Automated quantification of myocardial perfusion SPECT using simplified normal limits

Artificial Intelligence-Enhanced Perfusion Scoring Improves the Diagnostic Accuracy of Myocardial Perfusion Imaging

We previously demonstrated that a deep learning (DL) model of myocardial perfusion SPECT imaging improved accuracy for detection of obstructive coronary artery disease (CAD). We aimed to improve the clinical translatability of this artificial intelligence (AI) approach using the results to derive enhanced total perfusion deficit (TPD) and 17-segment summed scores. Methods: We used a cohort of patients undergoing myocardial perfusion imaging within 180 d of invasive coronary angiography. Obstructive CAD was defined as any stenosis of at least 70% or at least 50% in the left main coronary artery. We used per-vessel DL predictions to modulate polar map pixel scores. These transformed polar maps were then used to derive TPD-DL and summed stress score-DL. We compared diagnostic performance using area under the receiver operating characteristic curve (AUC). Results: In the 555 patients held out for testing, the median age was 65 y (interquartile range, 57-73 y), and 381 (69%) were male. Obstructive CAD was present in 329 (59%) patients. The prediction performance for obstructive CAD of stress TPD-DL (AUC, 0.837; 95% CI, 0.804-0.870) was higher than AI prediction alone (AUC, 0.795; 95% CI, 0.758-0.831; P = 0.005) and traditional stress TPD (AUC, 0.737; 95% CI, 0.696-0.778; P < 0.001). Summed stress score-DL had the second highest prediction performance (AUC, 0.822; 95% CI, 0.788-0.857) and higher AUC than traditional quantitative summed stress score (AUC, 0.728; 95% CI, 0.686-0.769; P < 0.001). At a threshold of 5%, the sensitivity and specificity of TPD rose from 72% to 79% and from 62% to 70%, respectively. Conclusion: Integrating AI predictions with traditional quantitative approaches leads to a simplified AI approach, presenting clinicians with familiar measures but operating with higher accuracy than traditional quantitative scoring. This approach may facilitate integration of new AI methods into clinical practice.

FDG PET/CT imaging and circulating biomarkers of inflammation in desmoplakin cardiomyopathy

AIMS

Inflammation has been implicated in the pathogenesis of desmoplakin (DSP) cardiomyopathy, and retrospective studies have described abnormal myocardial fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) findings in symptomatic patients eventually diagnosed with DSP cardiomyopathy. We aimed to prospectively investigate if ambulatory patients with DSP cardiomyopathy had myocardial FDG uptake PET/CT imaging indicative of myocardial inflammation and if they had circulating biomarker evidence of inflammation.

METHODS

We prospectively recruited participants with DSP cardiomyopathy and participants with titin cardiomyopathy as a comparator group. Blood samples for clinical labs and proteomic profiling, myocardial perfusion single-photon emission computed tomography (SPECT) and myocardial FDG PET/CT were obtained for all participants.

RESULTS

Ten participants with DSP cardiomyopathy (median age 36.5 years (28, 60); 80% female; 100% White and non-Hispanic) and four participants with titin cardiomyopathy (median age 55.5 years [38.5, 64]; 50% female; 100% White and non-Hispanic) were recruited. There were no significant differences between the groups in white blood cell count, ESR, hsCRP or hsTn. Three participants with DSP cardiomyopathy and two participants with titin cardiomyopathy had non-specific myocardial FDG uptake on PET/CT. All other participants had no myocardial FDG uptake. Integration of miRNA differential expression and their predicted targets from the differential expression proteomics data identified a total of 11 inverse miRNA-mRNA pairs potentially involved in the regulation of top 20 significantly enriched pathways, including pathways involved in metabolism, inflammasome/inflammatory signalling and cell death/pyroptosis.

CONCLUSIONS

In a group of ambulatory patients with DSP and titin cardiomyopathy, we found no differences in FDG PET/CT findings or clinical circulating biomarkers of inflammation. However, miRNA-seq/proteomics analyses identified several enriched pathways and unique miRNA-protein pairs between DSP and titin cardiomyopathy, including pathways involved in inflammasome/inflammatory signalling. Future work will centre on evaluation during myocarditis-like episodes.

Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction

Low-dose computed tomography attenuation correction (CTAC) scans are used in hybrid myocardial perfusion imaging (MPI) for attenuation correction and coronary calcium scoring, and contain additional anatomic and pathologic information not utilized in clinical assessment. We seek to uncover the full potential of these scans utilizing a holistic artificial intelligence (AI) approach. A multi-structure model segmented 33 structures and quantified 15 radiomics features in each organ in 10,480 patients from 4 sites. Coronary calcium and epicardial fat measures were obtained from separate AI models. The area under the receiver-operating characteristic curves (AUC) for all-cause mortality prediction of the model utilizing MPI, CT, stress test, and clinical features was 0.80 (95% confidence interval [0.74-0.87]), which was higher than for coronary calcium (0.64 [0.57-0.71]) or perfusion (0.62 [0.55-0.70]), with p < 0.001 for both. A comprehensive multimodality approach can significantly improve mortality prediction compared to MPI information alone in patients undergoing hybrid MPI.

Positron Range Correction Helps Enhance the Image Quality of Cardiac 82Rb PET/CT

The image quality and quantitative accuracy of 82Rb myocardial perfusion imaging (MPI) using PET is challenged by the extensive positron range (PR) effects, with the PR of 82Rb being about 7 mm in soft tissues. This study explored the feasibility of applying postacquisition PR correction (PRC) to routine 82Rb PET/CT MPI acquisitions and assessed its impact on diagnostic accuracy and image quality. Methods: We implemented a PRC method adjusted to 82Rb into a vendor-provided reconstruction toolbox, using tissue-specific corrections for soft tissue, bone, and air/lungs. The PRC was evaluated in 2 cohorts: the first comprised 25 healthy volunteers who underwent repeated 82Rb MPI within 2 wk, and the second included 66 patients with known or suspected coronary artery disease. We measured the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) for the volunteer cohort. In the patient cohort, the impact of PRC was evaluated as changes in the area under the receiver operating characteristic curve (AUC), using fractional flow reserve as the gold standard (values < 80% were considered significantly reduced). We calculated AUCs for stress and ischemic total perfusion deficits. Results: In the volunteer cohort, PRC-based reconstructions (standard reconstruction [STD] + PRC) demonstrated significantly improved SNR and CNR compared with STD, with median increases of 22% and 47% for SNR and CNR, respectively (P < 0.05). For the patient cohort, comparable AUCs were reported for STD- versus PRC-based reconstructions (stress total perfusion deficits, 0.84 vs. 0.83 [P = 0.49]; ischemic total perfusion deficits, 0.87 vs. 0.87 [P = 0.80]). Conclusion: PRC significantly enhances SNR and CNR compared with STD without affecting the diagnostic accuracy of the scans. Given the significantly improved image quality, PRC may be recommended for MPI using 82Rb PET/CT clinical-routine-assessment interpretation of TPD.

Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization

BACKGROUND

Coronary artery disease (CAD) has one of the highest mortality rates in humans worldwide. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) provides clinicians with myocardial metabolic information non-invasively. However, there are some limitations to interpreting SPECT images performed by physicians or automatic quantitative approaches. Radiomics analyzes images objectively by extracting quantitative features and can potentially reveal biological characteristics that the human eye cannot detect. However, the reproducibility and repeatability of some radiomic features can be highly susceptible to segmentation and imaging conditions.

PURPOSE

We aimed to assess the reproducibility of radiomic features extracted from uncorrected MPI-SPECT images reconstructed with 15 different settings before and after ComBat harmonization, along with evaluating the effectiveness of ComBat in realigning feature distributions.

MATERIALS AND METHODS

A total of 200 patients (50% normal and 50% abnormal) including rest and stress (without attenuation and scatter corrections) MPI-SPECT images were included. Images were reconstructed using 15 combinations of filter cut-off frequencies, filter orders, filter types, reconstruction algorithms, number of iterations and subsets resulting in 6000 images. Image segmentation was performed on the left ventricle in the first reconstruction for each patient and applied to 14 others. A total of 93 radiomic features were extracted from the segmented area, and ComBat was used to harmonize them. The intraclass correlation coefficient (ICC) and overall concordance correlation coefficient (OCCC) tests were performed before and after ComBat to examine the impact of each parameter on feature robustness and to assess harmonization efficiency. The ANOVA and the Kruskal-Wallis tests were performed to evaluate the effectiveness of ComBat in correcting feature distributions. In addition, the Student's t-test, Wilcoxon rank-sum, and signed-rank tests were implemented to assess the significance level of the impacts made by each parameter of different batches and patient groups (normal vs. abnormal) on radiomic features.

RESULTS

Before applying ComBat, the majority of features (ICC: 82, OCCC: 61) achieved high reproducibility (ICC/OCCC ≥ 0.900) under every batch except Reconstruction. The largest and smallest number of poor features (ICC/OCCC < 0.500) were obtained by IterationSubset and Order batches, respectively. The most reliable features were from the first-order (FO) and gray-level co-occurrence matrix (GLCM) families. Following harmonization, the minimum number of robust features increased (ICC: 84, OCCC: 78). Applying ComBat showed that Order and Reconstruction were the least and the most responsive batches, respectively. The most robust families, in a descending order, were found to be FO, neighborhood gray-tone difference matrix (NGTDM), GLCM, gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), and gray-level dependence matrix (GLDM) under Cut-off, Filter, and Order batches. The Wilcoxon rank-sum test showed that the number of robust features significantly differed under most batches in the Normal and Abnormal groups.

