CT attenuation correction improves quantitative risk prediction by cardiac SPECT in obese patients.

PURPOSE: This study aimed to compare the predictive value of CT attenuation-corrected stress total perfusion deficit (AC-sTPD) and non-corrected stress TPD (NC-sTPD) for major adverse cardiac events (MACE) in obese patients undergoing cadmium zinc telluride (CZT) SPECT myocardial perfusion imaging (MPI). METHODS: The study included 4,585 patients who underwent CZT SPECT/CT MPI for clinical indications (chest pain: 56%, shortness of breath: 13%, other: 32%) at Yale New Haven Hospital (age: 64 ± 12 years, 45% female, body mass index [BMI]: 30.0 ± 6.3 kg/m2, prior coronary artery disease: 18%). The association between AC-sTPD or NC-sTPD and MACE defined as the composite end point of mortality, nonfatal myocardial infarction or late coronary revascularization (> 90 days after SPECT) was evaluated with survival analysis. RESULTS: During a median follow-up of 25 months, 453 patients (10%) experienced MACE. In patients with BMI ≥ 35 kg/m2 (n = 931), those with AC-sTPD ≥ 3% had worse MACE-free survival than those with AC-sTPD < 3% (HR: 2.23, 95% CI: 1.40 - 3.55, p = 0.002) with no difference in MACE-free survival between patients with NC-sTPD ≥ 3% and NC-sTPD < 3% (HR:1.06, 95% CI:0.67 - 1.68, p = 0.78). AC-sTPD had higher AUC than NC-sTPD for the detection of 2-year MACE in patients with BMI ≥ 35 kg/m2 (0.631 versus 0.541, p = 0.01). In the overall cohort AC-sTPD had a higher ROC area under the curve (AUC, 0.641) than NC-sTPD (0.608; P = 0.01) for detection of 2-year MACE. In patients with BMI ≥ 35 kg/m2 AC sTPD provided significant incremental prognostic value beyond NC sTPD (net reclassification index: 0.14 [95% CI: 0.20 - 0.28]). CONCLUSIONS: AC sTPD outperformed NC sTPD in predicting MACE in patients undergoing SPECT MPI with BMI ≥ 35 kg/m2. These findings highlight the superior prognostic value of AC-sTPD in this patient population and underscore the importance of CT attenuation correction.

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.

Increasing angular sampling through deep learning for stationary cardiac SPECT image reconstruction.

BACKGROUND: The GE Discovery NM (DNM) 530c/570c are dedicated cardiac SPECT scanners with 19 detector modules designed for stationary imaging. This study aims to incorporate additional projection angular sampling to improve reconstruction quality. A deep learning method is also proposed to generate synthetic dense-view image volumes from few-view counterparts. METHODS: By moving the detector array, a total of four projection angle sets were acquired and combined for image reconstructions. A deep neural network is proposed to generate synthetic four-angle images with 76 ([Formula: see text]) projections from corresponding one-angle images with 19 projections. Simulated data, pig, physical phantom, and human studies were used for network training and evaluation. Reconstruction results were quantitatively evaluated using representative image metrics. The myocardial perfusion defect size of different subjects was quantified using an FDA-cleared clinical software. RESULTS: Multi-angle reconstructions and network results have higher image resolution, improved uniformity on normal myocardium, more accurate defect quantification, and superior quantitative values on all the testing data. As validated against cardiac catheterization and diagnostic results, deep learning results showed improved image quality with better defect contrast on human studies. CONCLUSION: Increasing angular sampling can substantially improve image quality on DNM, and deep learning can be implemented to improve reconstruction quality in case of stationary imaging.

Integration of coronary artery calcium scoring from CT attenuation scans by machine learning improves prediction of adverse cardiovascular events in patients undergoing SPECT/CT myocardial perfusion imaging.

