Artificial intelligence-enhanced risk stratification of cancer therapeutics-related cardiac dysfunction using electrocardiographic images.

Background: Risk stratification strategies for cancer therapeutics-related cardiac dysfunction (CTRCD) rely on serial monitoring by specialized imaging, limiting their scalability. Objectives: To examine an artificial intelligence (AI)-enhanced electrocardiographic (AI-ECG) surrogate for imaging risk biomarkers, and its association with CTRCD. Methods: Across a five-hospital U.S.-based health system (2013-2023), we identified patients with breast cancer or non-Hodgkin lymphoma (NHL) who received anthracyclines (AC) and/or trastuzumab (TZM), and a control cohort receiving immune checkpoint inhibitors (ICI). We deployed a validated AI model of left ventricular systolic dysfunction (LVSD) to ECG images (≥0.1, positive screen) and explored its association with i) global longitudinal strain (GLS) measured within 15 days (n=7,271 pairs); ii) future CTRCD (new cardiomyopathy, heart failure, or left ventricular ejection fraction [LVEF]<50%), and LVEF<40%. In the ICI cohort we correlated baseline AI-ECG-LVSD predictions with downstream myocarditis. Results: Higher AI-ECG LVSD predictions were associated with worse GLS (-18% [IQR:-20 to -17%] for predictions<0.1, to -12% [IQR:-15 to -9%] for ≥0.5 (p<0.001)). In 1,308 patients receiving AC/TZM (age 59 [IQR:49-67] years, 999 [76.4%] women, 80 [IQR:42-115] follow-up months) a positive baseline AI-ECG LVSD screen was associated with ~2-fold and ~4.8-fold increase in the incidence of the composite CTRCD endpoint (adj.HR 2.22 [95%CI:1.63-3.02]), and LVEF<40% (adj.HR 4.76 [95%CI:2.62-8.66]), respectively. Among 2,056 patients receiving ICI (age 65 [IQR:57-73] years, 913 [44.4%] women, follow-up 63 [IQR:28-99] months) AI-ECG predictions were not associated with ICI myocarditis (adj.HR 1.36 [95%CI:0.47-3.93]). Conclusion: AI applied to baseline ECG images can stratify the risk of CTRCD associated with anthracycline or trastuzumab exposure.

Multimodality Cardiac Imaging and the Imaging Workforce in the United States: Diversity, Disparities, and Future Directions.

Innovations in cardiac imaging have fundamentally advanced the understanding and treatment of cardiovascular disease. These advances in noninvasive cardiac imaging have also expanded the role of the cardiac imager and dramatically increased the demand for imagers who are cross-trained in multiple modalities. However, we hypothesize that there is significant variation in the availability of cardiac imaging expertise and a disparity in the adoption of advanced imaging technologies across the United States. To evaluate this, we have brought together the leaders of cardiovascular imaging societies, imaging trainees, as well as collaborated with national imaging accreditation commissions and imaging certification boards to assess the state of cardiac imaging and the diversity of the imaging workforce in the United States. Aggregate data confirm the presence of critical gaps, such as limited access to imaging and imaging expertise in rural communities, as well as disparities in the imaging workforce, notably among women and underrepresented minorities. Based on these results, we have proposed solutions to promote and maintain a robust and diverse community of cardiac imagers and improve equity and accessibility for cardiac imaging technologies.

Atrial fibrosis by cardiac MRI is a correlate for atrial stiffness in patients with atrial fibrillation.

