Improving Diagnostic Accuracy in Low-Dose SPECT Myocardial Perfusion Imaging With Convolutional Denoising Networks

Poisson diffusion probabilistic model for low-dose SPECT sinogram denoising

BACKGROUND

Low-dose single photon emission computed tomography (SPECT) sinograms often suffer from noise due to photon attenuation during the imaging process. As a result, developing effective denoising methods for low-dose SPECT images has become an essential research topic. Traditional image denoising methods struggle to balance noise reduction with the preservation of important image details, especially in medical applications where accurate image structures are critical.

PURPOSE

This paper proposes a diffusion probabilistic model based on Poisson noise, named the Poisson diffusion probabilistic model (PDPM), for denoising low-dose SPECT sinograms. Considering the physical principles behind the formation of low-dose SPECT sinograms, PDPM replaces the Gaussian noise traditionally used in diffusion models with Poisson noise, utilizing low-dose and normal-dose SPECT sinograms as the starting and ending points of the denoising process, respectively.

METHODS

We present a preliminary framework for PDPM that encompasses both the forward and reverse processes. Subsequently, we refine this preliminary framework by implementing two improvements: discarding the forward process and generating the training dataset using a method based on the ideal reverse process, as well as introducing our proposed Temporal Prediction Aggregation Module (TPAM) into the reverse process to enhance the model's image denoising performance.

RESULTS

Experiments conducted on the simulated SPECT dataset demonstrate that PDPM effectively improves the quality of sinogram images. Specifically, the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the sinograms increased from 19.3156 to 35.3446 (p < 0.0001 $p<0.0001$ ) and from 0.7531 to 0.9791 (p < 0.0001 $p<0.0001$ ), respectively. For the reconstructed images from the sinograms, the PSNR and SSIM improved from 25.7511 to 35.1335 (p < 0.0001 $p<0.0001$ ) and from 0.9286 to 0.9817 (p < 0.0001 $p<0.0001$ ), respectively. The experiments show that PDPM outperforms competitive methods in the task of low-dose SPECT sinogram denoising, including one traditional denoising algorithm and four deep learning methods. Experiments on clinical SPECT datasets further indicate that our method effectively reduces the coefficient of variation (COV) in the regions of interest (ROI) of the reconstructed images, enhancing the quality of the reconstructed images by denoising the SPECT sinograms.

CONCLUSIONS

The proposed PDPM demonstrates promising performance in the denoising of low-dose SPECT sinograms. We presented a preliminary framework for PDPM and refined it to create the final version of PDPM, which is designed for the task of low-dose SPECT sinogram denoising. Our PDPM achieved favorable denoising results on both simulated and clinical datasets.

Deep learning-based approach for acquisition time reduction in ventilation SPECT in patients after lung transplantation

We aimed to evaluate the image quality and diagnostic performance of chronic lung allograft dysfunction (CLAD) with lung ventilation single-photon emission computed tomography (SPECT) images acquired briefly using a convolutional neural network (CNN) in patients after lung transplantation and to explore the feasibility of short acquisition times. We retrospectively identified 93 consecutive lung-transplant recipients who underwent ventilation SPECT/computed tomography (CT). We employed a CNN to distinguish the images acquired in full time from those acquired in a short time. The image quality was evaluated using the structural similarity index (SSIM) loss and normalized mean square error (NMSE). The correlation between functional volume/morphological volume (F/M) ratios of full-time SPECT images and predicted SPECT images was evaluated. Differences in the F/M ratio were evaluated using Bland-Altman plots, and the diagnostic performance was compared using the area under the curve (AUC). The learning curve, obtained using MSE, converged within 100 epochs. The NMSE was significantly lower (P < 0.001) and the SSIM was significantly higher (P < 0.001) for the CNN-predicted SPECT images compared to the short-time SPECT images. The F/M ratio of full-time SPECT images and predicted SPECT images showed a significant correlation (r = 0.955, P < 0.0001). The Bland-Altman plot revealed a bias of -7.90% in the F/M ratio. The AUC values were 0.942 for full-time SPECT images, 0.934 for predicted SPECT images and 0.872 for short-time SPECT images. Our findings suggest that a deep-learning-based approach can significantly curtail the acquisition time of ventilation SPECT, while preserving the image quality and diagnostic accuracy for CLAD.

Applications of Artificial Intelligence for the Prediction and Diagnosis of Cancer Therapy-Related Cardiac Dysfunction in Oncology Patients

Cardiovascular diseases and cancer are the leading causes of morbidity and mortality in modern society. Expanding cancer therapies that have improved prognosis may also be associated with cardiotoxicity, and extended life span after survivorship is associated with the increasing prevalence of cardiovascular disease. As such, the field of cardio-oncology has been rapidly expanding, with an aim to identify cardiotoxicity and cardiac disease early in a patient who is receiving treatment for cancer or is in survivorship. Artificial intelligence is revolutionizing modern medicine with its ability to identify cardiac disease early. This article comprehensively reviews applications of artificial intelligence specifically applied to electrocardiograms, echocardiography, cardiac magnetic resonance imaging, and nuclear imaging to predict cardiac toxicity in the setting of cancer therapies, with a view to reduce early complications and cardiac side effects from cancer therapies such as chemotherapy, radiation therapy, or immunotherapy.

Sinogram-characteristic-informed network for efficient restoration of low-dose SPECT projection data

BACKGROUND

Single Photon Emission Computed Tomography (SPECT) sinogram restoration for low-dose imaging is a critical challenge in medical imaging. Existing methods often overlook the characteristics of the sinograms, necessitating innovative approaches.

PURPOSE

In this study, we introduce the Sinogram-characteristic-informed network (SCI-Net) to address the restoration of low-dose SPECT sinograms. Our aim is to build and train a model based on the characteristics of sinograms, including continuity, periodicity, multi-scale properties of lines in sinograms, and others, to enhance the model's understanding of the restoration process.

METHODS

SCI-Net incorporates several novel mechanisms tailored to exploit the inherent characteristics of sinograms. We implement a channel attention module with a decay mechanism to leverage continuity across adjacent sinograms, while a position attention module captures global correlations within individual sinograms. Additionally, we propose a multi-stage progressive integration mechanism to balance local detail and overall structure. Multiple regularization terms, customized to sinogram image characteristics, are embedded into the loss function for model training.