BACKGROUND: Machine learning (ML) has been previously applied for prognostication in patients undergoing SPECT myocardial perfusion imaging (MPI). We evaluated whether including attenuation CT coronary artery calcification (CAC) scoring improves ML prediction of major adverse cardiovascular events (MACE) in patients undergoing SPECT/CT MPI. METHODS: From the REFINE SPECT Registry 4770 patients with SPECT/CT performed at a single center were included (age: 64 ± 12 years, 45% female). ML algorithm (XGBoost) inputs were clinical risk factors, stress variables, SPECT imaging parameters, and expert-observer CAC scoring using CT attenuation correction scans performed to obtain CT attenuation maps. The ML model was trained and validated using tenfold hold-out validation. Receiver Operator Characteristics (ROC) curves were analyzed for prediction of MACE. MACE-free survival was evaluated with standard survival analyses. RESULTS: During a median follow-up of 24.1 months, 475 patients (10%) experienced MACE. Higher area under the ROC curve for MACE was observed with ML when CAC scoring was included (CAC-ML score, 0.77, 95% confidence interval [CI] 0.75-0.79) compared to ML without CAC (ML score, 0.75, 95% CI 0.73-0.77, P = .005) and when compared to CAC score alone (0.71, 95% CI 0.68-0.73, P < .001). Among clinical, imaging, and stress parameters, CAC score had highest variable importance for ML. On survival analysis patients with high CAC-ML score (> 0.091) had higher event rate when compared to patients with low CAC-ML score (hazard ratio 5.3, 95% CI 4.3-6.5, P < .001). CONCLUSION: Integration of attenuation CT CAC scoring improves the predictive value of ML risk score for MACE prediction in patients undergoing SPECT MPI.

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.

Post-reconstruction attenuation correction for SPECT myocardium perfusion imaging facilitated by deep learning-based attenuation map generation.

BACKGROUND: Attenuation correction can improve the quantitative accuracy of single-photon emission computed tomography (SPECT) images. Existing SPECT-only systems normally can only provide non-attenuation corrected (NC) images which are susceptible to attenuation artifacts. In this work, we developed a post-reconstruction attenuation correction (PRAC) approach facilitated by a deep learning-based attenuation map for myocardial perfusion SPECT imaging. METHODS: In the PRAC method, new projection data were estimated via forwardly projecting the scanner-generated NC image. Then an attenuation map, generated from NC image using a pretrained deep learning (DL) convolutional neural network, was incorporated into an offline reconstruction algorithm to obtain the attenuation-corrected images from the forwardly projected projections. We evaluated the PRAC method using 30 subjects with a DL network trained with 40 subjects, using the vendor-generated AC images and CT-based attenuation maps as the ground truth. RESULTS: The PRAC methods using DL-generated and CT-based attenuation maps were both highly consistent with the scanner-generated AC image. The globally normalized mean absolute errors were 1.1% ± .6% and .7% ± .4% and the localized absolute percentage errors were 8.9% ± 13.4% and 7.8% ± 11.4% in the left ventricular (LV) blood pool, respectively, and - 1.3% ± 8.0% and - 3.8% ± 4.5% in the LV myocardium for PRAC methods using DL-generated and CT-based attenuation maps, respectively. The summed stress scores after PRAC using both attenuation maps were more consistent with the ground truth than those of the NC images. CONCLUSION: We developed a PRAC approach facilitated by deep learning-based attenuation maps for SPECT myocardial perfusion imaging. It may be feasible for this approach to provide AC images for SPECT-only scanner data.

Cross-vender, cross-tracer, and cross-protocol deep transfer learning for attenuation map generation of cardiac SPECT.