A relationship between left atrial strain and pressure has been demonstrated in many studies, but not in an atrial fibrillation (AF) cohort. In this work, we hypothesized that elevated left atrial (LA) tissue fibrosis might mediate and confound the LA strain vs. pressure relationship, resulting instead in a relationship between LA fibrosis and stiffness index (mean LA pressure/LA reservoir strain). Sixty-seven patients with AF underwent a standard cardiac MR exam including long-axis cine views (2 and 4-ch) and a free-breathing high resolution three-dimensional late gadolinium enhancement (LGE) of the atrium (N = 41), within 30 days prior to AF ablation, at which procedure invasive mean left atrial pressure (LAP) was measured. LV and LA Volumes, EF, and comprehensive analysis of LA strains (strain and strain rates and strain timings during the atrial reservoir, conduit and active, i.e. active atrial contraction, phases) were measured and LA fibrosis content (LGE (ml)) was assessed from 3D LGE volumes. LA LGE was well correlated to atrial stiffness index overall (R = 0.59, p < 0.001), and among patient subgroups. Pressure was only correlated to maximal LA volume (R = 0.32) and the time to peak reservoir strain rate (R = 0.32) (both p < 0.01), among all functional measurements. LA reservoir strain was strongly correlated with LAEF (R = 0.95, p < 0.001) and LA minimum volume (r = 0.82, p < 0.001). In our AF cohort, pressure is correlated to maximum LA volume and time to peak reservoir strain. LA pressure/ LA reservoir strain, a metric of stiffness, correlates with LA fibrosis (LA LGE), reflecting Hook's Law.

Scientific document development standards for the society of cardiovascular computed tomography (SCCT): A statement from the SCCT Guidelines Committee.

The Society of Cardiovascular Computed Tomography (SCCT) is an international community of physicians, scientists and technologists advocating for research, education, and clinical excellence in the use of cardiovascular computed tomography (CCT). SCCT members are committed to improving health outcomes through effective use of CCT. The SCCT routinely authors, endorses, and jointly collaborates on scientific documents that reflect the best available evidence and expert consensus supported in practice of CCT. This paper outlines SCCT's methodology for developing scientific documents. It was formulated by members of the SCCT Guidelines Committee and approved by the SCCT Board of Directors.

Atrial Fibrosis by cardiac MRI is a correlate for atrial stiffness in patients with atrial fibrillation.

Aims: A relationship between left atrial strain and pressure has been demonstrated in many studies, but not in an atrial fibrillation (AF) cohort. In this work, we hypothesized that elevated left atrial (LA) tissue fibrosis might mediate and confound the LA strain vs. pressure relationship, resulting instead in a relationship between LA fibrosis and stiffness index (mean pressure/LA reservoir strain). Methods and Results: Sixty-seven patients with AF underwent a standard cardiac MR exam including long-axis cine views (2 and 4-ch) and a free-breathing high resolution three-dimensional late gadolinium enhancement (LGE) of the atrium (N=41), within 30 days prior to AF ablation, at which procedure invasive mean left atrial pressure (LAP) was measured. LV and LA Volumes, EF, and comprehensive analysis of LA strains (strain and strain rates and strain timings during the atrial reservoir, conduit and active phases) were measured and LA fibrosis content (LGE (ml)) was assessed from 3D LGE volumes. LA LGE was well correlated to atrial stiffness index (LA mean pressure/LA reservoir strain) overall (R=0.59, p<0.001), and among patient subgroups. Pressure was only correlated to maximal LA volume (R=0.32) and the time to peak reservoir strain rate (R=0.32), among all functional measurements. LA reservoir strain was strongly correlated with LAEF (R=0.95, p<0.001) and LA minimum volume (r=0.82, p<0.001). Conclusion: In our AF cohort, pressure is correlated to maximum LA volume and time to peak reservoir strain. LA LGE is a strong marker of stiffness.

Quantitative cardiovascular magnetic resonance findings and clinical risk factors predict cardiovascular outcomes in breast cancer patients.

