversarial network (GAN) architecture was developed, wherein the generator focused on refining CT images for more precise delineation, and the discriminator differentiated between real and augmented images. This architecture was coupled with the Mask R-CNN model to achieve meticulous GTV segmentation. An end-to-end training process facilitated the integration between the GAN and Mask R-CNN functionalities. Furthermore, a conditional random field (CRF) was incorporated to refine the initial masks generated by the Mask R-CNN model to ensure optimal segmentation accuracy. The performance was assessed using key metrics, namely, the Dice coefficient (DSC), intersection over union (IoU), accuracy, specificity, and sensitivity.

RESULTS

The GAN+Mask R-CNN+CRF integration method in this study performs well in GTV segmentation. In particular, the model has an overall average DSC of 0.819 ± 0.102 and an IoU of 0.712 ± 0.111 in the internal validation. The overall average DSC in the external validation data is 0.726 ± 0.128 and the IoU is 0.640 ± 0.136. It demonstrates favorable generalization ability.

CONCLUSION

The integration of the GAN, Mask R-CNN, and CRF optimization provides a pioneering tool for the sophisticated segmentation of the GTV in brain metastases using CT simulation localization images. The method proposed in this study can provide a robust automatic segmentation approach for brain metastases in the absence of MRI.

Transmission X-ray microscopy-based three-dimensional XANES imaging

Full-field transmission X-ray microscopy (TXM) in conjunction with X-ray absorption near edge structure (XANES) spectroscopy provides two-dimensional (2D) or three-dimensional (3D) morphological and chemical-specific information within samples at the tens of nanometer scale. This technique has a broad range of applications in materials sciences and battery research. Despite its extensive applicability, 2D XANES imaging is subject to the disadvantage of information overlap when the sample thickness is uneven. 3D XANES imaging combines 3D TXM with XANES to obtain 3D distribution information on chemical states. A 3D XANES imaging method has been established at the Shanghai Synchrotron Radiation Facility (SSRF) and has been used to characterize the structure and chemical state of commercial LiNixCoyMnzO2 (NCM, x + y + z = 1) battery powder materials. The imaging results provide a visual representation of the 3D chemical state information of the particles with depth resolution, allowing for the direct observation of 3D nickel oxidation. This paper will describe in detail the data acquisition, data processing, quantification and visualization analysis of 3D XANES imaging.

MPIGAN: An end-to-end deep based generative framework for high-resolution magnetic particle imaging reconstruction

BACKGROUND

Magnetic particle imaging (MPI) is a recently developed, non-invasive in vivo imaging technique to map the spatial distribution of superparamagnetic iron oxide nanoparticles (SPIONs) in animal tissues with high sensitivity and speed. It is a challenge to reconstruct images directly from the received signals of MPI device due to the complex physical behavior of the nanoparticles. System matrix and X-space are two commonly used MPI reconstruction methods, where the former is extremely time-consuming and the latter usually produces blurry images.

PURPOSE

Currently, we proposed an end-to-end machine learning framework to reconstruct high-resolution MPI images from 1-D voltage signals directly and efficiently.

METHODS

The proposed framework, which we termed "MPIGAN", was trained on a large MPI simulation dataset containing 291 597 pairs of high-resolution 2-D phantom images and each image's corresponding voltage signals, so that it was able to accurately capture the nonlinear relationship between the spatial distribution of SPIONs and the received voltage signal, and realized high-resolution MPI image reconstruction.

RESULTS

Experiment results showed that, MPIGAN exhibited remarkable abilities in high-resolution MPI image reconstruction. MPIGAN outperformed the traditional methods of system matrix and X-space in recovering the fine-scale structure of magnetic nanoparticles' spatial distribution and achieving enhanced reconstruction performance in both visual effects and quantitative assessments. Moreover, even when the received signals were severely contaminated with noise, MPIGAN could still generate high-quality MPI images.

CONCLUSION

Our study provides a promising AI solution for end-to-end, efficient, and high-resolution magnetic particle imaging reconstruction.