It has been proved feasible to generate attenuation maps (µ-maps) from cardiac SPECT using deep learning. However, this assumed that the training and testing datasets were acquired using the same scanner, tracer, and protocol. We investigated a robust generation of CT-derived µ-maps from cardiac SPECT acquired by different scanners, tracers, and protocols from the training data. We first pre-trained a network using 120 studies injected with 99mTc-tetrofosmin acquired from a GE 850 SPECT/CT with 360-degree gantry rotation, which was then fine-tuned and tested using 80 studies injected with 99mTc-sestamibi acquired from a Philips BrightView SPECT/CT with 180-degree gantry rotation. The error between ground-truth and predicted µ-maps by transfer learning was 5.13 ± 7.02%, as compared to 8.24 ± 5.01% by direct transition without fine-tuning and 6.45 ± 5.75% by limited-sample training. The error between ground-truth and reconstructed images with predicted µ-maps by transfer learning was 1.11 ± 1.57%, as compared to 1.72 ± 1.63% by direct transition and 1.68 ± 1.21% by limited-sample training. It is feasible to apply a network pre-trained by a large amount of data from one scanner to data acquired by another scanner using different tracers and protocols, with proper transfer learning.

Anger recall mental stress decreases 123I-metaiodobenzylguanidine (123I-MIBG) uptake and increases heterogeneity of cardiac sympathetic activity in the myocardium in patients with ischemic cardiomyopathy.

BACKGROUND: Acute psychological stressors such as anger can precipitate ventricular arrhythmias, but the mechanism is incompletely understood. Quantification of regional myocardial sympathetic activity with 123I-metaiodobenzylguanidine (123I-mIBG) SPECT imaging in conjunction with perfusion imaging during mental stress may identify a mismatch between perfusion and sympathetic activity that may exacerbate a mismatch between perfusion and sympathetic activity that could create a milieu of increased vulnerability to ventricular arrhythmia. METHODS: Five men with ischemic cardiomyopathy (ICM), and five age-matched healthy male controls underwent serial 123I-mIBG and 99mTc-Tetrofosmin SPECT/CT imaging during an anger recall mental stress task and dual isotope imaging was repeated approximately 1 week later during rest. Images were reconstructed using an iterative reconstruction algorithm with CT-based attenuation correction. The mismatch of left ventricular myocardial 123I-mIBG and 99mTc-Tetrofosmin was assessed along with radiotracer heterogeneity and the 123I-mIBG heart-to-mediastinal ratios (HMR) were calculated using custom software developed at Yale. RESULTS: The hemodynamic response to mental stress was similar in both groups. The resting-HMR was greater in healthy control subjects (3.67 ± 0.95) than those with ICM (3.18 ± 0.68, P = .04). Anger recall significantly decreased the HMR in ICM patients (2.62 ± 0.3, P = .04), but not in normal subjects. The heterogeneity of 123I-mIBG uptake in the myocardium was significantly increased in ICM patients during mental stress (26% ± 8.23% vs. rest: 19.62% ± 9.56%; P = .01), whereas the 99mTc-Tetrofosmin uptake pattern was unchanged. CONCLUSION: Mental stress decreased the 123I-mIBG HMR, increased mismatch between sympathetic activity and myocardial perfusion, and increased the heterogeneity of 123I-mIBG uptake in ICM patients, while there was no significant change in myocardial defect size or the heterogeneity of 99mTc-Tetrofosmin perfusion. The changes observed in this proof-of-concept study may provide valuable information about the trigger-substrate interaction and the potential vulnerability for ventricular arrhythmias.

Diagnostic accuracy of stress-only myocardial perfusion SPECT improved by deep learning.