CONCLUSION

The majority of radiomic features show high levels of robustness across different OSEM reconstruction parameters in uncorrected MPI-SPECT. ComBat is effective in realigning feature distributions and enhancing radiomic features reproducibility.

Radiomics Nomogram Derived from Gated Myocardial Perfusion SPECT for Identifying Ischemic Cardiomyopathy

Personalized management involving heart failure (HF) etiology is crucial for better prognoses. We aim to evaluate the utility of a radiomics nomogram based on gated myocardial perfusion imaging (GMPI) in distinguishing ischemic from non-ischemic origins of HF. A total of 172 heart failure patients with reduced left ventricular ejection fraction (HFrEF) who underwent GMPI scan were divided into training (n = 122) and validation sets (n = 50) based on chronological order of scans. Radiomics features were extracted from the resting GMPI. Four machine learning algorithms were used to construct radiomics models, and the model with the best performances were selected to calculate the Radscore. A radiomics nomogram was constructed based on the Radscore and independent clinical factors. Finally, the model performance was validated using operating characteristic curves, calibration curve, decision curve analysis, integrated discrimination improvement values (IDI), and the net reclassification index (NRI). Three optimal radiomics features were used to build a radiomics model. Total perfusion deficit (TPD) was identified as the independent factors of conventional GMPI metrics for building the GMPI model. In the validation set, the radiomics nomogram integrating the Radscore, age, systolic blood pressure, and TPD significantly outperformed the GMPI model in distinguishing ischemic cardiomyopathy (ICM) from non-ischemic cardiomyopathy (NICM) (AUC 0.853 vs. 0.707, p = 0.038). IDI analysis indicated that the nomogram improved diagnostic accuracy by 28.3% compared to the GMPI model in the validation set. By combining radiomics signatures with clinical indicators, we developed a GMPI-based radiomics nomogram that helps to identify the ischemic etiology of HFrEF.

The Updated Registry of Fast Myocardial Perfusion Imaging with Next-Generation SPECT (REFINE SPECT 2.0)

The Registry of Fast Myocardial Perfusion Imaging with Next-Generation SPECT (REFINE SPECT) has been expanded to include more patients and CT attenuation correction imaging. We present the design and initial results from the updated registry. Methods: The updated REFINE SPECT is a multicenter, international registry with clinical data and image files. SPECT images were processed by quantitative software and CT images by deep learning software detecting coronary artery calcium (CAC). Patients were followed for major adverse cardiovascular events (MACEs) (death, myocardial infarction, unstable angina, late revascularization). Results: The registry included scans from 45,252 patients from 13 centers (55.9% male, 64.7 ± 11.8 y). Correlating invasive coronary angiography was available for 3,786 (8.4%) patients. CT attenuation correction imaging was available for 13,405 patients. MACEs occurred in 6,514 (14.4%) patients during a median follow-up of 3.6 y (interquartile range, 2.5-4.8 y). Patients with a stress total perfusion deficit of 5% to less than 10% (unadjusted hazard ratio [HR], 2.42; 95% CI, 2.23-2.62) and a stress total perfusion deficit of at least 10% (unadjusted HR, 3.85; 95% CI, 3.56-4.16) were more likely to experience MACEs. Patients with a deep learning CAC score of 101-400 (unadjusted HR, 3.09; 95% CI, 2.57-3.72) and a CAC of more than 400 (unadjusted HR, 5.17; 95% CI, 4.41-6.05) were at increased risk of MACEs. Conclusion: The REFINE SPECT registry contains a comprehensive set of imaging and clinical variables. It will aid in understanding the value of SPECT myocardial perfusion imaging, leverage hybrid imaging, and facilitate validation of new artificial intelligence tools for improving prediction of adverse outcomes incorporating multimodality imaging.

Prognostic Value of Resting Left Ventricular Sphericity Indexes in Coronary Artery Disease With Preserved Ejection Fraction

BACKGROUND

Adverse left ventricular remodeling is a significant cardiovascular predictor for patients with coronary artery disease and preserved left ventricular ejection fraction (LVEF). However, the remodeling indexes reflecting left ventricular spherization by myocardial perfusion imaging are underexplored.

METHODS AND RESULTS

727 patients (mean age 59.8±13.5 years, 329 women) diagnosed or suspected coronary artery disease with preserved LVEF who underwent resting myocardial perfusion imaging were retrospectively enrolled. The myocardial perfusion imaging findings including the total perfusion deficit and sphericity indexes (shape index (SI) and eccentricity index (EI) obtained from gated (QGS) and non-gated (QPS) images) were collected. Major adverse cardiovascular events (MACE) were followed up for 45.1±22.0 months. All patients were divided into 4 subgroups based on total perfusion deficit at 10% and LVEF at 65%. Univariable comparative analyses were performed in 5 cohorts (all patients and 4 subgroups). Patients who experienced MACE displayed higher SI and/or lower EI (all P<0.05). Kaplan-Meier survival analyses suggested significant differences for SIQPS in all 5 cohorts, for EIQPS and EIQGS in 4 cohorts, and for end-systolic and end-diastolic SIQGS in 3 cohorts (all P<0.05). Multivariate Cox analysis showed that abnormal SI and EI remained statistically significant predictors for MACE after adjusting for total perfusion deficit, LVEF, and other confounding factors.

CONCLUSIONS

For patients diagnosed or suspected of coronary artery disease with preserved or supra-normal LVEF, resting sphericity indexes by myocardial perfusion imaging displayed incremental long-term prognostic value. Among these indicators, SIQPS is particularly promising across different perfusion or preserved functional conditions.

AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans enhances mortality prediction: multicenter study

Background

Computed tomography attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only utilized for attenuation correction and visual calcium estimation. We aimed to develop a novel artificial intelligence (AI)-based approach to obtain volumetric measurements of chest body composition from CTAC scans and evaluate these measures for all-cause mortality (ACM) risk stratification.

Methods

We applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry (four sites), to define chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle (SM), subcutaneous, intramuscular (IMAT), visceral (VAT), and epicardial (EAT) adipose tissues were quantified between automatically-identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation, and indexed volumes were evaluated for predicting ACM, adjusting for established risk factors and 18 other body compositions measures via Cox regression models and Kaplan-Meier curves.

Findings

End-to-end processing time was <2 minutes/scan with no user interaction. Of 9918 patients studied, 5451(55%) were male. During median 2.5 years follow-up, 610 (6.2%) patients died. High VAT, EAT and IMAT attenuation were associated with increased ACM risk (adjusted hazard ratio (HR) [95% confidence interval] for VAT: 2.39 [1.92, 2.96], p<0.0001; EAT: 1.55 [1.26, 1.90], p<0.0001; IMAT: 1.30 [1.06, 1.60], p=0.0124). Patients with high bone attenuation were at lower risk of death as compared to subjects with lower bone attenuation (adjusted HR 0.77 [0.62, 0.95], p=0.0159). Likewise, high SM volume index was associated with a lower risk of death (adjusted HR 0.56 [0.44, 0.71], p<0.0001).

Interpretations

CTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers which can be automatically measured and offer important additional prognostic value.

AI-Defined Cardiac Anatomy Improves Risk Stratification of Hybrid Perfusion Imaging

BACKGROUND

Computed tomography attenuation correction (CTAC) improves perfusion quantification of hybrid myocardial perfusion imaging by correcting for attenuation artifacts. Artificial intelligence (AI) can automatically measure coronary artery calcium (CAC) from CTAC to improve risk prediction but could potentially derive additional anatomic features.

OBJECTIVES

The authors evaluated AI-based derivation of cardiac anatomy from CTAC and assessed its added prognostic utility.

METHODS

The authors considered consecutive patients without known coronary artery disease who underwent single-photon emission computed tomography/computed tomography (CT) myocardial perfusion imaging at 3 separate centers. Previously validated AI models were used to segment CAC and cardiac structures (left atrium, left ventricle, right atrium, right ventricular volume, and left ventricular [LV] mass) from CTAC. They evaluated associations with major adverse cardiovascular events (MACEs), which included death, myocardial infarction, unstable angina, or revascularization.

RESULTS

In total, 7,613 patients were included with a median age of 64 years. During a median follow-up of 2.4 years (IQR: 1.3-3.4 years), MACEs occurred in 1,045 (13.7%) patients. Fully automated AI processing took an average of 6.2 ± 0.2 seconds for CAC and 15.8 ± 3.2 seconds for cardiac volumes and LV mass. Patients in the highest quartile of LV mass and left atrium, LV, right atrium, and right ventricular volume were at significantly increased risk of MACEs compared to patients in the lowest quartile, with HR ranging from 1.46 to 3.31. The addition of all CT-based volumes and CT-based LV mass improved the continuous net reclassification index by 23.1%.

CONCLUSIONS

AI can automatically derive LV mass and cardiac chamber volumes from CT attenuation imaging, significantly improving cardiovascular risk assessment for hybrid perfusion imaging.