RESULTS

The experimental evaluations are divided into two parts: simulation data evaluation and clinical evaluation. The simulation data evaluation is conducted on a dataset comprising ten organ types, generated by the SIMIND Monte Carlo program from extended cardiac-torso (XCAT) anatomical phantoms. The dataset includes a total of SPECT sinograms with low-dose as input data and normal-dose as ground truth, consisting of 3881 sinograms in the training dataset and 849 sinograms in the testing set. When comparing the restoration of low-dose sinograms to normal-dose references, SCI-Net effectively improves performance. Specifically, the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) on sinograms increase from 15.72 to 34.66 (p < $\text{p}< $ 0.001) and 0.6297 to 0.9834 (p < $\text{p}<$ 0.001), respectively, and on reconstructed images, reconstructed by maximum likelihood-expectation maximization (ML-EM), the PSNR and the SSIM improve from 21.95 to 33.14 (p < $\text{p}<$ 0.001) and 0.9084 to 0.9866 (p < $\text{p}<$ 0.001), respectively. We compared SCI-Net with existing methods, including baseline models, traditional reconstruction algorithms, end-to-end methods, sinogram restoration methods, and image post-processing methods. The experimental results and visual examples demonstrate that SCI-Net surpasses these existing methods in SPECT sinogram restoration. The clinical evaluation is conducted on clinical data of low-dose SPECT sinograms for spleen, thyroid, skull, and bone. These SPECT projection data are obtained from Discovery NM/CT670 scans. We compare the reconstructed images from the SCI-Net restored sinograms, the reconstructed images from the original low-dose sinograms, and the reconstructed images using the built-in algorithm of the Discovery NM/CT670. The results show that our method effectively reduces the coefficient of variation (COV) in the regions of interest (ROI) of the reconstructed images, thereby enhancing the quality of the reconstructed images through SPECT sinogram restoration.

CONCLUSIONS

Our proposed SCI-Net exhibits promising performance in the restoration of low-dose SPECT projection data. In the SCI-Net, we have implemented three mechanisms based on distinct forms, which are advantageous for the model to more effectively leverage the characteristics of sinograms and achieve commendable restoration outcomes.

Investigation of scatter energy window width and count levels for deep learning-based attenuation map estimation in cardiac SPECT/CT imaging

Objective.Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate attenuation correction (AC) in cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed SPECT images, which are performed on the photopeak window and often also on scatter windows. While prior studies have demonstrated improvements in DL performance when scatter window images are incorporated into the DL input, the comprehensive analysis of the impact of employing different scatter windows remains unassessed. Additionally, existing research mainly focuses on applying DL to SPECT scans obtained at clinical standard count levels. This study aimed to assess utilities of DL from two aspects: (1) investigating the impact when different scatter windows were used as input to DL, and (2) evaluating the performance of DL when applied on SPECT scans acquired at a reduced count level.Approach.We utilized 1517 subjects, with 386 subjects for testing and the remaining 1131 for training and validation.Main results.The results showed that as scatter window width increased from 4% to 30%, a slight improvement was observed in DL estimated attenuation maps. The application of DL models to quarter-count (¼-count) SPECT scans, compared to full-count scans, showed a slight reduction in performance. Nonetheless, discrepancies across different scatter window configurations and between count levels were minimal, with all normalized mean square error (NMSE) values remaining within 2.1% when comparing the different DL attenuation maps to the reference CT maps. For attenuation corrected SPECT slices using DL estimated maps, NMSE values were within 0.5% when compared to CT correction.Significance.This study, leveraging an extensive clinical dataset, showed that the performance of DL seemed to be consistent across the use of varied scatter window settings. Moreover, our investigation into reduced count studies indicated that DL could provide accurate AC even at a ¼-count level.

SPECT-MPI iterative denoising during the reconstruction process using a two-phase learned convolutional neural network

PURPOSE

The problem of image denoising in single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a fundamental challenge. Although various image processing techniques have been presented, they may degrade the contrast of denoised images. The proposed idea in this study is to use a deep neural network as the denoising procedure during the iterative reconstruction process rather than the post-reconstruction phase. This method could decrease the background coefficient of variation (COV_bkg) of the final reconstructed image, which represents the amount of random noise, while improving the contrast-to-noise ratio (CNR).

METHODS

In this study, a generative adversarial network is used, where its generator is trained by a two-phase approach. In the first phase, the network is trained by a confined image region around the heart in transverse view. The second phase improves the network's generalization by tuning the network weights with the full image size as the input. The network was trained and tested by a dataset of 247 patients who underwent two immediate serially high- and low-noise SPECT-MPI.

RESULTS

Quantitative results show that compared to post-reconstruction low pass filtering and post-reconstruction deep denoising methods, our proposed method can decline the COV_bkg of the images by up to 10.28% and 12.52% and enhance the CNR by up to 54.54% and 45.82%, respectively.

CONCLUSION

The iterative deep denoising method outperforms 2D low-pass Gaussian filtering with an 8.4-mm FWHM and post-reconstruction deep denoising approaches.

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.

DuDoCFNet: Dual-Domain Coarse-to-Fine Progressive Network for Simultaneous Denoising, Limited-View Reconstruction, and Attenuation Correction of Cardiac SPECT

Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as the latest GE MyoSPECT ES system, enables accelerated scanning and reduces hardware expenses but degrades reconstruction accuracy. Additionally, Computed Tomography (CT) is commonly used to derive attenuation maps ( μ -maps) for attenuation correction (AC) of cardiac SPECT, but it will introduce additional radiation exposure and SPECT-CT misalignments. Although various methods have been developed to solely focus on LD denoising, LV reconstruction, or CT-free AC in SPECT, the solution for simultaneously addressing these tasks remains challenging and under-explored. Furthermore, it is essential to explore the potential of fusing cross-domain and cross-modality information across these interrelated tasks to further enhance the accuracy of each task. Thus, we propose a Dual-Domain Coarse-to-Fine Progressive Network (DuDoCFNet), a multi-task learning method for simultaneous LD denoising, LV reconstruction, and CT-free μ -map generation of cardiac SPECT. Paired dual-domain networks in DuDoCFNet are cascaded using a multi-layer fusion mechanism for cross-domain and cross-modality feature fusion. Two-stage progressive learning strategies are applied in both projection and image domains to achieve coarse-to-fine estimations of SPECT projections and CT-derived μ -maps. Our experiments demonstrate DuDoCFNet's superior accuracy in estimating projections, generating μ -maps, and AC reconstructions compared to existing single- or multi-task learning methods, under various iterations and LD levels. The source code of this work is available at https://github.com/XiongchaoChen/DuDoCFNet-MultiTask.

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.

