Impact of fully automated assessment on interstudy reproducibility of biventricular volumes and function in cardiac magnetic resonance imaging

Cardiac function in a large animal model of myocardial infarction at 7 T: deep learning based automatic segmentation increases reproducibility

Cardiac magnetic resonance (CMR) imaging allows precise non-invasive quantification of cardiac function. It requires reliable image segmentation for myocardial tissue. Clinically used software usually offers automatic approaches for this step. These are, however, designed for segmentation of human images obtained at clinical field strengths. They reach their limits when applied to preclinical data and ultrahigh field strength (such as CMR of pigs at 7 T). In our study, eleven animals (seven with myocardial infarction) underwent four CMR scans each. Short-axis cine stacks were acquired and used for functional cardiac analysis. End-systolic and end-diastolic images were labelled manually by two observers and inter- and intra-observer variability were assessed. Aiming to make the functional analysis faster and more reproducible, an established deep learning (DL) model for myocardial segmentation in humans was re-trained using our preclinical 7 T data (n = 772 images and labels). We then tested the model on n = 288 images. Excellent agreement in parameters of cardiac function was found between manual and DL segmentation: For ejection fraction (EF) we achieved a Pearson's r of 0.95, an Intraclass correlation coefficient (ICC) of 0.97, and a Coefficient of variability (CoV) of 6.6%. Dice scores were 0.88 for the left ventricle and 0.84 for the myocardium.

Heart failure with preserved ejection fraction: diagnosis, risk assessment, and treatment

The aetiology of heart failure with preserved ejection fraction (HFpEF) is heterogenous and overlaps with that of several comorbidities like atrial fibrillation, diabetes mellitus, chronic kidney disease, valvular heart disease, iron deficiency, or sarcopenia. The diagnosis of HFpEF involves evaluating cardiac dysfunction through imaging techniques and assessing increased left ventricular filling pressure, which can be measured directly or estimated through various proxies including natriuretic peptides. To better narrow down the differential diagnosis of HFpEF, European and American heart failure guidelines advocate the use of different algorithms including comorbidities that require diagnosis and rigorous treatment during the evaluation process. Therapeutic recommendations differ between guidelines. Whilst sodium glucose transporter 2 inhibitors have a solid evidence base, the recommendations differ with regard to the use of inhibitors of the renin-angiotensin-aldosterone axis. Unless indicated for specific comorbidities, the use of beta-blockers should be discouraged in HFpEF. The aim of this article is to provide an overview of the current state of the art in HFpEF diagnosis, clinical evaluation, and treatment.

Inter-study reproducibility of cardiovascular magnetic resonance-derived hemodynamic force assessments

Cardiovascular magnetic resonance (CMR)-derived hemodynamic force (HDF) analyses have been introduced recently enabling more in-depth cardiac function evaluation. Inter-study reproducibility is important for a widespread clinical use but has not been quantified for this novel CMR post-processing tool yet. Serial CMR imaging was performed in 11 healthy participants in a median interval of 63 days (range 49-87). HDF assessment included left ventricular (LV) longitudinal, systolic peak and impulse, systolic/diastolic transition, diastolic deceleration as well as atrial thrust acceleration forces. Inter-study reproducibility and study sample sizes required to demonstrate 10%, 15% or 20% relative changes of HDF measurements were calculated. In addition, intra- and inter-observer analyses were performed. Intra- and inter-observer reproducibility was excellent for all HDF parameters according to intraclass correlation coefficient (ICC) values (> 0.80 for all). Inter-study reproducibility of all HDF parameters was excellent (ICC ≥ 0.80 for all) with systolic parameters showing lower coeffients of variation (CoV) than diastolic measurements (CoV 15.2% for systolic impulse vs. CoV 30.9% for atrial thrust). Calculated sample sizes to detect relative changes ranged from n = 12 for the detection of a 20% relative change in systolic impulse to n = 200 for the detection of 10% relative change in atrial thrust. Overall inter-study reproducibility of CMR-derived HDF assessments was sufficient with systolic HDF measurements showing lower inter-study variation than diastolic HDF analyses.

Assessment and diagnosis of right ventricular failure-retrospection and future directions

The right ventricle (RV) has a critical role in hemodynamics and right ventricular failure (RVF) often leads to poor clinical outcome. Despite the clinical importance of RVF, its definition and recognition currently rely on patients' symptoms and signs, rather than on objective parameters from quantifying RV dimensions and function. A key challenge is the geometrical complexity of the RV, which often makes it difficult to assess RV function accurately. There are several assessment modalities currently utilized in the clinical settings. Each diagnostic investigation has both advantages and limitations according to its characteristics. The purpose of this review is to reflect on the current diagnostic tools, consider the potential technological advancements and propose how to improve the assessment of right ventricular failure. Advanced technique such as automatic evaluation with artificial intelligence and 3-dimensional assessment for the complex RV structure has a potential to improve RV assessment by increasing accuracy and reproducibility of the measurements. Further, noninvasive assessments for RV-pulmonary artery coupling and right and left ventricular interaction are also warranted to overcome the load-related limitations for the accurate evaluation of RV contractile function. Future studies to cross-validate the advanced technologies in various populations are required.

