PET image super-resolution using generative adversarial networks

Super-resolution techniques for biomedical applications and challenges

Super-resolution (SR) techniques have revolutionized the field of biomedical applications by detailing the structures at resolutions beyond the limits of imaging or measuring tools. These techniques have been applied in various biomedical applications, including microscopy, magnetic resonance imaging (MRI), computed tomography (CT), X-ray, electroencephalogram (EEG), ultrasound, etc. SR methods are categorized into two main types: traditional non-learning-based methods and modern learning-based approaches. In both applications, SR methodologies have been effectively utilized on biomedical images, enhancing the visualization of complex biological structures. Additionally, these methods have been employed on biomedical data, leading to improvements in computational precision and efficiency for biomedical simulations. The use of SR techniques has resulted in more detailed and accurate analyses in diagnostics and research, essential for early disease detection and treatment planning. However, challenges such as computational demands, data interpretation complexities, and the lack of unified high-quality data persist. The article emphasizes these issues, underscoring the need for ongoing development in SR technologies to further improve biomedical research and patient care outcomes.

Neural blind deconvolution for deblurring and supersampling PSMA PET

Objective. To simultaneously deblur and supersample prostate specific membrane antigen (PSMA) positron emission tomography (PET) images using neural blind deconvolution.Approach. Blind deconvolution is a method of estimating the hypothetical 'deblurred' image along with the blur kernel (related to the point spread function) simultaneously. Traditionalmaximum a posterioriblind deconvolution methods require stringent assumptions and suffer from convergence to a trivial solution. A method of modelling the deblurred image and kernel with independent neural networks, called 'neural blind deconvolution' had demonstrated success for deblurring 2D natural images in 2020. In this work, we adapt neural blind deconvolution to deblur PSMA PET images while simultaneous supersampling to double the original resolution. We compare this methodology with several interpolation methods in terms of resultant blind image quality metrics and test the model's ability to predict accurate kernels by re-running the model after applying artificial 'pseudokernels' to deblurred images. The methodology was tested on a retrospective set of 30 prostate patients as well as phantom images containing spherical lesions of various volumes.Main results. Neural blind deconvolution led to improvements in image quality over other interpolation methods in terms of blind image quality metrics, recovery coefficients, and visual assessment. Predicted kernels were similar between patients, and the model accurately predicted several artificially-applied pseudokernels. Localization of activity in phantom spheres was improved after deblurring, allowing small lesions to be more accurately defined.Significance. The intrinsically low spatial resolution of PSMA PET leads to partial volume effects (PVEs) which negatively impact uptake quantification in small regions. The proposed method can be used to mitigate this issue, and can be straightforwardly adapted for other imaging modalities.

Impact of using sinogram domain data in the super-resolution of CT images on diagnostic information

BACKGROUND

In recent times, deep-learning-based super-resolution (DL-SR) techniques for computed tomography (CT) images have shown outstanding results in terms of full-reference image quality (FR-IQ) metrics (e.g., root mean square error and structural similarity index metric), which assesses IQ by measuring its similarity to the high-resolution (HR) image. In addition, IQ can be evaluated via task-based IQ (Task-IQ) metrics that evaluate the ability to perform specific tasks. Ironically, most proposed image domain-based SR techniques are not possible to improve a Task-IQ metric, which assesses the amount of information related to diagnosis.

PURPOSE

In the case of CT imaging systems, sinogram domain data can be utilized for SR techniques. Therefore, this study aims to investigate the impact of utilizing sinogram domain data on diagnostic information restoration ability.

METHODS

We evaluated three DL-SR techniques: using image domain data (Image-SR), using sinogram domain data (Sinogram-SR), and using sinogram as well as image domain data (Dual-SR). For Task-IQ evaluation, the Rayleigh discrimination task was used to evaluate diagnostic ability by focusing on the resolving power aspect, and an ideal observer (IO) can be used to perform the task. In this study, we used a convolutional neural network (CNN)-based IO that approximates the IO performance. We compared the IO performances of the SR techniques according to the data domain to evaluate the discriminative information restoration ability.

RESULTS

Overall, the low-resolution (LR) and SR exhibit lower IO performances compared with that of HR owing to their degraded discriminative information when detector binning is used. Next, between the SR techniques, Image-SR does not show superior IO performances compared to the LR image, but Sinogram-SR and Dual-SR show superior IO performances than the LR image. Furthermore, in Sinogram-SR, we confirm that FR-IQ and IO performance are positively correlated. These observations demonstrate that sinogram domain upsampling improves the representation ability for discriminative information in the image domain compared to the LR and Image-SR.

CONCLUSIONS

Unlike Image-SR, Sinogram-SR can improve the amount of discriminative information present in the image domain. This demonstrates that to improve the amount of discriminative information on the resolving power aspect, it is necessary to employ sinogram domain processing.

