-
1.
Ischemia and outcome prediction by cardiac CT based machine learning.
Brandt, V, Emrich, T, Schoepf, UJ, Dargis, DM, Bayer, RR, De Cecco, CN, Tesche, C
The international journal of cardiovascular imaging. 2020;(12):2429-2439
Abstract
Cardiac CT using non-enhanced coronary artery calcium scoring (CACS) and coronary CT angiography (cCTA) has been proven to provide excellent evaluation of coronary artery disease (CAD) combining anatomical and morphological assessment of CAD for cardiovascular risk stratification and therapeutic decision-making, in addition to providing prognostic value for the occurrence of adverse cardiac outcome. In recent years, artificial intelligence (AI) and, in particular, the application of machine learning (ML) algorithms, have been promoted in cardiovascular CT imaging for improved decision pathways, risk stratification, and outcome prediction in a more objective, reproducible, and rational manner. AI is based on computer science and mathematics that are based on big data, high performance computational infrastructure, and applied algorithms. The application of ML in daily routine clinical practice may hold potential to improve imaging workflow and to promote better outcome prediction and more effective decision-making in patient management. Moreover, CT represents a field wherein ML may be particularly useful, such as CACS and cCTA. Thus, the purpose of this review is to give a short overview about the contemporary state of ML based algorithms in cardiac CT, as well as to provide clinicians with currently available scientific data on clinical validation and implementation of these algorithms for the prediction of ischemia-specific CAD and cardiovascular outcome.
-
2.
Randomized Comparison Between Everolimus-Eluting Bioresorbable Scaffold and Metallic Stent: Multimodality Imaging Through 3 Years.
Onuma, Y, Honda, Y, Asano, T, Shiomi, H, Kozuma, K, Ozaki, Y, Namiki, A, Yasuda, S, Ueno, T, Ando, K, et al
JACC. Cardiovascular interventions. 2020;(1):116-127
Abstract
OBJECTIVES The aim of this study was to investigate the vascular responses and fates of the scaffold after bioresorbable vascular scaffold (BVS) implantation using multimodality imaging. BACKGROUND Serial comprehensive image assessments after BVS implantation in the context of a randomized trial have not yet been reported. METHODS In the ABSORB Japan trial, 400 patients were randomized to a BVS (n = 266) or a cobalt-chromium everolimus-eluting stent (n = 134). Through 3 years, patients underwent serial angiography and intravascular ultrasound or optical coherence tomography (OCT). RESULTS Luminal dimension at 3 years was consistently smaller with the BVS than with the cobalt-chromium everolimus-eluting stent (mean angiographic minimal luminal diameter 2.04 ± 0.63 mm vs. 2.40 ± 0.56 mm, mean difference -0.37 mm [95% confidence interval: -0.50 to -0.24 mm]; p < 0.001), mainly because of smaller device area (6.13 ± 2.03 mm2 vs. 7.15 ± 2.16 mm2, mean difference -1.04 mm2 [95% confidence interval: -1.66 to -0.42 mm2]; p < 0.001), and larger neointimal area (2.10 ± 0.61 mm2 vs. 1.86 ± 0.64 mm2, mean difference 0.24 mm2 [95% confidence interval: 0.06 to 0.43 mm2]; p = 0.01) by OCT. BVS-treated vessels did not show previously reported favorable vessel responses, such as positive vessel remodeling, late luminal enlargement, and restoration of vasomotion, although the OCT-based healing score was on average zero (interquartile range: 0.00 to 0.00). At 3 years, intraluminal scaffold dismantling (ISD) was observed in 14% of BVS. On serial OCT, ISD was observed in 6 lesions at 2 years, where the struts had been fully apposed at post-procedure, while ISD was observed in 12 lesions at 3 years, where 8 lesions were free from ISD on 2-year OCT. In 5 cases of very late scaffold thrombosis, strut discontinuities were detected in all 4 cases with available OCT immediately before reintervention. CONCLUSIONS In this multimodality serial imaging study, luminal dimension at 3 years was smaller with the BVS than with the cobalt-chromium everolimus-eluting stent. ISD, suspected to be one of the mechanisms of very late BVS thrombosis, was observed in a substantial proportion of cases at 3 years, which developed between post-procedure and 2 years and even beyond 2 years. (AVJ-301 Clinical Trial: A Clinical Evaluation of AVJ-301 [Absorb™ BVS] in Japanese Population [ABSORB JAPAN]; NCT01844284).