BACKGROUND: Cardiac magnetic resonance (CMR) global longitudinal strain and circumferential strain abnormalities have been associated with left ventricular ejection fraction (LVEF) reduction and cardiotoxicity from oncologic therapy. However, few studies have evaluated the associations of strain and cardiovascular outcomes. OBJECTIVES: To assess CMR circumferential and global longitudinal strain (GLS) correlations with cardiovascular outcomes including myocardial infarction, systolic dysfunction, diastolic dysfunction, arrhythmias and valvular disease in breast cancer patients treated with and without anthracyclines and/or trastuzumab therapy. METHODS: Breast cancer patients with a CMR from 2013-2017 at Yale New Haven Hospital were included. Patient co-morbidities, medications, and cardiovascular outcomes were obtained from chart review. Biostatistical analyses, including Pearson correlations, competing risk regression model, and competing risk survival curves comparing the two groups were analyzed. RESULTS: 116 breast cancer with CMRs were included in our analysis to assess differences between Anthracycline/Trastuzumab (AT) (62) treated versus non anthracycline/trastuzumab (NAT) (54) treated patients in terms of imaging characteristics and outcomes. More AT patients 17 (27.4%) developed systolic heart failure compared to the NAT group 6 (10.9%), p = 0.025. Statin use was associated with a significant reduction in future arrhythmias (HR 0.416; 95% CI 0.229-0.755, p = 0.004). In a sub-group of 13 patients that underwent stress CMR, we did not find evidence of microvascular dysfunction by sub-endocardial/sub-epicardial myocardial perfusion index ratio after adjusting for ischemic heart disease. CONCLUSIONS: In our study, CMR detected signs of subclinical cardiotoxicity such as strain abnormalities despite normal LV function and abnormal circumferential strain was associated with adverse cardiovascular outcomes such as valvular disease and systolic heart failure. Thus, CMR is an important tool during and after cancer treatment to identity and prognosticate cancer treatment-related cardiotoxicity.

Advances in Coronary Computed Tomographic Angiographic Imaging of Atherosclerosis for Risk Stratification and Preventive Care.

The diagnostic evaluation of coronary artery disease is undergoing a dramatic transformation with a new focus on atherosclerotic plaque. This review details the evidence needed for effective risk stratification and targeted preventive care based on recent advances in automated measurement of atherosclerosis from coronary computed tomography angiography (CTA). To date, research findings support that automated stenosis measurement is reasonably accurate, but evidence on variability by location, artery size, or image quality is unknown. The evidence for quantification of atherosclerotic plaque is unfolding, with strong concordance reported between coronary CTA and intravascular ultrasound measurement of total plaque volume (r >0.90). Statistical variance is higher for smaller plaque volumes. Limited data are available on how technical or patient-specific factors result in measurement variability by compositional subgroups. Coronary artery dimensions vary by age, sex, heart size, coronary dominance, and race and ethnicity. Accordingly, quantification programs excluding smaller arteries affect accuracy for women, patients with diabetes, and other patient subsets. Evidence is unfolding that quantification of atherosclerotic plaque is useful to enhance risk prediction, yet more evidence is required to define high-risk patients across varied populations and to determine whether such information is incremental to risk factors or currently used coronary computed tomography techniques (eg, coronary artery calcium scoring or visual assessment of plaque burden or stenosis). In summary, there is promise for the utility of coronary CTA quantification of atherosclerosis, especially if it can lead to targeted and more intensive cardiovascular prevention, notably for those patients with nonobstructive coronary artery disease and high-risk plaque features. The new quantification techniques available to imagers must not only provide sufficient added value to improve patient care, but also add minimal and reasonable cost to alleviate the financial burden on our patients and the health care system.

Impaired left-ventricular global longitudinal strain by feature-tracking cardiac MRI predicts mortality in systemic sclerosis.