A Hybrid Framework of Dual-Domain Signal Restoration and Multi-depth Feature Reinforcement for Low-Dose Lung CT Denoising

Low-dose computer tomography (LDCT) has been widely used in medical diagnosis. Various denoising methods have been presented to remove noise in LDCT scans. However, existing methods cannot achieve satisfactory results due to the difficulties in (1) distinguishing the characteristics of structures, textures, and noise confused in the image domain, and (2) representing local details and global semantics in the hierarchical features. In this paper, we propose a novel denoising method consisting of (1) a 2D dual-domain restoration framework to reconstruct noise-free structure and texture signals separately, and (2) a 3D multi-depth reinforcement U-Net model to further recover image details with enhanced hierarchical features. In the 2D dual-domain restoration framework, the convolutional neural networks are adopted in both the image domain where the image structures are well preserved through the spatial continuity, and the sinogram domain where the textures and noise are separately represented by different wavelet coefficients and processed adaptively. In the 3D multi-depth reinforcement U-Net model, the hierarchical features from the 3D U-Net are enhanced by the cross-resolution attention module (CRAM) and dual-branch graph convolution module (DBGCM). The CRAM preserves local details by integrating adjacent low-level features with different resolutions, while the DBGCM enhances global semantics by building graphs for high-level features in intra-feature and inter-feature dimensions. Experimental results on the LUNA16 dataset and 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge dataset illustrate the proposed method outperforms the state-of-the-art methods on removing noise from LDCT images with clear structures and textures, proving its potential in clinical practice.

Optimization of Fast Non-Local Means Noise Reduction Algorithm Parameter in Computed Tomographic Phantom Images Using 3D Printing Technology

Noise in computed tomography (CT) is inevitably generated, which lowers the accuracy of disease diagnosis. The non-local means approach, a software technique for reducing noise, is widely used in medical imaging. In this study, we propose a noise reduction algorithm based on fast non-local means (FNLMs) and apply it to CT images of a phantom created using 3D printing technology. The self-produced phantom was manufactured using filaments with similar density to human brain tissues. To quantitatively evaluate image quality, the contrast-to-noise ratio (CNR), coefficient of variation (COV), and normalized noise power spectrum (NNPS) were calculated. The results demonstrate that the optimized smoothing factors of FNLMs are 0.08, 0.16, 0.22, 0.25, and 0.32 at 0.001, 0.005, 0.01, 0.05, and 0.1 of noise intensities, respectively. In addition, we compared the optimized FNLMs with noisy, local filters and total variation algorithms. As a result, FNLMs showed superior performance compared to various denoising techniques. Particularly, comparing the optimized FNLMs to the noisy images, the CNR improved by 6.53 to 16.34 times, COV improved by 6.55 to 18.28 times, and the NNPS improved by 10-2 mm2 on average. In conclusion, our approach shows significant potential in enhancing CT image quality with anthropomorphic phantoms, thus addressing the noise issue and improving diagnostic accuracy.

Structure-aware diffusion for low-dose CT imaging

Reducing the radiation dose leads to the x-ray computed tomography (CT) images suffering from heavy noise and artifacts, which inevitably interferes with the subsequent clinic diagnostic and analysis. Leading works have explored diffusion models for low-dose CT imaging to avoid the structure degeneration and blurring effects of previous deep denoising models. However, most of them always begin their generative processes with Gaussian noise, which has little or no structure priors of the clean data distribution, thereby leading to long-time inference and unpleasant reconstruction quality. To alleviate these problems, this paper presents a Structure-Aware Diffusion model (SAD), an end-to-end self-guided learning framework for high-fidelity CT image reconstruction. First, SAD builds a nonlinear diffusion bridge between clean and degraded data distributions, which could directly learn the implicit physical degradation prior from observed measurements. Second, SAD integrates the prompt learning mechanism and implicit neural representation into the diffusion process, where rich and diverse structure representations extracted by degraded inputs are exploited as prompts, which provides global and local structure priors, to guide CT image reconstruction. Finally, we devise an efficient self-guided diffusion architecture using an iterative updated strategy, which further refines structural prompts during each generative step to drive finer image reconstruction. Extensive experiments on AAPM-Mayo and LoDoPaB-CT datasets demonstrate that our SAD could achieve superior performance in terms of noise removal, structure preservation, and blind-dose generalization, with few generative steps, even one step only.

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Deep learning-based harmonization of trabecular bone microstructures between high- and low-resolution CT imaging

BACKGROUND

Osteoporosis is a bone disease related to increased bone loss and fracture-risk. The variability in bone strength is partially explained by bone mineral density (BMD), and the remainder is contributed by bone microstructure. Recently, clinical CT has emerged as a viable option for in vivo bone microstructural imaging. Wide variations in spatial-resolution and other imaging features among different CT scanners add inconsistency to derived bone microstructural metrics, urging the need for harmonization of image data from different scanners.

