Search

The field of coronary plaque analysis is advancing including more quantitative analysis of coronary artery diseases such as plaque burden, high-risk plaque features, computed tomography-derived fractional flow reserve, and radiomics. Although these biomarkers have shown great promise for the diagnosis and prognosis of cardiac patients in a research setting, many of these advanced analyses are labour and time intensive and therefore hard to implement in daily clinical practice. Artificial intelligence (AI) is playing an increasing role in supporting the quantification of these new biomarkers. AI offers the opportunity to increase efficiency, reduce human error and reader variability and to increase the accuracy of diagnosis and prognosis by automating many processing and supporting clinicians in their decision-making. With the use of AI these novel analysis approaches for coronary artery disease can be made feasible for clinical practice without increasing cost and workload and potentially improve patient care.

Background Scar burden with late gadolinium enhancement (LGE) cardiac MRI (CMR) predicts arrhythmic events in patients with postinfarction in single-center studies. However, LGE analysis requires experienced human observers, is time consuming, and introduces variability. Purpose To test whether postinfarct scar with LGE CMR can be quantified fully automatically by machines and to compare the ability of LGE CMR scar analyzed by humans and machines to predict arrhythmic events. Materials and Methods This study is a retrospective analysis of the multicenter, multivendor CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry. Patients with chronic heart failure, echocardiographic left ventricular ejection fraction (LVEF) of less than 50%, and LGE CMR were recruited (from January 2015 through December 2020). In the current study, only patients with ischemic cardiomyopathy were included. Quantification of total, dense, and nondense scars was carried out by two experienced readers or a Ternaus network, trained and tested with LGE images of 515 and 246 patients, respectively. Univariable and multivariable Cox analyses were used to assess patient and cardiac characteristics associated with a major adverse cardiac event (MACE). Area under the receiver operating characteristic curve (AUC) was used to compare model performances. Results In 761 patients (mean age, 65 years ± 11, 671 men), 83 MACEs occurred. With use of the testing group, univariable Cox-analysis found New York Heart Association class, left ventricle volume and/or function parameters (by echocardiography or CMR), guideline criterion (LVEF of ≤35% and New York Heart Association class II or III), and LGE scar analyzed by humans or the machine-learning algorithm as predictors of MACE. Machine-based dense or total scar conferred incremental value over the guideline criterion for the association with MACE (AUC: 0.68 vs 0.63, P = .02 and AUC: 0.67 vs 0.63, P = .01, respectively). Modeling with competing risks yielded for dense and total scar (AUC: 0.67 vs 0.61, P = .01 and AUC: 0.66 vs 0.61, P = .005, respectively). Conclusion In this analysis of the multicenter CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry, fully automatic machine learning-based late gadolinium enhancement analysis reliably quantifies myocardial scar mass and improves the current prediction model that uses guideline-based risk criteria for implantable cardioverter defibrillator implantation. ClinicalTrials.gov registration no.: NCT03352648 Published under a CC BY 4.0 license. Supplemental material is available for this article. ispartof: Radiology vol:307 issue:3 pages:e222239- ispartof: location:United States status: published

BackgroundLatent tuberculosis infection (LTBI) has been associated with increased cardiovascular risk. We investigated the activation and pro-inflammatory profile of monocytes in individuals with LTBI and their association with coronary artery disease (CAD).MethodsIndividuals 40–70 years old in Lima, Peru, underwent QuantiFERON-TB testing to define LTBI, completed a coronary computed tomography angiography to evaluate CAD, and provided blood for monocyte profiling using flow cytometry. Cells were stimulated with lipopolysaccharide to assess interleukin-6 (IL-6) and tumor necrosis factor (TNF)–α responses.ResultsThe clinical characteristics of the LTBI (n = 28) and non-LTBI (n = 41) groups were similar. All monocyte subsets from LTBI individuals exhibited higher mean fluorescence intensity (MFI) of CX3CR1 and CD36 compared with non-LTBI individuals. LTBI individuals had an increased proportion of nonclassical monocytes expressing IL-6 (44.9 vs 26.9; P = .014), TNF-α (62.3 vs 35.1; P = .014), and TNF-α+IL-6+ (43.2 vs 36.6; P = .042). Among LTBI individuals, CAD was associated with lower CX3CR1 MFI on classical monocytes and lower CD36 MFI across all monocyte subsets. In multivariable analyses, lower CD36 MFI on total monocytes (b = −0.17; P = .002) and all subsets remained independently associated with CAD in LTBI.ConclusionsIndividuals with LTBI have distinct monocyte alterations suggestive of an exacerbated inflammatory response and tissue migration. Whether these alterations contribute to cardiovascular disease pathogenesis warrants further investigation.

Background: Coronary artery calcium (CAC) is commonly quantified as the product of 2 generally correlated measures: plaque area and calcium density. Objectives: The authors sought to determine whether discordance between calcium area and density has long-term prognostic importance in atherosclerotic cardiovascular disease (ASCVD) risk. Methods: The authors studied 10,373 primary prevention participants from the CAC Consortium with CAC >0. Based on their median values, calcium area and mean calcium density were divided into 4 mutually exclusive concordant/discordant groups. Cox proportional hazards regression assessed the association of calcium area/density groups with ASCVD mortality over a median of 11.7 years, adjusting for traditional risk factors and the Agatston CAC score. Results: The mean age was 56.7 years, and 24% were female. The prevalence of plaque discordance was 19% (9% low calcium area/high calcium density, 10% high calcium area/low calcium density). Female sex (odds ratio [OR]: 1.48 [95% CI: 1.27-1.74]) and body mass index (OR: 0.81 [95% CI: 0.76-0.87], per 5 kg/m 2 higher) were significantly associated with high calcium density discordance, whereas diabetes (OR: 2.23 [95% CI: 1.85-3.19]) was most strongly associated with discordantly low calcium density. Compared to those with low calcium area/low calcium density, individuals with low calcium area/high calcium density had a 71% lower risk of ASCVD death (HR: 0.29 [95% CI: 0.09-0.95]). Conclusions: For a given CAC score, high calcium density relative to plaque area confers lower long-term ASCVD risk, likely serving as an imaging marker of biological resilience for lesion vulnerability. Additional research is needed to define a robust definition of calcium area/density discordance for routine clinical risk prediction.

