Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising

Deep learning-based multi-frequency denoising for myocardial perfusion SPECT

BACKGROUND

Deep learning (DL)-based denoising has been proven to improve image quality and quantitation accuracy of low dose (LD) SPECT. However, conventional DL-based methods used SPECT images with mixed frequency components. This work aims to develop an integrated multi-frequency denoising network to further enhance LD myocardial perfusion (MP) SPECT denoising.

METHODS

Fifty anonymized patients who underwent routine 99mTc-sestamibi stress SPECT/CT scans were retrospectively recruited. Three LD datasets were obtained by reducing the 10 s acquisition time of full dose (FD) SPECT to be 5, 2 and 1 s per projection based on the list mode data for a total of 60 projections. FD and LD projections were Fourier transformed to magnitude and phase images, which were then separated into two or three frequency bands. Each frequency band was then inversed Fourier transformed back to the image domain. We proposed a 3D integrated attention-guided multi-frequency conditional generative adversarial network (AttMFGAN) and compared with AttGAN, and separate AttGAN for multi-frequency bands denoising (AttGAN-MF).The multi-frequency FD and LD projections of 35, 5 and 10 patients were paired for training, validation and testing. The LD projections to be tested were separated to multi-frequency components and input to corresponding networks to get the denoised components, which were summed to get the final denoised projections. Voxel-based error indices were measured on the cardiac region on the reconstructed images. The perfusion defect size (PDS) was also analyzed.

RESULTS

AttGAN-MF and AttMFGAN have superior performance on all physical and clinical indices as compared to conventional AttGAN. The integrated AttMFGAN is better than AttGAN-MF. Multi-frequency denoising with two frequency bands have generally better results than corresponding three-frequency bands methods.

CONCLUSIONS

AttGAN-MF and AttMFGAN are promising to further improve LD MP SPECT denoising.

Deep generative denoising networks enhance quality and accuracy of gated cardiac PET data

BACKGROUND

Cardiac positron emission tomography (PET) can visualize and quantify the molecular and physiological pathways of cardiac function. However, cardiac and respiratory motion can introduce blurring that reduces PET image quality and quantitative accuracy. Dual cardiac- and respiratory-gated PET reconstruction can mitigate motion artifacts but increases noise as only a subset of data are used for each time frame of the cardiac cycle.

AIM

The objective of this study is to create a zero-shot image denoising framework using a conditional generative adversarial networks (cGANs) for improving image quality and quantitative accuracy in non-gated and dual-gated cardiac PET images.

METHODS

Our study included retrospective list-mode data from 40 patients who underwent an 18F-fluorodeoxyglucose (18F-FDG) cardiac PET study. We initially trained and evaluated a 3D cGAN-known as Pix2Pix-on simulated non-gated low-count PET data paired with corresponding full-count target data, and then deployed the model on an unseen test set acquired on the same PET/CT system including both non-gated and dual-gated PET data.

RESULTS

Quantitative analysis demonstrated that the 3D Pix2Pix network architecture achieved significantly (p value<0.05) enhanced image quality and accuracy in both non-gated and gated cardiac PET images. At 5%, 10%, and 15% preserved count statistics, the model increased peak signal-to-noise ratio (PSNR) by 33.7%, 21.2%, and 15.5%, structural similarity index (SSIM) by 7.1%, 3.3%, and 2.2%, and reduced mean absolute error (MAE) by 61.4%, 54.3%, and 49.7%, respectively. When tested on dual-gated PET data, the model consistently reduced noise, irrespective of cardiac/respiratory motion phases, while maintaining image resolution and accuracy. Significant improvements were observed across all gates, including a 34.7% increase in PSNR, a 7.8% improvement in SSIM, and a 60.3% reduction in MAE.

CONCLUSION

The findings of this study indicate that dual-gated cardiac PET images, which often have post-reconstruction artifacts potentially affecting diagnostic performance, can be effectively improved using a generative pre-trained denoising network.

Full-dose whole-body PET synthesis from low-dose PET using high-efficiency denoising diffusion probabilistic model: PET consistency model

PURPOSE

Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients.