Semi-supervised low-dose SPECT restoration using sinogram inner-structure aware graph neural network

Objective.To mitigate the potential radiation risk, low-dose single photon emission computed tomography (SPECT) is of increasing interest. Numerous deep learning-based methods have been developed to perform low-dose imaging while maintaining image quality. However, most existing methods seldom explore the unique inner-structure inherent within sinograms. In addition, traditional supervised learning methods require large-scale labeled data, where the normal-dose data serves as annotation and is intractable to acquire in low-dose imaging. In this study, we aim to develop a novel sinogram inner-structure-aware semi-supervised framework for the task of low-dose SPECT sinogram restoration.Approach.The proposed framework retains the strengths of UNet, meanwhile introducing a sinogram-structure-based non-local neighbors graph neural network (SSN-GNN) module and a window-based K-nearest neighbors GNN (W-KNN-GNN) module to effectively exploit the inherent inner-structure within SPECT sinograms. Moreover, the proposed framework employs the mean teacher semi-supervised learning approach to leverage the information available in abundant unlabeled low-dose sinograms.Main results.The datasets exploited in this study were acquired from the (Extended Cardiac-Torso) XCAT anthropomorphic digital phantoms, which provide realistic images for imaging research of various modalities. Quantitative as well as qualitative results demonstrate that the proposed framework achieves superior performance compared to several state-of-the-art reconstruction methods. To further validate the effectiveness of the proposed framework, ablation and robustness experiments were also performed. The experimental results show that each component of the proposed framework effectively improves the model performance, and the framework exhibits superior robustness with respect to various noise levels. Besides, the proposed semi-supervised paradigm showcases the efficacy of incorporating supplementary unlabeled low-dose sinograms.Significance.The proposed framework improves the quality of low-dose SPECT reconstructed images by utilizing sinogram inner-structure and incorporating supplementary unlabeled data, which provides an important tool for dose reduction without sacrificing the image quality.

The Challenge of Single-Photon Emission Computed Tomography Image Segmentation in the Internal Dosimetry of 177Lu Molecular Therapies

The aim of this article is to review the single photon emission computed tomography (SPECT) segmentation methods used in patient-specific dosimetry of 177Lu molecular therapy. Notably, 177Lu-labelled radiopharmaceuticals are currently used in molecular therapy of metastatic neuroendocrine tumours (ligands for somatostatin receptors) and metastatic prostate adenocarcinomas (PSMA ligands). The proper segmentation of the organs at risk and tumours in targeted radionuclide therapy is an important part of the optimisation process of internal patient dosimetry in this kind of therapy. Because this is the first step in dosimetry assessments, on which further dose calculations are based, it is important to know the level of uncertainty that is associated with this part of the analysis. However, the robust quantification of SPECT images, which would ensure accurate dosimetry assessments, is very hard to achieve due to the intrinsic features of this device. In this article, papers on this topic were collected and reviewed to weigh up the advantages and disadvantages of the segmentation methods used in clinical practice. Degrading factors of SPECT images were also studied to assess their impact on the quantification of 177Lu therapy images. Our review of the recent literature gives an insight into this important topic. However, based on the PubMed and IEEE databases, only a few papers investigating segmentation methods in 177Lumolecular therapy were found. Although segmentation is an important step in internal dose calculations, this subject has been relatively lightly investigated for SPECT systems. This is mostly due to the inner features of SPECT. What is more, even when studies are conducted, they usually utilise the diagnostic radionuclide 99mTc and not a therapeutic one like 177Lu, which could be of concern regarding SPECT camera performance and its overall outcome on dosimetry.

Artificial Intelligence in Heart Failure: Friend or Foe?

In recent times, there have been notable changes in cardiovascular medicine, propelled by the swift advancements in artificial intelligence (AI). The present work provides an overview of the current applications and challenges of AI in the field of heart failure. It emphasizes the "garbage in, garbage out" issue, where AI systems can produce inaccurate results with skewed data. The discussion covers issues in heart failure diagnostic algorithms, particularly discrepancies between existing models. Concerns about the reliance on the left ventricular ejection fraction (LVEF) for classification and treatment are highlighted, showcasing differences in current scientific perceptions. This review also delves into challenges in implementing AI, including variable considerations and biases in training data. It underscores the limitations of current AI models in real-world scenarios and the difficulty in interpreting their predictions, contributing to limited physician trust in AI-based models. The overarching suggestion is that AI can be a valuable tool in clinicians' hands for treating heart failure patients, as far as existing medical inaccuracies have been addressed before integrating AI into these frameworks.

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.

Review of artificial intelligence clinical applications in Nuclear Medicine

This paper provides an in-depth analysis of the clinical applications of artificial intelligence (AI) in Nuclear Medicine, focusing on three key areas: neurology, cardiology, and oncology. Beginning with neurology, specifically Alzheimer's disease and Parkinson's disease, the paper examines reviews on diagnosis and treatment planning. The same pattern is followed in cardiology studies. In the final section on oncology, the paper explores the various AI applications in multiple cancer types, including lung, head and neck, lymphoma, and pancreatic cancer.

Observer studies of image quality of denoising reduced-count cardiac single photon emission computed tomography myocardial perfusion imaging by three-dimensional Gaussian post-reconstruction filtering and deep learning

BACKGROUND

The aim of this research was to asses perfusion-defect detection-accuracy by human observers as a function of reduced-counts for 3D Gaussian post-reconstruction filtering vs deep learning (DL) denoising to determine if there was improved performance with DL.

METHODS

SPECT projection data of 156 normally interpreted patients were used for these studies. Half were altered to include hybrid perfusion defects with defect presence and location known. Ordered-subset expectation-maximization (OSEM) reconstruction was employed with the optional correction of attenuation (AC) and scatter (SC) in addition to distance-dependent resolution (RC). Count levels varied from full-counts (100%) to 6.25% of full-counts. The denoising strategies were previously optimized for defect detection using total perfusion deficit (TPD). Four medical physicist (PhD) and six physician (MD) observers rated the slices using a graphical user interface. Observer ratings were analyzed using the LABMRMC multi-reader, multi-case receiver-operating-characteristic (ROC) software to calculate and compare statistically the area-under-the-ROC-curves (AUCs).

RESULTS

For the same count-level no statistically significant increase in AUCs for DL over Gaussian denoising was determined when counts were reduced to either the 25% or 12.5% of full-counts. The average AUC for full-count OSEM with solely RC and Gaussian filtering was lower than for the strategies with AC and SC, except for a reduction to 6.25% of full-counts, thus verifying the utility of employing AC and SC with RC.