PURPOSE

This paper presents a new deep learning (DL) method for the harmonization of bone microstructural images derived from low- and high-resolution CT scanners and evaluates the method's performance at the levels of image data as well as derived microstructural metrics.

METHODS

We generalized a three-dimensional (3D) version of GAN-CIRCLE that applies two generative adversarial networks (GANs) constrained by the identical, residual, and cycle learning ensemble (CIRCLE). Two GAN modules simultaneously learn to map low-resolution CT (LRCT) to high-resolution CT (HRCT) and vice versa. Twenty volunteers were recruited. LRCT and HRCT scans of the distal tibia of their left legs were acquired. Five-hundred pairs of LRCT and HRCT image blocks of64 × 64 × 64 $64 \times 64 \times 64 $ voxels were sampled for each of the twelve volunteers and used for training in supervised as well as unsupervised setups. LRCT and HRCT images of the remaining eight volunteers were used for evaluation. LRCT blocks were sampled at 32 voxel intervals in each coordinate direction and predicted HRCT blocks were stitched to generate a predicted HRCT image.

RESULTS

Mean ± standard deviation of structural similarity (SSIM) values between predicted and true HRCT using both 3DGAN-CIRCLE-based supervised (0.84 ± 0.03) and unsupervised (0.83 ± 0.04) methods were significantly (p < 0.001) higher than the mean SSIM value between LRCT and true HRCT (0.75 ± 0.03). All Tb measures derived from predicted HRCT by the supervised 3DGAN-CIRCLE showed higher agreement (CCC  ∈ $ \in $ [0.956 0.991]) with the reference values from true HRCT as compared to LRCT-derived values (CCC  ∈ $ \in $ [0.732 0.989]). For all Tb measures, except Tb plate-width (CCC = 0.866), the unsupervised 3DGAN-CIRCLE showed high agreement (CCC  ∈ $ \in $ [0.920 0.964]) with the true HRCT-derived reference measures. Moreover, Bland-Altman plots showed that supervised 3DGAN-CIRCLE predicted HRCT reduces bias and variability in residual values of different Tb measures as compared to LRCT and unsupervised 3DGAN-CIRCLE predicted HRCT. The supervised 3DGAN-CIRCLE method produced significantly improved performance (p < 0.001) for all Tb measures as compared to the two DL-based supervised methods available in the literature.

CONCLUSIONS

3DGAN-CIRCLE, trained in either unsupervised or supervised fashion, generates HRCT images with high structural similarity to the reference true HRCT images. The supervised 3DGAN-CIRCLE improves agreements of computed Tb microstructural measures with their reference values and outperforms the unsupervised 3DGAN-CIRCLE. 3DGAN-CIRCLE offers a viable DL solution to retrospectively improve image resolution, which may aid in data harmonization in multi-site longitudinal studies where scanner mismatch is unavoidable.

An adversarial learning approach to generate pressure support ventilation waveforms for asynchrony detection

BACKGROUND AND OBJECTIVE

Mechanical ventilation is a life-saving treatment for critically-ill patients. During treatment, patient-ventilator asynchrony (PVA) can occur, which can lead to pulmonary damage, complications, and higher mortality. While traditional detection methods for PVAs rely on visual inspection by clinicians, in recent years, machine learning models are being developed to detect PVAs automatically. However, training these models requires large labeled datasets, which are difficult to obtain, as labeling is a labour-intensive and time-consuming task, requiring clinical expertise. Simulating the lung-ventilator interactions has been proposed to obtain large labeled datasets to train machine learning classifiers. However, the obtained data lacks the influence of different hardware, of servo-controlled algorithms, and different sources of noise. Here, we propose VentGAN, an adversarial learning approach to improve simulated data by learning the ventilator fingerprints from unlabeled clinical data.

METHODS

In VentGAN, the loss functions are designed to add characteristics of clinical waveforms to the generated results, while preserving the labels of the simulated waveforms. To validate VentGAN, we compare the performance for detection and classification of PVAs when training a previously developed machine learning algorithm with the original simulated data and with the data generated by VentGAN. Testing is performed on independent clinical data labeled by experts. The McNemar test is applied to evaluate statistical differences in the obtained classification accuracy.

RESULTS

VentGAN significantly improves the classification accuracy for late cycling, early cycling and normal breaths (p< 0.01); no significant difference in accuracy was observed for delayed inspirations (p = 0.2), while the accuracy decreased for ineffective efforts (p< 0.01).

CONCLUSIONS

Generation of realistic synthetic data with labels by the proposed framework is feasible and represents a promising avenue for improving training of machine learning models.

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.