Automated vessel-specific coronary artery calcification quantification with deep learning in a large multi-centre registry

AIMS

Vessel-specific coronary artery calcification (CAC) is additive to global CAC for prognostic assessment. We assessed accuracy and prognostic implications of vessel-specific automated deep learning (DL) CAC analysis on electrocardiogram (ECG) gated and attenuation correction (AC) computed tomography (CT) in a large multi-centre registry.

METHODS AND RESULTS

Vessel-specific CAC was assessed in the left main/left anterior descending (LM/LAD), left circumflex (LCX), and right coronary artery (RCA) using a DL model trained on 3000 gated CT and tested on 2094 gated CT and 5969 non-gated AC CT. Vessel-specific agreement was assessed with linear weighted Cohen's Kappa for CAC zero, 1-100, 101-400, and >400 Agatston units (AU). Risk of major adverse cardiovascular events (MACE) was assessed during 2.4 ± 1.4 years follow-up, with hazard ratios (HR) and 95% confidence intervals (CI). There was strong to excellent agreement between DL and expert ground truth for CAC in LM/LAD, LCX and RCA on gated CT [0.90 (95% CI 0.89 to 0.92); 0.70 (0.68 to 0.73); 0.79 (0.77 to 0.81)] and AC CT [0.78 (0.77 to 0.80); 0.60 (0.58 to 0.62); 0.70 (0.68 to 0.71)]. MACE occurred in 242 (12%) undergoing gated CT and 841(14%) of undergoing AC CT. LM/LAD CAC >400 AU was associated with the highest risk of MACE on gated (HR 12.0, 95% CI 7.96, 18.0, P < 0.001) and AC CT (HR 4.21, 95% CI 3.48, 5.08, P < 0.001).

CONCLUSION

Vessel-specific CAC assessment with DL can be performed accurately and rapidly on gated CT and AC CT and provides important prognostic information.

Impact of cardiac size on diagnostic performance of single-photon emission computed tomography myocardial perfusion imaging: insights from the REgistry of Fast Myocardial Perfusion Imaging with NExt generation single-photon emission computed tomography

AIMS

Variation in diagnostic performance of single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) has been observed, yet the impact of cardiac size has not been well characterized. We assessed whether low left ventricular volume influences SPECT MPI's ability to detect obstructive coronary artery disease (CAD) and its interaction with age and sex.

METHODS AND RESULTS

A total of 2066 patients without known CAD (67% male, 64.7 ± 11.2 years) across nine institutions underwent SPECT MPI with solid-state scanners followed by coronary angiography as part of the REgistry of Fast Myocardial Perfusion Imaging with NExt Generation SPECT. Area under receiver-operating characteristic curve (AUC) analyses evaluated the performance of quantitative and visual assessments according to cardiac size [end-diastolic volume (EDV); <20th vs. ≥20th population or sex-specific percentiles], age (<75 vs. ≥75 years), and sex. Significantly decreased performance was observed in patients with low EDV compared with those without (AUC: population 0.72 vs. 0.78, P = 0.03; sex-specific 0.72 vs. 0.79, P = 0.01) and elderly patients compared with younger patients (AUC 0.72 vs. 0.78, P = 0.03), whereas males and females demonstrated similar AUC (0.77 vs. 0.76, P = 0.67). The reduction in accuracy attributed to lower volumes was primarily observed in males (sex-specific threshold: EDV 0.69 vs. 0.79, P = 0.01). Accordingly, a significant decrease in AUC, sensitivity, specificity, and negative predictive value for quantitative and visual assessments was noted in patients with at least two characteristics of low EDV, elderly age, or male sex.

CONCLUSION

Detection of CAD with SPECT MPI is negatively impacted by small cardiac size, most notably in elderly and male patients.

Self-supervised deep representation learning of a foundation transformer model enabling efficient ECG-based assessment of cardiac and coronary function with limited labels

Background: Although deep learning methods have shown great promise for identification of structural and functional cardiac abnormalities using electrocardiographic data, these methods are data hungry, posing a challenge for critically important tasks where ground truth labels are relatively scarce. Impaired coronary microvascular and vasomotor function is difficult to identify with standard clinical methods of cardiovascular testing such as coronary angiography and noninvasive single photon emission tomography (SPECT) myocardial perfusion imaging (MPI). Gold standard data from positron emission tomography (PET) are gaining emphasis in clinical guidelines but are expensive and only available in relatively limited centers. We hypothesized that signals embedded within resting and stress electrocardiograms (ECGs) identify individuals with microvascular and vasomotor dysfunction. Methods: We developed and pretrained a self-supervised foundation vision transformer model using a large database of unlabeled ECG waveforms (N=800,035). We then fine-tuned the foundation model for two clinical tasks: the difficult problem of identifying patients with impaired myocardial flow reserve (AI-MFR), and the relatively easier problem of detecting impaired LVEF (AI-LVEF). A second ECG database was labeled with task-specific annotations derived from quantitative PET MPI (N=4167). Diagnostic accuracy of AI predictions was tested in a holdout set of patients undergoing PET MPI (N=1031). Prognostic evaluation was performed in the PET holdout cohort, as well as independent cohorts of patients undergoing pharmacologic or exercise stress SPECT MPI (N=6635). Results: The diagnostic accuracy of AI-MFR with SSL pretraining increased significantly compared to de novo supervised training (AUROC, sensitivity, specificity: 0.758, 70.1%, 69.4% vs. 0.632, 66.1%, 57.3%, p < 0.0001). SSL pretraining also produced a smaller increase in AI-LVEF accuracy (AUROC, sensitivity, specificity: 0.946, 89.4%, 85.9% vs. 0.918, 87.6%, 82.5%, p < 0.02). Abnormal AI-MFR was found to be significantly associated with mortality risk in all three test cohorts (Hazard Ratio (HR) 2.61 [95% CI 1.83, 3.71], p < 0.0001, PET cohort; HR 2.30 [2.03, 2.61], p < 0.0001, pharmacologic stress SPECT cohort; HR 3.76 [2.36, 5.99], p < 0.0001, exercise stress SPECT cohort). Conclusion: SSL pretraining of a vision transformer foundation model enabled identification of signals predictive of impaired MFR, a hallmark of microvascular and vasomotor dysfunction, and impaired LV function in resting and stress ECG waveforms. These signals are powerful predictors of prognosis in patients undergoing routine noninvasive stress testing and could enable more efficient diagnosis and management of these common conditions.

Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction

Background

While low-dose computed tomography scans are traditionally used for attenuation correction in hybrid myocardial perfusion imaging (MPI), they also contain additional anatomic and pathologic information not utilized in clinical assessment. We seek to uncover the full potential of these scans utilizing a holistic artificial intelligence (AI)-driven image framework for image assessment.

Methods

Patients with SPECT/CT MPI from 4 REFINE SPECT registry sites were studied. A multi-structure model segmented 33 structures and quantified 15 radiomics features for each on CT attenuation correction (CTAC) scans. Coronary artery calcium and epicardial adipose tissue scores were obtained from separate deep-learning models. Normal standard quantitative MPI features were derived by clinical software. Extreme Gradient Boosting derived all-cause mortality risk scores from SPECT, CT, stress test, and clinical features utilizing a 10-fold cross-validation regimen to separate training from testing data. The performance of the models for the prediction of all-cause mortality was evaluated using area under the receiver-operating characteristic curves (AUCs).

Results

Of 10,480 patients, 5,745 (54.8%) were male, and median age was 65 (interquartile range [IQR] 57-73) years. During the median follow-up of 2.9 years (1.6-4.0), 651 (6.2%) patients died. The AUC for mortality prediction of the model (combining CTAC, MPI, and clinical data) was 0.80 (95% confidence interval [0.74-0.87]), which was higher than that of an AI CTAC model (0.78 [0.71-0.85]), and AI hybrid model (0.79 [0.72-0.86]) incorporating CTAC and MPI data (p<0.001 for all).

Conclusion

In patients with normal perfusion, the comprehensive model (0.76 [0.65-0.86]) had significantly better performance than the AI CTAC (0.72 [0.61-0.83]) and AI hybrid (0.73 [0.62-0.84]) models (p<0.001, for all).CTAC significantly enhances AI risk stratification with MPI SPECT/CT beyond its primary role - attenuation correction. A comprehensive multimodality approach can significantly improve mortality prediction compared to MPI information alone in patients undergoing cardiac SPECT/CT.

Caffeine consumed prior to cardiac stress testing may affect diagnostic accuracy of nuclear medicine myocardial imaging of myocardial ischemia: A systematic review and meta-analysis

BACKGROUND

Myocardial perfusion imaging (MPI) is a well-established, non-invasive imaging procedure for the diagnosis and evaluation of patients with known or suspected coronary artery disease. With the increasing use of pharmacologic stress agents in myocardial perfusion imaging, strict preparation, including caffeine abstinence, is required. The aim of this review was to determine the effect of caffeine consumed prior to nuclear cardiac stress testing on the diagnostic accuracy.

METHODS

Medline, Embase and CINAHL were searched from the earliest available time until August 2022. Methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies version 2. Data pertaining to diagnostic accuracy were analysed using meta-analysis where appropriate and overall certainty of evidence evaluated using the Grades of Research, Assessment, Development and Evaluation approach.