BACKGROUND. Transthoracic echocardiography (TTE) is the standard of care for initial evaluation of patients with suspected cardioembolic stroke. Although TTE is useful for assessing certain sources of cardiac emboli, its diagnostic capability is limited in the detection of other sources, including left atrial thrombus and aortic plaques.OBJECTIVE. The purpose of this article was to investigate sensitivity, specificity, and predictive value of cardiac CTA (CCTA), cardiac MRI (CMRI), and TTE for recurrence in patients with suspected cardioembolic stroke.METHODS. We retrospectively included 151 patients with suspected cardioembolic stroke who underwent TTE and either CMRI (n = 75) or CCTA (n = 76) between January 2013 and May 2017. We evaluated for the presence of left atrial thrombus, left ventricular thrombus, vulnerable aortic plaque, cardiac tumors, and valvular vegetation as causes of cardioembolic stroke. The end point was stroke recurrence. Sensitivity, specificity, PPV, and NPV for recurrent stroke were calculated; the diagnostic accuracy of CMRI, CCTA, and TTE was compared between and within groups using AUC.RESULTS. Twelve and 14 recurrent strokes occurred in the CCTA and CMRI groups, respectively. Sensitivity, specificity, PPV, and NPV were 33.3%, 93.7%, 50.0%, and 88.2% for CCTA; 14.3%, 80.3%, 14.3%, and 80.3% for CMRI; 14.3%, 83.6%, 16.7%, and 80.9% for TTE in the CMRI group; and 8.3%, 93.7%, 20.0%, and 84.5% for TTE in the CCTA group. Accuracy was not different (p>.05) between CCTA (AUC = 0.63; 95% CI, 0.49-0.77), CMRI (0.53; 95% CI, 0.42-0.63), TTE in the CMRI group (0.51; 95% CI, 0.40-0.61), and TTE in the CCTA group (0.51; 95% CI, 0.42-0.59). In the CCTA group, atrial and ventricular thrombus were detected by CCTA in three patients and TTE in one patient; in the CMRI group, thrombus was detected by CMRI in one patient and TTE in two patients.CONCLUSION. CCTA, CMRI, and TTE showed comparably high specificity and NPV for cardioembolic stroke recurrence. CCTA and CMRI may be valid alternatives to TTE. CCTA may be preferred given potentially better detection of atrial and ventricular thrombus.CLINICAL IMPACT. CCTA and CMRI have similar clinical performance as TTE for predicting cardioembolic stroke recurrence. This observation may be especially important when TTE provides equivocal findings.

Coronary artery calcium (CAC) is a specific marker of coronary atherosclerosis that can be used to measure calcified subclinical atherosclerotic burden. The Agatston method is the most widely used scoring algorithm for quantifying CAC and is expressed as the product of total calcium area and a quantized peak calcium density weighting factor defined by the calcification attenuation in HU on noncontrast computed tomography. Calcium density has emerged as an important area of inquiry because the Agatston score is upweighted based on the assumption that peak calcium density and atherosclerotic cardiovascular disease (ASCVD) risk are positively correlated. However, recent evidence demonstrates that calcium density is inversely associated with lesion vulnerability and ASCVD risk in population-based cohorts when accounting for age and plaque area. Here, we review calcium density by focusing on 3 main areas: 1) CAC scan acquisition parameters; 2) pathophysiology of calcified plaques; and 3) epidemiologic evidence relating calcium density to ASCVD outcomes. Through this process, we hope to provide further insight into the evolution of CAC scoring on noncontrast computed tomography.

We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 using 1208 chest X-rays (CXRs) of 396 COVID-19 patients obtained through the course of the disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using a two-stage transfer learning technique to train a convolutional neural network (CNN), we show that the algorithm is able to classify four classes of disease severity (normal, mild, moderate, and severe) with the average Area Under the Curve (AUC) of 0.93. In addition, we show that the outputs of different layers of the CNN under dominant filters provide valuable insight about the subtle patterns in the CXRs, which can improve the accuracy in the reading of CXRs by a radiologist. Finally, we show that our approach can be used for studying the disease progression in a single patient and its influencing factors. The results suggest that our technique can form the foundation of a more concrete clinical model to predict the evolution of COVID-19 severity and the efficacy of different treatments for each patient through using CXRs and clinical data in the early stages of the disease. This use of AI to assess the severity and possibly predicting the future stages of the disease early on, will be essential in dealing with the upcoming waves of COVID-19 and optimizing resource allocation and treatment.

The purpose of this review is to highlight the most impactful, educational, and frequently downloaded articles published in the Journal of Cardiovascular Computed Tomography (JCCT) for the year 2020. The JCCT reached new records in 2020 for the number of research submissions, published manuscripts, article downloads and social media impressions. The articles in this review were selected by the Editorial Board of the JCCT and are comprised predominately of original research publications in the following categories: Coronavirus disease 2019 (COVID-19), coronary artery disease, coronary physiology, structural heart disease, and technical advances. The Editorial Board would like to thank each of the authors, peer-reviewers and the readers of JCCT for making 2020 one of the most successful years in its history, despite the challenging circumstances of the global COVID-19 pandemic.