Impaired left-ventricular (LV) and right-ventricular (RV) cardiac magnetic resonance (CMR) strain has been documented in systemic sclerosis (SSc). However, it is unknown whether the CMR strain is predictive of adverse outcomes in SSc. Therefore, we set out to investigate the prognostic value of CMR strain in SSc. Patients with SSc who underwent CMR for clinical indications between 11/2010 and 07/2020 were retrospectively studied. LV and RV strain was evaluated by feature tracking. The association between strain, late gadolinium enhancement (LGE), and survival was evaluated with time to event and Cox-regression analyses. During the study period, 42 patients with SSc (age: 57 ± 14 years, 83% female, 57% limited cutaneous SSc, SSc duration: 7 ± 8 years) underwent CMR. During the median follow-up of 3.6 years, 11 patients died (26%). Compared to surviving patients, patients who died had significantly worse LV GLS (- 8.2 ± 6.2% versus - 12.1 ± 2.9%, p = 0.03), but no difference in LV global radial, circumferential, or RV strain values. Patients within the quartile of most impaired LV GLS (≥ - 12.8%, n = 10) had worse survival when compared to patients with preserved LV GLS (< - 12.8%, n = 32, log-rank p = 0.02), which persisted after controlling for LV cardiac output, LV cardiac index, reduced LV ejection fraction, or presence of LGE. In addition, patients who had both impaired LV GLS and LGE (n = 5) had worse survival than patients with LGE or impaired GLS alone (n = 14) and compared to those without any of these features (n = 17, p = 0.003). In our retrospective cohort of patients with SSc undergoing CMR for clinical indications, LV GLS and LGE were found to be predictive of overall survival.

Racial and Ethnic Disparities in All-Cause and Cardiovascular Mortality Among Cancer Patients in the U.S.

Background: With improved cancer survival, death from noncancer etiologies, especially cardiovascular disease (CVD) mortality, has come more into focus. Little is known about the racial and ethnic disparities in all-cause and CVD mortality among U.S. cancer patients. Objectives: This study sought to investigate racial and ethnic disparities in all-cause and CVD mortality among adults with cancer in the United States. Methods: Using the Surveillance, Epidemiology, and End Results (SEER) database from years 2000 to 2018, all-cause and CVD mortality among patients ≥18 years of age at the time of initial malignancy diagnosis were compared by race and ethnicity groups. The 10 most prevalent cancers were included. Cox regression models were used to estimate adjusted HRs for all-cause and CVD mortality using Fine and Gray's method for competing risks, as applicable. Results: Among a total of 3,674,511 participants included in our study, 1,644,067 (44.7%) died, with 231,386 (6.3%) deaths as a result of CVD. After adjusting for sociodemographic and clinical characteristics, non-Hispanic (NH) Black individuals had both higher all-cause (HR: 1.13; 95% CI: 1.13-1.14) and CVD (HR: 1.25; 95% CI: 1.24-1.27) mortality, whereas Hispanic and NH Asian/Pacific Islander had lower mortality than NH White patients. Racial and ethnic disparities were more prominent among patients 18 to 54 years of age and those with localized cancer. Conclusions: Significant racial and ethnic differences exist in both all-cause and CVD mortality among U.S. cancer patients. Our findings underscore the vital roles of accessible cardiovascular interventions and strategies to identify high-risk cancer populations who may benefit most from early and long-term survivorship care.

Myocardial Injury on CMR in Patients With COVID-19 and Suspected Cardiac Involvement.