Quasi-supervised learning for super-resolution PET

Low resolution of positron emission tomography (PET) limits its diagnostic performance. Deep learning has been successfully applied to achieve super-resolution PET. However, commonly used supervised learning methods in this context require many pairs of low- and high-resolution (LR and HR) PET images. Although unsupervised learning utilizes unpaired images, the results are not as good as that obtained with supervised deep learning. In this paper, we propose a quasi-supervised learning method, which is a new type of weakly-supervised learning methods, to recover HR PET images from LR counterparts by leveraging similarity between unpaired LR and HR image patches. Specifically, LR image patches are taken from a patient as inputs, while the most similar HR patches from other patients are found as labels. The similarity between the matched HR and LR patches serves as a prior for network construction. Our proposed method can be implemented by designing a new network or modifying an existing network. As an example in this study, we have modified the cycle-consistent generative adversarial network (CycleGAN) for super-resolution PET. Our numerical and experimental results qualitatively and quantitatively show the merits of our method relative to the state-of-the-art methods. The code is publicly available at https://github.com/PigYang-ops/CycleGAN-QSDL.

Artificial Intelligence for PET and SPECT Image Enhancement

Nuclear medicine imaging modalities such as PET and SPECT are confounded by high noise levels and low spatial resolution, necessitating postreconstruction image enhancement to improve their quality and quantitative accuracy. Artificial intelligence (AI) models such as convolutional neural networks, U-Nets, and generative adversarial networks have shown promising outcomes in enhancing PET and SPECT images. This review article presents a comprehensive survey of state-of-the-art AI methods for PET and SPECT image enhancement and seeks to identify emerging trends in this field. We focus on recent breakthroughs in AI-based PET and SPECT image denoising and deblurring. Supervised deep-learning models have shown great potential in reducing radiotracer dose and scan times without sacrificing image quality and diagnostic accuracy. However, the clinical utility of these methods is often limited by their need for paired clean and corrupt datasets for training. This has motivated research into unsupervised alternatives that can overcome this limitation by relying on only corrupt inputs or unpaired datasets to train models. This review highlights recently published supervised and unsupervised efforts toward AI-based PET and SPECT image enhancement. We discuss cross-scanner and cross-protocol training efforts, which can greatly enhance the clinical translatability of AI-based image enhancement tools. We also aim to address the looming question of whether the improvements in image quality generated by AI models lead to actual clinical benefit. To this end, we discuss works that have focused on task-specific objective clinical evaluation of AI models for image enhancement or incorporated clinical metrics into their loss functions to guide the image generation process. Finally, we discuss emerging research directions, which include the exploration of novel training paradigms, curation of larger task-specific datasets, and objective clinical evaluation that will enable the realization of the full translation potential of these models in the future.

Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations

Machine learning can predict neurosurgical diagnosis and outcomes, power imaging analysis, and perform robotic navigation and tumor labeling. State-of-the-art models can reconstruct and generate images, predict surgical events from video, and assist in intraoperative decision-making. In this review, we will detail the neurosurgical applications of machine learning, ranging from simple to advanced models, and their potential to transform patient care. As machine learning techniques, outputs, and methods become increasingly complex, their performance is often more impactful yet increasingly difficult to evaluate. We aim to introduce these advancements to the neurosurgical audience while suggesting major potential roadblocks to their safe and effective translation. Unlike the previous generation of machine learning in neurosurgery, the safe translation of recent advancements will be contingent on neurosurgeons' involvement in model development and validation.

PET image denoising based on denoising diffusion probabilistic model

PURPOSE

Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising.

METHODS

Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [[Formula: see text]F]FDG datasets and 140 brain [[Formula: see text]F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods.

RESULTS

Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance.

CONCLUSION

DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.

A super-resolution network for medical imaging via transformation analysis of wavelet multi-resolution

In recent years, deep learning super-resolution models for progressive reconstruction have achieved great success. However, these models which refer to multi-resolution analysis basically ignore the information contained in the lower subspaces and do not explore the correlation between features in the wavelet and spatial domain, resulting in not fully utilizing the auxiliary information brought by multi-resolution analysis with multiple domains. Therefore, we propose a super-resolution network based on the wavelet multi-resolution framework (WMRSR) to capture the auxiliary information contained in multiple subspaces and to be aware of the interdependencies between spatial domain and wavelet domain features. Initially, the wavelet multi-resolution input (WMRI) is generated by combining wavelet sub-bands obtained from each subspace through wavelet multi-resolution analysis and the corresponding spatial domain image content, which serves as input to the network. Then, the WMRSR captures the corresponding features from the WMRI in the wavelet domain and spatial domain, respectively, and fuses them adaptively, thus learning fully explored features in multi-resolution and multi-domain. Finally, the high-resolution images are gradually reconstructed in the wavelet multi-resolution framework by our convolution-based wavelet transform module which is suitable for deep neural networks. Extensive experiments conducted on two public datasets demonstrate that our method outperforms other state-of-the-art methods in terms of objective and visual qualities.