METHODS

We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Evaluation with normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), multi-scale structure similarity index (SSIM), normalized cross-correlation (NCC), and clinical evaluation including Human Ranking Score (HRS) and Standardized Uptake Value (SUV) Error analysis shows its superiority in synthesizing full-dose PET images from low-dose inputs.

RESULTS

In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278 ± 0.122%, PSNR of 33.783 ± 0.824 dB, SSIM of 0.964 ± 0.009, NCC of 0.968 ± 0.011, HRS of 4.543, and SUV Error of 0.255 ± 0.318%, with an average generation time of 62 s per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12× faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973 ± 0.066%, PSNR of 36.172 ± 0.801 dB, SSIM of 0.984 ± 0.004, NCC of 0.990 ± 0.005, HRS of 4.428, and SUV Error of 0.151 ± 0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario.

CONCLUSIONS

We propose PET-CM, the first efficient diffusion-model-based method, for estimating full-dose PET images from low-dose images. PET-CM provides comparable quality to the state-of-the-art diffusion model with higher efficiency. By utilizing this approach, it becomes possible to maintain high-quality PET images suitable for clinical use while mitigating the risks associated with radiation. The code is availble at https://github.com/shaoyanpan/Full-dose-Whole-body-PET-Synthesis-from-Low-dose-PET-Using-Consistency-Model.

TAI-GAN: A Temporally and Anatomically Informed Generative Adversarial Network for early-to-late frame conversion in dynamic cardiac PET inter-frame motion correction

Inter-frame motion in dynamic cardiac positron emission tomography (PET) using rubidium-82 (82Rb) myocardial perfusion imaging impacts myocardial blood flow (MBF) quantification and the diagnosis accuracy of coronary artery diseases. However, the high cross-frame distribution variation due to rapid tracer kinetics poses a considerable challenge for inter-frame motion correction, especially for early frames where intensity-based image registration techniques often fail. To address this issue, we propose a novel method called Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) that utilizes an all-to-one mapping to convert early frames into those with tracer distribution similar to the last reference frame. The TAI-GAN consists of a feature-wise linear modulation layer that encodes channel-wise parameters generated from temporal information and rough cardiac segmentation masks with local shifts that serve as anatomical information. Our proposed method was evaluated on a clinical 82Rb PET dataset, and the results show that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, the motion estimation accuracy and subsequent myocardial blood flow (MBF) quantification with both conventional and deep learning-based motion correction methods were improved compared to using the original frames. The code is available at https://github.com/gxq1998/TAI-GAN.

Application of convolutional neural networks in medical images: a bibliometric analysis

Background

In the field of medical imaging, the rapid rise of convolutional neural networks (CNNs) has presented significant opportunities for conserving healthcare resources. However, with the wide spread application of CNNs, several challenges have emerged, such as enormous data annotation costs, difficulties in ensuring user privacy and security, weak model interpretability, and the consumption of substantial computational resources. The fundamental challenge lies in optimizing and seamlessly integrating CNN technology to enhance the precision and efficiency of medical diagnosis.

Methods

This study sought to provide a comprehensive bibliometric overview of current research on the application of CNNs in medical imaging. Initially, bibliometric methods were used to calculate the frequency statistics, and perform the cluster analysis and the co-citation analysis of countries, institutions, authors, keywords, and references. Subsequently, the latent Dirichlet allocation (LDA) method was employed for the topic modeling of the literature. Next, an in-depth analysis of the topics was conducted, and the topics in the medical field, technical aspects, and trends in topic evolution were summarized. Finally, by integrating the bibliometrics and LDA results, the developmental trajectory, milestones, and future directions in this field were outlined.