BACKGROUND: Myocardial injury in patients with COVID-19 and suspected cardiac involvement is not well understood. OBJECTIVES: The purpose of this study was to characterize myocardial injury in a multicenter cohort of patients with COVID-19 and suspected cardiac involvement referred for cardiac magnetic resonance (CMR). METHODS: This retrospective study consisted of 1,047 patients from 18 international sites with polymerase chain reaction-confirmed COVID-19 infection who underwent CMR. Myocardial injury was characterized as acute myocarditis, nonacute/nonischemic, acute ischemic, and nonacute/ischemic patterns on CMR. RESULTS: In this cohort, 20.9% of patients had nonischemic injury patterns (acute myocarditis: 7.9%; nonacute/nonischemic: 13.0%), and 6.7% of patients had ischemic injury patterns (acute ischemic: 1.9%; nonacute/ischemic: 4.8%). In a univariate analysis, variables associated with acute myocarditis patterns included chest discomfort (OR: 2.00; 95% CI: 1.17-3.40, P = 0.01), abnormal electrocardiogram (ECG) (OR: 1.90; 95% CI: 1.12-3.23; P = 0.02), natriuretic peptide elevation (OR: 2.99; 95% CI: 1.60-5.58; P = 0.0006), and troponin elevation (OR: 4.21; 95% CI: 2.41-7.36; P < 0.0001). Variables associated with acute ischemic patterns included chest discomfort (OR: 3.14; 95% CI: 1.04-9.49; P = 0.04), abnormal ECG (OR: 4.06; 95% CI: 1.10-14.92; P = 0.04), known coronary disease (OR: 33.30; 95% CI: 4.04-274.53; P = 0.001), hospitalization (OR: 4.98; 95% CI: 1.55-16.05; P = 0.007), natriuretic peptide elevation (OR: 4.19; 95% CI: 1.30-13.51; P = 0.02), and troponin elevation (OR: 25.27; 95% CI: 5.55-115.03; P < 0.0001). In a multivariate analysis, troponin elevation was strongly associated with acute myocarditis patterns (OR: 4.98; 95% CI: 1.76-14.05; P = 0.003). CONCLUSIONS: In this multicenter study of patients with COVID-19 with clinical suspicion for cardiac involvement referred for CMR, nonischemic and ischemic patterns were frequent when cardiac symptoms, ECG abnormalities, and cardiac biomarker elevations were present.

Cardiac computed tomographic imaging in cardio-oncology: An expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT). Endorsed by the International Cardio-Oncology Society (ICOS).

Cardio-Oncology is a rapidly growing sub-specialty of medicine, however, there is very limited guidance on the use of cardiac CT (CCT) in the care of Cardio-Oncology patients. In order to fill in the existing gaps, this Expert Consensus statement comprised of a multidisciplinary collaboration of experts in Cardiology, Radiology, Cardiovascular Multimodality Imaging, Cardio-Oncology, Oncology and Radiation Oncology aims to summarize current evidence for CCT applications in Cardio-Oncology and provide practice recommendations for clinicians.

Advances in Multimodality Imaging in Cardio-Oncology: JACC State-of-the-Art Review.

The population of patients with cancer is rapidly expanding, and the diagnosis and monitoring of cardiovascular complications greatly rely on imaging. Numerous advances in the field of cardio-oncology and imaging have occurred in recent years. This review presents updated and practical approaches for multimodality cardiovascular imaging in the cardio-oncology patient and provides recommendations for imaging to detect the myriad of adverse cardiovascular effects associated with antineoplastic therapy, such as cardiomyopathy, atherosclerosis, vascular toxicity, myocarditis, valve disease, and cardiac masses. Uniquely, we address the role of cardiovascular imaging in patients with pre-existing cardiomyopathy, pregnant patients, long-term survivors, and populations with limited resources. We also address future avenues of investigation and opportunities for artificial intelligence applications in cardio-oncology imaging. This review provides a uniform practical approach to cardiovascular imaging for patients with cancer.

Impact of Social Vulnerability on Comorbid Cancer and Cardiovascular Disease Mortality in the United States.