Brain imaging with portable low-field MRI

The advent of portable, low-field MRI (LF-MRI) heralds new opportunities in neuroimaging. Low power requirements and transportability have enabled scanning outside the controlled environment of a conventional MRI suite, enhancing access to neuroimaging for indications that are not well suited to existing technologies. Maximizing the information extracted from the reduced signal-to-noise ratio of LF-MRI is crucial to developing clinically useful diagnostic images. Progress in electromagnetic noise cancellation and machine learning reconstruction algorithms from sparse k-space data as well as new approaches to image enhancement have now enabled these advancements. Coupling technological innovation with bedside imaging creates new prospects in visualizing the healthy brain and detecting acute and chronic pathological changes. Ongoing development of hardware, improvements in pulse sequences and image reconstruction, and validation of clinical utility will continue to accelerate this field. As further innovation occurs, portable LF-MRI will facilitate the democratization of MRI and create new applications not previously feasible with conventional systems.

Enhanced PET imaging using progressive conditional deep image prior

Objective.Unsupervised learning-based methods have been proven to be an effective way to improve the image quality of positron emission tomography (PET) images when a large dataset is not available. However, when the gap between the input image and the target PET image is large, direct unsupervised learning can be challenging and easily lead to reduced lesion detectability. We aim to develop a new unsupervised learning method to improve lesion detectability in patient studies.Approach.We applied the deep progressive learning strategy to bridge the gap between the input image and the target image. The one-step unsupervised learning is decomposed into two unsupervised learning steps. The input image of the first network is an anatomical image and the input image of the second network is a PET image with a low noise level. The output of the first network is also used as the prior image to generate the target image of the second network by iterative reconstruction method.Results.The performance of the proposed method was evaluated through the phantom and patient studies and compared with non-deep learning, supervised learning and unsupervised learning methods. The results showed that the proposed method was superior to non-deep learning and unsupervised methods, and was comparable to the supervised method.Significance.A progressive unsupervised learning method was proposed, which can improve image noise performance and lesion detectability.

Diffusion models in medical imaging: A comprehensive survey

Denoising diffusion models, a class of generative models, have garnered immense interest lately in various deep-learning problems. A diffusion probabilistic model defines a forward diffusion stage where the input data is gradually perturbed over several steps by adding Gaussian noise and then learns to reverse the diffusion process to retrieve the desired noise-free data from noisy data samples. Diffusion models are widely appreciated for their strong mode coverage and quality of the generated samples in spite of their known computational burdens. Capitalizing on the advances in computer vision, the field of medical imaging has also observed a growing interest in diffusion models. With the aim of helping the researcher navigate this profusion, this survey intends to provide a comprehensive overview of diffusion models in the discipline of medical imaging. Specifically, we start with an introduction to the solid theoretical foundation and fundamental concepts behind diffusion models and the three generic diffusion modeling frameworks, namely, diffusion probabilistic models, noise-conditioned score networks, and stochastic differential equations. Then, we provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms. To this end, we cover extensive applications of diffusion models in the medical domain, including image-to-image translation, reconstruction, registration, classification, segmentation, denoising, 2/3D generation, anomaly detection, and other medically-related challenges. Furthermore, we emphasize the practical use case of some selected approaches, and then we discuss the limitations of the diffusion models in the medical domain and propose several directions to fulfill the demands of this field. Finally, we gather the overviewed studies with their available open-source implementations at our GitHub.1 We aim to update the relevant latest papers within it regularly.

Generative AI for brain image computing and brain network computing: a review

Recent years have witnessed a significant advancement in brain imaging techniques that offer a non-invasive approach to mapping the structure and function of the brain. Concurrently, generative artificial intelligence (AI) has experienced substantial growth, involving using existing data to create new content with a similar underlying pattern to real-world data. The integration of these two domains, generative AI in neuroimaging, presents a promising avenue for exploring various fields of brain imaging and brain network computing, particularly in the areas of extracting spatiotemporal brain features and reconstructing the topological connectivity of brain networks. Therefore, this study reviewed the advanced models, tasks, challenges, and prospects of brain imaging and brain network computing techniques and intends to provide a comprehensive picture of current generative AI techniques in brain imaging. This review is focused on novel methodological approaches and applications of related new methods. It discussed fundamental theories and algorithms of four classic generative models and provided a systematic survey and categorization of tasks, including co-registration, super-resolution, enhancement, classification, segmentation, cross-modality, brain network analysis, and brain decoding. This paper also highlighted the challenges and future directions of the latest work with the expectation that future research can be beneficial.