PURPOSE: Deep convolutional neural networks (CNN) for single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) has been used to improve the diagnostic accuracy of coronary artery disease (CAD). This study was to design and evaluate a deep learning (DL) approach to automatic diagnosis of myocardial perfusion abnormalities from stress-only MPI. METHODS: The new DL approach developed for this study was compared to a conventional quantitative perfusion defect size (DS) method. A total of 37,243 patients (51.5% males) undergone stress 99mTc-Tetrofosmin or 99mTc-Sestamibi MPI were selected retrospectively from Yale New Haven Hospital. Patients were dichotomized as studies with normal (75.4%) or abnormal (24.6%) myocardial perfusion based on final diagnoses of clinical nuclear cardiologists. Stress myocardial perfusion defect size was calculated using Yale quantitative analytic software. A deep CNN was trained using the circumferential count profile maps derived from SPECT MPI and was evaluated for the diagnosis of perfusion abnormality with a 5-fold cross-validation approach. In each fold, 27,933, 1862 and 7448 patients were used as training, validation and testing datasets, respectively. The area under the receiver-operating characteristic curve (AUC) was calculated and analyzed for all patients as well as for the eight sub-groups classified based on patient genders, quantitative algorithms, radioactive tracers and SPECT cameras. RESULTS: The AUC value resulted from the DL method was significantly higher than that from the DS method (0.872 ± 0.002 vs. 0.838 ± 0.003, p < 0.01). Across the eight sub-groups, the DL method provided more consistent AUC values in terms of smaller standard deviation and higher diagnostic accuracy and specificity, but slightly lower sensitivity than the DS method (AUC: 0.865 ± 0.010 vs. 0.838 ± 0.019, Accuracy: 82.7% ± 2.5% vs. 78.5% ± 3.6%, Specificity: 84.9% ± 3.7% vs. 77.5% ± 6.5%, Sensitivity: 74.4% ± 4.2% vs. 79.8% ± 5.8%). CONCLUSIONS: The incorporation of deep learning for stress-only MPI has a considerable potential to improve the diagnostic accuracy and consistency in the detection of myocardial perfusion abnormalities.

New approach for quantification of left ventricular function from low-dose gated bloodpool SPECT: Validation and comparison with conventional methods in patients.

BACKGROUND: Planar equilibrium radionuclide angiocardiography (ERNA) has been used as the gold standard for assessment of left ventricular (LV) function for over three decades. However, this imaging modality has recently gained less favor due to growing concerns about radiation exposure. We developed a novel approach that involves integrating short axis slices of gated bloodpool SPECT for quantification of LV function with improved signal-to-noise ratio and reduced radioactive dose while maintaining image quality and quantitative precision. METHODS: Twenty patients referred for ERNA underwent standard in vitro 99mTc-labeling of red blood cells (RBC), and were initially imaged following a low-dose (~ 8 mCi) injection using a dedicated cardiac SPECT camera, and then had planar imaging following a high-dose (~ 25 mCi) injection. Four different quantification methods were utilized to assess the LV function and were compared for quantitative precision and inter-observer reproducibility of the quantitative assessments. RESULTS: The Yale method resulted in the most consistent assessment of LV function compared with the gold standard high-dose ERNA method, along with excellent inter-observer reproducibility. CONCLUSIONS: The new low-dose 99mTc-RBC imaging method provides precise quantification of LV function with a greater than 67% reduction in dose and may potentially improve assessment of regional function.

Quantification of myocardial blood flow (MBF) and reserve (MFR) incorporated with a novel segmentation approach: Assessments of quantitative precision and the lower limit of normal MBF and MFR in patients.

BACKGROUND: Quantification of myocardial blood flow (MBF) and myocardial flow reserve (MFR) has shown diagnostic and prognostic values for the assessment of coronary artery disease (CAD). This study aimed to evaluate in patients a highly automatic Yale-MQ (myocardial blood flow quantification) software incorporated with a novel image segmentation approach for quantification of global and regional MBF and MFR from dynamic 82Rb cardiac positron emission tomography (PET). METHODS: Global and regional MBFs and MFRs were quantified in 80 patients (18 normal and 62 CAD subjects) by two different observers using the Yale-MQ software. Lower limits of normal (LLN) values and intra- and inter-observer variabilities of MBFs and MFRs were calculated for the assessment of quantitative precision. The Yale-MQ was compared with a commercially available software (Corridor 4DM) being used as a reference. RESULTS: The Yale-MQ method provided precise assessments of LLNs of MBF and MFR. The global and regional MBFs and MFR quantified via Yale-MQ were correlated strongly with those via Corridor4DM (R ≥ 0.867). The intra- and inter-observer variabilities of MBFs and MFRs quantified via Yale-MQ were small (≤ 7.7% for MBFs and ≤ 10.0% for MFRs) with excellent correlations (R ≥ 0.980 for MBFs and R ≥ 0.976 for MFRs). CONCLUSIONS: The new Yale-MQ software associated with the automatic processing scheme provides a highly reproducible clinical tool for precise quantification of MBF and MFR in patients with reliable LLN values.