Background: Racial and social disparities exist in outcomes related to cancer and cardiovascular disease (CVD). Objectives: The aim of this cross-sectional study was to study the impact of social vulnerability on mortality attributed to comorbid cancer and CVD. Methods: The Centers for Disease Control and Prevention Wide-Ranging Online Data for Epidemiologic Research database (2015-2019) was used to obtain county-level mortality data attributed to cancer, CVD, and comorbid cancer and CVD. County-level social vulnerability index (SVI) data (2014-2018) were obtained from the CDC's Agency for Toxic Substances and Disease Registry. SVI percentiles were generated for each county and aggregated to form SVI quartiles. Age-adjusted mortality rates (AAMRs) were estimated and compared across SVI quartiles to assess the impact of social vulnerability on mortality related to cancer, CVD, and comorbid cancer and CVD. Results: The AAMR for comorbid cancer and CVD was 47.75 (95% CI: 47.66-47.85) per 100,000 person-years, with higher mortality in counties with greater social vulnerability. AAMRs for cancer and CVD were also significantly greater in counties with the highest SVIs. However, the proportional increase in mortality between the highest and lowest SVI counties was greater for comorbid cancer and CVD than for either cancer or CVD alone. Adults <45 years of age, women, Asian and Pacific Islanders, and Hispanics had the highest relative increase in comorbid cancer and CVD mortality between the fourth and first SVI quartiles, without significant urban-rural differences. Conclusions: Comorbid cancer and CVD mortality increased in counties with higher social vulnerability. Improved education, resource allocation, and targeted public health interventions are needed to address inequities in cardio-oncology.

Novel Cardiac Computed Tomography Methods for the Assessment of Anthracycline Induced Cardiotoxicity.

Anthracyclines are among the most frequently utilized anti-cancer therapies; however, their use is frequently associated with off-target cardiotoxic effects. Cardiac computed tomography (CCT) is a validated and rapidly evolving technology for the evaluation of cardiac structures, coronary anatomy and plaque, cardiac function and preprocedural planning. However, with emerging new techniques, CCT is rapidly evolving to offer information beyond the evaluation of cardiac structure and epicardial coronary arteries to provide details on myocardial deformation, extracellular volume, and coronary vasoreactivity. The potential for molecular imaging in CCT is also growing. In the current manuscript we review these emerging computed tomography techniques and their potential role in the evaluation of anthracycline-induced cardiotoxicity.

Women physicians in cardiovascular magnetic resonance: Past, present, and future.

Women's engagement in medicine, and more specifically cardiovascular imaging and cardiovascular MRI (CMR), has undergone a slow evolution over the past several decades. As a result, an increasing number of women have joined the cardiovascular imaging community to contribute their expertise. This collaborative work summarizes the barriers that women in cardiovascular imaging have overcome over the past several years, the positive interventions that have been implemented to better support women in the field of CMR, and the challenges that still remain, with a special emphasis on women physicians.

Cardiovascular safety profile of taxanes and vinca alkaloids: 30 years FDA registry experience.

OBJECTIVE: Antimicrotubular agents are among the most commonly used classes of chemotherapeutic agents, but the risk of cardiovascular adverse events (CVAEs) remains unclear. Our objective was to study the CVAEs associated with antimicrotubular agents. METHODS: The Food and Drug Administration's Adverse Event Reporting System was used to study CVAEs in adults from 1990 to 2020. Reported single-agent (only taxane or vinca alkaloid) CVAEs were compared with combination therapy (with at least one of the four major cardiotoxic drugs: anthracycline, HER2Neu inhibitors, tyrosine kinase inhibitors and checkpoint inhibitors) using adjusted polytomous logistic regression. RESULTS: Over 30 years, 134 398 adverse events were reported, of which 18 426 (13.4%) were CVAEs, with 74.1% due to taxanes and 25.9% due to vinca alkaloids. In 30 years, there has been a reduction in the proportion of reported CVAEs for taxanes from 15% to 11.8% (Cochran-Armitage P-trends <0.001) with no significant change in the proportion of reported CVAEs for vinca alkaloids (9.2%-11.7%; P-trends=0.06). The proportion of reported CVAEs was lower in both taxane and vinca alkaloid monotherapy versus combination therapy (reporting OR=0.50 and 0.55, respectively). Anthracyclines and HER2Neu inhibitor combinations with taxanes or vinca alkaloids primarily drove the higher burden of combination CVAEs. Hypertension requiring hospitalisation and heart failure was significantly lower in monotherapy versus combination antimicrotubular agent therapy. CONCLUSIONS: Antimicrotubular agents are associated with CVAEs, especially in combination chemotherapy regimens. Based on this study, we suggest routine cardiovascular assessment of patients with cancer before initiating antimicrotubular agents in combination therapy.