Medical image super-resolution reconstruction algorithms based on deep learning: A survey

BACKGROUND AND OBJECTIVE

With the high-resolution (HR) requirements of medical images in clinical practice, super-resolution (SR) reconstruction algorithms based on low-resolution (LR) medical images have become a research hotspot. This type of method can significantly improve image SR without improving hardware equipment, so it is of great significance to review it.

METHODS

Aiming at the unique SR reconstruction algorithms in the field of medical images, based on subdivided medical fields such as magnetic resonance (MR) images, computed tomography (CT) images, and ultrasound images. Firstly, we deeply analyzed the research progress of SR reconstruction algorithms, and summarized and compared the different types of algorithms. Secondly, we introduced the evaluation indicators corresponding to the SR reconstruction algorithms. Finally, we prospected the development trend of SR reconstruction technology in the medical field.

RESULTS

The medical image SR reconstruction technology based on deep learning can provide more abundant lesion information, relieve the expert's diagnosis pressure, and improve the diagnosis efficiency and accuracy.

CONCLUSION

The medical image SR reconstruction technology based on deep learning helps to improve the quality of medicine, provides help for the diagnosis of experts, and lays a solid foundation for the subsequent analysis and identification tasks of the computer, which is of great significance for improving the diagnosis efficiency of experts and realizing intelligent medical care.

Super-Resolution Processing of Synchrotron CT Images for Automated Fibre Break Analysis of Unidirectional Composites

Fibre breaks govern the strength of unidirectional composite materials under tension. The progressive development of fibre breaks is studied using in situ X-ray computed tomography, especially with synchrotron radiation. However, even with synchrotron radiation, the resolution of the time-resolved in situ images is not sufficient for a fully automated analysis of continuous mechanical deformations. We therefore investigate the possibility of increasing the quality of low-resolution in situ scans by means of super-resolution (SR) using 3D deep learning techniques, thus facilitating the subsequent fibre break identification. We trained generative neural networks (GAN) on datasets of high-(0.3 μm) and low-resolution (1.6 μm) statically acquired images. These networks were then applied to a low-resolution (1.1 μm) noisy image of a continuously loaded specimen. The statistical parameters of the fibre breaks used for the comparison are the number of individual breaks and the number of 2-plets and 3-plets per specimen volume. The fully automated process achieves an average accuracy of 82% of manually identified fibre breaks, while the semi-automated one reaches 92%. The developed approach allows the use of faster, low-resolution in situ tomography without losing the quality of the identified physical parameters.

Improving the diagnostic performance of computed tomography angiography for intracranial large arterial stenosis by a novel super-resolution algorithm based on multi-scale residual denoising generative adversarial network

BACKGROUND

Computed tomography angiography (CTA) is very popular because it is characterized by rapidity and accessibility. However, CTA is inferior to digital subtraction angiography (DSA) in the diagnosis of intracranial artery stenosis or occlusion. DSA is an invasive examination, so we optimized the quality of cephalic CTA images.

METHODS

We used 5000 CTA images to train multi-scale residual denoising generative adversarial network (MRDGAN). And then 71 CTA images with intracranial large arterial stenosis were treated by Super-Resolution based on Generative Adversarial Network (SRGAN), Enhanced Super-Resolution based on Generative Adversarial Network (ESRGAN) and post-trained MRDGAN, respectively. Peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) of the SRGAN, ESRGAN, MRDGAN and original CTA images were measured respectively. The qualities of MRDGAN and original images were visually assessed using a 4-point scale. The diagnostic coherence of digital subtraction angiography (DSA) with MRDGAN and original images was analyzed.

RESULTS

The PSNR was significantly higher in the MRDGAN CTA images (35.96 ± 1.51) than in the original (31.51 ± 1.43), SRGAN (25.75 ± 1.18) and ESRGAN (30.36 ± 1.05) CTA images (all P < 0.001). The SSIM was significantly higher in the MRDGAN CTA images (0.95 ± 0.02) than in the SRGAN (0.88 ± 0.03) and ESRGAN (0.90 ± 0.02) CTA images (all P < 0.01). The visual assessment was significantly higher in the MRDGAN CTA images (3.52 ± 0.58) than in the original CTA images (2.39 ± 0.69) (P < 0.05). The diagnostic coherence between MRDGAN and DSA (κ = 0.89) was superior to that between original images and DSA (κ = 0.62).

CONCLUSION

Our MRDGAN can effectively optimize original CTA images and improve its clinical diagnostic value for intracranial large artery stenosis.

SynthSR: A public AI tool to turn heterogeneous clinical brain scans into high-resolution T1-weighted images for 3D morphometry

Every year, millions of brain magnetic resonance imaging (MRI) scans are acquired in hospitals across the world. These have the potential to revolutionize our understanding of many neurological diseases, but their morphometric analysis has not yet been possible due to their anisotropic resolution. We present an artificial intelligence technique, "SynthSR," that takes clinical brain MRI scans with any MR contrast (T1, T2, etc.), orientation (axial/coronal/sagittal), and resolution and turns them into high-resolution T1 scans that are usable by virtually all existing human neuroimaging tools. We present results on segmentation, registration, and atlasing of >10,000 scans of controls and patients with brain tumors, strokes, and Alzheimer's disease. SynthSR yields morphometric results that are very highly correlated with what one would have obtained with high-resolution T1 scans. SynthSR allows sample sizes that have the potential to overcome the power limitations of prospective research studies and shed new light on the healthy and diseased human brain.