Objective: The purpose was to evaluate reader variability between experienced and in-training radiologists of COVID-19 pneumonia severity on chest radiograph (CXR), and to create a multireader database suitable for AI development. Methods: In this study, CXRs from polymerase chain reaction positive COVID-19 patients were reviewed. Six experienced cardiothoracic radiologists and two residents classified each CXR according to severity. One radiologist performed the classification twice to assess intraobserver variability. Severity classification was assessed using a 4-class system: normal (0), mild (1), moderate (2), and severe (3). A median severity score (Rad Med) for each CXR was determined for the six radiologists for development of a multireader database (XCOMS). Kendal Tau correlation and percentage of disagreement were calculated to assess variability. Results: A total of 397 patients (1208 CXRs) were included (mean age, 60 years SD ± 1), 189 men). Interobserver variability between the radiologists ranges between 0.67 and 0.78. Compared to the Rad Med score, the radiologists show good correlation between 0.79–0.88. Residents show slightly lower interobserver agreement of 0.66 with each other and between 0.69 and 0.71 with experienced radiologists. Intraobserver agreement was high with a correlation coefficient of 0.77. In 220 (18%), 707 (59%), 259 (21%) and 22 (2%) CXRs there was a 0, 1, 2 or 3 class-difference. In 594 (50%) CXRs the median scores of the residents and the radiologists were similar, in 578 (48%) and 36 (3%) CXRs there was a 1 and 2 class-difference. Conclusion: Experienced and in-training radiologists demonstrate good inter- and intraobserver agreement in COVID-19 pneumonia severity classification. A higher percentage of disagreement was observed in moderate cases, which may affect training of AI algorithms. Advances in knowledge: Most AI algorithms are trained on data labeled by a single expert. This study shows that for COVID-19 X-ray severity classification there is significant variability and disagreement between radiologist and between residents.

This review aims to summarize original articles published in the Journal of Cardiovascular Computed Tomography (JCCT) for the year 2021, focusing on those that had the most scientific and educational impact. The JCCT continues to expand; the number of submissions, published manuscripts, cited articles, article downloads, social media presence, and impact factor continues to increase. The articles selected by the Editorial Board of the JCCT in this review focus on coronary artery disease, coronary physiology, structural heart disease, and technical advances in cardiovascular CT. In addition, we highlight key consensus documents and guidelines published in the Journal in 2021. The Journal recognizes the tremendous work done by each author and reviewer this year - thank you.

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.

OBJECTIVE. The purpose of this study was to prospectively evaluate, using software support, the feasibility and the quantitative and qualitative image quality parameters of a tube voltage-tailored contrast medium (CM) application protocol for patient-specific injection during coronary CT angiography (CCTA). SUBJECTS AND METHODS. In the Voltage-Based Contrast Media Adaptation in Coronary Computed Tomography Angiography (VOLCANIC-CTA) study, a single-center trial, 120 patients referred for CCTA were prospectively assigned to a tube voltage-tailored CM injection protocol. Automated tube voltage levels were selected in 10-kV intervals and ranged from 70 to 130 kV, and the iodine delivery rate (IDR) was adapted to the tube voltage level using dedicated software. The administered CM volume (370 mg I/mL) ranged from 33 mL at 70 kV (IDR, 0.7 g I/s) to 65 mL at 130 kV (IDR, 1.7 g I/s). Attenuation was measured in the aorta and coronary arteries to calculate quantitative signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and 5-point scales were used to evaluate overall image quality. Radiation metrics were also assessed and compared among the protocols. RESULTS. The mean age of the study patients was 62.5 ± 11.9 (SD) years. Image quality was rated as diagnostic in all patients. Contrast attenuation peaked at 70 kV (p < 0.001), whereas SNR and CNR parameters showed no significant differences between tube voltage levels (p ≥ 0.085). Additionally, no significant differences in subjective image quality parameters were found among the different protocols (p ≥ 0.139). The lowest radiation dose values were observed in the group assigned to the 70-kV protocol, which had a median radiation effective dose of 2.0 mSv (p < 0.001). CONCLUSION. The proposed tube voltage-tailored injection protocol allows individualized scanning of patients undergoing CCTA and significantly reduces CM and radiation dose while maintaining a high diagnostic image quality.

Artificial intelligence (AI) is entering the clinical arena, and in the early stage, its implementation will be focused on the automatization tasks, improving diagnostic accuracy and reducing reading time. Many studies investigate the potential role of AI to support cardiac radiologist in their day-to-day tasks, assisting in segmentation, quantification, and reporting tasks. In addition, AI algorithms can be also utilized to optimize image reconstruction and image quality. Since these algorithms will play an important role in the field of cardiac radiology, it is increasingly important for radiologists to be familiar with the potential applications of AI. The main focus of this article is to provide an overview of cardiac-related AI applications for CT and MRI studies, as well as non-imaging-based applications for reporting and image optimization.

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.

Purpose: The purpose of this study was to evaluate the accuracy of a novel fully automated deep learning (DL) algorithm implementing a recurrent neural network (RNN) with long short-term memory (LSTM) for the detection of coronary artery calcium (CAC) from coronary computed tomography angiography (CCTA) data. Materials and Methods: Under an IRB waiver and in HIPAA compliance, a total of 194 patients who had undergone CCTA were retrospectively included. Two observers independently evaluated the image quality and recorded the presence of CAC in the right (RCA), the combination of left main and left anterior descending (LM-LAD), and left circumflex (LCx) coronary arteries. Noncontrast CACS scans were allowed to be used in cases of uncertainty. Heart and coronary artery centerline detection and labeling were automatically performed. Presence of CAC was assessed by a RNN-LSTM. The algorithm's overall and per-vessel sensitivity, specificity, and diagnostic accuracy were calculated. Results: CAC was absent in 84 and present in 110 patients. As regards CCTA, the median subjective image quality, signal-to-noise ratio, and contrast-to-noise ratio were 3.0, 13.0, and 11.4. A total of 565 vessels were evaluated. On a per-vessel basis, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 93.1% (confidence interval [CI], 84.3%-96.7%), 82.76% (CI, 74.6%-89.4%), and 86.7% (CI, 76.8%-87.9%), respectively, for the RCA, 93.1% (CI, 86.4%-97.7%), 95.5% (CI, 88.77%-98.75%), and 94.2% (CI. 90.2%-94.6%), respectively, for the LM-LAD, and 89.9% (CI, 80.2%-95.8%), 90.0% (CI, 83.2%-94.7%), and 89.9% (CI, 85.0%-94.1%), respectively, for the LCx. The overall sensitivity, specificity, and diagnostic accuracy were 92.1% (CI, 92.1%-95.2%), 88.9% (CI. 84.9%-92.1%), and 90.3% (CI, 88.0%-90.0%), respectively. When accounting for image quality, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 76.2%, 87.5%, and 82.2%, respectively, for poor-quality data sets and 93.3%, 89.2% and 90.9%, respectively, when data sets rated adequate or higher were combined. Conclusion: The proposed RNN-LSTM demonstrated high diagnostic accuracy for the detection of CAC from CCTA.