RESULTS

Six studies (307 participants) from a yield of 735 articles were identified. Meta-analysis of two studies found no difference in the left ventricular ejection fraction of patients pre and post caffeine consumption (MD -0.31 %, 95% CI -4.32% to 3.7%). Meta-analysis of three studies found there was uncertainty as to whether caffeine consumption affected reversibility (MD -2.16 segments 95% CI -4.61 to 0.28) and descriptive summary of three studies found mixed results for size of stress defects.

CONCLUSION

The low quality evidence synthesized in this systematic review suggests caffeine may affect the diagnostic accuracy in myocardial perfusion imaging for ischemia detection in patients with chest pain and intermediate-to-high risk of coronary artery disease.

AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging

Epicardial adipose tissue (EAT) volume and attenuation are associated with cardiovascular risk, but manual annotation is time-consuming. We evaluated whether automated deep learning-based EAT measurements from ungated computed tomography (CT) are associated with death or myocardial infarction (MI). We included 8781 patients from 4 sites without known coronary artery disease who underwent hybrid myocardial perfusion imaging. Of those, 500 patients from one site were used for model training and validation, with the remaining patients held out for testing (n = 3511 internal testing, n = 4770 external testing). We modified an existing deep learning model to first identify the cardiac silhouette, then automatically segment EAT based on attenuation thresholds. Deep learning EAT measurements were obtained in <2 s compared to 15 min for expert annotations. There was excellent agreement between EAT attenuation (Spearman correlation 0.90 internal, 0.82 external) and volume (Spearman correlation 0.90 internal, 0.91 external) by deep learning and expert segmentation in all 3 sites (Spearman correlation 0.90-0.98). During median follow-up of 2.7 years (IQR 1.6-4.9), 565 patients experienced death or MI. Elevated EAT volume and attenuation were independently associated with an increased risk of death or MI after adjustment for relevant confounders. Deep learning can automatically measure EAT volume and attenuation from low-dose, ungated CT with excellent correlation with expert annotations, but in a fraction of the time. EAT measurements offer additional prognostic insights within the context of hybrid perfusion imaging.

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.

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.

Improved diagnostic accuracy for coronary artery disease detection with quantitative 3D 82Rb PET myocardial perfusion imaging

PURPOSE

To establish requirements for normal databases for quantitative rubidium-82 (82Rb) PET MPI analysis with contemporary 3D PET/CT technology and reconstruction methods for maximizing diagnostic accuracy of total perfusion deficit (TPD), a combined metric of defect extent and severity, versus invasive coronary angiography.

METHODS

In total, 1571 patients with 82Rb PET/CT MPI on a 3D scanner and stress static images reconstructed with and without time-of-flight (TOF) modeling were identified. An additional eighty low pre-test probability of disease (PTP) patients reported as normal were used to form separate sex-stratified and sex-independent iterative and TOF normal databases. 3D normal databases were applied to matched patient reconstructions to quantify TPD. Per-patient and per-vessel performance of 3D versus 2D PET normal databases was assessed with receiver operator characteristic curve analysis. Diagnostic accuracy was evaluated at optimal thresholds established from PTP patients. Results were compared against logistic regression modeling of TPD adjusted for clinical variables, and standard clinical interpretation.

RESULTS

TPD diagnostic accuracy was significantly higher using 3D PET normal databases (per-patient: 80.1% for 3D databases, versus 74.9% and 77.7% for 2D database applied to iterative and TOF images respectively, p < 0.05). Differences in male and female normal distributions for 3D attenuation-corrected reconstructions were not clinically meaningful; therefore, sex-independent databases were used. Logistic regression modeling including TPD demonstrated improved performance over clinical reads.

CONCLUSIONS

Normal databases tailored to 3D PET images provide significantly improved diagnostic accuracy for PET MPI evaluation with automated quantitative TPD. Clinical application of these techniques should be considered to support accurate image interpretation.

Optimizing stress-only myocardial perfusion imaging: a clinical prediction model to improve patient selection

BACKGROUND

Stress-only single photon emission computed tomography myocardial perfusion imaging (MPI) offers numerous advantages in terms of improved workflow, cost and radiation reduction but is currently not widely utilized due to challenges in selecting appropriate patients for this technique.

METHODS

Data from 5959 individuals were used to derive (N = 4018) and validate (N = 1941) a binomial logistic regression model to predict normal stress MPI studies (stress total perfusion deficit  < 4%, ejection fraction ≥ 50%). Model performance was analyzed using receiver operator characteristic curves. A simplified point-scoring system was developed and its impact on imaging workflow was assessed.

RESULTS

Significant predictors of abnormal vs. normal stress MPI included male sex, age > 65 years, cardiomyopathy, congestive heart failure, myocardial infarction, angina, and pharmacological stress. The final model and simplified scoring system were associated with areas under the curve of 0.81 (95% CI 0.79-0.83) and 0.80 (95% CI 0.79-0.82) in the validation group, respectively. Use of the scoring system was estimated to result in a decrease of 56.5% in the number of non-contributory imaging studies acquired with minimal patient rescheduling.

CONCLUSION

A prediction tool derived from simple clinical information can identify candidates for stress-only MPI studies with a beneficial impact on departmental workflow.

Integrated myocardial flow reserve (iMFR) assessment: optimized PET blood flow quantification for diagnosis of coronary artery disease

PURPOSE

Distinguishing obstructive epicardial coronary artery disease (CAD) from microvascular dysfunction and diffuse atherosclerosis would be of immense benefit clinically. However, quantitative measures of absolute myocardial blood flow (MBF) integrate the effects of focal epicardial stenosis, diffuse atherosclerosis, and microvascular dysfunction. In this study, MFR and relative perfusion quantification were combined to create integrated MFR (iMFR) which was evaluated using data from a large clinical registry and an international multi-center trial and validated against invasive coronary angiography (ICA).

METHODS

This study included 1,044 clinical patients referred for 82Rb rest/stress positron emission tomography myocardial perfusion imaging and ICA, along with 231 patients from the Flurpiridaz 301 trial (clinicaltrials.gov NCT01347710). MFR and relative perfusion quantification were combined to create an iMFR map. The incremental value of iMFR was evaluated for diagnosis of obstructive stenosis, adjusted for patient demographics and pre-test probability of CAD. Models for high-risk anatomy (left main or three-vessel disease) were also constructed.

RESULTS

iMFR parameters of focally impaired perfusion resulted in best fitting diagnostic models. Receiver-operating characteristic analysis showed a slight improvement compared to standard quantitative perfusion approaches (AUC 0.824 vs. 0.809). Focally impaired perfusion was also associated with high-risk CAD anatomy (OR 1.40 for extent, and OR 2.40 for decreasing mean MFR). Diffusely impaired perfusion was associated with lower likelihood of obstructive CAD, and, in the absence of transient ischemic dilation (TID), with lower likelihood of high-risk CAD anatomy.

CONCLUSIONS

Focally impaired perfusion extent derived from iMFR assessment is a powerful incremental predictor of obstructive CAD while diffusely impaired perfusion extent can help rule out obstructive and high-risk CAD in the absence of TID.

Integrated myocardial flow reserve (iMFR) assessment: diffuse atherosclerosis and microvascular dysfunction are more strongly associated with mortality than focally impaired perfusion

BACKGROUND AND AIMS

Although treatment of ischemia-causing epicardial stenoses may improve symptoms of ischemia, current evidence does not suggest that revascularization improves survival. Conventional myocardial ischemia imaging does not uniquely identify diffuse atherosclerosis, microvascular dysfunction, or nonobstructive epicardial stenoses. We sought to evaluate the prognostic value of integrated myocardial flow reserve (iMFR), a novel noninvasive approach to distinguish the perfusion impact of focal atherosclerosis from diffuse coronary disease.

METHODS

This study analyzed a large single-center registry of consecutive patients clinically referred for rest-stress myocardial perfusion positron emission tomography. Cox proportional hazards modeling was used to assess the association of two previously reported and two novel perfusion measures with mortality risk: global stress myocardial blood flow (MBF); global myocardial flow reserve (MFR); and two metrics derived from iMFR analysis: the extents of focal and diffusely impaired perfusion.

RESULTS

In total, 6867 patients were included with a median follow-up of 3.4 years [1st-3rd quartiles, 1.9-5.0] and 1444 deaths (21%). Although all evaluated perfusion measures were independently associated with death, diffusely impaired perfusion extent (hazard ratio 2.65, 95%C.I. [2.37-2.97]) and global MFR (HR 2.29, 95%C.I. [2.08-2.52]) were consistently stronger predictors than stress MBF (HR 1.62, 95%C.I. [1.46-1.79]). Focally impaired perfusion extent (HR 1.09, 95%C.I. [1.03-1.16]) was only moderately related to mortality. Diffusely impaired perfusion extent remained a significant independent predictor of death when combined with global MFR (p < 0.0001), providing improved risk stratification (overall net reclassification improvement 0.246, 95%C.I. [0.183-0.310]).

CONCLUSIONS

The extent of diffusely impaired perfusion is a strong independent and additive marker of mortality risk beyond traditional risk factors, standard perfusion imaging, and global MFR, while focally impaired perfusion is only moderately related to mortality.