Results

A data set containing 6,310 articles in this field published from January 2013 to December 2023 was complied. With a total of 55,538 articles, the United States led in terms of the citation count, while in terms of the publication volume, China led with 2,385 articles. Harvard University emerged as the most influential institution, boasting an average of 69.92 citations per article. Within the realm of CNNs, residual neural network (ResNet) and U-Net stood out, receiving 1,602 and 1,419 citations, respectively, which highlights the significant attention these models have received. The impact of coronavirus disease 2019 (COVID-19) was unmistakable, as reflected by the publication of 597 articles, making it a focal point of research. Additionally, among various disease topics, with 290 articles, brain-related research was the most prevalent. Computed tomography (CT) imaging dominated the research landscape, representing 73% of the 30 different topics.

Conclusions

Over the past 11 years, CNN-related research in medical imaging has grown exponentially. The findings of the present study provide insights into the field's status and research hotspots. In addition, this article meticulously chronicled the development of CNNs and highlighted key milestones, starting with LeNet in 1989, followed by a challenging 20-year exploration period, and culminating in the breakthrough moment with AlexNet in 2012. Finally, this article explored recent advancements in CNN technology, including semi-supervised learning, efficient learning, trustworthy artificial intelligence (AI), and federated learning methods, and also addressed challenges related to data annotation costs, diagnostic efficiency, model performance, and data privacy.

A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches

Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.

DEMIST: A Deep-Learning-Based Detection-Task-Specific Denoising Approach for Myocardial Perfusion SPECT

There is an important need for methods to process myocardial perfusion imaging (MPI) single-photon emission computed tomography (SPECT) images acquired at lower-radiation dose and/or acquisition time such that the processed images improve observer performance on the clinical task of detecting perfusion defects compared to low-dose images. To address this need, we build upon concepts from model-observer theory and our understanding of the human visual system to propose a detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST). The approach, while performing denoising, is designed to preserve features that influence observer performance on detection tasks. We objectively evaluated DEMIST on the task of detecting perfusion defects using a retrospective study with anonymized clinical data in patients who underwent MPI studies across two scanners (N = 338). The evaluation was performed at low-dose levels of 6.25%, 12.5%, and 25% and using an anthropomorphic channelized Hotelling observer. Performance was quantified using area under the receiver operating characteristics curve (AUC). Images denoised with DEMIST yielded significantly higher AUC compared to corresponding low-dose images and images denoised with a commonly used task-agnostic deep learning-based denoising method. Similar results were observed with stratified analysis based on patient sex and defect type. Additionally, DEMIST improved visual fidelity of the low-dose images as quantified using root mean squared error and structural similarity index metric. A mathematical analysis revealed that DEMIST preserved features that assist in detection tasks while improving the noise properties, resulting in improved observer performance. The results provide strong evidence for further clinical evaluation of DEMIST to denoise low-count images in MPI SPECT.

A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches

Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.

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.

Med-cDiff: Conditional Medical Image Generation with Diffusion Models

Conditional image generation plays a vital role in medical image analysis as it is effective in tasks such as super-resolution, denoising, and inpainting, among others. Diffusion models have been shown to perform at a state-of-the-art level in natural image generation, but they have not been thoroughly studied in medical image generation with specific conditions. Moreover, current medical image generation models have their own problems, limiting their usage in various medical image generation tasks. In this paper, we introduce the use of conditional Denoising Diffusion Probabilistic Models (cDDPMs) for medical image generation, which achieve state-of-the-art performance on several medical image generation tasks.

Dynamic controllable residual generative adversarial network for low-dose computed tomography imaging

Background

Computed tomography (CT) imaging technology has become an indispensable auxiliary method in medical diagnosis and treatment. In mitigating the radiation damage caused by X-rays, low-dose computed tomography (LDCT) scanning is becoming more widely applied. However, LDCT scanning reduces the signal-to-noise ratio of the projection, and the resulting images suffer from serious streak artifacts and spot noise. In particular, the intensity of noise and artifacts varies significantly across different body parts under a single low-dose protocol.