Because of a recent increase in survival rates and life expectancy of patients with congenital heart disease (CHD), radiologists are facing new challenges when imaging the peculiar anatomy of individuals with repaired CHD. Cardiac computed tomography and magnetic resonance are paramount noninvasive imaging tools that are useful in assessing patients with repaired CHD, and both techniques are increasingly performed in centers where CHD is not the main specialization. This review provides general radiologists with insight into the main issues of imaging patients with repaired CHD, and the most common findings and complications of each individual pathology and its repair.

Objectives: Computed tomography (CT) myocardial perfusion imaging (CT-MPI) with hyperemia induced by regadenoson was evaluated for the detection of myocardial ischemia, safety, relative radiation exposure, and patient experience compared with single-photon emission computed tomography (SPECT) imaging.Materials and Methods: Twenty-four patients (66.5 y, 29% male) who had undergone clinically indicated SPECT imaging and provided written informed consent were included in this phase II, IRB-approved, and FDA-approved clinical trial. All patients underwent coronary CT angiography and CT-MPI with hyperemia induced by the intravenous administration of regadenoson (0.4 mg/5 mL). Patient experience and findings on CT-MPI images were compared to SPECT imaging.Results: Patient experience and safety were similar between CT-MPI and SPECT procedures and no serious adverse events due to the administration of regadenoson occurred. SPECT resulted in a higher number of mild adverse events than CT-MPI. Patient radiation exposure was similar during the combined coronary computed tomography angiography and CT-MPI (4.4 [2.7] mSv) and SPECT imaging (5.6 [1.7] mSv) (P-value 0.401) procedures. Using SPECT as the reference standard, CT-MPI analysis showed a sensitivity of 58.3% (95% confidence interval [CI]: 27.7-84.8), a specificity of 100% (95% CI: 73.5-100), and an accuracy of 79.1% (95% CI: 57.9-92.87). Low apparent sensitivity occurred when the SPECT defects were small and highly suspicious for artifacts.Conclusions: This study demonstrated that CT-MPI is safe, well tolerated, and can be performed with comparable radiation exposure to SPECT. CT-MPI has the benefit of providing both complete anatomic coronary evaluation and assessment of myocardial perfusion.

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.

Objectives This study was conducted to investigate the influence of coronary artery calcium (CAC) score on the diagnostic performance of machine-learning–based coronary computed tomography (CT) angiography (cCTA)–derived fractional flow reserve (CT-FFR). Background CT-FFR is used reliably to detect lesion-specific ischemia. Novel CT-FFR algorithms using machine-learning artificial intelligence techniques perform fast and require less complex computational fluid dynamics. Yet, influence of CAC score on diagnostic performance of the machine-learning approach has not been investigated. Methods Four hundred eighty-two vessels from 314 patients (62.3 ± 9.3 years, 77% male) who underwent cCTA followed by invasive FFR were investigated from the MACHINE (Machine Learning based CT Angiography derived FFR: a Multi-center Registry) registry data. CAC scores were quantified using the Agatston convention. The diagnostic performance of CT-FFR to detect lesion-specific ischemia was assessed across all Agatston score categories (CAC 0, >0 to Results The diagnostic accuracy of CT-FFR versus invasive FFR was superior to cCTA alone on a per-vessel level (78% vs. 60%) and per patient level (83% vs. 73%) across all Agatston score categories. No statistically significant differences in the diagnostic accuracy, sensitivity, or specificity of CT-FFR were observed across the categories. CT-FFR showed good discriminatory power in vessels with high Agatston scores (CAC ≥ 400) and high performance in low-to-intermediate Agatston scores (CAC >0 to 0 to Conclusions Machine-learning–based CT-FFR showed superior diagnostic performance over cCTA alone in CAC with a significant difference in the performance of CT-FFR as calcium burden/Agatston calcium score increased. (Machine Learning Based CT Angiography Derived FFR: a Multicenter, Registry [MACHINE] NCT02805621).

The field of artificial intelligence (AI) is currently experiencing a period of extensive growth in a wide variety of fields, medicine not being the exception. The base of AI is mathematics and computer science, and the current fame of AI in industry and research stands on 3 pillars: big data, high performance computing infrastructure, and algorithms. In the current digital era, increased storage capabilities and data collection systems, lead to a massive influx of data for AI algorithm. The size and quality of data are 2 major factors influencing performance of AI applications. However, it is highly dependent on the type of task at hand and algorithm chosen to perform this task. AI may potentially automate several tedious tasks in radiology, particularly in cardiothoracic imaging, by pre-readings for the detection of abnormalities, accurate quantifications, for example, oncologic volume lesion tracking and cardiac volume and image optimization. Although AI-based applications offer great opportunity to improve radiology workflow, several challenges need to be addressed starting from image standardization, sophisticated algorithm development, and large-scale evaluation. Integration of AI into the clinical workflow also needs to address legal barriers related to security and protection of patient-sensitive data and liability before AI will reach its full potential in cardiothoracic imaging.