TIST-Net: style transfer in dynamic contrast enhanced MRI using spatial and temporal information

Objective.Training deep learning models for image registration or segmentation of dynamic contrast enhanced (DCE) MRI data is challenging. This is mainly due to the wide variations in contrast enhancement within and between patients. To train a model effectively, a large dataset is needed, but acquiring it is expensive and time consuming. Instead, style transfer can be used to generate new images from existing images. In this study, our objective is to develop a style transfer method that incorporates spatio-temporal information to either add or remove contrast enhancement from an existing image.Approach.We propose a temporal image-to-image style transfer network (TIST-Net), consisting of an auto-encoder combined with convolutional long short-term memory networks. This enables disentanglement of the content and style latent spaces of the time series data, using spatio-temporal information to learn and predict key structures. To generate new images, we use deformable and adaptive convolutions which allow fine grained control over the combination of the content and style latent spaces. We evaluate our method, using popular metrics and a previously proposed contrast weighted structural similarity index measure. We also perform a clinical evaluation, where experts are asked to rank images generated by multiple methods.Main Results.Our model achieves state-of-the-art performance on three datasets (kidney, prostate and uterus) achieving an SSIM of 0.91 ± 0.03, 0.73 ± 0.04, 0.88 ± 0.04 respectively when performing style transfer between a non-enhanced image and a contrast-enhanced image. Similarly, SSIM results for style transfer from a contrast-enhanced image to a non-enhanced image were 0.89 ± 0.03, 0.82 ± 0.03, 0.87 ± 0.03. In the clinical evaluation, our method was ranked consistently higher than other approaches.Significance.TIST-Net can be used to generate new DCE-MRI data from existing images. In future, this may improve models for tasks such as image registration or segmentation by allowing small training datasets to be expanded.

Convolutional neural networks combined with conventional filtering to semantically segment plant roots in rapidly scanned X-ray computed tomography volumes with high noise levels

BACKGROUND

X-ray computed tomography (CT) is a powerful tool for measuring plant root growth in soil. However, a rapid scan with larger pots, which is required for throughput-prioritized crop breeding, results in high noise levels, low resolution, and blurred root segments in the CT volumes. Moreover, while plant root segmentation is essential for root quantification, detailed conditional studies on segmenting noisy root segments are scarce. The present study aimed to investigate the effects of scanning time and deep learning-based restoration of image quality on semantic segmentation of blurry rice (Oryza sativa) root segments in CT volumes.

RESULTS

VoxResNet, a convolutional neural network-based voxel-wise residual network, was used as the segmentation model. The training efficiency of the model was compared using CT volumes obtained at scan times of 33, 66, 150, 300, and 600 s. The learning efficiencies of the samples were similar, except for scan times of 33 and 66 s. In addition, The noise levels of predicted volumes differd among scanning conditions, indicating that the noise level of a scan time ≥ 150 s does not affect the model training efficiency. Conventional filtering methods, such as median filtering and edge detection, increased the training efficiency by approximately 10% under any conditions. However, the training efficiency of 33 and 66 s-scanned samples remained relatively low. We concluded that scan time must be at least 150 s to not affect segmentation. Finally, we constructed a semantic segmentation model for 150 s-scanned CT volumes, for which the Dice loss reached 0.093. This model could not predict the lateral roots, which were not included in the training data. This limitation will be addressed by preparing appropriate training data.

CONCLUSIONS

A semantic segmentation model can be constructed even with rapidly scanned CT volumes with high noise levels. Given that scanning times ≥ 150 s did not affect the segmentation results, this technique holds promise for rapid and low-dose scanning. This study offers insights into images other than CT volumes with high noise levels that are challenging to determine when annotating.

Application of MR images in radiotherapy planning for brain tumor based on deep learning

PURPOSE

Explore the function and dose calculation accuracy of MRI images in radiotherapy planning through deep learning methods.

METHODS

131 brain tumor patients undergoing radiotherapy with previous MR and CT images were recruited for this study. A new series of MRI from the aligned MR was firstly registered to CT images strictly using MIM software and then resampled. A deep learning method (U-NET) was used to establish a MRI-to-CT conversion model, for which 105 patient images were used as the training set and 26 patient images were used as the tuning set. Data from additional 8 patients were collected as the test set, and the accuracy of the model was evaluated from a dosimetric standpoint.

