Quantification of Aortic Valve Fibrotic and Calcific Tissue from CTA: Prospective Comparison with Histology.

Background Quantifying the fibrotic and calcific composition of the aortic valve at CT angiography (CTA) can be useful for assessing disease severity and outcomes of patients with aortic stenosis (AS); however, it has not yet been validated against quantitative histologic findings. Purpose To compare quantification of aortic valve fibrotic and calcific tissue composition at CTA versus histologic examination. Materials and Methods This prospective study included patients who underwent CTA before either surgical aortic valve replacement for AS or orthotopic heart transplant (controls) at two centers between January 2022 and April 2023. At CTA, fibrotic and calcific tissue composition were quantified using automated Gaussian mixture modeling applied to the density of aortic valve tissue components, calculated as [(volume/total tissue volume) × 100]. For histologic evaluation, explanted valve cusps were stained with Movat pentachrome as well as hematoxylin and eosin. For each cusp, three 5-µm slices were obtained. Fibrotic and calcific tissue composition were quantified using a validated artificial intelligence tool and averaged across the aortic valve. Correlations were assessed using the Spearman rank correlation coefficient. Intermodality and interobserver variability were measured using the intraclass correlation coefficient (ICC) and Bland-Altman plots. Results Twenty-nine participants (mean age, 63 years ± 10 [SD]; 23 male) were evaluated: 19 with severe AS, five with moderate AS, and five controls. Fibrocalcific tissue composition strongly correlated with histologic findings (r = 0.92; P < .001). The agreement between CTA and histologic findings for fibrocalcific tissue quantification was excellent (ICC, 0.94; P = .001), with underestimation of fibrotic composition at CTA (bias, -4.9%; 95% limits of agreement [LoA]: -18.5%, 8.7%). Finally, there was excellent interobserver repeatability for fibrotic (ICC, 0.99) and calcific (ICC, 0.99) aortic valve tissue volume measurements, with no evidence of a difference in measurements between readers (bias, -0.04 cm3 [95% LoA: -0.27 cm3, 0.19 cm3] and 0.02 cm3 [95% LoA: -0.14 cm3, 0.19 cm3], respectively). Conclusion In a direct comparison, standardized quantitative aortic valve tissue characterization at CTA showed excellent concordance with histologic findings and demonstrated interobserver reproducibility. Clinical trial registration no. NCT06136689 Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Almeida in this issue.

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.

Diagnostic safety of a machine learning-based automatic patient selection algorithm for stress-only myocardial perfusion SPECT.

BACKGROUND: Stress-only myocardial perfusion imaging (MPI) markedly reduces radiation dose, scanning time, and cost. We developed an automated clinical algorithm to safely cancel unnecessary rest imaging with high sensitivity for obstructive coronary artery disease (CAD). METHODS AND RESULTS: Patients without known CAD undergoing both MPI and invasive coronary angiography from REFINE SPECT were studied. A machine learning score (MLS) for prediction of obstructive CAD was generated using stress-only MPI and pre-test clinical variables. An MLS threshold with a pre-defined sensitivity of 95% was applied to the automated patient selection algorithm. Obstructive CAD was present in 1309/2079 (63%) patients. MLS had higher area under the receiver operator characteristic curve (AUC) for prediction of CAD than reader diagnosis and TPD (0.84 vs 0.70 vs 0.78, P < .01). An MLS threshold of 0.29 had superior sensitivity than reader diagnosis and TPD for obstructive CAD (95% vs 87% vs 87%, P < .01) and high-risk CAD, defined as stenosis of the left main, proximal left anterior descending, or triple-vessel CAD (sensitivity 96% vs 89% vs 90%, P < .01). CONCLUSIONS: The MLS is highly sensitive for prediction of both obstructive and high-risk CAD from stress-only MPI and can be applied to a stress-first protocol for automatic cancellation of unnecessary rest imaging.

Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study.