PURPOSE The purpose of this study was to evaluate the utilization of invasive and noninvasive tests and compare cost in patients presenting with chest pain to the emergency department (ED) who underwent either triple-rule-out computed tomography angiography (TRO-CTA) or standard of care. MATERIALS AND METHODS We performed a retrospective single-center analysis of 2156 ED patients who presented with acute chest pain with a negative initial troponin and electrocardiogram for myocardial injury. Patient cohorts matched by patient characteristics who had undergone TRO-CTA as a primary imaging test (n=1139) or standard of care without initial CTA imaging (n=1017) were included in the study. ED visits, utilization of tests, and costs during the initial episode of hospital care were compared. RESULTS No significant differences in the diagnosis of coronary artery disease, pulmonary embolism, or aortic dissection were observed. Median ED waiting time (4.5 vs. 7.0 h, P

Coronary physiology assessments have been shown by multiple trials to add clinical value in detecting significant coronary artery disease and predicting cardiovascular outcomes. Fractional flow reserve (FFR) obtained during invasive coronary angiography (ICA) has become the new reference standard for hemodynamic significance detection. Absolute myocardial blood flow (MBF) quantification by means of dynamic positron emission tomography (dPET) has high diagnostic and prognostic values. FFR is an invasive measure and as such cannot be applied broadly, while MBF quantification is commonly performed on standard vascular territories intermixing normal flow from normal regions with abnormal flow from abnormal regions and consequently limiting its diagnostic power. The aim of this study is to provide physicians with reliable software tools for the non-invasive assessment of lesion-specific physiological significance for the entire coronary tree by combining PET-derived absolute flow data and coronary computed tomography angiography (CTA)-derived anatomy and coronary centerlines. The dynamic PET/CTA myocardial blood flow assessment with fused imagery (DEMYSTIFY) study is an observational prospective clinical study to develop algorithms and software tools to fuse coronary anatomy data obtained from CTA with dPET data to non-invasively measure absolute MBF, myocardial flow reserve, and relative flow reserve across specific coronary lesions. Patients (N = 108) will be collected from 4 institutions (Emory University Hospital, USA; Chonnam National University Hospital, South Korea; Samsung Medical Center, South Korea; Seoul National University Hospital, South Korea). These results will be compared to those obtained invasively in the catheterization laboratory and to a relatively novel non-invasive technique to estimate FFR based on CTA and computational fluid dynamics. Success of these developments should lead to the following benefits: (1) eliminate unnecessary invasive coronary angiography in patients with no significant lesions, (2) avoid stenting physiologically insignificant lesions, (3) guide percutaneous coronary interventions process to the location of significant lesions, (4) provide a flow-color-coded 3D roadmap of the entire coronary tree to guide bypass surgery, and (5) use less radiation and lower the cost from unnecessary procedures. The DEMYSTIFY study has been registered on ClinicalTrials.gov with registration number NCT04221594.

Background and aims Artificial intelligence (AI) is increasing its role in diagnosis of patients with suspicious coronary artery disease. The aim of this manuscript is to develop a deep convolutional neural network (CNN) to classify coronary computed tomography angiography (CCTA) in the correct Coronary Artery Disease Reporting and Data System (CAD-RADS) category. Methods Two hundred eighty eight patients who underwent clinically indicated CCTA were included in this single-center retrospective study. The CCTAs were stratified by CAD-RADS scores by expert readers and considered as reference standard. A deep CNN was designed and tested on the CCTA dataset and compared to on-site reading. The deep CNN analyzed the diagnostic accuracy of the following three Models based on CAD-RADS classification: Model A (CAD-RADS 0 vs CAD-RADS 1–2 vs CAD-RADS 3,4,5), Model 1 (CAD-RADS 0 vs CAD-RADS>0), Model 2 (CAD-RADS 0–2 vs CAD-RADS 3–5). Time of analysis for both physicians and CNN were recorded. Results Model A showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 47%, 74%, 77%, 46% and 60%, respectively. Model 1 showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 66%, 91%, 92%, 63%, 86%, respectively. Conversely, Model 2 demonstrated the following sensitivity, specificity, negative predictive value, positive predictive value and accuracy: 82%, 58%, 74%, 69%, 71%, respectively. Time of analysis was significantly lower using CNN as compared to on-site reading (530.5 ± 179.1 vs 104.3 ± 1.4 sec, p=0.01) Conclusions Deep CNN yielded accurate automated classification of patients with CAD-RADS.

Aims Right ventricular systolic dysfunction (RVSD) is an important determinant of outcomes in heart failure (HF) cohorts. While the quantitative assessment of RV function is challenging using 2D-echocardiography, cardiac magnetic resonance (CMR) is the gold standard with its high spatial resolution and precise anatomical definition. We sought to investigate the prognostic value of CMR-derived RV systolic function in a large cohort of HF with reduced ejection fraction (HFrEF). Methods and results Study cohort comprised of patients enrolled in the CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DefibrillAtor ThErapy registry who had HFrEF and had simultaneous baseline CMR and echocardiography (n = 2449). RVSD was defined as RV ejection fraction (RVEF) Conclusion RV systolic dysfunction is an independent predictor of ACM in HFrEF, with a more pronounced prognostic value in select subgroups, likely reflecting the importance of RVSD in the early stages of HF progression.

