Comparative analysis of late gadolinium enhancement assessment techniques for monitoring fibrotic changes in myocarditis follow-up.

OBJECTIVES: To compare the repeatability and interrelation of various late gadolinium enhancement (LGE) assessment techniques for monitoring fibrotic changes in myocarditis follow-up. MATERIALS AND METHODS: LGE extent change between baseline and 3-month cardiovascular magnetic resonance (CMR) was compared in patients with acute myocarditis using the full width at half maximum (FWHM), gray-scale thresholds at 5 and 6 standard deviations (SD5 and SD6), visual assessment with threshold (VAT) and full manual (FM) techniques. In addition, visual presence score (VPS), visual transmurality score (VTS), and a simplified visual change score (VCS) were assessed. Intraclass-correlation (ICC) was used to evaluate repeatability, and methods were compared using Spearman's correlation. RESULTS: Forty-seven patients (38 male, median age: 27 [IQR: 21; 38] years) were included. LGE extent change differed among quantitative techniques (p < 0.01), with variability in the proportion of patients showing LGE change during follow-up (FWHM: 62%, SD5: 74%, SD6: 66%, VAT: 43%, FM: 60%, VPS: 53%, VTS: 77%, VCS: 89%). Repeatability was highest with FWHM (ICC: 0.97) and lowest with SD5 (ICC: 0.89). Semiquantitative scoring had slightly lower values (VPS ICC: 0.81; VTS ICC: 0.71). VCS repeatability was excellent (ICC: 0.93). VPS and VTS correlated with quantitative techniques, while VCS was positively associated with VPS, VTS, VAT, and FM, but not with FWHM, SD5, and SD6. CONCLUSION: FWHM offers the least observer-dependent LGE follow-up after myocarditis. VPS, VTS, and VCS are practical alternatives, showing reliable correlations with quantitative methods. Classification of patients exhibiting either stable or changing LGE relies on the assessment technique. CLINICAL RELEVANCE STATEMENT: This study shows that LGE monitoring in myocarditis is technique-dependent; the FWHM method yields the most consistent fibrotic tracking results, with scoring-based techniques as reliable alternatives. KEY POINTS: Recognition of fibrotic changes during myocarditis follow-up is significantly influenced by the choice of the quantification technique employed. The FWHM technique ensures highly repeatable tracking of myocarditis-related LGE changes. Segment-based visual scoring and the simplified visual change score offer practical, reproducible alternatives in resource-limited settings.

Latent Coronary Plaque Morphology From Computed Tomography Angiography, Molecular Disease Activity on Positron Emission Tomography, and Clinical Outcomes.

BACKGROUND: Assessments of coronary disease activity with 18F-sodium fluoride positron emission tomography and radiomics-based precision coronary plaque phenotyping derived from coronary computed tomography angiography may enhance risk stratification in patients with coronary artery disease. We sought to investigate whether the prognostic information provided by these 2 approaches is complementary in the prediction of myocardial infarction. METHODS: Patients with known coronary artery disease underwent coronary 18F-sodium fluoride positron emission tomography and coronary computed tomography angiography on a hybrid positron emission tomography/computed tomography scanner. Coronary 18F-NaF uptake was determined by the coronary microcalcification activity. We performed quantitative plaque analysis of coronary computed tomography angiography datasets and extracted 1103 radiomic features for each plaque. Using weighted correlation network analysis, we derived latent morphological features of coronary lesions which were aggregated to patient-level radiomics nomograms to predict myocardial infarction. RESULTS: Among 260 patients with established coronary artery disease (age, 65±9 years; 83% men), 179 (69%) participants showed increased coronary 18F-NaF activity (coronary microcalcification activity>0). Over 53 (40-59) months of follow-up, 18 patients had a myocardial infarction. Using weighted correlation network analysis, we derived 15 distinct eigen radiomic features representing latent morphological coronary plaque patterns in an unsupervised fashion. Following adjustments for calcified, noncalcified, and low-density noncalcified plaque volumes and 18F-NaF coronary microcalcification activity, 4 radiomic features remained independent predictors of myocardial infarction (hazard ratio, 1.46 [95% CI, 1.03-2.08]; P=0.03; hazard ratio, 1.62 [95% CI, 1.04-2.54]; P=0.02; hazard ratio, 1.49 [95% CI, 1.07-2.06]; P=0.01; and hazard ratio, 1.50 (95% CI, 1.05-2.13); P=0.02). CONCLUSIONS: In patients with established coronary artery disease, latent coronary plaque morphological features, quantitative plaque volumes, and disease activity on 18F-sodium fluoride positron emission tomography are additive predictors of myocardial infarction.

Deep Learning Analysis of Chest Radiographs to Triage Patients with Acute Chest Pain Syndrome.