Myocardial creep and cardiorespiratory motion correction improves diagnostic accuracy of Rubidium-82 cardiac positron emission tomography

AIM

To evaluate the feasibility of retrospectively detecting and correcting periodical (cardiac and respiratory motion) and non-periodical shifts of the myocardial position (myocardial creep) using only the acquired Rubidium-82 positron emission tomography raw (listmode) data.

METHODS

This study comprised 25 healthy participants (median age = 23 years) who underwent repeat rest/adenosine stress Rubidium-82 myocardial perfusion imaging (MPI) and 53 patients (median age = 64 years) considered for revascularization who underwent a single MPI session. All subjects were evaluated for myocardial creep during MPI by assessing the myocardial position every 200 ms. A proposed motion correction protocol, including corrections for cardiorespiratory and creep motion (3xMC), was compared to a guideline-recommended protocol (StandardRecon). For the volunteers, we report test-retest repeatability using standard error of measurements (SEM). For the patient cohort, we evaluated the area under the receiver operating curve (AUC) for both stress and ischemic total perfusion deficits (sTPD and iTPD, respectively) using myocardial ischemia defined as fractional flow reserve values < 0.8 in the relevant coronary segment as the gold standard.

RESULTS

Test-retest repeatability was significantly improved following corrections for myocardial creep (SEM; sTPD: StandardRecon = 2.2, 3xMC = 1.8; iTPD: StandardRecon = 1.6, 3xMC = 1.2). AUC analysis of the ROC curves revealed significant improvements for iTPD measurements following 3xMC [sTPD: StandardRecon = 0.88, 3xMC = 0.92 (P = .21); iTPD: StandardRecon = 0.88, 3xMC = 0.95 (P = .039)].

CONCLUSION

3xMC has the potential to improve the diagnostic accuracy of myocardial MPI obtained from positron emission tomography. Therefore, its use should be considered both in clinical routine and large-scale multicenter studies.

Dose-consistent dynamic SPECT

BACKGROUND

Coronary flow reserve (CFR) values measured by dynamic SPECT systems are typically consistent with other modalities (e.g., PET). However, large discrepancies are often observed for individual patients. Positioning of the region-of-interest (ROI), representing the arterial input function (AIF) could explain some of these discrepancies. We explored the possibility of positioning the ROI in a manner that evaluates its consistency with patient-based injected radiotracer doses.

METHODS

Dose-consistent dynamic SPECT methodology was introduced, and its application was demonstrated in a twenty-patient clinical study. The effect of various ROI positions was investigated and comparison to myocardial perfusion imaging was performed.

RESULTS

Mean AIF ratios were consistent with the injected dose ratios for all examined ROI positions. Good agreement (> 80%) between total perfusion deficit and CFR was found in the detection of obstructive CAD patients for all ROIs considered. However, for individual patients, significant dependence on ROI position was observed (altering CFR by typically 30%). The proposed methodology's uncertainty was evaluated (~ 7%) and found to be smaller than the variability due to choice of ROI position.

CONCLUSION

Dose-consistent dynamic SPECT may contribute to evaluating uncertainty of CFR measurements and may potentially decrease uncertainty by allowing improved ROI positioning for individual patients.

Usefulness of phase analysis on ECG gated single photon emission computed tomography myocardial perfusion imaging

Electrocardiogram (ECG)-gated single photon emission computed tomography myocardial perfusion imaging (GSPECT-MPI) is widely used for assessing coronary artery disease. Phase analysis on GSPECT-MPI can assess left ventricular mechanical dyssynchrony quantitatively on standard GSPECT-MPI alongside myocardial perfusion and function assessment. It has been shown that phase variables by GSPECT-MPI correlate well with tissue Doppler imaging by echocardiography. Main phase variables quantified by GSPECT-MPI are entropy, bandwidth, and phase standard deviation. Although those variables are automatically obtained from several software packages including Quantitative Gated SPECT and Emory Cardiac Toolbox, the methods for their measurement vary in each package. Several studies have shown that phase analysis has predictive value for response to cardiac resynchronization therapy and prognostic value for future adverse cardiac events beyond standard GSPECT-MPI variables. In this review, we summarize the basics of phase analysis on GSPECT-MPI and usefulness of phase analysis in clinical practice.

Unsupervised learning to characterize patients with known coronary artery disease undergoing myocardial perfusion imaging

PURPOSE

Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI).

METHODS

From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%).

RESULTS

Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference).

CONCLUSIONS

Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.

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.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.

Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events

Low-dose ungated CT attenuation correction (CTAC) scans are commonly obtained with SPECT/CT myocardial perfusion imaging. Despite the characteristically low image quality of CTAC, deep learning (DL) can potentially quantify coronary artery calcium (CAC) from these scans in an automatic manner. We evaluated CAC quantification derived with a DL model, including correlation with expert annotations and associations with major adverse cardiovascular events (MACE). Methods: We trained a convolutional long short-term memory DL model to automatically quantify CAC on CTAC scans using 6,608 studies (2 centers) and evaluated the model in an external cohort of patients without known coronary artery disease (n = 2,271) obtained in a separate center. We assessed agreement between DL and expert annotated CAC scores. We also assessed associations between MACE (death, revascularization, myocardial infarction, or unstable angina) and CAC categories (0, 1-100, 101-400, or >400) for scores manually derived by experienced readers and scores obtained fully automatically by DL using multivariable Cox models (adjusted for age, sex, past medical history, perfusion, and ejection fraction) and net reclassification index. Results: In the external testing population, DL CAC was 0 in 908 patients (40.0%), 1-100 in 596 (26.2%), 100-400 in 354 (15.6%), and >400 in 413 (18.2%). Agreement in CAC category by DL CAC and expert annotation was excellent (linear weighted κ, 0.80), but DL CAC was obtained automatically in less than 2 s compared with about 2.5 min for expert CAC. DL CAC category was an independent risk factor for MACE with hazard ratios in comparison to a CAC of zero: CAC of 1-100 (2.20; 95% CI, 1.54-3.14; P < 0.001), CAC of 101-400 (4.58; 95% CI, 3.23-6.48; P < 0.001), and CAC of more than 400 (5.92; 95% CI, 4.27-8.22; P < 0.001). Overall, the net reclassification index was 0.494 for DL CAC, which was similar to expert annotated CAC (0.503). Conclusion: DL CAC from SPECT/CT attenuation maps agrees well with expert CAC annotations and provides a similar risk stratification but can be obtained automatically. DL CAC scores improved classification of a significant proportion of patients as compared with SPECT myocardial perfusion alone.

Texture analysis of SPECT myocardial perfusion provides prognostic value for dilated cardiomyopathy

BACKGROUND

Texture analysis (TA) has demonstrated clinical values in extracting information, quantifying inhomogeneity, evaluating treatment outcomes, and predicting long-term prognosis for cardiac diseases. The aim of this study was to explore whether TA of SPECT myocardial perfusion could contribute to improving the prognosis of dilated cardiomyopathy (DCM) patients.

METHODS

Eighty-eight patients were recruited in our study between 2009 and 2020 who were diagnosed with DCM and underwent single-photon emission tomography myocardial perfusion imaging (SPECT MPI). Forty TA features were obtained from quantitative analysis of SPECT imaging in subjects with myocardial perfusion at rest. All patients were divided into two groups: the all-cause death group and the survival group. The prognostic value of texture parameters was assessed by Cox regression and Kaplan-Meier analysis.

RESULTS

Twenty-five all-cause deaths (28.4%) were observed during the follow-up (39.2±28.7 months). Compared with the survival group, NT-proBNP and total perfusion deficit (TPD) were higher and left ventricular ejection fraction (LVEF) was lower in the all-cause death group. In addition, 26 out of 40 texture parameters were significantly different between the two groups. Univariate Cox regression analysis revealed that NT-proBNP, LVEF, and 25 texture parameters were significantly associated with all-cause death. The multivariate Cox regression analysis showed that low gray-level emphasis (LGLE) (P = 0.010, HR = 4.698, 95% CI 1.457-15.145) and long-run low gray-level emphasis (LRLGE) (P =0.002, HR = 6.085, 95% CI 1.906-19.422) were independent predictors of the survival outcome. When added to clinical parameters, LVEF, TPD, and TA parameters, including LGLE and LRLGE, were incrementally associated with all-cause death (global chi-square statistic of 26.246 vs. 33.521; P = 0.028, global chi-square statistic of 26.246 vs. 34.711; P = 0.004).

CONCLUSION

TA based on gated SPECT MPI could discover independent prognostic predictors of all-cause death in medically treated patients with DCM. Moreover, TA parameters, including LGLE and LRLGE, independent of the total perfusion deficit of the cardiac myocardium, appeared to provide incremental prognostic value for DCM patients.

External validation of the CRAX2MACE model

BACKGROUND

Single-photon emission computed tomography (SPECT) myocardial perfusion is frequently used to predict risk of major adverse cardiovascular events (MACE). We performed an external validation of the CRAX2MACE score, developed to estimate 2-year risk of MACE in patients with suspected coronary artery disease (CAD).