Ischemic cardiomyopathy (ICM) is one of the most common causes of congestive heart failure. In patients with ICM, tissue characterization with cardiac magnetic resonance imaging (CMR) allows for evaluation of myocardial abnormalities in acute and chronic settings. Myocardial edema, microvascular obstruction (MVO), intracardiac thrombus, intramyocardial hemorrhage, and late gadolinium enhancement of the myocardium are easily depicted using standard CMR sequences. In the acute setting, tissue characterization is mainly focused on assessment of ventricular thrombus and MVO, which are associated with poor prognosis. Conversely, in chronic ICM, it is important to depict late gadolinium enhancement and myocardial ischemia using stress perfusion sequences. Overall, with CMR's ability to accurately characterize myocardial tissue in acute and chronic ICM, it represents a valuable diagnostic and prognostic imaging method for treatment planning. In particular, tissue characterization abnormalities in the acute setting can provide information regarding the patients that may develop major adverse cardiac event and show the presence of ventricular thrombus; in the chronic setting, evaluation of viable myocardium can be fundamental for planning myocardial revascularization. In this review, the main findings on tissue characterization are illustrated in acute and chronic settings using qualitative and quantitative tissue characterization.

Rationale and Objectives To evaluate the diagnostic accuracy of a prototype noncontrast, free-breathing, self-navigated 3D (SN3D) MR angiography (MRA) technique for the assessment of coronary artery anatomy in children with known or suspected coronary anomalies, using CT angiography (CTA) as the reference standard. Materials and Methods Twenty-one children (15 male, 12.3 ± 2.6 years) were prospectively enrolled between July 2014 and August 2016 in this IRB-approved, HIPAA-compliant study. Patients underwent same-day unenhanced SN3D-MRA and contrast-enhanced CTA. Two observers rated the visualization of coronary artery segments and diagnostic confidence on a 3-point scale and assessed coronary arteries for anomalous origin, as well as interarterial and intramural course. Sensitivity, specificity, positive (PPV) and negative predictive values (NPV) of SN3D-MRA for the detection of coronary artery abnormalities were calculated. Interobserver agreement was assessed using Intraclass Correlation Coefficients (ICC). Results Fourteen children showed coronary artery abnormalities on CTA. The visualization of coronary segments was rated significantly higher for CTA compared to MRA (p Conclusions Noncontrast SN3D-MRA is highly accurate for the detection of coronary artery anomalies in pediatric patients while diagnostic confidence and coronary artery visualization remain superior with CTA.

Prevalence of patients with congenital heart disease (CHD) is rapidly increasing due to continuous advancements in diagnostic techniques and medical or surgical treatment approaches. Along with cardiac computed tomography angiography, cardiac magnetic resonance (CMR) serves as a fundamental imaging modality for pre-surgical planning in patients with CHD, as CMR allows for the evaluation of cardiac and great vessel anatomy, biventricular function, flow dynamics, and tissue characterization. This information is essential for risk-assessment and optimal timing of surgical interventions. This article discusses the current role of pediatric cardiac MR imaging as a practical preoperative assessment tool in the pediatric population.

Background: The aim of this study was to assess the potential of rest-stress DECT iodine quantification to discriminate between normal, ischemic, and infarcted myocardium.Methods: Patients who underwent rest-stress DECT on a 2nd generation dual-source system and cardiac magnetic resonance (CMR) were retrospectively included from a prospective study cohort. CMR was performed to identify ischemic and infarcted myocardium and categorize patients into ischemic, infarcted, and control groups. Controls were analyzed on a per-slice and per-segment basis. Regions of interest (ROIs) were placed in ischemic and infarcted areas based on CMR. Additionally, ROIs were placed in the septal area to assess normal and remote myocardium.Results: We included 42 patients: 10 ischemic, 17 infarcted, and 15 controls. Iodine concentrations showed no significant between segments in controls. Iodine concentrations for normal myocardium increased significantly from rest to stress (median 3.7 mg/mL (interquartile range 3.5-3.9) vs. 4.5 mg/mL (4.3-4.9)) (p Conclusion: DECT iodine concentration from rest-stress imaging can potentially differentiate between normal, ischemic, and infarcted myocardium.

The purpose of this work was to assess the performance of a convolutional neural network (CNN) for automatic thoracic aortic measurements in a heterogeneous population. From June 2018 to May 2019, this study retrospectively analyzed 250 chest CT scans with or without contrast enhancement and electrocardiographic gating from a heterogeneous population with or without aortic pathologic findings. Aortic diameters at nine locations and maximum aortic diameter were measured manually and with an algorithm (Artificial Intelligence Rad Companion Chest CT prototype, Siemens Healthineers) by using a CNN. A total of 233 examinations performed with 15 scanners from three vendors in 233 patients (median age, 65 years [IQR, 54–72 years]; 144 men) were analyzed: 68 (29%) without pathologic findings, 72 (31%) with aneurysm, 51 (22%) with dissection, and 42 (18%) with repair. No evidence of a difference was observed in maximum aortic diameter between manual and automatic measurements (P = .48). Overall measurements displayed a bias of −1.5 mm and a coefficient of repeatability of 8.0 mm at Bland-Altman analyses. Contrast enhancement, location, pathologic finding, and positioning inaccuracy negatively influenced reproducibility (P < .003). Sites with dissection or repair showed lower agreement than did sites without. The CNN performed well in measuring thoracic aortic diameters in a heterogeneous multivendor CT dataset. Keywords: CT, Vascular, Aorta © RSNA, 2022

PURPOSE The aim of this pilot study was to prospectively evaluate the first integrated positron emission tomography (PET)/dual-energy computed tomography (DECT) system performance in patients with non-small cell lung cancer (NSCLC). MATERIALS AND METHODS In this single-center, prospective trial, consecutive patients with NSCLC referred for a PET study between May 2017 and June 2018 were enrolled. All patients received contrast-enhanced imaging on a clinical PET/DECT system. Data analysis included PET-based standard uptake values (SUVmax) and DECT-based iodine densities of tumor masses, lymph nodes, and distant metastases. Results were analyzed using correlation tests and receiver operating characteristics curves. RESULTS The study population was composed of 21 patients (median age 62 y, 14 male patients). A moderate positive correlation was found between iodine density values (2.2 mg/mL) and SUVmax (10.5) in tumor masses (ρ=0.53, P