Background Patients presenting to the emergency department (ED) with acute chest pain (ACP) syndrome undergo additional testing to exclude acute coronary syndrome (ACS), pulmonary embolism (PE), or aortic dissection (AD), often yielding negative results. Purpose To assess whether deep learning (DL) analysis of the initial chest radiograph may help triage patients with ACP syndrome more efficiently. Materials and Methods This retrospective study used electronic health records of patients with ACP syndrome at presentation who underwent a combination of chest radiography and additional cardiovascular or pulmonary imaging or stress tests at two hospitals (Massachusetts General Hospital [MGH], Brigham and Women's Hospital [BWH]) between January 2005 and December 2015. A DL model was trained on 23 005 patients from MGH to predict a 30-day composite end point of ACS, PE, AD, and all-cause mortality based on chest radiographs. Area under the receiver operating characteristic curve (AUC) was used to compare performance between models (model 1: age + sex; model 2: model 1 + conventional troponin or d-dimer positivity; model 3: model 2 + DL predictions) in internal and external test sets from MGH and BWH, respectively. Results At MGH, 5750 patients (mean age, 59 years ± 17 [SD]; 3329 men, 2421 women) were evaluated. Model 3, which included DL predictions, significantly improved discrimination of those with the composite outcome compared with models 2 and 1 (AUC, 0.85 [95% CI: 0.84, 0.86] vs 0.76 [95% CI: 0.74, 0.77] vs 0.62 [95% CI: 0.60 0.64], respectively; P < .001 for all). When using a sensitivity threshold of 99%, 14% (813 of 5750) of patients could be deferred from cardiovascular or pulmonary testing for differential diagnosis of ACP syndrome using model 3 compared with 2% (98 of 5750) of patients using model 2 (P < .001). Model 3 maintained its diagnostic performance in different age, sex, race, and ethnicity groups. In external validation at BWH (22 764 patients; mean age, 57 years ± 17; 11 470 women), trends were similar and improved after fine tuning. Conclusion Deep learning analysis of chest radiographs may facilitate more efficient triage of patients with acute chest pain syndrome in the emergency department. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Goo in this issue.

Prognostic value of CT-derived coronary artery disease characteristics varies by ASCVD risk: insights from the PROMISE trial.

OBJECTIVES: To compare the prognostic value of individual CT-derived coronary artery disease (CAD) characteristics across categories of clinical cardiovascular risk. METHODS: The central core laboratory assessed coronary artery calcium (CAC), obstructive CAD (stenosis ≥ 50%), and high-risk plaque (HRP) in stable outpatients with suspected CAD enrolled in the PROMISE trial. Multivariable Cox regression models (endpoint: unstable angina, nonfatal myocardial infarction, or all-cause mortality; median follow-up: 2 years) were used to compare hazard ratios (HR) of the CT measures between low-borderline (< 7.5%) and moderate-high (≥ 7.5%) atherosclerotic cardiovascular disease (ASCVD) risk based on the pooled cohort equation. RESULTS: Among 4356 included patients (aged 61 ± 8 years, 52% women), 67% had ASCVD risk ≥ 7.5%. Stratified by ASCVD risk, CAD ≥ 50% had nearly threefold greater HR in individuals with ASCVD < 7.5% (aHR, 6.85; 95% CI, 2.33-20.15; p < 0.001) vs. ASCVD ≥ 7.5% (aHR: 2.66, 95% CI: 1.67-4.25, p < 0.001; interaction p = 0.041). CAC predicted events solely in ASCVD ≥ 7.5% patients (aHR: 1.92, 95% CI: 1.01-3.63, p = 0.045; interaction p = 0.571), while HRP predicted events only in ASCVD < 7.5% (aHR: 3.11, 95% CI: 1.09-8.85, p = 0.034; interaction p = 0.034). CONCLUSIONS: Prognostic values of CT-derived CAD characteristics differ by ASCVD risk categories. While CAD ≥ 50% has the highest prognostic value regardless of ASCVD risk, CAC is prognostic in high and HRP in low ASCVD risk. These findings suggest that CAD ≥ 50% and HRP detection rather than CAC scoring may better risk-stratify symptomatic low-risk patients and thus potentially improve downstream care. KEY POINTS: • Prognostic value of individual CT-derived CAD characteristics differs by categories of cardiovascular risk. • Presence of obstructive coronary artery stenosis ≥ 50% has the highest prognostic value regardless of cardiovascular risk. • Coronary artery calcium is independently prognostic in high and high-risk plaque features in low cardiovascular risk.

Impact of virtual monoenergetic levels on coronary plaque volume components using photon-counting computed tomography.