BACKGROUND: We sought to evaluate the association of metabolic syndrome (MetS) and computed tomography (CT)-derived cardiometabolic biomarkers (non-alcoholic fatty liver disease [NAFLD] and epicardial adipose tissue [EAT] measures) with long-term risk of major adverse cardiovascular events (MACE) in asymptomatic individuals. METHODS: This was a post-hoc analysis of the prospective EISNER (Early-Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) study of participants who underwent baseline coronary artery calcium (CAC) scoring CT and 14-year follow-up for MACE (myocardial infarction, late revascularization, or cardiac death). EAT volume (cm3) and attenuation (Hounsfield units [HU]) were quantified from CT using fully automated deep learning software (< 30 s per case). NAFLD was defined as liver-to-spleen attenuation ratio < 1.0 and/or average liver attenuation < 40 HU. RESULTS: In the final population of 2068 participants (59% males, 56 ± 9 years), those with MetS (n = 280;13.5%) had a greater prevalence of NAFLD (26.0% vs. 9.9%), higher EAT volume (114.1 cm3 vs. 73.7 cm3), and lower EAT attenuation (-76.9 HU vs. -73.4 HU; all p < 0.001) compared to those without MetS. At 14 ± 3 years, MACE occurred in 223 (10.8%) participants. In multivariable Cox regression, MetS was associated with increased risk of MACE (HR 1.58 [95% CI 1.10-2.27], p = 0.01) independently of CAC score; however, not after adjustment for EAT measures (p = 0.27). In a separate Cox analysis, NAFLD predicted MACE (HR 1.78 [95% CI 1.21-2.61], p = 0.003) independently of MetS, CAC score, and EAT measures. Addition of EAT volume to current risk assessment tools resulted in significant net reclassification improvement for MACE (22% over ASCVD risk score; 17% over ASCVD risk score plus CAC score). CONCLUSIONS: MetS, NAFLD, and artificial intelligence-based EAT measures predict long-term MACE risk in asymptomatic individuals. Imaging biomarkers of cardiometabolic disease have the potential for integration into routine reporting of CAC scoring CT to enhance cardiovascular risk stratification. Trial registration NCT00927693.

Prediction of revascularization by coronary CT angiography using a machine learning ischemia risk score.

OBJECTIVES: The machine learning ischemia risk score (ML-IRS) is a machine learning-based algorithm designed to identify hemodynamically significant coronary disease using quantitative coronary computed tomography angiography (CCTA). The purpose of this study was to examine whether the ML-IRS can predict revascularization in patients referred for invasive coronary angiography (ICA) after CCTA. METHODS: This study was a post hoc analysis of a prospective dual-center registry of sequential patients undergoing CCTA followed by ICA within 3 months, referred from inpatient, outpatient, and emergency department settings (n = 352, age 63 ± 10 years, 68% male). The primary outcome was revascularization by either percutaneous coronary revascularization or coronary artery bypass grafting. Blinded readers performed semi-automated quantitative coronary plaque analysis. The ML-IRS was automatically computed. Relationships between clinical risk factors, coronary plaque features, and ML-IRS with revascularization were examined. RESULTS: The study cohort consisted of 352 subjects with 1056 analyzable vessels. The ML-IRS ranged between 0 and 81% with a median of 18.7% (6.4-34.8). Revascularization was performed in 26% of vessels. Vessels receiving revascularization had higher ML-IRS (33.6% (21.1-55.0) versus 13.0% (4.5-29.1), p < 0.0001), as well as higher contrast density difference, and total, non-calcified, calcified, and low-density plaque burden. ML-IRS, when added to a traditional risk model based on clinical data and stenosis to predict revascularization, resulted in increased area under the curve from 0.69 (95% CI: 0.65-0.72) to 0.78 (95% CI: 0.75-0.81) (p < 0.0001), with an overall continuous net reclassification improvement of 0.636 (95% CI: 0.503-0.769; p < 0.0001). CONCLUSIONS: ML-IRS from quantitative coronary CT angiography improved the prediction of future revascularization and can potentially identify patients likely to receive revascularization if referred to cardiac catheterization. KEY POINTS: • Machine learning ischemia risk from quantitative coronary CT angiography was significantly higher in patients who received revascularization versus those who did not receive revascularization. • The machine learning ischemia risk score was significantly higher in patients with invasive fractional flow ≤ 0.8 versus those with > 0.8. • The machine learning ischemia risk score improved the prediction of future revascularization significantly when added to a standard prediction model including stenosis.

Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT).

BACKGROUND: We aim to establish a multicenter registry collecting clinical, imaging, and follow-up data for patients who undergo myocardial perfusion imaging (MPI) with the latest generation SPECT scanners. METHODS: REFINE SPECT (REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT) uses a collaborative design with multicenter contribution of clinical data and images into a comprehensive clinical-imaging database. All images are processed by quantitative software. Over 290 individual imaging variables are automatically extracted from each image dataset and merged with clinical variables. In the prognostic cohort, patient follow-up is performed for major adverse cardiac events. In the diagnostic cohort (patients with correlating invasive angiography), angiography and revascularization results within 6 months are obtained. RESULTS: To date, collected prognostic data include scans from 20,418 patients in 5 centers (57% male, 64.0 ± 12.1 years) who underwent exercise (48%) or pharmacologic stress (52%). Diagnostic data include 2079 patients in 9 centers (67% male, 64.7 ± 11.2 years) who underwent exercise (39%) or pharmacologic stress (61%). CONCLUSION: The REFINE SPECT registry will provide a resource for collaborative projects related to the latest generation SPECT-MPI. It will aid in the development of new artificial intelligence tools for automated diagnosis and prediction of prognostic outcomes.

Upper reference limits of transient ischemic dilation ratio for different protocols on new-generation cadmium zinc telluride cameras: A report from REFINE SPECT registry.

BACKGROUND: Upper reference limits for transient ischemic dilation (TID) have not been rigorously established for cadmium-zinc-telluride (CZT) camera systems. We aimed to derive TID limits for common myocardial perfusion imaging protocols utilizing a large, multicenter registry (REFINE SPECT). METHODS: One thousand six hundred and seventy-two patients with low likelihood of coronary artery disease with normal perfusion findings were identified. Images were processed with Quantitative Perfusion SPECT software (Cedars-Sinai Medical Center, Los Angeles, CA). Non-attenuation-corrected, camera-, radiotracer-, and stress protocol-specific TID limits in supine position were derived from 97.5th percentile and mean + 2 standard deviations (SD). Reference limits were compared for different solid-state cameras (D-SPECT vs. Discovery), radiotracers (technetium-99m-sestamibi vs. tetrofosmin), different types of stress (exercise vs. four different vasodilator-based protocols), and different vasodilator-based protocols. RESULTS: TID measurements did not follow Gaussian distribution in six out of eight subgroups. TID limits ranged from 1.18 to 1.52 (97.5th percentile) and 1.18 to 1.39 (mean + 2SD). No difference was noted between D-SPECT and Discovery cameras (P = 0.71) while differences between exercise and vasodilator-based protocols (adenosine, regadenoson, or regadenoson-walk) were noted (all P < 0.05). CONCLUSIONS: We used a multicenter registry to establish camera-, radiotracer-, and protocol-specific upper reference limits of TID for supine position on CZT camera systems. Reference limits did not differ between D-SPECT and Discovery camera.

Standardized volumetric plaque quantification and characterization from coronary CT angiography: a head-to-head comparison with invasive intravascular ultrasound.