Background Tuberculosis (TB) has been linked to an increased risk of atherosclerotic cardiovascular disease (ASCVD). We assessed whether latent TB infection (LTBI) is associated with subclinical coronary atherosclerosis in 2 TB-prevalent areas. Methods We analyzed cross-sectional data from studies conducted in Lima, Peru, and Kampala, Uganda. Individuals ≥40 years old were included. We excluded persons with known history of ASCVD events or active TB. Participants underwent QuantiFERON-TB (QFT) testing to define LTBI and computed tomography angiography to examine coronary atherosclerosis. A Coronary Artery Disease–Reporting Data System (CAD-RADS) score ≥3 defined obstructive CAD (plaque causing ≥50% stenosis). Results 113 and 91 persons with and without LTBI, respectively, were included. There were no significant differences between LTBI and non-LTBI participants in terms of age (median [interquartile range]; 56 [51–62] vs 55 [49–64] years; P = .829), male sex (38% vs 42%; P = .519), or 10-year ASCVD risk scores (7.1 [3.2–11.7] vs 6.1 [2.8–1.8]; P = .533). CAD prevalence (any plaque) was similar between groups (29% vs 24%; P = .421). Obstructive CAD was present in 9% of LTBI and 3% of non-LTBI individuals (P = .095). LTBI was associated with obstructive CAD after adjusting for ASCVD risk score, HIV status, and study site (adjusted OR, 4.96; 95% CI, 1.05–23.44; P = .043). Quantitative QFT TB antigen minus Nil interferon-γ responses were associated with obstructive CAD (adjusted OR, 1.2; 95% CI, 1.03–1.41; P = .022). Conclusions LTBI was independently associated with an increased likelihood of subclinical obstructive CAD. Our data indicate that LTBI is a nontraditional correlate of ASCVD risk.

Objectives To assess the feasibility of quantitative analysis of dynamic computed tomography angiography (dCTA) for the detection of endoleaks in patients who underwent endovascular repair of abdominal aortic aneurysms (EVAR). Material and methods Twenty patients scheduled for contrast-enhanced CT angiography (CTA) of the abdominal aorta post-EVAR were prospectively enrolled. All patients received a standard triphasic CTA protocol, followed by an additional dCTA. The dCTA acquisition enabled reconstruction of color-coded maps depicting blood perfusion and a dCTA dataset of the aneurysm sac. Observers assessed the dCTA and dynamic CT perfusion (dCTP) images for the detection of endoleaks, establishing diagnostic confidence based on a modified 5-point Likert scale. An index was calculated for the ratio between the endoleak and aneurysm sac using blood flow for dCTP and Hounsfield units (HU) for dCTA. The Wilcoxon test compared the endoleak index and the diagnostic confidence of the observers. Results In total, 19 patients (18 males, median age 74 years [70.5–75.7]) were included for analysis. Nine endoleaks were detected in 7 patients using triphasic CTA as the reference standard. There was complete agreement for endoleak detection between the two techniques on a per-patient basis. Both dCTA and dCTP identified an additional endoleak in one patient. The diagnostic confidence using dCTP for detection of endoleaks was not significantly superior to dCTA (5.0 [5–5] vs. 4.5 [4–5], respectively; p = 0.11); however, dCTP demonstrated superior diagnostic confidence for endoleak exclusion compared to dCTA (1.0 [1–1] vs 1.5 [1.5–1.5], respectively; p Conclusions Quantitative analysis of dCTP imaging can aid in the detection of endoleaks and demonstrates a higher endoleak detection rate than triphasic CTA, as well as a strong correlation with visual assessment of dCTA images.