OBJECTIVES: Virtual monoenergetic images (VMIs) from photon-counting CT (PCCT) may change quantitative coronary plaque volumes. We aimed to assess how plaque component volumes change with respect to VMIs. METHODS: Coronary CT angiography (CTA) images were acquired using a dual-source PCCT and VMIs were reconstructed between 40 and 180 keV in 10-keV increments. Polychromatic images at 120 kVp (T3D) were used as reference. Quantitative plaque analysis was performed on T3D images and segmentation masks were copied to VMI reconstructions. Calcified plaque (CP; > 350 Hounsfield units, HU), non-calcified plaque (NCP; 30 to 350 HU), and low-attenuation NCP (LAP; - 100 to 30 HU) volumes were calculated using fixed thresholds. RESULTS: We analyzed 51 plaques from 51 patients (67% male, mean age 65 ± 12 years). Average attenuation and contrast-to-noise ratio (CNR) decreased significantly with increasing keV levels, with similar values observed between T3D and 70 keV images (299 ± 209 vs. 303 ± 225 HU, p = 0.15 for mean HU; 15.5 ± 3.7 vs. 15.8 ± 3.5, p = 0.32 for CNR). Mean NCP volume was comparable between T3D and 100-180-keV reconstructions. There was a monotonic decrease in mean CP volume, with a significant difference between all VMIs and T3D (p < 0.05). LAP volume increased with increasing keV levels and all VMIs showed a significant difference compared to T3D, except for 50 keV (28.0 ± 30.8 mm3 and 28.6 ± 30.1 mm3, respectively, p = 0.63). CONCLUSIONS: Estimated coronary plaque volumes significantly differ between VMIs. Normalization protocols are needed to have comparable results between future studies, especially for LAP volume which is currently defined using a fixed HU threshold. CLINICAL RELEVANCE STATEMENT: Different virtual monoenergetic images from photon-counting CT alter attenuation values and therefore corresponding plaque component volumes. New clinical standards and protocols are required to determine the optimal thresholds to derive plaque volumes from photon-counting CT. KEY POINTS: • Utilizing different VMI energy levels from photon-counting CT for the analysis of coronary artery plaques leads to substantial changes in attenuation values and corresponding plaque component volumes. • Low-energy images (40-70 keV) improved contrast-to-noise ratio, however also increased image noise. • Normalization protocols are needed to have comparable results between future studies, especially for low-attenuation plaque volume which is currently defined using a fixed HU threshold.

Proteomic Signature of Subclinical Coronary Artery Disease in People With HIV: Analysis of the REPRIEVE Mechanistic Substudy.

BACKGROUND: People with HIV (PWH) have subclinical coronary artery disease (CAD) despite low traditional atherosclerotic cardiovascular disease (ASCVD) risk scores. Coronary plaque in PWH presents as a unique phenotype, but little is known about the contributions of specific inflammatory pathways to plaque phenotypes in PWH. METHODS: The REPRIEVE Mechanistic Substudy enrolled PWH on ART without known cardiovascular disease. We used a targeted discovery proteomics approach to evaluate 246 unique proteins representing cardiovascular, inflammatory, and immune pathways. Proteomic signatures were determined for presence of coronary artery calcium (CAC > 0) and presence of coronary plaque. RESULTS: Data were available for 662 participants (aged 51 [SD 6] years, ASCVD risk score 4.9% [SD 3.1%]). Among 12 proteins associated with both CAC and presence of coronary plaque, independent of ASCVD risk score, the odds ratios were highest for NRP1: 5.1 (95% confidence interval [CI], 2.3-11.4) for CAC and 2.9 (95% CI, 1.4-6.1) for presence of plaque. Proteins uniquely related to presence of plaque were CST3, LTBR, MEPE, PLC, SERPINA5, and TNFSF13B; in contrast, DCN, IL-6RA, OSMR, ST2, and VCAM1 were only related to CAC. CONCLUSIONS: Distinct immune and inflammatory pathways are differentially associated with subclinical CAD phenotypes among PWH. This comprehensive set of targets should be further investigated to reduce atherosclerosis and ASCVD in PWH. CLINICAL TRIALS REGISTRATION: NCT02344290.

Deep learning-based atherosclerotic coronary plaque segmentation on coronary CT angiography.

OBJECTIVES: Volumetric evaluation of coronary artery disease (CAD) allows better prediction of cardiac events. However, CAD segmentation is labor intensive. Our objective was to create an open-source deep learning (DL) model to segment coronary plaques on coronary CT angiography (CCTA). METHODS: Three hundred eight individuals' 894 CCTA scans with 3035 manually segmented plaques by an expert reader (considered as ground truth) were used to train (186/308, 60%), validate (tune, 61/308, 20%), and test (61/308, 20%) a 3D U-net model. We also evaluated the model on an external test set of 50 individuals with vulnerable plaques acquired at a different site. Furthermore, we applied transfer learning on 77 individuals' data and re-evaluated the model's performance using intra-class correlation coefficient (ICC). RESULTS: On the test set, DL outperformed the currently used minimum cost approach method to quantify total: ICC: 0.88 [CI: 0.85-0.91] vs. 0.63 [CI: 0.42-0.76], noncalcified: 0.84 [CI: 0.80-0.88] vs. 0.45 [CI: 0.26-0.59], calcified: 0.99 [CI: 0.98-0.99] vs. 0.96 [CI: 0.94-0.97], and low attenuation noncalcified: 0.25 [CI: 0.13-0.37] vs. -0.01 [CI: -0.13 to 0.11] plaque volumes. On the external dataset, substantial improvement was observed in DL model performance after transfer learning, total: 0.62 [CI: 0.01-0.84] vs. 0.94 [CI: 0.87-0.97], noncalcified: 0.54 [CI: -0.04 to 0.80] vs. 0.93 [CI: 0.86-0.96], calcified: 0.91 [CI:0.85-0.95] vs. 0.95 [CI: 0.91-0.97], and low attenuation noncalcified 0.48 [CI: 0.18-0.69] vs. 0.86 [CI: 0.76-0.92]. CONCLUSIONS: Our open-source DL algorithm achieved excellent agreement with expert CAD segmentations. However, transfer learning may be required to achieve accurate segmentations in the case of different plaque characteristics or machinery. KEY POINTS: • Deep learning 3D U-net model for coronary segmentation achieves comparable results with expert readers' volumetric plaque quantification. • Transfer learning may be needed to achieve similar results for other scanner and plaque characteristics. • The developed deep learning algorithm is open-source and may be implemented in any CT analysis software.