CONCLUSION

We did not find any indication that at the dose levels investigated and with the DL network employed, that DL denoising was superior in AUC to optimized 3D post-reconstruction Gaussian filtering.

Physics-Guided Deep Scatter Estimation by Weak Supervision for Quantitative SPECT

Accurate scatter estimation is important in quantitative SPECT for improving image contrast and accuracy. With a large number of photon histories, Monte-Carlo (MC) simulation can yield accurate scatter estimation, but is computationally expensive. Recent deep learning-based approaches can yield accurate scatter estimates quickly, yet full MC simulation is still required to generate scatter estimates as ground truth labels for all training data. Here we propose a physics-guided weakly supervised training framework for fast and accurate scatter estimation in quantitative SPECT by using a 100× shorter MC simulation as weak labels and enhancing them with deep neural networks. Our weakly supervised approach also allows quick fine-tuning of the trained network to any new test data for further improved performance with an additional short MC simulation (weak label) for patient-specific scatter modelling. Our method was trained with 18 XCAT phantoms with diverse anatomies / activities and then was evaluated on 6 XCAT phantoms, 4 realistic virtual patient phantoms, 1 torso phantom and 3 clinical scans from 2 patients for 177Lu SPECT with single / dual photopeaks (113, 208 keV). Our proposed weakly supervised method yielded comparable performance to the supervised counterpart in phantom experiments, but with significantly reduced computation in labeling. Our proposed method with patient-specific fine-tuning achieved more accurate scatter estimates than the supervised method in clinical scans. Our method with physics-guided weak supervision enables accurate deep scatter estimation in quantitative SPECT, while requiring much lower computation in labeling, enabling patient-specific fine-tuning capability in testing.

Comparison of post reconstruction- and reconstruction-based deep learning denoising methods in cardiac SPECT

Objective. The quality of myocardial perfusion SPECT (MPS) images is often hampered by low count statistics. Poor image quality might hinder reporting the studies and in the worst case lead to erroneous diagnosis. Deep learning (DL)-based methods can be used to improve the quality of the low count studies. DL can be applied in several different methods, which might affect the outcome. The aim of this study was to investigate the differences between post reconstruction- and reconstruction-based denoising methods.Approach. A UNET-type network was trained using ordered subsets expectation maximization (OSEM) reconstructed MPS studies acquired with half, quarter and eighth of full-activity. The trained network was applied as a post reconstruction denoiser (OSEM+DL) and it was incorporated into a regularized reconstruction algorithm as a deep learning penalty (DLP). OSEM+DL and DLP were compared against each other and against OSEM images without DL denoising in terms of noise level, myocardium-ventricle contrast and defect detection performance with signal-to-noise ratio of a non-prewhitening matched filter (NPWMF-SNR) applied to artificial perfusion defects inserted into defect-free clinical MPS scans. Comparisons were made using half-, quarter- and eighth-activity data.Main results. OSEM+DL provided lower noise level at all activities than other methods. DLP's noise level was also always lower than matching activity OSEM's. In addition, OSEM+DL and DLP outperformed OSEM in defect detection performance, but contrary to noise level ranking DLP had higher NPWMF-SNR overall than OSEM+DL. The myocardium-ventricle contrast was highest with DLP and lowest with OSEM+DL. Both OSEM+DL and DLP offered better image quality than OSEM, but visually perfusion defects were deeper in OSEM images at low activities.Significance. Both post reconstruction- and reconstruction-based DL denoising methods have great potential for MPS. The preference between these methods is a trade-off between smoother images and better defect detection performance.

Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

[Opportunities for artificial intelligence in radiation protection : Improving safety of diagnostic imaging]

CLINICAL/METHODOLOGICAL ISSUE

Imaging of structures of internal organs often requires ionizing radiation, which is a health risk. Reducing the radiation dose can increase the image noise, which means that images provide less information.

STANDARD RADIOLOGICAL METHODS

This problem is observed in commonly used medical imaging modalities such as computed tomography (CT), positron emission tomography (PET), single photon emission computed tomography (SPECT), angiography, fluoroscopy, and any modality that uses ionizing radiation for imaging.

METHODOLOGICAL INNOVATIONS

Artificial intelligence (AI) can improve the quality of low-dose images and help minimize radiation exposure. Potential applications are explored, and frameworks and procedures are critically evaluated.

PERFORMANCE

The performance of AI models varies. High-performance models could be used in clinical settings in the near future. Several challenges (e.g., quantitative accuracy, insufficient training data) must be addressed for optimal performance and widespread adoption of this technology in the field of medical imaging.

PRACTICAL RECOMMENDATIONS

To fully realize the potential of AI and deep learning (DL) in medical imaging, research and development must be intensified. In particular, quality control of AI models must be ensured, and training and testing data must be uncorrelated and quality assured. With sufficient scientific validation and rigorous quality management, AI could contribute to the safe use of low-dose techniques in medical imaging.

Need for objective task-based evaluation of deep learning-based denoising methods: A study in the context of myocardial perfusion SPECT

BACKGROUND

Artificial intelligence-based methods have generated substantial interest in nuclear medicine. An area of significant interest has been the use of deep-learning (DL)-based approaches for denoising images acquired with lower doses, shorter acquisition times, or both. Objective evaluation of these approaches is essential for clinical application.

PURPOSE

DL-based approaches for denoising nuclear-medicine images have typically been evaluated using fidelity-based figures of merit (FoMs) such as root mean squared error (RMSE) and structural similarity index measure (SSIM). However, these images are acquired for clinical tasks and thus should be evaluated based on their performance in these tasks. Our objectives were to: (1) investigate whether evaluation with these FoMs is consistent with objective clinical-task-based evaluation; (2) provide a theoretical analysis for determining the impact of denoising on signal-detection tasks; and (3) demonstrate the utility of virtual imaging trials (VITs) to evaluate DL-based methods.

METHODS

A VIT to evaluate a DL-based method for denoising myocardial perfusion SPECT (MPS) images was conducted. To conduct this evaluation study, we followed the recently published best practices for the evaluation of AI algorithms for nuclear medicine (the RELAINCE guidelines). An anthropomorphic patient population modeling clinically relevant variability was simulated. Projection data for this patient population at normal and low-dose count levels (20%, 15%, 10%, 5%) were generated using well-validated Monte Carlo-based simulations. The images were reconstructed using a 3-D ordered-subsets expectation maximization-based approach. Next, the low-dose images were denoised using a commonly used convolutional neural network-based approach. The impact of DL-based denoising was evaluated using both fidelity-based FoMs and area under the receiver operating characteristic curve (AUC), which quantified performance on the clinical task of detecting perfusion defects in MPS images as obtained using a model observer with anthropomorphic channels. We then provide a mathematical treatment to probe the impact of post-processing operations on signal-detection tasks and use this treatment to analyze the findings of this study.

