Search

During the latest years, artificial intelligence, and especially machine learning (ML), have experienced a growth in popularity due to their versatility and potential in solving complex problems. In fact, ML allows the efficient handling of big volumes of data, allowing to tackle issues that were unfeasible before, especially with deep learning, which utilizes multilayered neural networks. Cardiac computed tomography (CT) is also experiencing a rise in examination numbers, and ML might help handle the increasing derived information. Moreover, cardiac CT presents some fields wherein ML may be pivotal, such as coronary calcium scoring, CT angiography, and perfusion. In particular, the main applications of ML involve image preprocessing and postprocessing, and the development of risk assessment models based on imaging findings. Concerning image preprocessing, ML can help improve image quality by optimizing acquisition protocols or removing artifacts that may hinder image analysis and interpretation. ML in image postprocessing might help perform automatic segmentations and shorten examination processing times, also providing tools for tissue characterization, especially concerning plaques. The development of risk assessment models from ML using data from cardiac CT could aid in the stratification of patients who undergo cardiac CT in different risk classes and better tailor their treatment to individual conditions. While ML is a powerful tool with great potential, applications in the field of cardiac CT are still expanding, and not yet routinely available in clinical practice due to the need for extensive validation. Nevertheless, ML is expected to have a big impact on cardiac CT in the near future.

Background: The influence of computed tomography (CT) reconstruction algorithms on the performance of machine-learning-based CT-derived fractional flow reserve (CT-FFR ML ) has not been investigated. CT-FFR ML values and processing time of two reconstruction algorithms were compared using an on-site workstation., Methods: CT-FFR ML was computed on 40 coronary CT angiography (CCTA) datasets that were reconstructed with both iterative reconstruction in image space (IRIS) and filtered back-projection (FBP) algorithms. CT-FFR ML was computed on a per-vessel and per-segment basis as well as distal to lesions with ≥50% stenosis on CCTA. Processing times were recorded. Significant flow-limiting stenosis was defined as invasive FFR and CT-FFR ML values ≤ 0.80. Pearson's correlation, Wilcoxon, and McNemar statistical testing were used for data analysis., Results: Per-vessel analysis of IRIS and FBP reconstructions demonstrated significantly different CT-FFR ML values (p ≤ 0.05). Correlation of CT-FFR ML values between algorithms was high for the left main (r = 0.74), left anterior descending (r = 0.76), and right coronary (r = 0.70) arteries. Proximal and middle segments showed a high correlation of CT-FFR ML values (r = 0.73 and r = 0.67, p ≤ 0.001, respectively), despite having significantly different averages (p ≤ 0.05). No difference in diagnostic accuracy was observed (both 81.8%, p = 1.000). Of the 40 patients, 10 had invasive FFR results. Per-lesion correlation with invasive FFR values was moderate for IRIS (r = 0.53, p = 0.117) and FBP (r = 0.49, p = 0.142). Processing time was significantly shorter using IRIS (15.9 vs. 19.8 min, p ≤ 0.05)., Conclusion: CT reconstruction algorithms influence CT-FFR ML analysis, potentially affecting patient management. Additionally, iterative reconstruction improves CT-FFR ML post-processing speed., (Published by Elsevier Inc.)