To determine the association of asymptomatic diverticular disease as assessed by magnetic resonance imaging (MRI) with adipose tissue compartments, hepatic steatosis and constitutional risk factors within a cohort drawn from a Western general population. Asymptomatic subjects enrolled in a prospective case-control study underwent a 3 Tesla MRI scan, including an isotropic VIBE-Dixon sequence of the entire trunk. The presence and extent of diverticular disease were categorized according to the number of diverticula in each colonic segment in a blinded fashion. The amount of visceral, subcutaneous, and total adipose tissue (VAT, SAT, and TAT) was quantified by MRI. Additionally, the degree of hepatic steatosis, indicated as hepatic proton density fat fraction (hepatic PDFF) was determined using a multi-echo T1w sequence. Constitutional cardiometabolic risk factors were obtained and univariate and multivariate associations were calculated. A total of 371 subjects were included in the analysis (58.2 % male, 56.2 ± 9.2 years). Based on MRI, 154 participants (41.5 %) had diverticular disease with 62 cases (17 %) being advanced diverticular disease. Subjects with advanced diverticular disease had a significantly higher body mass index (BMI) (BMI: 29.9 ± 5.1 vs. 27.5 ± 4.6, p 0.001; respectively). Furthermore, all adipose tissue compartments were increased in subjects with advanced diverticular disease (e. g. VAT: 6.0 ± 2.8 vs. 4.2 ± 2.6 and SAT: 9.2 ± 3.6 vs. 7.8 ± 3.6, all p 0.001, respectively). Similarly, subjects with advanced diverticular disease had significantly higher hepatic PDFF (4.9 [2.7, 11.4] vs. 6.1 [5.5, 14.6], p = 0.002). Advanced diverticular disease is associated with an increased volume of adipose tissue compartments and BMI, which may suggest a metabolic role in disease development.· Diverticular disease is associated with constitutional risk factors such as BMI.. · Excess of adipose tissue compartments and hepatic steatosis are associated with the prevalence of diverticular disease.. · Our results suggest a shared pathological pathway of cardiometabolic alterations and the prevalence of diverticular disease.. · MRI is feasible for the assessment of adipose tissue compartments, hepatic steatosis, and diverticular disease and allows identification of patients who are at risk but in an asymptomatic disease state..· Storz C, Rospleszcz S, Askani E et al. Magnetic Resonance Imaging of Diverticular Disease and its Association with Adipose Tissue Compartments and Constitutional Risk Factors in Subjects from a Western General Population. Fortschr Röntgenstr 2021; 193: 33 - 41.ZIEL: Ziel dieser Studie war es, den Zusammenhang zwischen asymptomatischer Divertikulose und Körperfettkompartimenten, Hepatosteatose sowie konstitutionellen Risikofaktoren, erhoben mittels Magnetresonanztomografie (MRT), in einem westlichen Normalkolletkiv zu untersuchen. Gesunde, asymptomatische Teilnehmer wurden in eine prospektive Fall-Kontroll-Studie eingeschlossen und mittels 3-Tesla-Ganzkörper-MRT untersucht. Anhand einer isotropen VIBE-Dixon-Sequenz des Abdomens wurden das Ausmaß einer Divertikulose (Anzahl der Divertikel pro Kolonsegment) sowie das Volumen des viszeralen, subkutanen und totalen Fettgewebes (VAT, SAT und TAT) bestimmt. Zusätzlich wurde der Grad einer Hepatosteatose (hepatic proton density fat fraction (hepatic PDFF)) mittels einer Multiecho-T1w-Sequenz ermittelt. Konstitutionelle kardiometabolische Risikofaktoren wurden erhoben und univariate und multivariate Analysen durchgeführt. Insgesamt wurden 371 Teilnehmer in die Analyse eingeschlossen (58,2 % Männer; 56,2 ± 9,2 Jahre alt). Basierend auf den MRT-Ergebnissen hatten 154 Probanden (41,5 %) eine Divertikulose, 62 (17 %) eine fortgeschrittene Divertikulose. Probanden mit fortgeschrittener Divertikulose hatten im Vergleich zu Probanden ohne Divertikulose einen höheren BMI (BMI: 29,9 ± 5,1 vs. 27,5 ± 4,6; p 0,001). Alle Fettkompartimente waren bei Teilnehmern mit fortgeschrittener Divertikulose erhöht (bspw. VAT: 6,0 ± 2,8 vs. 4,2 ± 2,6 und SAT: 9,2 ± 3,6 vs. 7,8 ± 3,6, jeweils p 0,001). Ebenfalls wurde eine signifikant höhere Hepatosteatose bei Teilnehmern mit fortgeschrittener Divertikulose gefunden (hepatic PDFF: 4,9 (2,7, 11,4] vs. 6,1 (5,5, 14,6); p = 0,002). Die fortgeschrittene Divertikulose geht signifikant mit höheren metabolischen Fettgewebsveränderungen, insbesondere vermehrten Körperfettkompartimenten und erhöhten BMI-Werten einher. Dies lässt einen metabolischen Pathomechanismus in der Entstehung der Divertikulose vermuten.· Das Vorhandensein einer Divertikulose ist mit konstitutionellen Risikofaktoren (bspw. BMI) assoziiert.. · Vermehrte Körperfettmengen und Hepatosteatose sind mit einer Divertikulose assoziiert.. · Unsere Ergebnisse lassen einen geteilten Pathomechanismus durch kardiometabolische Veränderungen und das Vorhandensein einer Divertikulose vermuten.. · Die MRT ermöglicht die Erfassung von Körperfettkompartimenten, einer Hepatosteatose sowie einer Divertikulose und ermöglicht somit eine Identifikation von Risikofaktoren in einem asymptomatischen Krankheitsstatus..

Purpose: To evaluate deep-learning based calcium quantification on Chest CT scans compared with manual evaluation, and to enable interpretation in terms of the traditional Agatston score on dedicated Cardiac CT.Methods: Automated calcium quantification was performed using a combination of deep-learning convolution neural networks with a ResNet-architecture for image features and a fully connected neural network for spatial coordinate features. Calcifications were identified automatically, after which the algorithm automatically excluded all non-coronary calcifications using coronary probability maps and aortic segmentation. The algorithm was first trained on cardiac-CTs and refined on non-triggered chest-CTs. This study used on 95 patients (cohort 1), who underwent both dedicated calcium scoring and chest-CT acquisitions using the Agatston score as reference standard and 168 patients (cohort 2) who underwent chest-CT only using qualitative expert assessment for external validation. Results from the deep-learning model were compared to Agatston-scores(cardiac-CTs) and manually determined calcium volumes(chest-CTs) and risk classifications.Results: In cohort 1, the Agatston score and AI determined calcium volume shows high correlation with a correlation coefficient of 0.921(p < 0.001) and R-2 of 0.91. According to the Agatston categories, a total of 67(70 %) were correctly classified with a sensitivity of 91 % and specificity of 92 % in detecting presence of coronary calcifications. Manual determined calcium volume on chest-CT showed excellent correlation with the AI volumes with a correlation coefficient of 0.923(p < 0.001) and R-2 of 0.96, no significant difference was found (p = 0.247). According to qualitative risk classifications in cohort 2, 138(82 %) cases were correctly classified with a k-coefficient of 0.74, representing good agreement. All wrongly classified scans (30(18 %)) were attributed to an adjacent category.Conclusion: Artificial intelligence based calcium quantification on chest-CTs shows good correlation compared to reference standards. Fully automating this process may reduce evaluation time and potentially optimize clinical calcium scoring without additional acquisitions.

Gated computed tomography (CT) might not adequately predict occurrence of post-implantation transcatheter aortic valve replacement (TAVR) complications in hostile aortic root as it would require a more complex integration of morphological, functional and hemodynamical parameters. We used a computational framework based on finite element analysis (FEA) to simulate patient-specific implantation. Application of biomechanical modelling using FEA to gated-CT was able to demonstrate the relation of the device with voluminous calcification, its consequent misalignment and a significant stent deformation. Use of FEA and other advanced computed predictive modelling techniques as an adjunct to CT scan could improve our understanding of TAVR, potentially predict complications and fate of the devices after implantation and inform patient-specific treatment.