RESULTS

Comparing the synthetic CT images with the original CT images, the difference in dosimetric parameters D98, D95, D2 and Dmean of PTV in 8 patients was less than 0.5%. The gamma passed rates of PTV and whole body volume were: 1%/1 mm: 93.96%±6.75%, 2%/2 mm: 99.87%±0.30%, 3%/3 mm: 100.00%±0.00%; and 1%/1 mm: 99.14%±0.80%, 2%/2 mm: 99.92%±0.08%, 3%/3 mm: 99.99%±0.01%.

CONCLUSION

MR images can be used both in delineation and treatment efficacy evaluation and in dose calculation. Using the deep learning way to convert MR image to CT image is a viable method and can be further used in dose calculation.

Patient-derived PixelPrint phantoms for evaluating clinical imaging performance of a deep learning CT reconstruction algorithm

Objective. Deep learning reconstruction (DLR) algorithms exhibit object-dependent resolution and noise performance. Thus, traditional geometric CT phantoms cannot fully capture the clinical imaging performance of DLR. This study uses a patient-derived 3D-printed PixelPrint lung phantom to evaluate a commercial DLR algorithm across a wide range of radiation dose levels.Method. The lung phantom used in this study is based on a patient chest CT scan containing ground glass opacities and was fabricated using PixelPrint 3D-printing technology. The phantom was placed inside two different size extension rings to mimic a small- and medium-sized patient and was scanned on a conventional CT scanner at exposures between 0.5 and 20 mGy. Each scan was reconstructed using filtered back projection (FBP), iterative reconstruction, and DLR at five levels of denoising. Image noise, contrast to noise ratio (CNR), root mean squared error, structural similarity index (SSIM), and multi-scale SSIM (MS SSIM) were calculated for each image.Results.DLR demonstrated superior performance compared to FBP and iterative reconstruction for all measured metrics in both phantom sizes, with better performance for more aggressive denoising levels. DLR was estimated to reduce dose by 25%-83% in the small phantom and by 50%-83% in the medium phantom without decreasing image quality for any of the metrics measured in this study. These dose reduction estimates are more conservative compared to the estimates obtained when only considering noise and CNR.Conclusion. DLR has the capability of producing diagnostic image quality at up to 83% lower radiation dose, which can improve the clinical utility and viability of lower dose CT scans. Furthermore, the PixelPrint phantom used in this study offers an improved testing environment with more realistic tissue structures compared to traditional CT phantoms, allowing for structure-based image quality evaluation beyond noise and contrast-based assessments.

The Role of Artificial Intelligence in Cardiac Imaging

Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.

Image factory: A method for synthesizing novel CT images with anatomical guidance

BACKGROUND

Deep learning in medical applications is limited due to the low availability of large labeled, annotated, or segmented training datasets. With the insufficient data available for model training comes the inability of these networks to learn the fine nuances of the space of possible images in a given medical domain, leading to the possible suppression of important diagnostic features hence making these deep learning systems suboptimal in their performance and vulnerable to adversarial attacks.

PURPOSE

We formulate a framework to address this lack of labeled data problem. We test this formulation in computed tomographic images domain and present an approach that can synthesize large sets of novel CT images at high resolution across the full Hounsfield (HU) range.

METHODS

Our method only requires a small annotated dataset of lung CT from 30 patients (available online at the TCIA) and a large nonannotated dataset with high resolution CT images from 14k patients (received from NIH, not publicly available). It then converts the small annotated dataset into a large annotated dataset, using a sequence of steps including texture learning via StyleGAN, label learning via U-Net and semi-supervised learning via CycleGAN/Pixel-to-Pixel (P2P) architectures. The large annotated dataset so generated can then be used for the training of deep learning networks for medical applications. It can also be put to use for the synthesis of CT images with varied anatomies that were nonexistent within either of the input datasets, enriching the dataset even further.

RESULTS

We demonstrate our framework via lung CT-Scan synthesis along with their novel generated annotations and compared it with other state of the art generative models that only produce images without annotations. We evaluate our framework effectiveness via a visual turing test with help of a few doctors and radiologists.

CONCLUSIONS

We gain the capability of generating an unlimited amount of annotated CT images. Our approach works for all HU windows with minimal depreciation in anatomical plausibility and hence could be used as a general purpose framework for annotated data augmentation for deep learning applications in medical imaging.