METHODS

Patients who underwent clinically indicated SPECT with available follow-up for MACE were included (N = 2,985). The prediction performance for MACE (revascularization, myocardial infarction, or death) within 2 years for CRAX2MACE was compared with stress and ischemic total perfusion deficit (TPD) using area under the receiver operating characteristic curve (AUC). Calibration was assessed with calibration plots, Brier score, and the Hosmer-Lemeshow test.

RESULTS

MACE occurred within 2 years in 243 (8.1%) patients. The AUC for CRAX2MACE (0.710, 95% CI 0.677-0.743) was significantly higher compared to stress TPD (AUC 0.669, 95% CI 0.632-0.706, P = .010) and ischemic TPD (AUC 0.664, 95% CI 0.627-0.700, P < .001). The model had acceptable goodness-of-fit (P = .103) and was well-calibrated with Brier score of 0.071.

CONCLUSION

CRAX2MACE had higher predictive performance for 2-year MACE than quantitative perfusion in an external population. The current model is simple to use and could be implemented to assist physicians when estimating patient risk.

Anthropomorphic cardiac phantom for dynamic SPECT

BACKGROUND

As myocardial blood flow measurement (MBF) in SPECT systems became recently available, significant effort has been devoted to its validation. For that purpose, we have developed a cardiac phantom that is able to mimic physiological radiotracer variation in the left ventricle cavity and in the myocardium, while performing beating-like motion. The new phantom is integrated inside a standard anthropomorphic torso allowing a realistic tissue attenuation and gamma-ray scattering METHODS AND RESULTS: A mechanical cardiac phantom was integrated in a commercially available anthropomorphic torso. Using a GE Discovery 530c SPECT, measurements were performed. It was found that gamma-ray attenuation effects are significant and limit the MBF measurements to global/three-vessel resolution. Dynamic SPECT experiments were performed to validate MBF accuracy and showed mean relative error of 14%. Finally, the effect of varying radiotracer dose on the accuracy of dynamic SPECT was studied CONCLUSIONS: A dynamic cardiac phantom has been developed and successfully integrated in a standard SPECT torso. A good agreement was found between SPECT-reported MBF values and the expected results. Despite increased noise-to-signal ratio when radiotracer doses were reduced, MBF uncertainty did not increase significantly down to very low doses, thanks to the temporal integration of the activity during the measurement.

Deep Learning-Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT

To improve diagnostic accuracy, myocardial perfusion imaging (MPI) SPECT studies can use CT-based attenuation correction (AC). However, CT-based AC is not available for most SPECT systems in clinical use, increases radiation exposure, and is impacted by misregistration. We developed and externally validated a deep-learning model to generate simulated AC images directly from non-AC (NC) SPECT, without the need for CT. Methods: SPECT myocardial perfusion imaging was performed using 99mTc-sestamibi or 99mTc-tetrofosmin on contemporary scanners with solid-state detectors. We developed a conditional generative adversarial neural network that applies a deep learning model (DeepAC) to generate simulated AC SPECT images. The model was trained with short-axis NC and AC images performed at 1 site (n = 4,886) and was tested on patients from 2 separate external sites (n = 604). We assessed the diagnostic accuracy of the stress total perfusion deficit (TPD) obtained from NC, AC, and DeepAC images for obstructive coronary artery disease (CAD) with area under the receiver-operating-characteristic curve. We also quantified the direct count change among AC, NC, and DeepAC images on a per-voxel basis. Results: DeepAC could be obtained in less than 1 s from NC images; area under the receiver-operating-characteristic curve for obstructive CAD was higher for DeepAC TPD (0.79; 95% CI, 0.72-0.85) than for NC TPD (0.70; 95% CI, 0.63-0.78; P < 0.001) and similar to AC TPD (0.81; 95% CI, 0.75-0.87; P = 0.196). The normalcy rate in the low-likelihood-of-coronary-disease population was higher for DeepAC TPD (70.4%) and AC TPD (75.0%) than for NC TPD (54.6%, P < 0.001 for both). The positive count change (increase in counts) was significantly higher for AC versus NC (median, 9.4; interquartile range, 6.0-14.2; P < 0.001) than for AC versus DeepAC (median, 2.4; interquartile range, 1.3-4.2). Conclusion: In an independent external dataset, DeepAC provided improved diagnostic accuracy for obstructive CAD, as compared with NC images, and this accuracy was similar to that of actual AC. DeepAC simplifies the task of artifact identification for physicians, avoids misregistration artifacts, and can be performed rapidly without the need for CT hardware and additional acquisitions.

Multi-center, multi-vendor validation of deep learning-based attenuation correction in SPECT MPI: data from the international flurpiridaz-301 trial

PURPOSE

Although SPECT myocardial perfusion imaging (MPI) is susceptible to artifacts from soft tissue attenuation, most scans are performed without attenuation correction. Deep learning-based attenuation corrected (DLAC) polar maps improved diagnostic accuracy for detection of coronary artery disease (CAD) beyond non-attenuation-corrected (NAC) polar maps in a large single center study. However, the generalizability of this approach to other institutions with different scanner models and protocols is uncertain. In this study, we evaluated the diagnostic performance of DLAC compared to NAC for detection of CAD as defined by invasive coronary angiography (ICA) in a large multi-center trial.

METHODS

During the phase 3 flurpiridaz multi-center diagnostic clinical trial, conducted over 74 international sites, patients with known or suspected CAD who were referred for a clinically indicated ICA were enrolled. Using receiver operating characteristic (ROC) analysis, we evaluated the detectability of obstructive CAD, defined by quantitative coronary angiography by a core laboratory, using total perfusion deficit (TPD) as an integrated measure of defect extent and severity on DLAC polar maps compared to NAC polar maps. This was also compared against the visual scoring of three expert core lab readers.

RESULTS

Out of 755 patients, 722 (69% male) had evaluable SPECT and ICA for this study. ROC analysis demonstrated significant improvement in detecting per-patient obstructive CAD with DLAC over NAC with area under the curve (AUC) of 0.752 (95% CI: 0.711-0.792) for DLAC compared to 0.717 (0.675-0.759) for NAC (p value = 0.016). Compared to the consensus of expert readers AUC = 0.743 (0.701-0.784), DLAC was comparable (p value = 0.913), whereas NAC underperformed (p value = 0.051).

CONCLUSION

DL-based attenuation correction improves diagnostic performance of SPECT MPI for detecting CAD in data from a large multi-center clinical trial regardless of SPECT camera model or protocol.

TRIAL REGISTRATION

A Phase 3 Multi-center Study to Assess PET Imaging of Flurpiridaz F 18 Injection in Patients With CAD, ClinicalTrials.gov Identifier: NCT01347710, registered on 4 May 2011. https://clinicaltrials.gov/ct2/show/study/NCT01347710.

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.

Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning

BACKGROUND

Myocardial perfusion imaging (MPI) is frequently used to provide risk stratification, but methods to improve the accuracy of these predictions are needed.

OBJECTIVES

The authors developed an explainable deep learning (DL) model (HARD MACE [major adverse cardiac events]-DL) for the prediction of death or nonfatal myocardial infarction (MI) and validated its performance in large internal and external testing groups.

METHODS

Patients undergoing single-photon emission computed tomography MPI were included, with 20,401 patients in the training and internal testing group (5 sites) and 9,019 in the external testing group (2 different sites). HARD MACE-DL uses myocardial perfusion, motion, thickening, and phase polar maps combined with age, sex, and cardiac volumes. The primary outcome was all-cause mortality or nonfatal MI. Prognostic accuracy was evaluated using area under the receiver-operating characteristic curve (AUC).

RESULTS

During internal testing, patients with normal perfusion and elevated HARD MACE-DL risk were at higher risk than patients with abnormal perfusion and low HARD MACE-DL risk (annualized event rate, 2.9% vs 1.2%; P < 0.001). Patients in the highest quartile of HARD MACE-DL score had an annual rate of death or MI (4.8%) 10-fold higher than patients in the lowest quartile (0.48% per year). In external testing, the AUC for HARD MACE-DL (0.73; 95% CI: 0.71-0.75) was higher than a logistic regression model (AUC: 0.70), stress total perfusion deficit (TPD) (AUC: 0.65), and ischemic TPD (AUC: 0.63; all P < 0.01). Calibration, a measure of how well predicted risk matches actual risk, was excellent in both groups (Brier score, 0.079 for internal and 0.070 for external).

CONCLUSIONS

The DL model predicts death or MI directly from MPI, by estimating patient-level risk with good calibration and improved accuracy compared with traditional quantitative approaches. The model incorporates mechanisms to explain to the physician which image regions contribute to the adverse event prediction.

Polar map-free 3D deep learning algorithm to predict obstructive coronary artery disease with myocardial perfusion CZT-SPECT

PURPOSE

Deep learning (DL) models have been shown to outperform total perfusion deficit (TPD) quantification in predicting obstructive coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, previously published methods have depended on polar maps, required manual correction, and normal database. In this study, we propose a polar map-free 3D DL algorithm to predict obstructive disease.