Clinical Impact of Cardiovascular Magnetic Resonance in Cancer Patients With Suspected Cardiomyopathy.

Objectives: To assess the clinical impact of Cardiovascular Magnetic Resonance (CMR) in clinical decision making of cancer patients with a suspected cardiomyopathy in a tertiary cancer center. Background: Cardiomyopathies of diverse etiologies are frequently encountered in a Cardio-Oncology practice. The clinical impact of CMR after a presumptive diagnosis of cardiomyopathy has not been studied in cancer patients. Methods: We reviewed data on cancer patients with presumptive diagnosis of cardiomyopathy who underwent CMR in a tertiary cancer center. The clinical impact of CMR was defined as either change in clinical diagnosis or management post CMR results. Univariate and multivariate logistic regression models were used to assess whether any of the baseline characteristics were predictive of the clinical impact of CMR. Results: A total of 110 consecutive patients were identified. Clinical impact of CMR was seen in 68 (62%) patients. Change in the clinical diagnosis and management was seen in 56 (51%) and 41 (37%) of patients, respectively. The most common change was prevention of endomyocardial biopsy in 26 patients (24%). Overall, patients with higher left ventricular ejection fraction (LVEF) by echocardiography (echo), clinical impact was influenced more by CMR (LVEF of 37.2 ± 12.3% vs. 51.5 ± 11.6%, p < 0.001). Cancer diagnosis of multiple myeloma was associated with change in the management post CMR (adjusted OR of 25.6, 95% CI 4.0-162.4, p = 0.001). Suspicion of infiltrative cardiomyopathy was associated with a higher likelihood of change in diagnosis. Having an LVEF≥40 by echo was associated with change in diagnosis and management by CMR. Conclusions: Utilization of CMR has a significant clinical impact in cancer patients with suspected cardiomyopathy. Patients with cancer diagnosis of multiple myeloma, suspicion of infiltrative cardiomyopathy and those with higher LVEF by echo seem to benefit more from CMR.

Left atrial evaluation by cardiovascular magnetic resonance: sensitive and unique biomarkers.

Left atrial (LA) imaging is still not routinely used for diagnosis and risk stratification, although recent studies have emphasized its importance as an imaging biomarker. Cardiovascular magnetic resonance is able to evaluate LA structure and function, metrics that serve as early indicators of disease, and provide prognostic information, e.g. regarding diastolic dysfunction, and atrial fibrillation (AF). MR angiography defines atrial anatomy, useful for planning ablation procedures, and also for characterizing atrial shapes and sizes that might predict cardiovascular events, e.g. stroke. Long-axis cine images can be evaluated to define minimum, maximum, and pre-atrial contraction LA volumes, and ejection fractions (EFs). More modern feature tracking of these cine images provides longitudinal LA strain through the cardiac cycle, and strain rates. Strain may be a more sensitive marker than EF and can predict post-operative AF, AF recurrence after ablation, outcomes in hypertrophic cardiomyopathy, stratification of diastolic dysfunction, and strain correlates with atrial fibrosis. Using high-resolution late gadolinium enhancement (LGE), the extent of fibrosis in the LA can be estimated and post-ablation scar can be evaluated. The LA LGE method is widely available, its reproducibility is good, and validations with voltage-mapping exist, although further scan-rescan studies are needed, and consensus regarding atrial segmentation is lacking. Using LGE, scar patterns after ablation in AF subjects can be reproducibly defined. Evaluation of 'pre-existent' atrial fibrosis may have roles in predicting AF recurrence after ablation, predicting new-onset AF and diastolic dysfunction in patients without AF. LA imaging biomarkers are ready to enter into diagnostic clinical practice.