Reliable Delineation of Clinical Target Volumes for Cervical Cancer Radiotherapy on CT/MR Dual-Modality Images

Accurate delineation of the clinical target volume (CTV) is a crucial prerequisite for safe and effective radiotherapy characterized. This study addresses the integration of magnetic resonance (MR) images to aid in target delineation on computed tomography (CT) images. However, obtaining MR images directly can be challenging. Therefore, we employ AI-based image generation techniques to "intelligentially generate" MR images from CT images to improve CTV delineation based on CT images. To generate high-quality MR images, we propose an attention-guided single-loop image generation model. The model can yield higher-quality images by introducing an attention mechanism in feature extraction and enhancing the loss function. Based on the generated MR images, we propose a CTV segmentation model fusing multi-scale features through image fusion and a hollow space pyramid module to enhance segmentation accuracy. The image generation model used in this study improves the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) from 14.87 and 0.58 to 16.72 and 0.67, respectively, and improves the feature distribution distance and learning-perception image similarity from 180.86 and 0.28 to 110.98 and 0.22, achieving higher quality image generation. The proposed segmentation method demonstrates high accuracy, compared with the FCN method, the intersection over union ratio and the Dice coefficient are improved from 0.8360 and 0.8998 to 0.9043 and 0.9473, respectively. Hausdorff distance and mean surface distance decreased from 5.5573 mm and 2.3269 mm to 4.7204 mm and 0.9397 mm, respectively, achieving clinically acceptable segmentation accuracy. Our method might reduce physicians' manual workload and accelerate the diagnosis and treatment process while decreasing inter-observer variability in identifying anatomical structures.

Technical note: Minimizing CIED artifacts on a 0.35 T MRI-Linac using deep learning

BACKGROUND

Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT).

PURPOSE

This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT.

METHODS

Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the remaining two volunteers were used for testing. In addition, the dataset was reorganized three times using a Leave-One-Out scheme. Tracking metrics [Dice similarity coefficient (DSC), target registration error (TRE), and 95 percentile Hausdorff distance (95% HD)] were evaluated for whole-heart contours. Image quality metrics [normalized root mean square error (nRMSE), peak signal-to-noise ratio (PSNR), and multiscale structural similarity (MS-SSIM) scores] were evaluated. The technique was also tested qualitatively on three additional ICD datasets (Group B) including a patient with an implanted ICD.

RESULTS

For the whole-heart contour with CycleGAN reconstruction: 1) Mean DSC rose from 0.910 to 0.935; 2) Mean TRE dropped from 4.488 to 2.877 mm; and 3) Mean 95% HD dropped from 10.236 to 7.700 mm. For the whole-body slice with CycleGAN reconstruction: 1) Mean nRMSE dropped from 0.644 to 0.420; 2) Mean MS-SSIM rose from 0.779 to 0.819; and 3) Mean PSNR rose from 18.744 to 22.368. The three Group B datasets evaluated qualitatively displayed a reduction in ICD artifacts in the heart.

CONCLUSION

CycleGAN-generated reconstructions significantly improved both tracking and image quality metrics when used to mitigate artifacts from ICDs.

A Review of deep learning methods for denoising of medical low-dose CT images

To prevent patients from being exposed to excess of radiation in CT imaging, the most common solution is to decrease the radiation dose by reducing the X-ray, and thus the quality of the resulting low-dose CT images (LDCT) is degraded, as evidenced by more noise and streaking artifacts. Therefore, it is important to maintain high quality CT image while effectively reducing radiation dose. In recent years, with the rapid development of deep learning technology, deep learning-based LDCT denoising methods have become quite popular because of their data-driven and high-performance features to achieve excellent denoising results. However, to our knowledge, no relevant article has so far comprehensively introduced and reviewed advanced deep learning denoising methods such as Transformer structures in LDCT denoising tasks. Therefore, based on the literatures related to LDCT image denoising published from year 2016-2023, and in particular from 2020 to 2023, this study presents a systematic survey of current situation, and challenges and future research directions in LDCT image denoising field. Four types of denoising networks are classified according to the network structure: CNN-based, Encoder-Decoder-based, GAN-based, and Transformer-based denoising networks, and each type of denoising network is described and summarized from the perspectives of structural features and denoising performances. Representative deep-learning denoising methods for LDCT are experimentally compared and analyzed. The study results show that CNN-based denoising methods capture image details efficiently through multi-level convolution operation, demonstrating superior denoising effects and adaptivity. Encoder-decoder networks with MSE loss, achieve outstanding results in objective metrics. GANs based methods, employing innovative generators and discriminators, obtain denoised images that exhibit perceptually a closeness to NDCT. Transformer-based methods have potential for improving denoising performances due to their powerful capability in capturing global information. Challenges and opportunities for deep learning based LDCT denoising are analyzed, and future directions are also presented.