This study investigated the impact of coronary CT angiography (cCTA)-derived plaque markers and machine-learning-based CT-derived fractional flow reserve (CT-FFR) to identify adverse cardiac outcome. Data of 82 patients (60 ± 11 years, 62% men) who underwent cCTA and invasive coronary angiography (ICA) were analyzed in this single-center retrospective, institutional review board-approved, HIPAA-compliant study. Follow-up was performed to record major adverse cardiac events (MACE). Plaque quantification of lesions responsible for MACE and control lesions was retrospectively performed semiautomatically from cCTA together with machine-learning based CT-FFR. The discriminatory value of plaque markers and CT-FFR to predict MACE was evaluated. After a median follow-up of 18.5 months (interquartile range 11.5 to 26.6 months), MACE was observed in 18 patients (21%). In a multivariate analysis the following markers were predictors of MACE (odds ratio [OR]): lesion length (OR 1.16, p = 0.018), low-attenuation plaque (<30 HU) (OR 4.59, p = 0.003), Napkin ring sign (OR 2.71, p = 0.034), stenosis ≥50% (OR 3.83, p 0.042), and CT-FFR ≤0.80 (OR 7.78, p = 0.001). Receiver operating characteristics analysis including stenosis ≥50%, plaque markers and CT-FFR ≤0.80 (Area under the curve 0.94) showed incremental discriminatory power over stenosis ≥50% alone (Area under the curve 0.60, p <0.0001) for the prediction of MACE. cCTA-derived plaque markers and machine-learning CT-FFR demonstrate predictive value to identify MACE. In conclusion, combining plaque markers with machine-learning CT-FFR shows incremental discriminatory power over cCTA stenosis grading alone., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Objectives: We sought to investigate the diagnostic performance of coronary CT angiography (cCTA)-derived plaque markers combined with deep machine learning-based fractional flow reserve (CT-FFR) to identify lesion-specific ischemia using invasive FFR as the reference standard., Methods: Eighty-four patients (61 ± 10 years, 65% male) who had undergone cCTA followed by invasive FFR were included in this single-center retrospective, IRB-approved, HIPAA-compliant study. Various plaque markers were derived from cCTA using a semi-automatic software prototype and deep machine learning-based CT-FFR. The discriminatory value of plaque markers and CT-FFR to identify lesion-specific ischemia on a per-vessel basis was evaluated using invasive FFR as the reference standard., Results: One hundred three lesion-containing vessels were investigated. 32/103 lesions were hemodynamically significant by invasive FFR. In a multivariate analysis (adjusted for Framingham risk score), the following markers showed predictive value for lesion-specific ischemia (odds ratio [OR]): lesion length (OR 1.15, p = 0.037), non-calcified plaque volume (OR 1.02, p = 0.007), napkin-ring sign (OR 5.97, p = 0.014), and CT-FFR (OR 0.81, p < 0.0001). A receiver operating characteristics analysis showed the benefit of identifying plaque markers over cCTA stenosis grading alone, with AUCs increasing from 0.61 with ≥ 50% stenosis to 0.83 with addition of plaque markers to detect lesion-specific ischemia. Further incremental benefit was realized with the addition of CT-FFR (AUC 0.93)., Conclusion: Coronary CTA-derived plaque markers portend predictive value to identify lesion-specific ischemia when compared to cCTA stenosis grading alone. The addition of CT-FFR to plaque markers shows incremental discriminatory power., Key Points: • Coronary CT angiography (cCTA)-derived quantitative plaque markers of atherosclerosis portend high discriminatory power to identify lesion-specific ischemia. • Coronary CT angiography-derived fractional flow reserve (CT-FFR) shows superior diagnostic performance over cCTA alone in detecting lesion-specific ischemia. • A combination of plaque markers with CT-FFR provides incremental discriminatory value for detecting flow-limiting stenosis.

Propelled by the synergy of the groundbreaking advancements in the ability to analyze high-dimensional datasets and the increasing availability of imaging and clinical data, machine learning (ML) is poised to transform the practice of cardiovascular medicine. Owing to the growing body of literature validating both the diagnostic performance as well as the prognostic implications of anatomic and physiologic findings, coronary computed tomography angiography (CCTA) is now a well-established non-invasive modality for the assessment of cardiovascular disease. ML has been increasingly utilized to optimize performance as well as extract data from CCTA as well as non-contrast enhanced cardiac CT scans. The purpose of this review is to describe the contemporary state of ML based algorithms applied to cardiac CT, as well as to provide clinicians with an understanding of its benefits and associated limitations., (Copyright © 2018. Published by Elsevier Inc.)

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. [ABSTRACT FROM AUTHOR]