-
3.
Motion-corrected coronary calcium scores by a convolutional neural network: a robotic simulating study.
Zhang, Y, van der Werf, NR, Jiang, B, van Hamersvelt, R, Greuter, MJW, Xie, X
European radiology. 2020;(2):1285-1294
Abstract
OBJECTIVE To classify motion-induced blurred images of calcified coronary plaques so as to correct coronary calcium scores on nontriggered chest CT, using a deep convolutional neural network (CNN) trained by images of motion artifacts. METHODS Three artificial coronary arteries containing nine calcified plaques of different densities (high, medium, and low) and sizes (large, medium, and small) were attached to a moving robotic arm. The artificial arteries moving at 0-90 mm/s were scanned to generate nine categories (each from one calcified plaque) of images with motion artifacts. An inception v3 CNN was fine-tuned and validated. Agatston scores of the predicted classification by CNN were considered as corrected scores. Variation of Agatston scores on moving plaque and by CNN correction was calculated using the scores at rest as reference. RESULTS The overall accuracy of CNN classification was 79.2 ± 6.1% for nine categories. The accuracy was 88.3 ± 4.9%, 75.9 ± 6.4%, and 73.5 ± 5.0% for the high-, medium-, and low-density plaques, respectively. Compared with the Agatston score at rest, the overall median score variation was 37.8% (1st and 3rd quartile, 10.5% and 68.8%) in moving plaques. CNN correction largely decreased the variation to 3.7% (1.9%, 9.1%) (p < 0.001, Mann-Whitney U test) and improved the sensitivity (percentage of non-zero scores among all the scores) from 65 to 85% for detection of coronary calcifications. CONCLUSIONS In this experimental study, CNN showed the ability to classify motion-induced blurred images and correct calcium scores derived from nontriggered chest CT. CNN correction largely reduces the overall Agatston score variation and increases the sensitivity to detect calcifications. KEY POINTS • A deep CNN architecture trained by CT images of motion artifacts showed the ability to correct coronary calcium scores from blurred images. • A correction algorithm based on deep CNN can be used for a tenfold reduction in Agatston score variations from 38 to 3.7% of moving coronary calcified plaques and to improve the sensitivity from 65 to 85% for the detection of calcifications. • This experimental study provides a method to improve its accuracy for coronary calcium scores that is a fundamental step towards a real clinical scenario.
-
4.
Prognostic value of coronary artery calcium score in symptomatic individuals: A meta-analysis of 34,000 subjects.
Lo-Kioeng-Shioe, MS, Rijlaarsdam-Hermsen, D, van Domburg, RT, Hadamitzky, M, Lima, JAC, Hoeks, SE, Deckers, JW
International journal of cardiology. 2020;:56-62
Abstract
BACKGROUND Coronary artery calcium (CAC) scanning has evolved into an important subclinical prediction method for cardiovascular diseases in asymptomatic subjects. However, the prognostic implication of CAC scanning in symptomatic individuals is less clear. OBJECTIVES To assess the prognostic utility of CAC in predicting risk of major adverse cardiac events (MACE) in stable patients with suspected CAD. METHODS We did a systematic electronic literature search for studies presenting original data in CAC score, and reporting cardiovascular events in stable, symptomatic patients as primary outcome. Primary outcome of the meta-analysis was the occurrence of MACE, a composite of late coronary revascularization, hospitalization for unstable angina or heart failure, nonfatal myocardial infarction, and cardiac death or all-cause mortality. Using random effects models, we pooled relative risk ratios of CAC for MACE, and adjusted hazard ratios (HR) of the associations between different CAC strata (CAC 0-100,100-400, and ≥ 400, versus CAC = 0) and incident MACE. RESULTS We included 19 observational studies (n = 34,041). In total, 1601 events were analyzed, of which 158 in patients with CAC = 0. The pooled relative risk ratio was 5.71 (95%-CI: 3.98;8.19) for subjects with CAC > 0. The pooled estimate of adjusted HRs demonstrated increasing, positive associations, with the strongest association for CAC > 400 (HR: 4.88; 95%-CI: 2.44;9.27). CONCLUSIONS This meta-analysis demonstrated that increased levels of CAC are strongly and independently associated with increased risk for MACE in stable, symptomatic patients with suspected CAD, showing increasing risk with greater CAC scores. Application of CAC scanning as a prediction method could be useful for a considerable number of such patients.