RESULTS

Based on fidelity-based FoMs, denoising using the considered DL-based method led to significantly superior performance. However, based on ROC analysis, denoising did not improve, and in fact, often degraded detection-task performance. This discordance between fidelity-based FoMs and task-based evaluation was observed at all the low-dose levels and for different cardiac-defect types. Our theoretical analysis revealed that the major reason for this degraded performance was that the denoising method reduced the difference in the means of the reconstructed images and of the channel operator-extracted feature vectors between the defect-absent and defect-present cases.

CONCLUSIONS

The results show the discrepancy between the evaluation of DL-based methods with fidelity-based metrics versus the evaluation on clinical tasks. This motivates the need for objective task-based evaluation of DL-based denoising approaches. Further, this study shows how VITs provide a mechanism to conduct such evaluations computationally, in a time and resource-efficient setting, and avoid risks such as radiation dose to the patient. Finally, our theoretical treatment reveals insights into the reasons for the limited performance of the denoising approach and may be used to probe the effect of other post-processing operations on signal-detection tasks.

Reduction of SPECT acquisition time using deep learning: A phantom study

Single photon emission computed tomography (SPECT) procedures are characterized by long acquisition time to acquire diagnostically acceptable image data. The goal of this investigation was to assess the feasibility of using a deep convolutional neural network (DCNN) to reduce the acquisition time. The DCNN was implemented using the PyTorch and trained using image data from standard SPECT quality phantoms. The under-sampled image dataset is provided to neural network as input, while missing projections were provided as targets. The network is to produce for the output the missing projections. The baseline method of calculating the missing projections as arithmetic means of adjacent ones was introduced. The obtained synthesized projections and reconstructed images were compared to original data and baseline data across several parameters using PyTorch and PyTorch Image Quality code libraries. Results obtained from comparisons of projection and reconstructed image data show the DCNN clearly outperforming the baseline method. However, subsequent analysis revealed the synthesized image data being more comparable to under-sampled than to fully-sampled image data. The results of this investigation imply that neural network can replicate coarser objects better. However, densely sampled clinical image datasets, coarse reconstruction matrices and patient data featuring coarse structures combined with a lack of baseline data generation methods will hamper the ability to analyse the neural network outputs correctly. This study calls for use of phantom image data and introduction of a baseline method in the evaluation of neural network outputs.

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.

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.

Preparing for the Artificial Intelligence Revolution in Nuclear Cardiology

A major opportunity in nuclear cardiology is the many significant artificial intelligence (AI) applications that have recently been reported. These developments include using deep learning (DL) for reducing the needed injected dose and acquisition time in perfusion acquisitions also due to DL improvements in image reconstruction and filtering, SPECT attenuation correction using DL without need for transmission images, DL and machine learning (ML) use for feature extraction to define myocardial left ventricular (LV) borders for functional measurements and improved detection of the LV valve plane and AI, ML, and DL implementations for MPI diagnosis, prognosis, and structured reporting. Although some have, most of these applications have yet to make it to widespread commercial distribution due to the recency of their developments, most reported in 2020. We must be prepared both technically and socio-economically to fully benefit from these and a tsunami of other AI applications that are coming.

Comparison of deep learning-based denoising methods in cardiac SPECT

BACKGROUND

Myocardial perfusion SPECT (MPS) images often suffer from artefacts caused by low-count statistics. Poor-quality images can lead to misinterpretations of perfusion defects. Deep learning (DL)-based methods have been proposed to overcome the noise artefacts. The aim of this study was to investigate the differences among several DL denoising models.

METHODS

Convolution neural network (CNN), residual neural network (RES), UNET and conditional generative adversarial neural network (cGAN) were generated and trained using ordered subsets expectation maximization (OSEM) reconstructed MPS studies acquired with full, half, three-eighths and quarter acquisition time. All DL methods were compared against each other and also against images without DL-based denoising. Comparisons were made using half and quarter time acquisition data. The methods were evaluated in terms of noise level (coefficient of variation of counts, CoV), structural similarity index measure (SSIM) in the myocardium of normal patients and receiver operating characteristic (ROC) analysis of realistic artificial perfusion defects inserted into normal MPS scans. Total perfusion deficit scores were used as observer rating for the presence of a perfusion defect.

RESULTS

All the DL denoising methods tested provided statistically significantly lower noise level than OSEM without DL-based denoising with the same acquisition time. CoV of the myocardium counts with the different DL noising methods was on average 7% (CNN), 8% (RES), 7% (UNET) and 14% (cGAN) lower than with OSEM. All DL methods also outperformed full time OSEM without DL-based denoising in terms of noise level with both half and quarter acquisition time, but this difference was not statistically significant. cGAN had the lowest CoV of the DL methods at all noise levels. Image quality and polar map uniformity of DL-denoised images were also better than reduced acquisition time OSEM's. SSIM of the reduced acquisition time OSEM was overall higher than with the DL methods. The defect detection performance of full time OSEM measured as area under the ROC curve (AUC) was on average 0.97. Half time OSEM, CNN, RES and UNET provided equal or nearly equal AUC. However, with quarter time data CNN, RES and UNET had an average AUC of 0.93, which was lower than full time OSEM's AUC, but equal to quarter acquisition time OSEM. cGAN did not achieve the defect detection performance of the other DL methods. Its average AUC with half time data was 0.94 and 0.91 with quarter time data.

CONCLUSIONS

DL-based denoising effectively improved noise level with slightly lower perfusion defect detection performance than full time reconstruction. cGAN achieved the lowest noise level, but at the same time the poorest defect detection performance among the studied DL methods.

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.

Artificial Intelligence in Nuclear Cardiology

Artificial intelligence (AI) encompasses a variety of computer algorithms that have a wide range of potential clinical applications in nuclear cardiology. This article will introduce core terminology and concepts for AI including classifications of AI as well as training and testing regimens. We will then highlight the potential role for AI to improve image registration and image quality. Next, we will discuss methods for AI-driven image attenuation correction. Finally, we will review advancements in machine learning and deep-learning applications for disease diagnosis and risk stratification, including efforts to improve clinical translation of this valuable technology with explainable AI models.