Temporal assessment of lesion morphology on radiological images beyond lesion volumes-a proof-of-principle study.

OBJECTIVES: To develop a general framework to assess temporal changes in lesion morphology on radiological images beyond volumetric changes and to test whether cocaine abstinence changes coronary plaque structure on serial coronary CT angiography (CTA). METHODS: Chronic cocaine users with human immunodeficiency virus (HIV) infection were prospectively enrolled to undergo cash-based contingency management to achieve cocaine abstinence. Participants underwent coronary CTA at baseline and 6 and 12 months following recruitment. We segmented all coronary plaques and extracted 1103 radiomic features. We implemented weighted correlation network analysis to derive consensus eigen radiomic features (named as different colors) and used linear mixed models and mediation analysis to assess whether cocaine abstinence affects plaque morphology correcting for clinical variables and plaque volumes and whether serum biomarkers causally mediate these changes. Furthermore, we used Bayesian hidden Markov network changepoint analysis to assess the potential rewiring of the radiomic network. RESULTS: Sixty-nine PLWH (median age 55 IQR: 52-59 years, 19% female) completed the study, of whom 26 achieved total abstinence. Twenty consensus eigen radiomic features were derived. Cocaine abstinence significantly affected the pink and cyan eigen features (-0.04 CI: [-0.06; -0.02], p = 0.0009; 0.03 CI: [0.001; 0.04], p = 0.0017, respectively). These effects were mediated through changes in endothelin-1 levels. In abstinent individuals, we observed significant rewiring of the latent radiomic signature network. CONCLUSIONS: Using our proposed framework, we found 1 year of cocaine abstinence to significantly change specific latent coronary plaque morphological features and rewire the latent morphologic network above and beyond changes in plaque volumes and clinical characteristics. KEY POINTS: • We propose a general methodology to decompose the latent morphology of lesions on radiological images using a radiomics-based systems biology approach. • As a proof-of-principle, we show that 1 year of cocaine abstinence results in significant changes in specific latent coronary plaque morphologic features and rewiring of the latent morphologic network above and beyond changes in plaque volumes and clinical characteristics. • We found endothelin-1 levels to mediate these structural changes providing potential pathological pathways warranting further investigation.

Microstructural alterations measured by diffusion tensor imaging following transcatheter aortic valve replacement and their association with cerebral ischemic injury and cognitive function - a prospective study.

PURPOSE: We assessed diffusion tensor imaging (DTI) metric changes of the corpus callosum and cingulum correlated to postprocedural ischemic lesion load (ILL) and cognitive performance in transcatheter aortic valve replacement (TAVR). METHODS: TAVR subjects had DTI post-TAVR (≤ 8 days) and at 6 months (78 participants, males 56%, age 78.8 years ± 6.3) and four neurocognitive tests (pre-TAVR, post-TAVR, 6 months, 1 year). DTI metrics (fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), radial diffusivity (RD)) were calculated for 7 regions: corpus callosum (genu, body, splenium) and cingulum (cingulate gyrus, parahippocampal cingulum bilaterally). DTI metrics post-TAVR and at 6 months were compared with Student's t-test (p < 0.0071) and ANOVA covarying for sex, ILL (p < 0.05) with post hoc analysis of ILL groups (p < 0.0167). Repeated-measures linear mixed-effect model (p < 0.05) was performed to investigate the effect of time and ILL on cognition. RESULTS: At 6 months, significant decrease of the following DTI metrics was detected: AD (genu, body, splenium, right parahippocampal cingulum: p ≤ 0.0046); MD (body, both cingulate gyri: p ≤ 0.0050); RD (left cingulate gyrus: p = 0.0021); FA (splenium: p < 0.0001). ANOVA confirmed significant effect of female sex on AD + MD reduction (body, right cingulate gyrus) and AD reduction (left cingulate gyrus) (p ≤ 0.0254). Significant negative effect of ILL on some DTI metric changes was found (AD + MD-body: p ≤ 0.0050; MD-left cingulate gyrus: p = 0.0087). Cognitive performance remained stable with significant negative correlation of ILL and retrograde memory and visual scores (p ≤ 0.0483). CONCLUSION: Significant effect of TAVR on cerebral microstructural integrity was found with reduced diffusivities opposite to the trends reported in various neurodegenerative conditions/ageing, notably in women and lower ILL, and with preserved/improved cognition. TRIAL REGISTRATION NUMBER: NCT02826200 at ClinicalTrials.gov; date of registration: 07. July 2016.

Spatial analysis of factors impacting lower limb major amputation rates in Hungary: Is geography partially destiny?