Deep learning-based attenuation map generation for myocardial perfusion SPECT.

PURPOSE: Attenuation correction using CT transmission scanning increases the accuracy of single-photon emission computed tomography (SPECT) and enables quantitative analysis. Current existing SPECT-only systems normally do not support transmission scanning and therefore scans on these systems are susceptible to attenuation artifacts. Moreover, the use of CT scans also increases radiation dose to patients and significant artifacts can occur due to the misregistration between the SPECT and CT scans as a result of patient motion. The purpose of this study is to develop an approach to estimate attenuation maps directly from SPECT emission data using deep learning methods. METHODS: Both photopeak window and scatter window SPECT images were used as inputs to better utilize the underlying attenuation information embedded in the emission data. The CT-based attenuation maps were used as labels with which cardiac SPECT/CT images of 65 patients were included for training and testing. We implemented and evaluated deep fully convolutional neural networks using both standard training and training using an adversarial strategy. RESULTS: The synthetic attenuation maps were qualitatively and quantitatively consistent with the CT-based attenuation map. The globally normalized mean absolute error (NMAE) between the synthetic and CT-based attenuation maps were 3.60% ± 0.85% among the 25 testing subjects. The SPECT reconstructed images corrected using the CT-based attenuation map and synthetic attenuation map are highly consistent. The NMAE between the reconstructed SPECT images that were corrected using the synthetic and CT-based attenuation maps was 0.26% ± 0.15%, whereas the localized absolute percentage error was 1.33% ± 3.80% in the left ventricle (LV) myocardium and 1.07% ± 2.58% in the LV blood pool. CONCLUSION: We developed a deep convolutional neural network to estimate attenuation maps for SPECT directly from the emission data. The proposed method is capable of generating highly reliable attenuation maps to facilitate attenuation correction for SPECT-only scanners for myocardial perfusion imaging.

SPECT Imaging of 2-D and 3-D Distributed Sources with Near-Field Coded Aperture Collimation: Computer Simulation and Real Data Validation.

The imaging of distributed sources with near-field coded aperture (CA) remains extremely challenging and is broadly considered unsuitable for single-photon emission computerized tomography (SPECT). This study proposes a novel CA SPECT reconstruction approach and evaluates the feasibilities of imaging and reconstructing distributed hot sources and cold lesions using near-field CA collimation and iterative image reconstruction. Computer simulations were designed to compare CA and pinhole collimations in two-dimensional radionuclide imaging. Digital phantoms were created and CA images of the phantoms were reconstructed using maximum likelihood expectation maximization (MLEM). Errors and the contrast-to-noise ratio (CNR) were calculated and image resolution was evaluated. An ex vivo rat heart with myocardial infarction was imaged using a micro-SPECT system equipped with a custom-made CA module and a commercial 5-pinhole collimator. Rat CA images were reconstructed via the three-dimensional (3-D) MLEM algorithm developed for CA SPECT with and without correction for a large projection angle, and 5-pinhole images were reconstructed using the commercial software provided by the SPECT system. Phantom images of CA were markedly improved in terms of image quality, quantitative root-mean-squared error, and CNR, as compared to pinhole images. CA and pinhole images yielded similar image resolution, while CA collimation resulted in fewer noise artifacts. CA and pinhole images of the rat heart were well reconstructed and the myocardial perfusion defects could be clearly discerned from 3-D CA and 5-pinhole SPECT images, whereas 5-pinhole SPECT images suffered from severe noise artifacts. Image contrast of CA SPECT was further improved after correction for the large projection angle used in the rat heart imaging. The computer simulations and small-animal imaging study presented herein indicate that the proposed 3-D CA SPECT imaging and reconstruction approaches worked reasonably well, demonstrating the feasibilities of achieving high sensitivity and high resolution SPECT using near-field CA collimation.