Deep learning-enhanced nuclear medicine SPECT imaging applied to cardiac studies

Deep learning (DL) has a growing popularity and is a well-established method of artificial intelligence for data processing, especially for images and videos. Its applications in nuclear medicine are broad and include, among others, disease classification, image reconstruction, and image de-noising. Positron emission tomography (PET) and single-photon emission computerized tomography (SPECT) are major image acquisition technologies in nuclear medicine. Though several studies have been conducted to apply DL in many nuclear medicine domains, such as cancer detection and classification, few studies have employed such methods for cardiovascular disease applications. The present paper reviews recent DL approaches focused on cardiac SPECT imaging. Extensive research identified fifty-five related studies, which are discussed. The review distinguishes between major application domains, including cardiovascular disease diagnosis, SPECT attenuation correction, image denoising, full-count image estimation, and image reconstruction. In addition, major findings and dominant techniques employed for the mentioned task are revealed. Current limitations of DL approaches and future research directions are discussed.

Hybrid Methodology Based on Symmetrized Dot Pattern and Convolutional Neural Networks for Fault Diagnosis of Power Cables

This study proposes a recognition method based on symmetrized dot pattern (SDP) analysis and convolutional neural network (CNN) for rapid and accurate diagnosis of insulation defect problems by detecting the partial discharge (PD) signals of XLPE power cables. First, a normal and three power cable models with different insulation defects are built. The PD signals resulting from power cable insulation defects are measured. The frequency and amplitude variations of PD signals from different defects are reflected by comprehensible images using the proposed SDP analysis method. The features of different power cable defects are presented. Finally, the feature image is trained and identified by CNN to achieve a power cable insulation fault diagnosis system. The experimental results show that the proposed method could accurately diagnose the fault types of power cable insulation defects with a recognition accuracy of 98%. The proposed method is characterized by a short detection time and high diagnostic accuracy. It can effectively detect the power cable PD to identify the fault type of the insulation defect.

Improving detection accuracy of perfusion defect in standard dose SPECT-myocardial perfusion imaging by deep-learning denoising

BACKGROUND

We previously developed a deep-learning (DL) network for image denoising in SPECT-myocardial perfusion imaging (MPI). Here we investigate whether this DL network can be utilized for improving detection of perfusion defects in standard-dose clinical acquisitions.

METHODS

To quantify perfusion-defect detection accuracy, we conducted a receiver-operating characteristic (ROC) analysis on reconstructed images with and without processing by the DL network using a set of clinical SPECT-MPI data from 190 subjects. For perfusion-defect detection hybrid studies were used as ground truth, which were created from clinically normal studies with simulated realistic lesions inserted. We considered ordered-subset expectation-maximization (OSEM) reconstruction with corrections for attenuation, resolution, and scatter and with 3D Gaussian post-filtering. Total perfusion deficit (TPD) scores, computed by Quantitative Perfusion SPECT (QPS) software, were used to evaluate the reconstructed images.

RESULTS

Compared to reconstruction with optimal Gaussian post-filtering (sigma = 1.2 voxels), further DL denoising increased the area under the ROC curve (AUC) from 0.80 to 0.88 (P-value < 10-4). For reconstruction with less Gaussian post-filtering (sigma = 0.8 voxels), thus better spatial resolution, DL denoising increased the AUC value from 0.78 to 0.86 (P-value < 10-4) and achieved better spatial resolution in reconstruction.

CONCLUSIONS

DL denoising can effectively improve the detection of abnormal defects in standard-dose SPECT-MPI images over conventional reconstruction.

Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising

BACKGROUND

Myocardial perfusion (MP) SPECT is a well-established method for diagnosing cardiac disease, yet its radiation risk poses safety concern. This study aims to apply and evaluate the use of Pix2Pix generative adversarial network (Pix2Pix GAN) in denoising low dose MP SPECT images.

METHODS

One hundred male and female patients with different 99mTc-sestamibi activity distributions, organ and body sizes were simulated by a population of digital 4D Extended Cardiac Torso (XCAT) phantoms. Realistic noisy SPECT projections of full dose of 987 MBq injection and 16 min acquisition, and low dose ranged from 1/20 to 1/2 of the full dose, were generated by an analytical projector from the right anterior oblique (RAO) to the left posterior oblique (LPO) positions. Additionally, twenty patients underwent ~1,184 MBq 99mTc-sestamibi stress SPECT/CT scan were also retrospectively recruited for the study. For each patient, low dose SPECT images (7/10 to 1/10 of full dose) were generated from the full dose list mode data. Our Pix2Pix GAN model was trained with full dose and low dose reconstructed SPECT image pairs. Normalized mean square error (NMSE), structural similarity index (SSIM), coefficient of variation (CV), full-width-at-half-maximum (FWHM) and relative defect size differences (RSD) of Pix2Pix GAN processed images were evaluated along with a reference convolutional auto encoder (CAE) network and post-reconstruction filters.

RESULTS

NMSE values of 0.0233±0.004 vs. 0.0249±0.004 and 0.0313±0.007 vs. 0.0579±0.016 were obtained on 1/2 and 1/20 dose level for Pix2Pix GAN and CAE in the simulation study, while they were 0.0376±0.010 vs. 0.0433±0.010 and 0.0907±0.020 vs. 0.1186±0.025 on 7/10 and 1/10 dose level in the clinical study. Similar results were also obtained from the SSIM, CV, FWHM and RSD values. Overall, the use of Pix2Pix GAN was superior to other denoising methods in all physical indices, particular in the lower dose levels in the simulation and clinical study.

CONCLUSIONS

The Pix2Pix GAN method is effective to reduce the noise level of low dose MP SPECT. Further studies on clinical performance are warranted to demonstrate its full clinical effectiveness.

Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT

PURPOSE

Deep-learning-based attenuation correction (AC) for SPECT includes both indirect and direct approaches. Indirect approaches generate attenuation maps (μ-maps) from emission images, while direct approaches predict AC images directly from non-attenuation-corrected (NAC) images without μ-maps. For dedicated cardiac SPECT scanners with CZT detectors, indirect approaches are challenging due to the limited field-of-view (FOV). In this work, we aim to 1) first develop novel indirect approaches to improve the AC performance for dedicated SPECT; and 2) compare the AC performance between direct and indirect approaches for both general purpose and dedicated SPECT.