Background: Lower limb major amputations represent a substantial public health burden in Hungary, where previous research revealed markedly high rates with significant spatial variations. Therefore, we aimed to assess to what extent healthcare and socio-economic factors in the local environment explain the regional disparity. Patients and methods: In a retrospective cohort analysis, based on the healthcare administrative data of the Hungarian population, lower limb major amputations were identified from 1st of January 2017 to 31st of December 2019. The permanent residence of the amputees on the local administrative level (197 geographic units) was used to identify potential healthcare (outpatient care, revascularisation activity) and socio-economic (educational attainment, local infrastructure and services, income and employment) determinants of amputations. Spatial effects were modelled using the spatial Durbin error regression model. Results: 10,209 patients underwent 11,649 lower limb major amputations in the observational period. In our spatial analysis, outpatient care was not associated with local amputation rates. However, revascularisation activity in a geographic unit entailed an increased rate of amputations, while revascularisations in the neighbouring areas were associated with a lower rate of amputations, resulting in an overall neutral effect (ß=-0.002, 95% CI: -0.05 - 0.04, p=0.96). The local socio-economic environment had a significant direct inverse association with amputations (ß=-7.45, 95% CI: -10.50 - -4.42, p<0.0001) . Our spatial model showed better performance than the traditional statistical modelling (ordinary least squares regression), explaining 37% of the variation in amputations rates. Conclusions: Regional environmental factors explain a substantial portion of spatial disparities in amputation practice. While the socio-economic environment shows a significant inverse relationship with the regional amputation rates, the impact of the local healthcare-related factors (outpatient care, revascularisation activity) is not straightforward. Unravelling the impact of the location on amputation practice requires complex spatial modelling, which may guide efficient healthcare policy decisions.

Contribution of Risk Factors to the Development of Coronary Atherosclerosis as Confirmed via Coronary CT Angiography: A Longitudinal Radiomics-based Study.

Background Various cardiovascular risk factors are thought to modify atherosclerosis in a similar fashion (ie, by increasing the magnitude of coronary artery disease [CAD]). However, coronary CT angiography allows precision phenotyping of plaque characteristics through use of radiomics. Purpose To assess whether different cardiovascular risk factors have distinctive contributions to the changes in plaque morphologic features over time. Materials and Methods Individuals with or without HIV infection and cocaine use and without cardiovascular symptoms underwent coronary CT angiography between May 2004 and August 2015. In the current HIPAA-compliant study, the effects of cocaine use, HIV infection, and atherosclerotic cardiovascular disease (ASCVD) risk on the temporal changes (mean ± standard deviation, 4.0 years ± 2.3 between CT angiographic examinations) in CAD structure were analyzed by using radiomic analysis. The changes in radiomic features were analyzed by using linear mixed models, with correction for factors that may change plaque structure: high-sensitivity C-reactive protein level, statin use, positive family history of CAD, and total plaque volume to account for any potential intrinsic correlation between volume and morphologic features. Clusters among significant radiomic features were identified by using hierarchical clustering. Bonferroni-corrected P values less than .00004 (.05 divided by 1276) were considered to indicate significant differences. Results Of 1429 participants, 300 with CAD confirmed at coronary CT angiography were randomly selected (mean age, 48 years ± 7; 210 men, 226 people infected with HIV, 174 people who use cocaine) and 1276 radiomic features were quantified for each plaque. Cocaine use was significantly associated with 23.7% (303 of 1276) of the radiomic features, HIV infection was significantly associated with 1.3% (17 of 1276), and elevated ASCVD risk was significantly associated with 8.2% (104 of 1276) (P < .00004 for all). Parameters associated with elevated ASCVD risk or cocaine use and HIV infection did not overlap. There were 13 clusters among the 409 parameters, eight of which were affected only by cocaine use and three of which were affected only by ASCVD risk. Conclusion Radiomics-based precision phenotyping indicated that conventional risk factors, cocaine use, and HIV infection each had different effects on CT angiographic morphologic changes in coronary atherosclerosis over 4 years. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Schoepf and Emrich in this issue.

Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT.

In daily clinical practice, clinicians integrate available data to ascertain the diagnostic and prognostic probability of a disease or clinical outcome for their patients. For patients with suspected or known cardiovascular disease, several anatomical and functional imaging techniques are commonly performed to aid this endeavor, including coronary computed tomography angiography (CCTA) and nuclear cardiology imaging. Continuous improvement in positron emission tomography (PET), single-photon emission computed tomography (SPECT), and CT hardware and software has resulted in improved diagnostic performance and wide implementation of these imaging techniques in daily clinical practice. However, the human ability to interpret, quantify, and integrate these data sets is limited. The identification of novel markers and application of machine learning (ML) algorithms, including deep learning (DL) to cardiovascular imaging techniques will further improve diagnosis and prognostication for patients with cardiovascular diseases. The goal of this position paper of the European Association of Nuclear Medicine (EANM) and the European Association of Cardiovascular Imaging (EACVI) is to provide an overview of the general concepts behind modern machine learning-based artificial intelligence, highlights currently prefered methods, practices, and computational models, and proposes new strategies to support the clinical application of ML in the field of cardiovascular imaging using nuclear cardiology (hybrid) and CT techniques.

Cardiovascular risk factors and illicit drug use may have a more profound effect on coronary atherosclerosis progression in people living with HIV.