-
5.
The Relationship of Coronary Artery Calcium and Clinical Coronary Artery Disease with Cognitive Function: A Systematic Review and Meta-Analysis.
Xia, C, Vonder, M, Sidorenkov, G, Oudkerk, M, de Groot, JC, van der Harst, P, de Bock, GH, De Deyn, PP, Vliegenthart, R
Journal of atherosclerosis and thrombosis. 2020;(9):934-958
-
-
Free full text
-
Abstract
AIM: Coronary artery disease (CAD) and cognitive impairment are common in the elderly, with evidence for shared risk factors and pathophysiological processes. The coronary artery calcium (CAC) score is a marker of subclinical CAD, which may allow early detection of individuals prone to cognitive decline. Prior studies on associations of CAC and clinical CAD with cognitive impairment had discrepant results. This systematic review aims to evaluate the association of (sub)clinical CAD with cognitive function, cognitive decline, and diagnosis of mild cognitive impairment (MCI) or dementia. METHODS A systematic search was conducted in MEDLINE, Embase, and Web of Science until February 2019, supplemented with citations tracking. Two reviewers independently screened studies and extracted information including odds ratios (ORs) and hazard ratios (HRs). RESULTS Forty-six studies, 10 on CAC and 36 on clinical CAD, comprising 1,248,908 participants were included in the systematic review. Studies about associations of (sub)clinical CAD with cognitive function and cognitive decline had heterogeneous methodology and inconsistent findings. Two population-based studies investigated the association between CAC and risk of dementia over 6-12.2 years using different CAC scoring methods. Both found a tendency toward higher risk of dementia as CAC severity increased. Meta-analysis in 15 studies (663,250 individuals) showed an association between CAD and MCI/dementia (pooled OR 1.32, 95%CI 1.17-1.48) with substantial heterogeneity (I2=87.0%, p<0.001). Pooled HR of CAD for incident MCI/dementia over 3.2-25.5 years in six longitudinal studies (70,060 individuals) was 1.51 (95%CI 1.24-1.85), with low heterogeneity (I2=14.1%, p=0.32). Sensitivity analysis did not detect any study that was of particular influence on the pooled OR or HR. CONCLUSIONS Limited evidence suggests the CAC score is associated with risk of dementia. In clinical CAD, risk of MCI and dementia is increased by 50%, as supported by stronger evidence.
-
6.
Coronary 18F-Fluoride Uptake and Progression of Coronary Artery Calcification.