Comparison of the prognostic value between quantification and visual estimation of coronary calcification from attenuation CT in patients undergoing SPECT myocardial perfusion imaging.

We investigated the prognostic utility of visually estimated coronary artery calcification (VECAC) from low dose computed tomography attenuation correction (CTAC) scans obtained during SPECT/CT myocardial perfusion imaging (MPI), and assessed how it compares to coronary artery calcifications (CAC) quantified by calcium score on CTACs (QCAC). From the REFINE SPECT Registry 4,236 patients without prior coronary stenting with SPECT/CT performed at a single center were included (age: 64 ± 12 years, 47% female). VECAC in each coronary artery (left main, left anterior descending, circumflex, and right) were scored separately as 0 (absent), 1 (mild), 2 (moderate), or 3 (severe), yielding a possible score of 0-12 for each patient (overall VECAC grade zero:0, mild:1-2, moderate: 3-5, severe: >5). CAC scoring of CTACs was performed at the REFINE SPECT core lab with dedicated software. VECAC was correlated with categorized QCAC (zero: 0, mild: 1-99, moderate: 100-399, severe: ≥400). A high degree of correlation was observed between VECAC and QCAC, with 73% of VECACs in the same category as QCAC and 98% within one category. There was substantial agreement between VECAC and QCAC (weighted kappa: 0.78 with 95% confidence interval: 0.76-0.79, p < 0.001). During a median follow-up of 25 months, 372 patients (9%) experienced major adverse cardiovascular events (MACE). In survival analysis, both VECAC and QCAC were associated with MACE. The area under the receiver operating characteristic curve for 2-year-MACE was similar for VECAC when compared to QCAC (0.694 versus 0.691, p = 0.70). In conclusion, visual assessment of CAC on low-dose CTAC scans provides good estimation of QCAC in patients undergoing SPECT/CT MPI. Visually assessed CAC has similar prognostic value for MACE in comparison to QCAC.

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.

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.

Deep-Learning-Based Few-Angle Cardiac SPECT Reconstruction Using Transformer.

Convolutional neural networks (CNNs) have been extremely successful in various medical imaging tasks. However, because the size of the convolutional kernel used in a CNN is much smaller than the image size, CNN has a strong spatial inductive bias and lacks a global understanding of the input images. Vision Transformer, a recently emerged network structure in computer vision, can potentially overcome the limitations of CNNs for image-reconstruction tasks. In this work, we proposed a slice-by-slice Transformer network (SSTrans-3D) to reconstruct cardiac SPECT images from 3D few-angle data. To be specific, the network reconstructs the whole 3D volume using a slice-by-slice scheme. By doing so, SSTrans-3D alleviates the memory burden required by 3D reconstructions using Transformer. The network can still obtain a global understanding of the image volume with the Transformer attention blocks. Lastly, already reconstructed slices are used as the input to the network so that SSTrans-3D can potentially obtain more informative features from these slices. Validated on porcine, phantom, and human studies acquired using a GE dedicated cardiac SPECT scanner, the proposed method produced images with clearer heart cavity, higher cardiac defect contrast, and more accurate quantitative measurements on the testing data as compared with a deep U-net.

TAI-GAN: Temporally and Anatomically Informed GAN for Early-to-Late Frame Conversion in Dynamic Cardiac PET Motion Correction.

The rapid tracer kinetics of rubidium-82 (82Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical 82Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.