OBJECTIVES: To assess whether HIV infection directly or indirectly promotes coronary artery disease (CAD) volume progression in a longitudinal study of African Americans. METHODS: We randomly selected 300 individuals with subclinical CAD (210 male; age: 48.0 ± 7.2 years; 226 HIV infected, 174 cocaine users) from 1429 cardiovascularly asymptomatic participants of a prospective epidemiological study between May 2004 and August 2015. Individuals underwent coronary CT angiography at two time points (mean follow-up: 4.0 ± 2.3 years). We quantified noncalcified (NCP: -100-350HU), low-attenuation noncalcified (LA-NCP: -100-30HU), and calcified (CP: ≥ 351 HU) plaque volumes. Linear mixed models were used to assess the effects of HIV infection, atherosclerotic cardiovascular disease (ASCVD) risk, and years of cocaine use on plaque volumes. RESULTS: There was no significant difference in annual progression rates between HIV-infected and HIV-uninfected regarding NCP (8.7 [IQR: 3.0-19.4] mm3/year vs. 4.9 [IQR: 1.5-18.3] mm3/year, p = 0.14), LA-NCP (0.2 [IQR: 0.0-1.6] mm3/year vs. 0.2 [IQR: 0.0-0.9] mm3/year, p = 0.07) or CP volumes (0.3 [IQR: 0.0-3.4] mm3/year vs. 0.1 [IQR: 0.0-3.2] mm3/year, p = 0.30). Multivariately, HIV infection was not associated with NCP (-6.9mm3, CI: [-32.8-19.0], p = 0.60), LA-NCP (-0.1mm3, CI: [-2.6-2.4], p = 0.92), or CP volumes (-0.3mm3, CI: [-9.3-8.6], p = 0.96). However, each percentage of ASCVD and each year of cocaine use significantly increased total, NCP, and CP volumes among HIV-infected individuals, but not among HIV-uninfected. Importantly, none of the HIV-associated medications had any effect on plaque volumes (p > 0.05 for all). CONCLUSIONS: The more profound adverse effect of risk factors in HIV-infected individuals may explain the accelerated progression of CAD in these people, as HIV infection was not independently associated with any coronary plaque volume. KEY POINTS: • Human immunodeficiency virus-infected individuals may have similar subclinical coronary artery disease, as the infection is not independently associated with coronary plaque volumes. • However, cardiovascular risk factors and illicit drug use may have a more profound effect on atherosclerosis progression in those with human immunodeficiency virus infection, which may explain the accelerated progression of CAD in these people. • Nevertheless, through rigorous prevention and abstinence from illicit drugs, these individuals may experience similar cardiovascular outcomes as -uninfected individuals.

Patients with Moderate Non-Culprit Coronary Lesions of Recent Acute Coronary Syndrome.

Fractional flow reserve (FFR) measurement was compared to dobutamine stress echocardiography (DSE) instable angina (SA) with stable coronary lesion (s) (SCL (s) ) in a few trials; however, similar comparisons in patients with acute coronary syndrome (ACS) with non-culprit lesion (s) (NCL (s) ) are lacking. Our objectives were to prospectively evaluate the diagnostic performance of FFR with two different cutoff values (< 0.80 and < 0.75) relative to DSE in moderate (30%-70% diameter stenosis) NCLs (ACS group) and to compare these observations with those measured in SCLs (SA group). One hundred seventy-five consecutive patients with SA (n = 86) and ACS (n = 89) with 225 coronary lesions (109 SCLs and 116 NCLs) were enrolled. In contrast to the ACS cohort in SA patients, normal DSE was associated with higher FFR values compared to those with abnormal DSE (P = 0.051 versus P = 0.006). In addition, in the SA group, a significant correlation was observed between DSE (regional wall motion score index at peak stress) and FFR (r = -0.290; P = 0.002), whereas a similar association was absent (r = -0.029; P = 0.760) among ACS patients. In the SA group, decreasing the FFR cutoff value (< 0.80 versus < 0.75) improved the concordance of FFR with DSE (70.6% versus 81.7%) without altering its discriminatory power (area under the curve; 0.68 versus 0.63; P = 0.369), whereas in the ACS group, concordance remained similar (69.0% versus 71.6%) and discriminatory power decreased (0.62 versus 0.51; P = 0.049), respectively. In conclusion, lesion-specific FFR assessment may have different relevance in patients with moderate NCLs than in patients with SCLs.

Left Ventricular Systolic Function Has Strong Independent Genetic Background from Diastolic Function: A Classical Twin Study.

Background and Objectives: No data are available on whether the heritability of left ventricle (LV) systolic and diastolic parameters are independent of each other. Therefore, our aim was to assess the magnitude of common and independent genetic and environmental factors defining LV systolic and diastolic function. Materials and Methods: We analyzed 184 asymptomatic twins (65% female, mean age: 56 ± 9 years). Transthoracic echocardiography was performed to measure LV systolic (global longitudinal and circumferential strain; basal and apical rotation) and diastolic (early diastolic velocity of mitral inflow and lateral mitral annulus tissue; deceleration time and early diastolic strain rate) parameters using conventional and speckle-tracking echocardiography. Genetic structural equation models were evaluated to quantify the proportion of common and specific genetic (Ac, As) and environmental factors (Ec, Es) contributing to the phenotypes. Results: LV systolic parameters had no common genetic or environmental heritability (Ac range: 0-0%; Ec range: 0-0%; As range: 57-77%; Es range: 24-43%). Diastolic LV parameters were mainly determined by common genetic and environmental effects (Ac range: 9-40%; Ec range: 11-49%; As range: 0-29%; Es range: 0-51%). Systolic parameters had no common genetic or environmental factors (Ac = 0%; Ec = 0%) with diastolic metrics. Conclusions: Systolic LV parameters have a strong genetic predisposition to any impact. They share no common genetic or environmental factors with each other or with diastolic parameters, indicating that they may deteriorate specifically to given effects. However, diastolic functional parameters are mainly affected by common environmental influences, suggesting that pathological conditions may deteriorate them equally. Estimation of the genetic and environmental influence and interdependence on systolic and diastolic LV function may help the understanding of the pathomechanism of different heart failure classification types.