METHODS

We included 1861 subjects who underwent MPI using cadmium-zinc-telluride camera and subsequent coronary angiography. The subjects were divided into parameterization and external validation groups. We implemented a fully automatic algorithm to segment myocardium, perform registration, and apply normalization. We further flattened the image based on spherical coordinate system transformation. The proposed model consisted of a component to predict patent arteries and a component to predict disease in each vessel. The model was cross-validated in the parameterization group, and then further tested using the external validation group. The performance was assessed by area under receiver operating characteristic curves (AUCs) and compared with TPD.

RESULTS

Our algorithm preprocessed all images accurately as confirmed by visual inspection. In patient-based analysis, the AUC of the proposed model was significantly higher than that for stress-TPD (0.84 vs 0.76, p < 0.01). In vessel-based analysis, the proposed model also outperformed regional stress-TPD (AUC = 0.80 vs 0.72, p < 0.01). The addition of quantitative images did not improve the performance.

CONCLUSIONS

Our proposed polar map-free 3D DL algorithm to predict obstructive CAD from MPI outperformed TPD and did not require manual correction or a normal database.

Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion SPECT images

PURPOSE

Artificial intelligence (AI) has high diagnostic accuracy for coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, when trained using high-risk populations (such as patients with correlating invasive testing), the disease probability can be overestimated due to selection bias. We evaluated different strategies for training AI models to improve the calibration (accurate estimate of disease probability), using external testing.

METHODS

Deep learning was trained using 828 patients from 3 sites, with MPI and invasive angiography within 6 months. Perfusion was assessed using upright (U-TPD) and supine total perfusion deficit (S-TPD). AI training without data augmentation (model 1) was compared to training with augmentation (increased sampling) of patients without obstructive CAD (model 2), and patients without CAD and TPD < 2% (model 3). All models were tested in an external population of patients with invasive angiography within 6 months (n = 332) or low likelihood of CAD (n = 179).

RESULTS

Model 3 achieved the best calibration (Brier score 0.104 vs 0.121, p < 0.01). Improvement in calibration was particularly evident in women (Brier score 0.084 vs 0.124, p < 0.01). In external testing (n = 511), the area under the receiver operating characteristic curve (AUC) was higher for model 3 (0.930), compared to U-TPD (AUC 0.897) and S-TPD (AUC 0.900, p < 0.01 for both).

CONCLUSION

Training AI models with augmentation of low-risk patients can improve calibration of AI models developed to identify patients with CAD, allowing more accurate assignment of disease probability. This is particularly important in lower-risk populations and in women, where overestimation of disease probability could significantly influence down-stream patient management.

Semi-quantitative assessment of ischemia with rubidium-82 PET myocardial perfusion imaging

PURPOSE

Semi-quantitative scores can be used as an adjunct to visual assessment in rubidium-82 positron emission tomography (82Rb PET). The semi-quantitative cut-off values used in 82Rb PET are derived from single-photon emission computed tomography (SPECT). It is unknown whether these cut-off values can be extrapolated to 82Rb PET. We compared the semi-quantitative with the visual assessment of ischemia and determined which summed difference score (SDS) score predicts ischemia best.

METHODS

We included 108 patients who underwent 82Rb PET imaging and performed visual and semi-quantitative assessment. A scan with a SDS ≥ 2 and a summed stress score (SSS) ≥ 4 was considered to demonstrate ischemia. We compared the semi-quantitative with the visual assessment.

RESULTS

41 (38%) Normal scans, and 67 (62%) scans with ischemia and/or an irreversible defect were included. The semi-quantitative assessment showed ischemia more often than the visual assessment (51% vs 29%, P < .001). Patients with a low or intermediate pre-test probability of coronary artery disease (CAD) and a SDS < 4 did not demonstrate ischemia by visual assessment.

CONCLUSION

Semi-quantitative assessment in 82Rb PET imaging clearly demonstrates the presence of ischemia. Ischemia is unlikely in patients with low and intermediate pre-test probability of CAD and a SDS < 4.

Semi-quantitative assessment of ischemia with rubidium-82 PET myocardial perfusion imaging

PURPOSE

Semi-quantitative scores can be used as an adjunct to visual assessment in rubidium-82 positron emission tomography (⁸²Rb PET). The semi-quantitative cut-off values used in ⁸²Rb PET are derived from single-photon emission computed tomography (SPECT). It is unknown whether these cut-off values can be extrapolated to ⁸²Rb PET. We compared the semi-quantitative with the visual assessment of ischemia and determined which summed difference score (SDS) score predicts ischemia best.

METHODS

We included 108 patients who underwent ⁸²Rb PET imaging and performed visual and semi-quantitative assessment. A scan with a SDS ≥ 2 and a summed stress score (SSS) ≥ 4 was considered to demonstrate ischemia. We compared the semi-quantitative with the visual assessment.

RESULTS

41 (38%) Normal scans, and 67 (62%) scans with ischemia and/or an irreversible defect were included. The semi-quantitative assessment showed ischemia more often than the visual assessment (51% vs 29%, P < .001). Patients with a low or intermediate pre-test probability of coronary artery disease (CAD) and a SDS < 4 did not demonstrate ischemia by visual assessment.

CONCLUSION

Semi-quantitative assessment in ⁸²Rb PET imaging clearly demonstrates the presence of ischemia. Ischemia is unlikely in patients with low and intermediate pre-test probability of CAD and a SDS < 4.

Regional myocardial perfusion imaging in predicting vessel-related outcome: interplay between the perfusion results and angiographic findings

BACKGROUND

Despite myocardial perfusion imaging (MPI) by cadmium-zinc-telluride (CZT) single-photon emission computed tomography (SPECT) camera is largely used in the diagnosis and risk stratification of patients with suspected or known coronary artery disease (CAD), no data are available on the prognostic value of a regional MPI evaluation. We evaluated the prognostic value of regional MPI by the CZT camera in predicting clinical outcomes at the vessel level in patients with available angiographic data.

METHODS AND RESULTS

Five hundred and forty-one subjects with suspected or known CAD referred to 99mTc-sestamibi gated CZT-SPECT cardiac imaging and with available angiographic data were studied. Both regional total perfusion deficit (TPD) and ischemic TPD (ITPD) were calculated separately for each vascular territory (left anterior descending, left circumflex, and right coronary artery). The outcome end points were cardiac death, target vessel-related myocardial infarction, or late coronary revascularization. The prevalence of CAD ≥ 50%, regional stress TPD, and regional ITPD was significantly higher in vessels with events as compared to those without (both P < 0.001). The receiver operating characteristics area under the curve for regional ITPD for the identification of vessel-related events was 0.81 (95% confidence interval 0.75-0.86). An ITPD value of 2.0% provided the best trade-off for identifying the vessel-related event. At multivariable analysis, both CAD ≥ 50% and ITPD ≥ 2.0% resulted in independent predictors of events.

CONCLUSIONS

Regional myocardial perfusion assessed by the CZT camera demonstrated good reliability in predicting vessel-related events in patients with suspected or known CAD.

Machine learning to predict abnormal myocardial perfusion from pre-test features

BACKGROUND

Accurately predicting which patients will have abnormal perfusion on MPI based on pre-test clinical information may help physicians make test selection decisions. We developed and validated a machine learning (ML) model for predicting abnormal perfusion using pre-test features.

METHODS

We included consecutive patients who underwent SPECT MPI, with 20,418 patients from a multi-center (5 sites) international registry in the training population and 9019 patients (from 2 separate sites) in the external testing population. The ML (extreme gradient boosting) model utilized 30 pre-test features to predict the presence of abnormal myocardial perfusion by expert visual interpretation.

RESULTS

In external testing, the ML model had higher prediction performance for abnormal perfusion (area under receiver-operating characteristic curve [AUC] 0.762, 95% CI 0.750-0.774) compared to the clinical CAD consortium (AUC 0.689) basic CAD consortium (AUC 0.657), and updated Diamond-Forrester models (AUC 0.658, p < 0.001 for all). Calibration (validation of the continuous risk prediction) was superior for the ML model (Brier score 0.149) compared to the other models (Brier score 0.165 to 0.198, all p < 0.001).

CONCLUSION

ML can predict abnormal myocardial perfusion using readily available pre-test information. This model could be used to help guide physician decisions regarding non-invasive test selection.

Effect of changes in perfusion defect size during serial stress myocardial perfusion imaging on cardiovascular outcomes in patients treated with primary percutaneous coronary intervention after myocardial infarction

BACKGROUND

We evaluated the prognostic value of changes in perfusion defect size (PDS) on serial MPS in patients treated with primary percutaneous coronary intervention (PCI) after acute myocardial infarction (AMI).

METHODS

We enrolled 112 patients treated with primary PCI after AMI who underwent two stress MPS within 1 month and after 6 months. Improvement in PDS was defined as a reduction ≥5%. Remodeling was defined as an increase in left ventricular (LV) end-diastolic volume index ≥20%. Cardiac events included cardiac death, nonfatal MI, unstable angina, repeated revascularization, and heart failure.

RESULTS

During a median follow-up of 86 months, 22 events occurred. Event rate was higher (P < .01) in patients with worsening of PDS compared to those with unchanged or improved PDS. Moreover, patients with remodeling had a higher (P < .001) event rate compared to those without. At Cox analysis, worsening of PDS and remodeling resulted independent predictors of events (both P < .01). Patients with both worsening of PDS and remodeling had the worst event-free survival (P <.001).