Artificial Intelligence Enabled Fully Automated CMR Function Quantification for Optimized Risk Stratification in Patients Undergoing Transcatheter Aortic Valve Replacement

Background

Cardiovascular magnetic resonance imaging is considered the reference standard for assessing cardiac morphology and function and has demonstrated prognostic utility in patients undergoing transcatheter aortic valve replacement (TAVR). Novel fully automated analyses may facilitate data analyses but have not yet been compared against conventional manual data acquisition in patients with severe aortic stenosis (AS).

Methods

Fully automated and manual biventricular assessments were performed in 139 AS patients scheduled for TAVR using commercially available software (suiteHEART®, Neosoft; QMass®, Medis Medical Imaging Systems). Volumetric assessment included left ventricular (LV) mass, LV/right ventricular (RV) end-diastolic/end-systolic volume, LV/RV stroke volume, and LV/RV ejection fraction (EF). Results of fully automated and manual analyses were compared. Regression analyses and receiver operator characteristics including area under the curve (AUC) calculation for prediction of the primary study endpoint cardiovascular (CV) death were performed.

Results

Fully automated and manual assessment of LVEF revealed similar prediction of CV mortality in univariable (manual: hazard ratio (HR) 0.970 (95% CI 0.943–0.997) p=0.032; automated: HR 0.967 (95% CI 0.939–0.995) p=0.022) and multivariable analyses (model 1: (including significant univariable parameters) manual: HR 0.968 (95% CI 0.938–0.999) p=0.043; automated: HR 0.963 [95% CI 0.933–0.995] p=0.024; model 2: (including CV risk factors) manual: HR 0.962 (95% CI 0.920–0.996) p=0.027; automated: HR 0.954 (95% CI 0.920–0.989) p=0.011). There were no differences in AUC (LVEF fully automated: 0.686; manual: 0.661; p=0.21). Absolute values of LV volumes differed significantly between automated and manual approaches (p < 0.001 for all). Fully automated quantification resulted in a time saving of 10 minutes per patient.

Conclusion

Fully automated biventricular volumetric assessments enable efficient and equal risk prediction compared to conventional manual approaches. In addition to significant time saving, this may provide the tools for optimized clinical management and stratification of patients with severe AS undergoing TAVR.

Assessment of right ventricular size and function from cardiovascular magnetic resonance images using artificial intelligence

BACKGROUND

Theoretically, artificial intelligence can provide an accurate automatic solution to measure right ventricular (RV) ejection fraction (RVEF) from cardiovascular magnetic resonance (CMR) images, despite the complex RV geometry. However, in our recent study, commercially available deep learning (DL) algorithms for RVEF quantification performed poorly in some patients. The current study was designed to test the hypothesis that quantification of RV function could be improved in these patients by using more diverse CMR datasets in addition to domain-specific quantitative performance evaluation metrics during the cross-validation phase of DL algorithm development.

METHODS

We identified 100 patients from our prior study who had the largest differences between manually measured and automated RVEF values. Automated RVEF measurements were performed using the original version of the algorithm (DL1), an updated version (DL2) developed from a dataset that included a wider range of RV pathology and validated using multiple domain-specific quantitative performance evaluation metrics, and conventional methodology performed by a core laboratory (CORE). Each of the DL-RVEF approaches was compared against CORE-RVEF reference values using linear regression and Bland-Altman analyses. Additionally, RVEF values were classified into 3 categories: ≤ 35%, 35-50%, and ≥ 50%. Agreement between RVEF classifications made by the DL approaches and the CORE measurements was tested.

RESULTS

CORE-RVEF and DL-RVEFs were obtained in all patients (feasibility of 100%). DL2-RVEF correlated with CORE-RVEF better than DL1-RVEF (r = 0.87 vs. r = 0.42), with narrower limits of agreement. As a result, DL2 algorithm also showed increasing accuracy from 0.53 to 0.80 for categorizing RV function.

CONCLUSIONS

The use of a new DL algorithm cross-validated on a dataset with a wide range of RV pathology using multiple domain-specific metrics resulted in a considerable improvement in the accuracy of automated RVEF measurements. This improvement was demonstrated in patients whose images were the most challenging and resulted in the largest RVEF errors. These findings underscore the critical importance of this strategy in the development of DL approaches for automated CMR measurements.