METHODS

For dedicated SPECT, we developed strategies to predict truncated μ-maps from NAC images reconstructed with a small matrix, or full μ-maps from NAC images reconstructed with a large matrix using 270 anonymized clinical studies scanned on a GE Discovery NM/CT 570c SPECT/CT. For general purpose SPECT, we implemented direct and indirect approaches using 400 anonymized clinical studies scanned on a GE NM/CT 850c SPECT/CT. NAC images in both photopeak and scatter windows were input to predict μ-maps or AC images.

RESULTS

For dedicated SPECT, the averaged normalized mean square error (NMSE) using our proposed strategies with full μ-maps was 1.20 ± 0.72% as compared to 2.21 ± 1.17% using the previous direct approaches. The polar map absolute percent error (APE) using our approaches was 3.24 ± 2.79% (R² = 0.9499) as compared to 4.77 ± 3.96% (R² = 0.9213) using direct approaches. For general purpose SPECT, the averaged NMSE of the predicted AC images using the direct approaches was 2.57 ± 1.06% as compared to 1.37 ± 1.16% using the indirect approaches.

CONCLUSIONS

We developed strategies of generating μ-maps for dedicated cardiac SPECT with small FOV. For both general purpose and dedicated SPECT, indirect approaches showed superior performance of AC than direct approaches.

Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept

Background

To generate high-quality bone scan SPECT images from only 1/7 scan time SPECT images using deep learning-based enhancement method.

Materials and methods

Normal-dose (925–1110 MBq) clinical technetium 99 m-methyl diphosphonate (99mTc-MDP) SPECT/CT images and corresponding SPECT/CT images with 1/7 scan time from 20 adult patients with bone disease and a phantom were collected to develop a lesion-attention weighted U²-Net (Qin et al. in Pattern Recognit 106:107404, 2020), which produces high-quality SPECT images from fast SPECT/CT images. The quality of synthesized SPECT images from different deep learning models was compared using PSNR and SSIM. Clinic evaluation on 5-point Likert scale (5 = excellent) was performed by two experienced nuclear physicians. Average score and Wilcoxon test were constructed to assess the image quality of 1/7 SPECT, DL-enhanced SPECT and the standard SPECT. SUVmax, SUVmean, SSIM and PSNR from each detectable sphere filled with imaging agent were measured and compared for different images.

Results

U²-Net-based model reached the best PSNR (40.8) and SSIM (0.788) performance compared with other advanced deep learning methods. The clinic evaluation showed the quality of the synthesized SPECT images is much higher than that of fast SPECT images (P < 0.05). Compared to the standard SPECT images, enhanced images exhibited the same general image quality (P > 0.999), similar detail of 99mTc-MDP (P = 0.125) and the same diagnostic confidence (P = 0.1875). 4, 5 and 6 spheres could be distinguished on 1/7 SPECT, DL-enhanced SPECT and the standard SPECT, respectively. The DL-enhanced phantom image outperformed 1/7 SPECT in SUVmax, SUVmean, SSIM and PSNR in quantitative assessment.

Conclusions

Our proposed method can yield significant image quality improvement in the noise level, details of anatomical structure and SUV accuracy, which enabled applications of ultra fast SPECT bone imaging in real clinic settings.

LU-Net: combining LSTM and U-Net for sinogram synthesis in sparse-view SPECT reconstruction

Lowering the dose in single-photon emission computed tomography (SPECT) imaging to reduce the radiation damage to patients has become very significant. In SPECT imaging, lower radiation dose can be achieved by reducing the activity of administered radiotracer, which will lead to projection data with either sparse projection views or reduced photon counts per view. Direct reconstruction of sparse-view projection data may lead to severe ray artifacts in the reconstructed image. Many existing works use neural networks to synthesize the projection data of sparse-view to address the issue of ray artifacts. However, these methods rarely consider the sequence feature of projection data along projection view. This work is dedicated to developing a neural network architecture that accounts for the sequence feature of projection data at adjacent view angles. In this study, we propose a network architecture combining Long Short-Term Memory network (LSTM) and U-Net, dubbed LU-Net, to learn the mapping from sparse-view projection data to full-view data. In particular, the LSTM module in the proposed network architecture can learn the sequence feature of projection data at adjacent angles to synthesize the missing views in the sinogram. All projection data used in the numerical experiment are generated by the Monte Carlo simulation software SIMIND. We evenly sample the full-view sinogram and obtain the 1/2-, 1/3- and 1/4-view projection data, respectively, representing three different levels of view sparsity. We explore the performance of the proposed network architecture at the three simulated view levels. Finally, we employ the preconditioned alternating projection algorithm (PAPA) to reconstruct the synthesized projection data. Compared with U-Net and traditional iterative reconstruction method with total variation regularization as well as PAPA solver (TV-PAPA), the proposed network achieves significant improvement in both global and local quality metrics.

Investigating the limited performance of a deep-learning-based SPECT denoising approach: An observer-study-based characterization

Multiple objective assessment of image-quality (OAIQ)-based studies have reported that several deep-learning (DL)-based denoising methods show limited performance on signal-detection tasks. Our goal was to investigate the reasons for this limited performance. To achieve this goal, we conducted a task-based characterization of a DL-based denoising approach for individual signal properties. We conducted this study in the context of evaluating a DL-based approach for denoising single photon-emission computed tomography (SPECT) images. The training data consisted of signals of different sizes and shapes within a clustered-lumpy background, imaged with a 2D parallel-hole-collimator SPECT system. The projections were generated at normal and 20% low-count level, both of which were reconstructed using an ordered-subset-expectation-maximization (OSEM) algorithm. A convolutional neural network (CNN)-based denoiser was trained to process the low-count images. The performance of this CNN was characterized for five different signal sizes and four different signal-to-background ratio (SBRs) by designing each evaluation as a signal-known-exactly/background-known-statistically (SKE/BKS) signal-detection task. Performance on this task was evaluated using an anthropomorphic channelized Hotelling observer (CHO). As in previous studies, we observed that the DL-based denoising method did not improve performance on signal-detection tasks. Evaluation using the idea of observer-study-based characterization demonstrated that the DL-based denoising approach did not improve performance on the signal-detection task for any of the signal types. Overall, these results provide new insights on the performance of the DL-based denoising approach as a function of signal size and contrast. More generally, the observer study-based characterization provides a mechanism to evaluate the sensitivity of the method to specific object properties, and may be explored as analogous to characterizations such as modulation transfer function for linear systems. Finally, this work underscores the need for objective task-based evaluation of DL-based denoising approaches.