Doris, MK, Meah, MN, Moss, AJ, Andrews, JPM, Bing, R, Gillen, R, Weir, N, Syed, M, Daghem, M, Shah, A, et al
Circulation. Cardiovascular imaging. 2020;(12):e011438
-
-
Free full text
-
Abstract
Background Positron emission tomography (PET) using 18F-sodium fluoride (18F-fluoride) to detect microcalcification may provide insight into disease activity in coronary atherosclerosis. This study aimed to investigate the relationship between 18F-fluoride uptake and progression of coronary calcification in patients with clinically stable coronary artery disease. Methods Patients with established multivessel coronary atherosclerosis underwent 18F-fluoride PET-computed tomography angiography and computed tomography calcium scoring, with repeat computed tomography angiography and calcium scoring at one year. Coronary PET uptake was analyzed qualitatively and semiquantitatively in diseased vessels by measuring maximum tissue-to-background ratio. Coronary calcification was quantified by measuring calcium score, mass, and volume. Results In a total of 183 participants (median age 66 years, 80% male), 116 (63%) patients had increased 18F-fluoride uptake in at least one vessel. Individuals with increased 18F-fluoride uptake demonstrated more rapid progression of calcification compared with those without uptake (change in calcium score, 97 [39-166] versus 35 [7-93] AU; P<0.0001). Indeed, the calcium score only increased in coronary segments with 18F-fluoride uptake (from 95 [30-209] to 148 [61-289] AU; P<0.001) and remained unchanged in segments without 18F-fluoride uptake (from 46 [16-113] to 49 [20-115] AU; P=0.329). Baseline coronary 18F-fluoride maximum tissue-to-background ratio correlated with 1-year change in calcium score, calcium volume, and calcium mass (Spearman ρ=0.37, 0.38, and 0.46, respectively; P<0.0001 for all). At the segmental level, baseline 18F-fluoride activity was an independent predictor of calcium score at 12 months (P<0.001). However, at the patient level, this was not independent of age, sex, and baseline calcium score (P=0.50). Conclusions Coronary 18F-fluoride uptake identifies both patients and individual coronary segments with more rapid progression of coronary calcification, providing important insights into disease activity within the coronary circulation. At the individual patient level, total calcium score remains an important marker of disease burden and progression. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT02110303.
-
7.
Association between debulking area of rotational atherectomy and platform revolution speed-Frequency domain optical coherence tomography analysis.
Mizutani, K, Hara, M, Nakao, K, Yamaguchi, T, Okai, T, Nomoto, Y, Kajio, K, Kaneno, Y, Yamazaki, T, Ehara, S, et al
Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions. 2020;(1):E1-E7
Abstract
OBJECTIVES In this study, we sought to investigate the association between revolution speed of rotational atherectomy (RA) and debulking area assessed by frequency domain-optical coherence tomography (FD-OCT). BACKGROUND The number of patients with severe calcified coronary artery disease requiring treatment with calcium ablation, such as RA, is increasing. However, there is little evidence available regarding the association between debulking area and revolution speed during RA. METHODS We retrospectively investigated 30 consecutive severely calcified coronary lesions in 29 patients who underwent RA under FD-OCT guidance. The association between preset revolution speed of RA and burr size-corrected debulking area of the calcified lesion was evaluated using a multivariable regression model with nonlinear restricted-cubic-spline, which can help assess nonlinear associations between variables. RESULTS The median age of study participants was 73 years (quartile 65-78); 82.8% were male. The median burr size was 1.5 mm (1.5-1.75); median total duration of ablation was 120 s (100-180). FD-OCT revealed that the post-procedural minimum lumen area increased significantly from 1.64 mm2 (1.40-2.09) to 2.45 mm2 (2.11-2.98) (p < .001). In addition, the burr size-corrected debulking area increased significantly as the preset revolution speed decreased (p = .018), especially when the revolution speed was less than 150,000 rpm. This result implies that additional lumen gain will be obtained by decreasing rpm when the burr speed is set at <150,000 rpm. CONCLUSIONS FD-OCT demonstrated that RA with lower revolution speed, below 150,000 rpm, has the potential to achieve greater calcium debulking effect in patients with severe calcified coronary lesions.
-
8.
The effect of Shexiang Tongxin Dropping Pills on coronary microvascular dysfunction (CMVD) among those with a mental disorder and non-obstructive coronary artery disease based on stress cardiac magnetic resonance images: A study protocol.