PET image enhancement using artificial intelligence for better characterization of epilepsy lesions

INTRODUCTION

[18F]fluorodeoxyglucose ([18F]FDG) brain PET is used clinically to detect small areas of decreased uptake associated with epileptogenic lesions, e.g., Focal Cortical Dysplasias (FCD) but its performance is limited due to spatial resolution and low contrast. We aimed to develop a deep learning-based PET image enhancement method using simulated PET to improve lesion visualization.

METHODS

We created 210 numerical brain phantoms (MRI segmented into 9 regions) and assigned 10 different plausible activity values (e.g., GM/WM ratios) resulting in 2100 ground truth high quality (GT-HQ) PET phantoms. With a validated Monte-Carlo PET simulator, we then created 2100 simulated standard quality (S-SQ) [18F]FDG scans. We trained a ResNet on 80% of this dataset (10% used for validation) to learn the mapping between S-SQ and GT-HQ PET, outputting a predicted HQ (P-HQ) PET. For the remaining 10%, we assessed Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Root Mean Squared Error (RMSE) against GT-HQ PET. For GM and WM, we computed recovery coefficients (RC) and coefficient of variation (COV). We also created lesioned GT-HQ phantoms, S-SQ PET and P-HQ PET with simulated small hypometabolic lesions characteristic of FCDs. We evaluated lesion detectability on S-SQ and P-HQ PET both visually and measuring the Relative Lesion Activity (RLA, measured activity in the reduced-activity ROI over the standard-activity ROI). Lastly, we applied our previously trained ResNet on 10 clinical epilepsy PETs to predict the corresponding HQ-PET and assessed image quality and confidence metrics.

RESULTS

Compared to S-SQ PET, P-HQ PET improved PNSR, SSIM and RMSE; significatively improved GM RCs (from 0.29 ± 0.03 to 0.79 ± 0.04) and WM RCs (from 0.49 ± 0.03 to 1 ± 0.05); mean COVs were not statistically different. Visual lesion detection improved from 38 to 75%, with average RLA decreasing from 0.83 ± 0.08 to 0.67 ± 0.14. Visual quality of P-HQ clinical PET improved as well as reader confidence.

CONCLUSION

P-HQ PET showed improved image quality compared to S-SQ PET across several objective quantitative metrics and increased detectability of simulated lesions. In addition, the model generalized to clinical data. Further evaluation is required to study generalization of our method and to assess clinical performance in larger cohorts.

Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

Applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging: A review

PURPOSE

This paper reviews recent applications of Generative Adversarial Networks (GANs) in Positron Emission Tomography (PET) imaging. Recent advances in Deep Learning (DL) and GANs catalysed the research of their applications in medical imaging modalities. As a result, several unique GAN topologies have emerged and been assessed in an experimental environment over the last two years.

METHODS

The present work extensively describes GAN architectures and their applications in PET imaging. The identification of relevant publications was performed via approved publication indexing websites and repositories. Web of Science, Scopus, and Google Scholar were the major sources of information.

RESULTS

The research identified a hundred articles that address PET imaging applications such as attenuation correction, de-noising, scatter correction, removal of artefacts, image fusion, high-dose image estimation, super-resolution, segmentation, and cross-modality synthesis. These applications are presented and accompanied by the corresponding research works.

CONCLUSION

GANs are rapidly employed in PET imaging tasks. However, specific limitations must be eliminated to reach their full potential and gain the medical community's trust in everyday clinical practice.

Generative Adversarial Networks in Brain Imaging: A Narrative Review

Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.

Deep learning-based image reconstruction and post-processing methods in positron emission tomography for low-dose imaging and resolution enhancement

Image processing plays a crucial role in maximising diagnostic quality of positron emission tomography (PET) images. Recently, deep learning methods developed across many fields have shown tremendous potential when applied to medical image enhancement, resulting in a rich and rapidly advancing literature surrounding this subject. This review encapsulates methods for integrating deep learning into PET image reconstruction and post-processing for low-dose imaging and resolution enhancement. A brief introduction to conventional image processing techniques in PET is firstly presented. We then review methods which integrate deep learning into the image reconstruction framework as either deep learning-based regularisation or as a fully data-driven mapping from measured signal to images. Deep learning-based post-processing methods for low-dose imaging, temporal resolution enhancement and spatial resolution enhancement are also reviewed. Finally, the challenges associated with applying deep learning to enhance PET images in the clinical setting are discussed and future research directions to address these challenges are presented.