Methods

To improve the quality of different degraded LDCT images in a unified framework, we developed a generative adversarial learning framework with a dynamic controllable residual. First, the generator network consists of the basic subnetwork and the conditional subnetwork. Inspired by the dynamic control strategy, we designed the basic subnetwork to adopt a residual architecture, with the conditional subnetwork providing weights to control the residual intensity. Second, we chose the Visual Geometry Group Network-128 (VGG-128) as the discriminator to improve the noise artifact suppression and feature retention ability of the generator. Additionally, a hybrid loss function was specifically designed, including the mean square error (MSE) loss, structural similarity index metric (SSIM) loss, adversarial loss, and gradient penalty (GP) loss.

Results

The results obtained on two datasets show the competitive performance of the proposed framework, with a 3.22 dB peak signal-to-noise ratio (PSNR) margin, 0.03 SSIM margin, and 0.2 contrast-to-noise ratio margin on the Challenge data and a 1.0 dB PSNR margin and 0.01 SSIM margin on the real data.

Conclusions

Experimental results demonstrated the competitive performance of the proposed method in terms of noise decrease, structural retention, and visual impression improvement.

Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT

BACKGROUND

Low-dose (LD) myocardial perfusion (MP) SPECT suffers from high noise level, leading to compromised diagnostic accuracy. Here we investigated the denoising performance for MP-SPECT using a conditional generative adversarial network (cGAN) in projection-domain (cGAN-prj) and reconstruction-domain (cGAN-recon).

METHODS

Sixty-four noisy SPECT projections were simulated for a population of 100 XCAT phantoms with different anatomical variations and 99mTc-sestamibi distributions. Series of LD projections were obtained by scaling the full dose (FD) count rate to be 1/20 to 1/2 of the original. Twenty patients with 99mTc-sestamibi stress SPECT/CT scans were retrospectively analyzed. For each patient, LD SPECT images (7/10 to 1/10 of FD) were generated from the FD list mode data. All projections were reconstructed by the quantitative OS-EM method. A 3D cGAN was implemented to predict FD images from their corresponding LD images in the projection- and reconstruction-domain. The denoised projections were reconstructed for analysis in various quantitative indices along with cGAN-recon, Gaussian, and Butterworth-filtered images.

RESULTS

cGAN denoising improves image quality as compared to LD and conventional post-reconstruction filtering. cGAN-prj can further reduce the dose level as compared to cGAN-recon without compromising the image quality.

CONCLUSIONS

Denoising based on cGAN-prj is superior to cGAN-recon for MP-SPECT.

Deep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion SPECT

BACKGROUND

Deep learning (DL)-based attenuation correction (AC) is promising to improve myocardial perfusion (MP) SPECT. We aimed to optimize and compare the DL-based direct and indirect AC methods, with and without SPECT and CT mismatch.

METHODS

One hundred patients with different 99mTc-sestamibi activity distributions and anatomical variations were simulated by a population of XCAT phantoms. Additionally, 34 patients 99mTc-sestamibi stress/rest SPECT/CT scans were retrospectively recruited. Projections were reconstructed by OS-EM method with or without AC. Mismatch between SPECT and CT images was modeled. A 3D conditional generative adversarial network (cGAN) was optimized for two DL-based AC methods: (i) indirect approach, i.e., non-attenuation corrected (NAC) SPECT paired with the corresponding attenuation map for training. The projections were reconstructed with the DL-generated attenuation map for AC; (ii) direct approach, i.e., NAC SPECT paired with the corresponding AC SPECT for training to perform direct AC.

RESULTS

Mismatch between SPECT and CT degraded DL-based AC performance. The indirect approach is superior to direct approach for various physical and clinical indices, even with mismatch modeled.

CONCLUSION

DL-based estimation of attenuation map for AC is superior and more robust to direct generation of AC SPECT.

Personalization of 99mTc-sestamibi activity in SPECT/CT myocardial perfusion imaging with the cardiofocal SmartZoom® collimator

BACKGROUND

Patient radioprotection in myocardial perfusion imaging (MPI)-SPECT is important but difficult to optimize. The aim of this study was to adjust injected activity according to patient size-weight or BMI-by using a cardiofocal collimator camera.