Calcium scoring: a personalized probability assessment predicts the need for additional or alternative testing to coronary CT angiography.

OBJECTIVE: To assess whether anthropometrics, clinical risk factors, and coronary artery calcium score (CACS) can predict the need of further testing after coronary CT angiography (CTA) due to non-diagnostic image quality and/or the presence of significant stenosis. METHODS: Consecutive patients who underwent coronary CTA due to suspected coronary artery disease (CAD) were included in our retrospective analysis. We used multivariate logistic regression and receiver operating characteristics analysis containing anthropometric factors: body mass index, heart rate, and rhythm irregularity (model 1); and parameters used for pre-test likelihood estimation: age, sex, and type of angina (model 2); and also added total calcium score (model 3) to predict downstream testing. RESULTS: We analyzed 4120 (45.7% female, 57.9 ± 12.1 years) patients. Model 3 significantly outperformed models 1 and 2 (area under the curve, 0.84 [95% CI 0.83-0.86] vs. 0.56 [95% CI 0.54-0.58] and 0.72 [95% CI 0.70-0.74], p < 0.001). For patients with sinus rhythm of 50 bpm, in case of non-specific angina, CACS above 435, 756, and 944; in atypical angina CACS above 381, 702, and 890; and in typical angina CACS above 316, 636, and 824 correspond to 50%, 80%, and 90% probability of further testing, respectively. However, higher heart rates and arrhythmias significantly decrease these cutoffs (p < 0.001). CONCLUSION: CACS significantly increases the ability to identify patients in whom deferral from coronary CTA may be advised as CTA does not lead to a final decision regarding CAD management. Our results provide individualized cutoff values for given probabilities of the need of additional testing, which may facilitate personalized decision-making to perform or defer coronary CTA. KEY POINTS: • Anthropometric parameters on their own are insufficient predictors of downstream testing. Adding parameters of the Diamond and Forrester pre-test likelihood test significantly increases the power of prediction. • Total CACS is the most important independent predictor to identify patients in whom coronary CTA may not be recommended as CTA does not lead to a final decision regarding CAD management. • We determined specific CACS cutoff values based on the probability of downstream testing by angina-, arrhythmia-, and heart rate-based groups of patients to help individualize patient management.

Long-term cocaine use is associated with increased coronary plaque burden - a pilot study.

Background: There is a lack of research regarding whether prolonged use of cocaine would lead to increase of coronary plaque burden. Objectives: To study the effects of cocaine use on the coronary artery plaque volume. We hypothesize the longer the cocaine use, the greater the plaque burden. Methods: We used coronary computed tomography angiography to evaluate plaque volumes. The study included chronic (N = 33 with 27 HIV+) and non-cocaine users (N = 15 with 12 HIV+). Chronic cocaine use was defined as use by any route for at least 6 months, administered at least 4 times/month. The Student's t-test was used to compare the plaque volumes between chronic and non-cocaine users. Multivariable regression analysis adjusted for age, sex, body mass index, HIV status, cigarette smoking, diabetes, and total cholesterol was performed to determine the relationship between years of cocaine use and plaque volumes. Results: The total plaque volumes between groups showed no difference (p = .065). However, the total left anterior descending artery (LAD) plaque volume in the chronic cocaine group was significantly higher than that in the non-cocaine group (p = .047). For each year increase in cocaine use, total plaque volume and total LAD plaque volume increased by 7.23 mm3 (p = .013) and 4.56 mm3 (p = .001), respectively. In the multivariable analyses, both total plaque volume and total LAD plaque volume were significantly associated with years of cocaine use (p = .039 and 0.013, respectively). Conclusion: Prolonged cocaine use accelerates the development of sub-clinical atherosclerosis.

Radiomics versus Visual and Histogram-based Assessment to Identify Atheromatous Lesions at Coronary CT Angiography: An ex Vivo Study.