Systematic Review of Generative Adversarial Networks (GANs) for Medical Image Classification and Segmentation

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging-related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations.

PET/MR Technology: Advancement and Challenges

When this article was written, it coincided with the 11th anniversary of the installation of our PET/MR device in Munich. In fact, this was the first fully integrated device to be in clinical use. During this time, we have observed many interesting behaviors, to put it kindly. However, it is more critical that in this process, our understanding of the system also improved - including the advantages and limitations from a technical, logistical, and medical perspective. The last decade of PET/MRI research has certainly been characterized by most sites looking for a "key application." There were many ideas in this context and before and after the devices became available, some of which were based on the earlier work with integrating data from single devices. These involved validating classical PET methods with MRI (eg, perfusion or oncology diagnostics). More important, however, were the scenarios where intermodal synergies could be expected. In this review, we look back on this decade-long journey, at the challenges overcome and those still to come.

Noise2Void: unsupervised denoising of PET images

Objective:Elevated noise levels in positron emission tomography (PET) images lower image quality and quantitative accuracy and are a confounding factor for clinical interpretation. The objective of this paper is to develop a PET image denoising technique based on unsupervised deep learning.Significance:Recent advances in deep learning have ushered in a wide array of novel denoising techniques, several of which have been successfully adapted for PET image reconstruction and post-processing. The bulk of the deep learning research so far has focused on supervised learning schemes, which, for the image denoising problem, require paired noisy and noiseless/low-noise images. This requirement tends to limit the utility of these methods for medical applications as paired training datasets are not always available. Furthermore, to achieve the best-case performance of these methods, it is essential that the datasets for training and subsequent real-world application have consistent image characteristics (e.g. noise, resolution, etc), which is rarely the case for clinical data. To circumvent these challenges, it is critical to develop unsupervised techniques that obviate the need for paired training data.Approach:In this paper, we have adapted Noise2Void, a technique that relies on corrupt images alone for model training, for PET image denoising and assessed its performance using PET neuroimaging data. Noise2Void is an unsupervised approach that uses a blind-spot network design. It requires only a single noisy image as its input, and, therefore, is well-suited for clinical settings. During the training phase, a single noisy PET image serves as both the input and the target. Here we present a modified version of Noise2Void based on a transfer learning paradigm that involves group-level pretraining followed by individual fine-tuning. Furthermore, we investigate the impact of incorporating an anatomical image as a second input to the network.Main Results:We validated our denoising technique using simulation data based on the BrainWeb digital phantom. We show that Noise2Void with pretraining and/or anatomical guidance leads to higher peak signal-to-noise ratios than traditional denoising schemes such as Gaussian filtering, anatomically guided non-local means filtering, and block-matching and 4D filtering. We used the Noise2Noise denoising technique as an additional benchmark. For clinical validation, we applied this method to human brain imaging datasets. The clinical findings were consistent with the simulation results confirming the translational value of Noise2Void as a denoising tool.

Self-supervised CT super-resolution with hybrid model

Software-based methods can improve CT spatial resolution without changing the hardware of the scanner or increasing the radiation dose to the object. In this work, we aim to develop a deep learning (DL) based CT super-resolution (SR) method that can reconstruct low-resolution (LR) sinograms into high-resolution (HR) CT images. We mathematically analyzed imaging processes in the CT SR imaging problem and synergistically integrated the SR model in the sinogram domain and the deblur model in the image domain into a hybrid model (SADIR). SADIR incorporates the CT domain knowledge and is unrolled into a DL network (SADIR-Net). The SADIR-Net is a self-supervised network, which can be trained and tested with a single sinogram. SADIR-Net was evaluated through SR CT imaging of a Catphan700 physical phantom and a real porcine phantom, and its performance was compared to the other state-of-the-art (SotA) DL-based CT SR methods. On both phantoms, SADIR-Net obtains the highest information fidelity criterion (IFC), structure similarity index (SSIM), and lowest root-mean-square-error (RMSE). As to the modulation transfer function (MTF), SADIR-Net also obtains the best result and improves the MTF50% by 69.2% and MTF10% by 69.5% compared with FBP. Alternatively, the spatial resolutions at MTF50% and MTF10% from SADIR-Net can reach 91.3% and 89.3% of the counterparts reconstructed from the HR sinogram with FBP. The results show that SADIR-Net can provide performance comparable to the other SotA methods for CT SR reconstruction, especially in the case of extremely limited training data or even no data at all. Thus, the SADIR method could find use in improving CT resolution without changing the hardware of the scanner or increasing the radiation dose to the object.