Tian, J, Zhang, L, Yang, X, Zuo, H, Zhao, X, Yong, J, He, Y, Song, X
Medicine. 2020;(21):e20099
-
-
Free full text
-
Abstract
INTRODUCTION Coronary microvascular dysfunction (CMVD), highly prevalent among patients with a mental disorder (anxiety or depression), is closely related to adverse cardiac events, including hospitalization, sudden cardiac death, and myocardial infarction. Shexiang Tongxin Dropping Pills (STDP), a traditional Chinese medicine, exerts endothelial protective function by anti-inflammation, anti-oxidative stress, and promoting blood circulation. STDP protects against CMVD in previous fundamental studies. The present trial is aiming at evaluating the effect of STDP on CMVD among depressed or anxious patients with non-obstructive coronary artery disease (NOCAD). METHODS AND ANALYSIS Seventy-two depressed or anxious patients diagnosed with NOCAD combined with CMVD utilizing coronary artery angiography and stress cardiac magnetic resonance (CMR) will be recruited in the present study. These patients will be randomized into two groups, namely, Nicorandil group (Nicorandil combined with routine medicine), and STDP groups (STDP combined with routine medicine). The change of CMVD status by assessing absolute myocardial blood flow and myocardial reperfusion using stress CMR 3-month after discharge is defined as the primary endpoint. Major adverse cardiac events (MACEs), quality of life (QOL), and metal disorder improvement are defined as the secondary endpoints. Seattle angina questionnaire (SAQ) which is used to assess angina pectoris and QOL will be recorded at 1-, 3-, 6-, 9-, 12-month of follow-up. Seven-item Generalized Anxiety Disorder Scale (GAD-7) and 9-item depression module from the Patient Health Questionnaire (PHQ9) which utilized to evaluate anxiety and depression, respectively, will be recorded at 1-, 3-, 6-, 9-, 12-month of follow-up. This study will first evaluate the efficacy of STDP on CMVD among patients with a mental disorder and NOCAD, and discuss the potential mechanisms, providing therapeutic evidence for the STDP for these patients.
-
9.
Artificial Intelligence in Coronary Computed Tomography Angiography: From Anatomy to Prognosis.
Muscogiuri, G, Van Assen, M, Tesche, C, De Cecco, CN, Chiesa, M, Scafuri, S, Guglielmo, M, Baggiano, A, Fusini, L, Guaricci, AI, et al
BioMed research international. 2020;:6649410
Abstract
Cardiac computed tomography angiography (CCTA) is widely used as a diagnostic tool for evaluation of coronary artery disease (CAD). Despite the excellent capability to rule-out CAD, CCTA may overestimate the degree of stenosis; furthermore, CCTA analysis can be time consuming, often requiring advanced postprocessing techniques. In consideration of the most recent ESC guidelines on CAD management, which will likely increase CCTA volume over the next years, new tools are necessary to shorten reporting time and improve the accuracy for the detection of ischemia-inducing coronary lesions. The application of artificial intelligence (AI) may provide a helpful tool in CCTA, improving the evaluation and quantification of coronary stenosis, plaque characterization, and assessment of myocardial ischemia. Furthermore, in comparison with existing risk scores, machine-learning algorithms can better predict the outcome utilizing both imaging findings and clinical parameters. Medical AI is moving from the research field to daily clinical practice, and with the increasing number of CCTA examinations, AI will be extensively utilized in cardiac imaging. This review is aimed at illustrating the state of the art in AI-based CCTA applications and future clinical scenarios.
-
10.
Coronary artery disease with normal lipids and low coronary artery calcium in two women with high lipoprotein(a).
Haxhi, J, Pershwitz, G, Thompson, PD
Journal of clinical lipidology. 2020;(2):186-188
Abstract
We present 2 patients with elevated levels of lipoprotein (a) and significant coronary artery disease despite having little coronary artery calcification. Clinicians should be aware that patients with elevated lipoprotein (a) may have important coronary artery disease with low coronary artery calcification scores.