CONCLUSION

In patients treated with primary PCI after AMI, worsening of PDS and remodeling are associated to higher risk of events at long-term follow-up. Gated stress MPS improves risk stratification in these patients.

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.

Quantitative myocardial perfusion SPECT/CT for the assessment of myocardial tracer uptake in patients with three-vessel coronary artery disease: Initial experiences and results

BACKGROUND

To evaluate quantitative myocardial perfusion SPECT/CT datasets for routine clinical reporting and the assessment of myocardial tracer uptake in patients with severe TVCAD.

METHODS

MPS scans were reconstructed as quantitative SPECT datasets using CTs from internal (SPECT/CT, Q_INT) and external (PET/CT, Q_EXT) sources for attenuation correction. TPD was calculated and compared to the TPD from non-quantitative SPECT datasets of the same patients. SUVmax, SUVpeak, and SUVmean were compared between Q_INT and Q_EXT SPECT datasets. Global SUVmax and SUVpeak were compared between patients with and without TVCAD.

RESULTS

Quantitative reconstruction was feasible. TPD showed an excellent correlation between quantitative and non-quantitative SPECT datasets. SUVmax, SUVpeak, and SUVmean showed an excellent correlation between Q_INT and Q_EXT SPECT datasets, though mean SUVmean differed significantly between the two groups. Global SUVmax and SUVpeak were significantly reduced in patients with TVCAD.

CONCLUSIONS

Absolute quantification of myocardial tracer uptake is feasible. The method seems to be robust and principally suitable for routine clinical reporting. Quantitative SPECT might become a valuable tool for the assessment of severe coronary artery disease in a setting of balanced ischemia, where potentially life-threatening conditions might otherwise go undetected.

Differences in Prognostic Value of Myocardial Perfusion Single-Photon Emission Computed Tomography Using High-Efficiency Solid-State Detector Between Men and Women in a Large International Multicenter Study

BACKGROUND

Semiquantitative assessment of stress myocardial perfusion defect has been shown to have greater prognostic value for prediction of major adverse cardiac events (MACE) in women compared with men in single-center studies with conventional single-photon emission computed tomography (SPECT) cameras. We evaluated sex-specific difference in the prognostic value of automated quantification of ischemic total perfusion defect (ITPD) and the interaction between sex and ITPD using high-efficiency SPECT cameras with solid-state detectors in an international multicenter imaging registry (REFINE SPECT [Registry of Fast Myocardial Perfusion Imaging With Next-Generation SPECT]).

METHODS

Rest and exercise or pharmacological stress SPECT myocardial perfusion imaging were performed in 17 833 patients from 5 centers. MACE was defined as the first occurrence of death or myocardial infarction. Total perfusion defect (TPD) at rest, stress, and ejection fraction were quantified automatically by software. ITPD was given by stressTPD-restTPD. Cox proportional hazards model was used to evaluate the association between ITPD versus MACE-free survival and expressed as a hazard ratio.

RESULTS

In 10614 men and 7219 women, with a median follow-up of 4.75 years (interquartile range, 3.7-6.1), there were 1709 MACE. In a multivariable Cox model, after adjusting for revascularization and other confounding variables, ITPD was associated with MACE (hazard ratio, 1.08 [95% CI, 1.05-1.1]; P<0.001). There was an interaction between ITPD and sex (P<0.001); predicted survival for ITPD<5% was worse among men compared to women, whereas survival among women was worse than men for ITPD≥5%, P<0.001.

CONCLUSIONS

In the international, multicenter REFINE SPECT registry, moderate and severe ischemia as quantified by ITPD from high-efficiency SPECT is associated with a worse prognosis in women compared with men.

Prognostic value of early left ventricular ejection fraction reserve during regadenoson stress solid-state SPECT-MPI

BACKGROUND

We hypothesized early post-stress left ventricular ejection fraction reserve (EFR) on solid-state-SPECT is associated with major cardiac adverse events (MACE).

METHODS

151 patients (70 ± 12 years, male 50%) undergoing same-day rest/regadenoson stress 99mTc-sestamibi solid-state SPECT were followed for MACE. Rest imaging was performed in the upright and supine positions. Early stress imaging was started 2 minutes after the regadenoson injection in the supine position and followed by late stress acquisition in the upright position. Total perfusion deficit (TPD) and functional parameters were quantified automatically. EFR, ∆end-diastolic volume (EDV), and end-systolic volume (ESV) were calculated as the difference between stress and rest values in the same position. EFR < 0%, ∆EDV ≥ 5 ml, or ∆ESV ≥ 5 ml was defined as abnormal.

RESULTS

During the follow-up (mean 3.2 years), 28 MACE occurred (19%). In Kaplan-Meier analysis, there was a significantly decreased event-free survival in patients with early EFR < 0% (P = 0.004). Similarly, there was a decreased event-free survival in patients with ∆ESV ≥ 5 ml at early stress (P = 0.003). However, EFR, ∆EDV, and ∆ESV at late stress were not associated with MACE-free survival. Cox proportional hazards model adjusting for clinical information and stress TPD demonstrated that EFR, ∆EDV, and ∆ESV at early stress were significantly associated with MACE (P < 0.05 for all).

CONCLUSIONS

Reduced early post-stress EFR on vasodilator stress solid-state SPECT is associated with MACE.

Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry

BACKGROUND

Machine learning (ML) models can improve prediction of major adverse cardiovascular events (MACE), but in clinical practice some values may be missing. We evaluated the influence of missing values in ML models for patient-specific prediction of MACE risk.

METHODS

We included 20,179 patients from the multicenter REFINE SPECT registry with MACE follow-up data. We evaluated seven methods for handling missing values: 1) removal of variables with missing values (ML-Remove), 2) imputation with median and unique category for continuous and categorical variables, respectively (ML-Traditional), 3) unique category for missing variables (ML-Unique), 4) cluster-based imputation (ML-Cluster), 5) regression-based imputation (ML-Regression), 6) missRanger imputation (ML-MR), and 7) multiple imputation (ML-MICE). We trained ML models with full data and simulated missing values in testing patients. Prediction performance was evaluated using area under the receiver-operating characteristic curve (AUC) and compared with a model without missing values (ML-All), expert visual diagnosis and total perfusion deficit (TPD).

RESULTS

During mean follow-up of 4.7 ± 1.5 years, 3,541 patients experienced at least one MACE (3.7% annualized risk). ML-All (reference model-no missing values) had AUC 0.799 for MACE risk prediction. All seven models with missing values had lower AUC (ML-Remove: 0.778, ML-MICE: 0.774, ML-Cluster: 0.771, ML-Traditional: 0.771, ML-Regression: 0.770, ML-MR: 0.766, and ML-Unique: 0.766; p < 0.01 for ML-Remove vs remaining methods). Stress TPD (AUC 0.698) and visual diagnosis (0.681) had the lowest AUCs.

CONCLUSION

Missing values reduce the accuracy of ML models when predicting MACE risk. Removing variables with missing values and retraining the model may yield superior patient-level prediction performance.

Clinical Deployment of Explainable Artificial Intelligence of SPECT for Diagnosis of Coronary Artery Disease

BACKGROUND

Explainable artificial intelligence (AI) can be integrated within standard clinical software to facilitate the acceptance of the diagnostic findings during clinical interpretation.

OBJECTIVES

This study sought to develop and evaluate a novel, general purpose, explainable deep learning model (coronary artery disease-deep learning [CAD-DL]) for the detection of obstructive CAD following single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI).

METHODS

A total of 3,578 patients with suspected CAD undergoing SPECT MPI and invasive coronary angiography within a 6-month interval from 9 centers were studied. CAD-DL computes the probability of obstructive CAD from stress myocardial perfusion, wall motion, and wall thickening maps, as well as left ventricular volumes, age, and sex. Myocardial regions contributing to the CAD-DL prediction are highlighted to explain the findings to the physician. A clinical prototype was integrated using a standard clinical workstation. Diagnostic performance by CAD-DL was compared to automated quantitative total perfusion deficit (TPD) and reader diagnosis.

RESULTS

In total, 2,247 patients (63%) had obstructive CAD. In 10-fold repeated testing, the area under the receiver-operating characteristic curve (AUC) (95% CI) was higher according to CAD-DL (AUC: 0.83 [95% CI: 0.82-0.85]) than stress TPD (AUC: 0.78 [95% CI: 0.77-0.80]) or reader diagnosis (AUC: 0.71 [95% CI: 0.69-0.72]; P < 0.0001 for both). In external testing, the AUC in 555 patients was higher according to CAD-DL (AUC: 0.80 [95% CI: 0.76-0.84]) than stress TPD (AUC: 0.73 [95% CI: 0.69-0.77]) or reader diagnosis (AUC: 0.65 [95% CI: 0.61-0.69]; P < 0.001 for all). The present model can be integrated within standard clinical software and generates results rapidly (<12 seconds on a standard clinical workstation) and therefore could readily be incorporated into a typical clinical workflow.

CONCLUSIONS

The deep-learning model significantly surpasses the diagnostic accuracy of standard quantitative analysis and clinical visual reading for MPI. Explainable artificial intelligence can be integrated within standard clinical software to facilitate acceptance of artificial intelligence diagnosis of CAD following MPI.