Background Visual and histogram-based assessments of coronary CT angiography have limited accuracy in the identification of advanced lesions. Radiomics-based machine learning (ML) could provide a more accurate tool. Purpose To compare the diagnostic performance of radiomics-based ML with that of visual and histogram-based assessment of ex vivo coronary CT angiography cross sections to identify advanced atherosclerotic lesions defined with histologic examination. Materials and Methods In this prospective study, 21 coronary arteries from seven hearts obtained from male donors (mean age, 52.3 years ± 5.3) were imaged ex vivo with coronary CT angiography between February 23, 2009, and July 31, 2010. From 95 coronary plaques, 611 histologic cross sections were coregistered with coronary CT cross sections. Lesions were considered advanced if early fibroatheroma, late fibroatheroma, or thin-cap atheroma was present. CT cross sections were classified as showing homogeneous, heterogeneous, or napkin-ring sign plaques on the basis of visual assessment. The area of low attenuation (<30 HU) and the average Hounsfield unit were quantified. Radiomic parameters were extracted and used as inputs to ML algorithms. Eight radiomics-based ML models were trained on randomly selected cross sections (training set, 75% of the cross sections) to identify advanced lesions. Visual assessment, histogram-based assessment, and the best ML model were compared on the remaining 25% of the data (validation set) by using the area under the receiver operating characteristic curve (AUC) to identify advanced lesions. Results After excluding sections with no visible plaque (n = 134) and with heavy calcium (n = 32), 445 cross sections were analyzed. Of those 445 cross sections, 134 (30.1%) were advanced lesions. Visual assessment of the 445 cross sections indicated that 207 (46.5%) were homogeneous, 200 (44.9%) were heterogeneous, and 38 (8.5%) demonstrated the napkin-ring sign. A radiomics-based ML model incorporating 13 parameters outperformed visual assessment (AUC = 0.73 with 95% confidence interval [CI] of 0.63, 0.84 vs 0.65 with 95% CI of 0.56, 0.73, respectively; P = .04), area of low attenuation (AUC = 0.55 with 95% CI of 0.42, 0.68; P = .01), and average Hounsfield unit (AUC = 0.53 with 95% CI of 0.42, 0.65; P = .004) in the identification of advanced atheromatous lesions. Conclusion Radiomics-based machine learning analysis improves the discriminatory power of coronary CT angiography in the identification of advanced atherosclerotic lesions. Published under a CC BY 4.0 license.

Comprehensive coronary plaque assessment in patients with obstructive sleep apnea.

Obstructive sleep apnea (OSA) is associated with an increased risk of cardiovascular disease. Previous studies have assessed the relationship between OSA and coronary artery disease (CAD) using coronary artery calcium score (CAC) measurements. However, limited data are available regarding the association of OSA with non-calcified plaque burden. We therefore aimed to assess the relationship between CAD severity as assessed by coronary computed tomography angiography (CTA) and OSA. Forty-one adult subjects (59 ± 9 years, 15 men) underwent a 256-slice coronary CTA, which was followed by a diagnostic attended cardiorespiratory polygraphy (n = 13) or polysomnography (n = 28). Segment involvement score (SIS), segment stenosis score (SSS) and CAC were used to quantify total CAD burden. Correlation analysis was used to assess potential associations between CAD and OSA. Twenty-two patients were diagnosed with OSA. SIS and SSS were elevated in OSA (2.90 ± 2.78 versus 1.79 ± 2.39 and 4.91 ± 5.94 versus 1.79 ± 4.54, OSA versus controls, SIS and SSS respectively, both p < 0.01) and correlated with OSA severity as measured by the apnea-hypopnea index (AHI, r = 0.41 and 0.43, p < 0.01) and oxygen desaturation index (ODI, r = 0.45 and 0.46, p < 0.01). However, no significant correlation was observed between CAC and OSA. Compared to CAC, SIS and SSS provide additional information on coronary plaque burden in OSA, which shows a significant association with OSA.

Multidetector CT angiography of the Circle of Willis: association of its variants with carotid artery disease and brain ischemia.

PURPOSE: (1) to estimate the prevalence of Circle of Willis (CoW) variants in patients undergoing carotid endarterectomy, (2) to correlate these variants to controls and (3) cerebral ischemia depicted by computed tomography (CT). MATERIALS AND METHODS: After Institutional Review Board approval, data of 544 carotid endarterectomy patients (331 males, mean age 69±8 years) and 196 controls (117 males, mean age 66±11 years) who underwent brain CT and carotid CT angiography (CTA) were retrospectively analysed. Two observers independently classified each CoW segment as normal, hypoplastic (diameter <0.8 mm) or non-visualized. Four groups of CoW variants based on the number of hypoplastic/non-visualized segments were correlated with clinical data (ANOVA, χ2 and multivariate logistic regression analysis). Intra- and inter-observer agreement was estimated using Cohen κ statistics. RESULTS: High prevalence of CoW variants (97%) and compromised CoW (81%) was observed in the study group and significant difference was found in the distribution of CoW variants compared to controls (p<0.001), internal carotid artery (ICA) stenosis being the only independent predictor of CoW morphology (p<0.001). Significant correlation was found between CoW configuration and brain ischemia in the study group (p=0.002). ICA stenosis of ≥90% was associated to higher rate of ipsilateral A1 hypoplasia/non-visualization (p<0.001). Intra- and inter-observer agreement was from substantial to almost perfect (Cohen κ=0.75-1.0). CONCLUSION: Highly variable CoW morphology was demonstrated in patients undergoing endarterectomy compared to controls. Likely compromised CoW in relation to cerebral ischemia was observed in a large cohort of carotid endarterectomy subjects. KEY POINTS: • CoW variant distribution significantly differed in the study and control groups (p<0.001). • ICA stenosis was the only independent predictor of CoW morphology (p<0.001). • Severely compromised CoW configuration showed significant association with brain ischemia (p=0.002).