OBJECTIVES: We sought to evaluate the accuracy of standardized total plaque volume (TPV) measurement and low-density non-calcified plaque (LDNCP) assessment from coronary CT angiography (CTA) in comparison with intravascular ultrasound (IVUS). METHODS: We analyzed 118 plaques without extensive calcifications from 77 consecutive patients who underwent CTA prior to IVUS. CTA TPV was measured with semi-automated software comparing both scan-specific (automatically derived from scan) and fixed attenuation thresholds. From CTA, %LDNCP was calculated voxels below multiple LDNCP thresholds (30, 45, 60, 75, and 90 Hounsfield units [HU]) within the plaque. On IVUS, the lipid-rich component was identified by echo attenuation, and its size was measured using attenuation score (summed score ∕ analysis length) based on attenuation arc (1 = < 90°; 2 = 90-180°; 3 = 180-270°; 4 = 270-360°) every 1 mm. RESULTS: TPV was highly correlated between CTA using scan-specific thresholds and IVUS (r = 0.943, p < 0.001), with no significant difference (2.6 mm3, p = 0.270). These relationships persisted for calcification patterns (maximal IVUS calcium arc of 0°, < 90°, or ≥ 90°). The fixed thresholds underestimated TPV (- 22.0 mm3, p < 0.001) and had an inferior correlation with IVUS (p < 0.001) compared with scan-specific thresholds. A 45-HU cutoff yielded the best diagnostic performance for identification of lipid-rich component, with an area under the curve of 0.878 vs. 0.840 for < 30 HU (p = 0.023), and corresponding %LDNCP resulted in the strongest correlation with the lipid-rich component size (r = 0.691, p < 0.001). CONCLUSIONS: Standardized noninvasive plaque quantification from CTA using scan-specific thresholds correlates highly with IVUS. Use of a < 45-HU threshold for LDNCP quantification improves lipid-rich plaque assessment from CTA. KEY POINTS: • Standardized scan-specific threshold-based plaque quantification from coronary CT angiography provides an accurate total plaque volume measurement compared with intravascular ultrasound. • Attenuation histogram-based low-density non-calcified plaque quantification can improve lipid-rich plaque assessment from coronary CT angiography.

Post-pericardiotomy Syndrome.

Post-pericardiotomy syndrome (PPS) occurs in a subgroup of patients who have undergone cardiothoracic surgery and is characterized by fever, pleuritic pain, pleural effusion, and pericardial effusion. It is associated with significant morbidity, and the leading complications include tamponade and constrictive pericarditis. Epidemiologic studies have found that PPS often occurs among younger patients; however, there is a lack of comprehensive risk stratification. It is therefore important to be able to identify patients who are at high risk for developing this disease. The diagnosis is made if patients present with 2 out of the following 5 criteria; fever, pericardial or pleuritic chest pain, pericardial or pleural friction rub, pericardial effusion, and pleural effusion with elevated C-reactive protein (CRP). Pericardial effusion associated with PPS is detected by echocardiography, and cardiac MRI is used for evaluation of pericardial thickening as well as inflammation associated with PPS. These imaging modalities have been invaluable for monitoring the efficacy of treatment in PPS. Aspirin, nonsteroidal anti-inflammatory agents (NSAID), and colchicine are the mainstay of the current treatment for PPS. Although steroids are used for refractory cases of PPS, they are associated with significant side effects when used for long-term treatment of this disease. It is important for future research to focus on identification of clinical, serologic, and genetic markers that may predispose patients to PPS. There is also a need for clinical trials to address the use of targeted immunomodulatory treatment for this disease.

Infectious Myocarditis on FDG-PET Imaging Mimicking Sarcoidosis.

Cardiac positron emission tomography with fluorine-18 fluorodeoxyglucose (FDG-PET) is often used for the diagnosis of cardiac involvement in sarcoidosis. Areas of segmental perfusion defects coupled with FDG uptake are considered to represent active inflammation. However, these findings may be associated with other inflammatory myocardial diseases. We describe a case of tuberculous myocarditis with imaging findings mimicking those found in cardiac sarcoidosis.