Recycling diagnostic MRI for empowering brain morphometric research - Critical & practical assessment on learning-based image super-resolution

Preliminary studies have shown the feasibility of deep learning (DL)-based super-resolution (SR) technique for reconstructing thick-slice/gap diagnostic MR images into high-resolution isotropic data, which would be of great significance for brain research field if the vast amount of diagnostic MRI data could be successively put into brain morphometric study. However, less evidence has addressed the practicability of the strategy, because lack of a large-sample available real data for constructing DL model. In this work, we employed a large cohort (n = 2052) of peculiar data with both low through-plane resolution diagnostic and high-resolution isotropic brain MR images from identical subjects. By leveraging a series of SR approaches, including a proposed novel DL algorithm of Structure Constrained Super Resolution Network (SCSRN), the diagnostic images were transformed to high-resolution isotropic data to meet the criteria of brain research in voxel-based and surface-based morphometric analyses. We comprehensively assessed image quality and the practicability of the reconstructed data in a variety of morphometric analysis scenarios. We further compared the performance of SR approaches to the ground truth high-resolution isotropic data. The results showed (i) DL-based SR algorithms generally improve the quality of diagnostic images and render morphometric analysis more accurate, especially, with the most superior performance of the novel approach of SCSRN. (ii) Accuracies vary across brain structures and methods, and (iii) performance increases were higher for voxel than for surface based approaches. This study supports that DL-based image super-resolution potentially recycle huge amount of routine diagnostic brain MRI deposited in sleeping state, and turning them into useful data for neurometric research.

Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement

High noise and low spatial resolution are two key confounding factors that limit the qualitative and quantitative accuracy of PET images. Artificial intelligence models for image denoising and deblurring are becoming increasingly popular for the postreconstruction enhancement of PET images. We present a detailed review of recent efforts for artificial intelligence-based PET image enhancement with a focus on network architectures, data types, loss functions, and evaluation metrics. We also highlight emerging areas in this field that are quickly gaining popularity, identify barriers to large-scale adoption of artificial intelligence models for PET image enhancement, and discuss future directions.

Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast

Most existing algorithms for automatic 3D morphometry of human brain MRI scans are designed for data with near-isotropic voxels at approximately 1 mm resolution, and frequently have contrast constraints as well-typically requiring T1-weighted images (e.g., MP-RAGE scans). This limitation prevents the analysis of millions of MRI scans acquired with large inter-slice spacing in clinical settings every year. In turn, the inability to quantitatively analyze these scans hinders the adoption of quantitative neuro imaging in healthcare, and also precludes research studies that could attain huge sample sizes and hence greatly improve our understanding of the human brain. Recent advances in convolutional neural networks (CNNs) are producing outstanding results in super-resolution and contrast synthesis of MRI. However, these approaches are very sensitive to the specific combination of contrast, resolution and orientation of the input images, and thus do not generalize to diverse clinical acquisition protocols - even within sites. In this article, we present SynthSR, a method to train a CNN that receives one or more scans with spaced slices, acquired with different contrast, resolution and orientation, and produces an isotropic scan of canonical contrast (typically a 1 mm MP-RAGE). The presented method does not require any preprocessing, beyond rigid coregistration of the input scans. Crucially, SynthSR trains on synthetic input images generated from 3D segmentations, and can thus be used to train CNNs for any combination of contrasts, resolutions and orientations without high-resolution real images of the input contrasts. We test the images generated with SynthSR in an array of common downstream analyses, and show that they can be reliably used for subcortical segmentation and volumetry, image registration (e.g., for tensor-based morphometry), and, if some image quality requirements are met, even cortical thickness morphometry. The source code is publicly available at https://github.com/BBillot/SynthSR.

A review of medical image data augmentation techniques for deep learning applications

Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.

Applications of artificial intelligence in nuclear medicine image generation

Recently, the application of artificial intelligence (AI) in medical imaging (including nuclear medicine imaging) has rapidly developed. Most AI applications in nuclear medicine imaging have focused on the diagnosis, treatment monitoring, and correlation analyses with pathology or specific gene mutation. It can also be used for image generation to shorten the time of image acquisition, reduce the dose of injected tracer, and enhance image quality. This work provides an overview of the application of AI in image generation for single-photon emission computed tomography (SPECT) and positron emission tomography (PET) either without or with anatomical information [CT or magnetic resonance imaging (MRI)]. This review focused on four aspects, including imaging physics, image reconstruction, image postprocessing, and internal dosimetry. AI application in generating attenuation map, estimating scatter events, boosting image quality, and predicting internal dose map is summarized and discussed.