METHODS

The correlation equation between size and observed counts in image was determined in patients who underwent stress Tc-99m-sestamibi MPI-SPECT/CT with a cardiofocal collimator-equipped conventional Anger SPECT/CT system. Image quality analyses by seven nuclear physicians were conducted to determine the minimum patient size-independent observed count threshold that yielded sufficient image quality for perfusion-defect diagnosis. These data generated an equation that can be used to calculate personalized activity for patients according to their size.

RESULTS

Analysis of consecutive patients (n = 294) showed that weight correlated with observed counts better than body mass index. The correlation equation was used to generate the equation that expressed the relationship between observed counts, patient weight, and injected activity. Image quality analysis with 50 images yielded an observed count threshold of 22,000 counts. Using this threshold means that the injected activity in patients with < 100 kg would be reduced (e.g., by 67% in 45-kg patients). Patients who are heavier than 100 kg would also benefit from the use of the threshold because although the injected activity would be higher (up to 78% for 150-kg patients), good image quality would be obtained.

CONCLUSIONS

This study provided a method for determining the optimal injected activity according to patient weight without compromising the image quality of conventional Anger SPECT/CT systems equipped with a cardiofocal collimator. Personalized injected activities for each patient weight ranging from 45 to 150 kg were generated, to standardize the resulting image quality independently of patient attenuation. This approach improves patient/staff radioprotection because it reduces the injected activity for < 100-kg patients (the majority of patients).

Fast myocardial perfusion SPECT denoising using an attention-guided generative adversarial network

Purpose

Deep learning-based denoising is promising for myocardial perfusion (MP) SPECT. However, conventional convolutional neural network (CNN)-based methods use fixed-sized convolutional kernels to convolute one region within the receptive field at a time, which would be ineffective for learning the feature dependencies across large regions. The attention mechanism (Att) is able to learn the relationships between the local receptive field and other voxels in the image. In this study, we propose a 3D attention-guided generative adversarial network (AttGAN) for denoising fast MP-SPECT images.

Methods

Fifty patients who underwent 1184 MBq ^99mTc-sestamibi stress SPECT/CT scan were retrospectively recruited. Sixty projections were acquired over 180° and the acquisition time was 10 s/view for the full time (FT) mode. Fast MP-SPECT projection images (1 s to 7 s) were generated from the FT list mode data. We further incorporated binary patient defect information (0 = without defect, 1 = with defect) into AttGAN (AttGAN-def). AttGAN, AttGAN-def, cGAN, and Unet were implemented using Tensorflow with the Adam optimizer running up to 400 epochs. FT and fast MP-SPECT projection pairs of 35 patients were used for training the networks for each acquisition time, while 5 and 10 patients were applied for validation and testing. Five-fold cross-validation was performed and data for all 50 patients were tested. Voxel-based error indices, joint histogram, linear regression, and perfusion defect size (PDS) were analyzed.

Results

All quantitative indices of AttGAN-based networks are superior to cGAN and Unet on all acquisition time images. AttGAN-def further improves AttGAN performance. The mean absolute error of PDS by AttcGAN-def was 1.60 on acquisition time of 1 s/prj, as compared to 2.36, 2.76, and 3.02 by AttGAN, cGAN, and Unet.

Conclusion

Denoising based on AttGAN is superior to conventional CNN-based networks for MP-SPECT.

Towards Outdoor Electromagnetic Field Exposure Mapping Generation Using Conditional GANs

With the ongoing fifth-generation cellular network (5G) deployment, electromagnetic field exposure has become a critical concern. However, measurements are scarce, and accurate electromagnetic field reconstruction in a geographic region remains challenging. This work proposes a conditional generative adversarial network to address this issue. The main objective is to reconstruct the electromagnetic field exposure map accurately according to the environment's topology from a few sensors located in an outdoor urban environment. The model is trained to learn and estimate the propagation characteristics of the electromagnetic field according to the topology of a given environment. In addition, the conditional generative adversarial network-based electromagnetic field mapping is compared with simple kriging. Results show that the proposed method produces accurate estimates and is a promising solution for exposure map reconstruction.