Deep learning applications in myocardial perfusion imaging, a systematic review and meta-analysis

Background

Coronary artery disease (CAD) is a leading cause of death worldwide, and the diagnostic process comprises of invasive testing with coronary angiography and non-invasive imaging, in addition to history, clinical examination, and electrocardiography (ECG). A highly accurate assessment of CAD lies in perfusion imaging which is performed by myocardial perfusion scintigraphy (MPS) and magnetic resonance imaging (stress CMR). Recently deep learning has been increasingly applied on perfusion imaging for better understanding of the diagnosis, safety, and outcome of CAD.The aim of this review is to summarise the evidence behind deep learning applications in myocardial perfusion imaging.

Methods

A systematic search was performed on MEDLINE and EMBASE databases, from database inception until September 29, 2020. This included all clinical studies focusing on deep learning applications and myocardial perfusion imaging, and excluded competition conference papers, simulation and animal studies, and studies which used perfusion imaging as a variable with different focus. This was followed by review of abstracts and full texts. A meta-analysis was performed on a subgroup of studies which looked at perfusion images classification. A summary receiver-operating curve (SROC) was used to compare the performance of different models, and area under the curve (AUC) was reported. Effect size, risk of bias and heterogeneity were tested.

Results

46 studies in total were identified, the majority were MPS studies (76%). The most common neural network was convolutional neural network (CNN) (41%). 13 studies (28%) looked at perfusion imaging classification using MPS, the pooled diagnostic accuracy showed AUC = 0.859. The summary receiver operating curve (SROC) comparison showed superior performance of CNN (AUC = 0.894) compared to MLP (AUC = 0.848). The funnel plot was asymmetrical, and the effect size was significantly different with p value < 0.001, indicating small studies effect and possible publication bias. There was no significant heterogeneity amongst studies according to Q test (p = 0.2184).

Conclusion

Deep learning has shown promise to improve myocardial perfusion imaging diagnostic accuracy, prediction of patients' events and safety. More research is required in clinical applications, to achieve better care for patients with known or suspected CAD.

Deep learning-based denoising of low-dose SPECT myocardial perfusion images: quantitative assessment and clinical performance

Purpose

This work was set out to investigate the feasibility of dose reduction in SPECT myocardial perfusion imaging (MPI) without sacrificing diagnostic accuracy. A deep learning approach was proposed to synthesize full-dose images from the corresponding low-dose images at different dose reduction levels in the projection space.

Methods

Clinical SPECT-MPI images of 345 patients acquired on a dedicated cardiac SPECT camera in list-mode format were retrospectively employed to predict standard-dose from low-dose images at half-, quarter-, and one-eighth-dose levels. To simulate realistic low-dose projections, 50%, 25%, and 12.5% of the events were randomly selected from the list-mode data through applying binomial subsampling. A generative adversarial network was implemented to predict non-gated standard-dose SPECT images in the projection space at the different dose reduction levels. Well-established metrics, including peak signal-to-noise ratio (PSNR), root mean square error (RMSE), and structural similarity index metrics (SSIM) in addition to Pearson correlation coefficient analysis and clinical parameters derived from Cedars-Sinai software were used to quantitatively assess the predicted standard-dose images. For clinical evaluation, the quality of the predicted standard-dose images was evaluated by a nuclear medicine specialist using a seven-point (− 3 to + 3) grading scheme.

Results

The highest PSNR (42.49 ± 2.37) and SSIM (0.99 ± 0.01) and the lowest RMSE (1.99 ± 0.63) were achieved at a half-dose level. Pearson correlation coefficients were 0.997 ± 0.001, 0.994 ± 0.003, and 0.987 ± 0.004 for the predicted standard-dose images at half-, quarter-, and one-eighth-dose levels, respectively. Using the standard-dose images as reference, the Bland–Altman plots sketched for the Cedars-Sinai selected parameters exhibited remarkably less bias and variance in the predicted standard-dose images compared with the low-dose images at all reduced dose levels. Overall, considering the clinical assessment performed by a nuclear medicine specialist, 100%, 80%, and 11% of the predicted standard-dose images were clinically acceptable at half-, quarter-, and one-eighth-dose levels, respectively.

Conclusion

The noise was effectively suppressed by the proposed network, and the predicted standard-dose images were comparable to reference standard-dose images at half- and quarter-dose levels. However, recovery of the underlying signals/information in low-dose images beyond a quarter of the standard dose would not be feasible (due to very poor signal-to-noise ratio) which will adversely affect the clinical interpretation of the resulting images.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05614-7.

Development of attenuation correction methods using deep learning in brain-perfusion single-photon emission computed tomography

PURPOSE

Computed tomography (CT)-based attenuation correction (CTAC) in single-photon emission computed tomography (SPECT) is highly accurate, but it requires hybrid SPECT/CT instruments and additional radiation exposure. To obtain attenuation correction (AC) without the need for additional CT images, a deep learning method was used to generate pseudo-CT images has previously been reported, but it is limited because of cross-modality transformation, resulting in misalignment and modality-specific artifacts. This study aimed to develop a deep learning-based approach using non-attenuation-corrected (NAC) images and CTAC-based images for training to yield AC images in brain-perfusion SPECT. This study also investigated whether the proposed approach is superior to conventional Chang's AC (ChangAC).

METHODS

In total, 236 patients who underwent brain-perfusion SPECT were randomly divided into two groups: the training group (189 patients; 80%) and the test group (47 patients; 20%). Two models were constructed using Autoencoder (AutoencoderAC) and U-Net (U-NetAC), respectively. ChangAC, AutoencoderAC, and U-NetAC approaches were compared with CTAC using qualitative analysis (visual evaluation) and quantitative analysis (normalized mean squared error [NMSE] and the percentage error in each brain region). Statistical analyses were performed using the Wilcoxon signed-rank sum test and Bland-Altman analysis.

RESULTS

U-NetAC had the highest visual evaluation score. The NMSE results for the U-NetAC were the lowest, followed by AutoencoderAC and ChangAC (P < 0.001). Bland-Altman analysis showed a fixed bias for ChangAC and AutoencoderAC and a proportional bias for ChangAC. ChangAC underestimated counts by 30-40% in all brain regions. AutoencoderAC and U-NetAC produced mean errors of <1% and maximum errors of 3%, respectively.

CONCLUSION

New deep learning-based AC methods for AutoencoderAC and U-NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U-NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo-CT images. To verify our models' generalizability, external validation is required.

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.

Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting

Purpose

In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics.

Methods

In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing).

Results

The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training.

Conclusion

The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05244-z.