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT

In daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

Quantitative Molecular Positron Emission Tomography Imaging Using Advanced Deep Learning Techniques

The widespread availability of high-performance computing and the popularity of artificial intelligence (AI) with machine learning and deep learning (ML/DL) algorithms at the helm have stimulated the development of many applications involving the use of AI-based techniques in molecular imaging research. Applications reported in the literature encompass various areas, including innovative design concepts in positron emission tomography (PET) instrumentation, quantitative image reconstruction and analysis techniques, computer-aided detection and diagnosis, as well as modeling and prediction of outcomes. This review reflects the tremendous interest in quantitative molecular imaging using ML/DL techniques during the past decade, ranging from the basic principles of ML/DL techniques to the various steps required for obtaining quantitatively accurate PET data, including algorithms used to denoise or correct for physical degrading factors as well as to quantify tracer uptake and metabolic tumor volume for treatment monitoring or radiation therapy treatment planning and response prediction.This review also addresses future opportunities and current challenges facing the adoption of ML/DL approaches and their role in multimodality imaging.

Quantitative PET in the 2020s: a roadmap

Positron emission tomography (PET) plays an increasingly important role in research and clinical applications, catalysed by remarkable technical advances and a growing appreciation of the need for reliable, sensitive biomarkers of human function in health and disease. Over the last 30 years, a large amount of the physics and engineering effort in PET has been motivated by the dominant clinical application during that period, oncology. This has led to important developments such as PET/CT, whole-body PET, 3D PET, accelerated statistical image reconstruction, and time-of-flight PET. Despite impressive improvements in image quality as a result of these advances, the emphasis on static, semi-quantitative 'hot spot' imaging for oncologic applications has meant that the capability of PET to quantify biologically relevant parameters based on tracer kinetics has not been fully exploited. More recent advances, such as PET/MR and total-body PET, have opened up the ability to address a vast range of new research questions, from which a future expansion of applications and radiotracers appears highly likely. Many of these new applications and tracers will, at least initially, require quantitative analyses that more fully exploit the exquisite sensitivity of PET and the tracer principle on which it is based. It is also expected that they will require more sophisticated quantitative analysis methods than those that are currently available. At the same time, artificial intelligence is revolutionizing data analysis and impacting the relationship between the statistical quality of the acquired data and the information we can extract from the data. In this roadmap, leaders of the key sub-disciplines of the field identify the challenges and opportunities to be addressed over the next ten years that will enable PET to realise its full quantitative potential, initially in research laboratories and, ultimately, in clinical practice.

Application and Construction of Deep Learning Networks in Medical Imaging

Deep learning (DL) approaches are part of the machine learning (ML) subfield concerned with the development of computational models to train artificial intelligence systems. DL models are characterized by automatically extracting high-level features from the input data to learn the relationship between matching datasets. Thus, its implementation offers an advantage over common ML methods that often require the practitioner to have some domain knowledge of the input data to select the best latent representation. As a result of this advantage, DL has been successfully applied within the medical imaging field to address problems, such as disease classification and tumor segmentation for which it is difficult or impossible to determine which image features are relevant. Therefore, taking into consideration the positive impact of DL on the medical imaging field, this article reviews the key concepts associated with its evolution and implementation. The sections of this review summarize the milestones related to the development of the DL field, followed by a description of the elements of deep neural network and an overview of its application within the medical imaging field. Subsequently, the key steps necessary to implement a supervised DL application are defined, and associated limitations are discussed.

Deep learning for brain disorders: from data processing to disease treatment

In order to reach precision medicine and improve patients' quality of life, machine learning is increasingly used in medicine. Brain disorders are often complex and heterogeneous, and several modalities such as demographic, clinical, imaging, genetics and environmental data have been studied to improve their understanding. Deep learning, a subpart of machine learning, provides complex algorithms that can learn from such various data. It has become state of the art in numerous fields, including computer vision and natural language processing, and is also growingly applied in medicine. In this article, we review the use of deep learning for brain disorders. More specifically, we identify the main applications, the concerned disorders and the types of architectures and data used. Finally, we provide guidelines to bridge the gap between research studies and clinical routine.

Deconvolutional neural network for image super-resolution

This study builds a fully deconvolutional neural network (FDNN) and addresses the problem of single image super-resolution (SISR) by using the FDNN. Although SISR using deep neural networks has been a major research focus, the problem of reconstructing a high resolution (HR) image with an FDNN has received little attention. A few recent approaches toward SISR are to embed deconvolution operations into multilayer feedforward neural networks. This paper constructs a deep FDNN for SISR that possesses two remarkable advantages compared to existing SISR approaches. The first improves the network performance without increasing the depth of the network or embedding complex structures. The second replaces all convolution operations with deconvolution operations to implement an effective reconstruction. That is, the proposed FDNN only contains deconvolution layers and learns an end-to-end mapping from low resolution (LR) to HR images. Furthermore, to avoid the oversmoothness of the mean squared error loss, the trained image is treated as a probability distribution, and the Kullback-Leibler divergence is introduced into the final loss function to achieve enhanced recovery. Although the proposed FDNN only has 10 layers, it is successfully evaluated through extensive experiments. Compared with other state-of-the-art methods and deep convolution neural networks with 20 or 30 layers, the proposed FDNN achieves better performance for SISR.